helper.h is used by all units, but not all require the NEON
definitions. Move them to a new header; the next commit will
remove it from the common helper.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper.h | 207 +---------------------------
target/arm/tcg/helper-a64.h.inc | 7 -
target/arm/tcg/helper-neon.h.inc | 224 +++++++++++++++++++++++++++++++
3 files changed, 225 insertions(+), 213 deletions(-)
create mode 100644 target/arm/tcg/helper-neon.h.inc
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 2419650ec6..2600c150f4 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -103,198 +103,11 @@ DEF_HELPER_FLAGS_2(rebuild_hflags_a64, TCG_CALL_NO_RWG, void, env, int)
DEF_HELPER_FLAGS_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32)
-DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i64, env, i32, i64, i64)
-
DEF_HELPER_3(shl_cc, i32, env, i32, i32)
DEF_HELPER_3(shr_cc, i32, env, i32, i32)
DEF_HELPER_3(sar_cc, i32, env, i32, i32)
DEF_HELPER_3(ror_cc, i32, env, i32, i32)
-/* neon_helper.c */
-DEF_HELPER_FLAGS_3(neon_qadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_qadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_qadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_qadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_qadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_qadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_uqadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_uqadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_uqadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_uqadd_s64, TCG_CALL_NO_RWG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(neon_sqadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_sqadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_sqadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(neon_sqadd_u64, TCG_CALL_NO_RWG, i64, env, i64, i64)
-DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qsub_s16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qsub_u32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qsub_s32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qadd_u64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qadd_s64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qsub_u64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qsub_s64, i64, env, i64, i64)
-
-DEF_HELPER_2(neon_hadd_s8, i32, i32, i32)
-DEF_HELPER_2(neon_hadd_u8, i32, i32, i32)
-DEF_HELPER_2(neon_hadd_s16, i32, i32, i32)
-DEF_HELPER_2(neon_hadd_u16, i32, i32, i32)
-DEF_HELPER_2(neon_hadd_s32, s32, s32, s32)
-DEF_HELPER_2(neon_hadd_u32, i32, i32, i32)
-DEF_HELPER_2(neon_rhadd_s8, i32, i32, i32)
-DEF_HELPER_2(neon_rhadd_u8, i32, i32, i32)
-DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32)
-DEF_HELPER_2(neon_rhadd_u16, i32, i32, i32)
-DEF_HELPER_2(neon_rhadd_s32, s32, s32, s32)
-DEF_HELPER_2(neon_rhadd_u32, i32, i32, i32)
-DEF_HELPER_2(neon_hsub_s8, i32, i32, i32)
-DEF_HELPER_2(neon_hsub_u8, i32, i32, i32)
-DEF_HELPER_2(neon_hsub_s16, i32, i32, i32)
-DEF_HELPER_2(neon_hsub_u16, i32, i32, i32)
-DEF_HELPER_2(neon_hsub_s32, s32, s32, s32)
-DEF_HELPER_2(neon_hsub_u32, i32, i32, i32)
-
-DEF_HELPER_2(neon_pmin_u8, i32, i32, i32)
-DEF_HELPER_2(neon_pmin_s8, i32, i32, i32)
-DEF_HELPER_2(neon_pmin_u16, i32, i32, i32)
-DEF_HELPER_2(neon_pmin_s16, i32, i32, i32)
-DEF_HELPER_2(neon_pmax_u8, i32, i32, i32)
-DEF_HELPER_2(neon_pmax_s8, i32, i32, i32)
-DEF_HELPER_2(neon_pmax_u16, i32, i32, i32)
-DEF_HELPER_2(neon_pmax_s16, i32, i32, i32)
-
-DEF_HELPER_2(neon_shl_u16, i32, i32, i32)
-DEF_HELPER_2(neon_shl_s16, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_u8, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_s8, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_u16, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_s16, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_u32, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_s32, i32, i32, i32)
-DEF_HELPER_2(neon_rshl_u64, i64, i64, i64)
-DEF_HELPER_2(neon_rshl_s64, i64, i64, i64)
-DEF_HELPER_3(neon_qshl_u8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_s8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_u16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_s16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_u32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_s32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshl_u64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qshl_s64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qshlu_s8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshlu_s16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshlu_s32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qshlu_s64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qrshl_u8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_s8, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_u16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_s16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64)
-DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64)
-
-DEF_HELPER_2(neon_add_u8, i32, i32, i32)
-DEF_HELPER_2(neon_add_u16, i32, i32, i32)
-DEF_HELPER_2(neon_padd_u8, i32, i32, i32)
-DEF_HELPER_2(neon_padd_u16, i32, i32, i32)
-DEF_HELPER_2(neon_sub_u8, i32, i32, i32)
-DEF_HELPER_2(neon_sub_u16, i32, i32, i32)
-DEF_HELPER_2(neon_mul_u8, i32, i32, i32)
-DEF_HELPER_2(neon_mul_u16, i32, i32, i32)
-
-DEF_HELPER_2(neon_tst_u8, i32, i32, i32)
-DEF_HELPER_2(neon_tst_u16, i32, i32, i32)
-DEF_HELPER_2(neon_tst_u32, i32, i32, i32)
-
-DEF_HELPER_1(neon_clz_u8, i32, i32)
-DEF_HELPER_1(neon_clz_u16, i32, i32)
-DEF_HELPER_1(neon_cls_s8, i32, i32)
-DEF_HELPER_1(neon_cls_s16, i32, i32)
-DEF_HELPER_1(neon_cls_s32, i32, i32)
-DEF_HELPER_1(neon_cnt_u8, i32, i32)
-DEF_HELPER_FLAGS_1(neon_rbit_u8, TCG_CALL_NO_RWG_SE, i32, i32)
-
-DEF_HELPER_3(neon_qdmulh_s16, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrdmulh_s16, i32, env, i32, i32)
-DEF_HELPER_4(neon_qrdmlah_s16, i32, env, i32, i32, i32)
-DEF_HELPER_4(neon_qrdmlsh_s16, i32, env, i32, i32, i32)
-DEF_HELPER_3(neon_qdmulh_s32, i32, env, i32, i32)
-DEF_HELPER_3(neon_qrdmulh_s32, i32, env, i32, i32)
-DEF_HELPER_4(neon_qrdmlah_s32, i32, env, s32, s32, s32)
-DEF_HELPER_4(neon_qrdmlsh_s32, i32, env, s32, s32, s32)
-
-DEF_HELPER_1(neon_narrow_u8, i32, i64)
-DEF_HELPER_1(neon_narrow_u16, i32, i64)
-DEF_HELPER_2(neon_unarrow_sat8, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u8, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s8, i32, env, i64)
-DEF_HELPER_2(neon_unarrow_sat16, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u16, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s16, i32, env, i64)
-DEF_HELPER_2(neon_unarrow_sat32, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u32, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s32, i32, env, i64)
-DEF_HELPER_1(neon_narrow_high_u8, i32, i64)
-DEF_HELPER_1(neon_narrow_high_u16, i32, i64)
-DEF_HELPER_1(neon_narrow_round_high_u8, i32, i64)
-DEF_HELPER_1(neon_narrow_round_high_u16, i32, i64)
-DEF_HELPER_1(neon_widen_u8, i64, i32)
-DEF_HELPER_1(neon_widen_s8, i64, i32)
-DEF_HELPER_1(neon_widen_u16, i64, i32)
-DEF_HELPER_1(neon_widen_s16, i64, i32)
-
-DEF_HELPER_2(neon_addl_u16, i64, i64, i64)
-DEF_HELPER_2(neon_addl_u32, i64, i64, i64)
-DEF_HELPER_2(neon_paddl_u16, i64, i64, i64)
-DEF_HELPER_2(neon_paddl_u32, i64, i64, i64)
-DEF_HELPER_2(neon_subl_u16, i64, i64, i64)
-DEF_HELPER_2(neon_subl_u32, i64, i64, i64)
-DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64)
-DEF_HELPER_3(neon_addl_saturate_s64, i64, env, i64, i64)
-DEF_HELPER_2(neon_abdl_u16, i64, i32, i32)
-DEF_HELPER_2(neon_abdl_s16, i64, i32, i32)
-DEF_HELPER_2(neon_abdl_u32, i64, i32, i32)
-DEF_HELPER_2(neon_abdl_s32, i64, i32, i32)
-DEF_HELPER_2(neon_abdl_u64, i64, i32, i32)
-DEF_HELPER_2(neon_abdl_s64, i64, i32, i32)
-DEF_HELPER_2(neon_mull_u8, i64, i32, i32)
-DEF_HELPER_2(neon_mull_s8, i64, i32, i32)
-DEF_HELPER_2(neon_mull_u16, i64, i32, i32)
-DEF_HELPER_2(neon_mull_s16, i64, i32, i32)
-
-DEF_HELPER_1(neon_negl_u16, i64, i64)
-DEF_HELPER_1(neon_negl_u32, i64, i64)
-
-DEF_HELPER_FLAGS_2(neon_qabs_s8, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qabs_s16, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qabs_s32, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qabs_s64, TCG_CALL_NO_RWG, i64, env, i64)
-DEF_HELPER_FLAGS_2(neon_qneg_s8, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32)
-DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64)
-
-DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
-DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr)
-DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr)
-DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr)
-DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr)
-DEF_HELPER_3(neon_acge_f64, i64, i64, i64, ptr)
-DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, ptr)
-
-DEF_HELPER_FLAGS_2(neon_unzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_unzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qunzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qunzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qunzip32, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_zip8, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_zip16, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr)
-
DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
@@ -396,13 +209,6 @@ DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
@@ -618,8 +424,6 @@ DEF_HELPER_FLAGS_4(gvec_ushl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_pmul_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(neon_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_3(gvec_ssra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(gvec_ssra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(gvec_ssra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
@@ -698,16 +502,6 @@ DEF_HELPER_FLAGS_5(gvec_mls_idx_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_mls_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_sqdmulh_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_sqdmulh_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
@@ -783,4 +577,5 @@ DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG,
#include "tcg/helper-sme.h.inc"
#endif
+#include "tcg/helper-neon.h.inc"
#include "tcg/helper-mve.h.inc"
diff --git a/target/arm/tcg/helper-a64.h.inc b/target/arm/tcg/helper-a64.h.inc
index e6c518323e..adff15600d 100644
--- a/target/arm/tcg/helper-a64.h.inc
+++ b/target/arm/tcg/helper-a64.h.inc
@@ -23,19 +23,12 @@ DEF_HELPER_2(msr_i_spsel, void, env, i32)
DEF_HELPER_2(msr_i_daifset, void, env, i32)
DEF_HELPER_2(msr_i_daifclear, void, env, i32)
DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
-DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
-DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
DEF_HELPER_FLAGS_3(recpsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
-DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64)
-DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64)
-DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64)
-DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
diff --git a/target/arm/tcg/helper-neon.h.inc b/target/arm/tcg/helper-neon.h.inc
new file mode 100644
index 0000000000..838d05c359
--- /dev/null
+++ b/target/arm/tcg/helper-neon.h.inc
@@ -0,0 +1,224 @@
+/*
+ * ARM NEON helper definitions
+ *
+ * Copyright (c) 2007, 2008 CodeSourcery.
+ * Written by Paul Brook
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i64, env, i32, i64, i64)
+
+DEF_HELPER_FLAGS_3(neon_qadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_qadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_qadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_qadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_qadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_qadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_uqadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_uqadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_uqadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_uqadd_s64, TCG_CALL_NO_RWG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(neon_sqadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_sqadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_sqadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(neon_sqadd_u64, TCG_CALL_NO_RWG, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qadd_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_s64, i64, env, i64, i64)
+
+DEF_HELPER_2(neon_hadd_s8, i32, i32, i32)
+DEF_HELPER_2(neon_hadd_u8, i32, i32, i32)
+DEF_HELPER_2(neon_hadd_s16, i32, i32, i32)
+DEF_HELPER_2(neon_hadd_u16, i32, i32, i32)
+DEF_HELPER_2(neon_hadd_s32, s32, s32, s32)
+DEF_HELPER_2(neon_hadd_u32, i32, i32, i32)
+DEF_HELPER_2(neon_rhadd_s8, i32, i32, i32)
+DEF_HELPER_2(neon_rhadd_u8, i32, i32, i32)
+DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32)
+DEF_HELPER_2(neon_rhadd_u16, i32, i32, i32)
+DEF_HELPER_2(neon_rhadd_s32, s32, s32, s32)
+DEF_HELPER_2(neon_rhadd_u32, i32, i32, i32)
+DEF_HELPER_2(neon_hsub_s8, i32, i32, i32)
+DEF_HELPER_2(neon_hsub_u8, i32, i32, i32)
+DEF_HELPER_2(neon_hsub_s16, i32, i32, i32)
+DEF_HELPER_2(neon_hsub_u16, i32, i32, i32)
+DEF_HELPER_2(neon_hsub_s32, s32, s32, s32)
+DEF_HELPER_2(neon_hsub_u32, i32, i32, i32)
+
+DEF_HELPER_2(neon_pmin_u8, i32, i32, i32)
+DEF_HELPER_2(neon_pmin_s8, i32, i32, i32)
+DEF_HELPER_2(neon_pmin_u16, i32, i32, i32)
+DEF_HELPER_2(neon_pmin_s16, i32, i32, i32)
+DEF_HELPER_2(neon_pmax_u8, i32, i32, i32)
+DEF_HELPER_2(neon_pmax_s8, i32, i32, i32)
+DEF_HELPER_2(neon_pmax_u16, i32, i32, i32)
+DEF_HELPER_2(neon_pmax_s16, i32, i32, i32)
+
+DEF_HELPER_2(neon_shl_u16, i32, i32, i32)
+DEF_HELPER_2(neon_shl_s16, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_u8, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_s8, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_u16, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_s16, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_u32, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_s32, i32, i32, i32)
+DEF_HELPER_2(neon_rshl_u64, i64, i64, i64)
+DEF_HELPER_2(neon_rshl_s64, i64, i64, i64)
+DEF_HELPER_3(neon_qshl_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qshl_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qshlu_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshlu_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshlu_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshlu_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qrshl_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64)
+
+DEF_HELPER_2(neon_add_u8, i32, i32, i32)
+DEF_HELPER_2(neon_add_u16, i32, i32, i32)
+DEF_HELPER_2(neon_padd_u8, i32, i32, i32)
+DEF_HELPER_2(neon_padd_u16, i32, i32, i32)
+DEF_HELPER_2(neon_sub_u8, i32, i32, i32)
+DEF_HELPER_2(neon_sub_u16, i32, i32, i32)
+DEF_HELPER_2(neon_mul_u8, i32, i32, i32)
+DEF_HELPER_2(neon_mul_u16, i32, i32, i32)
+
+DEF_HELPER_2(neon_tst_u8, i32, i32, i32)
+DEF_HELPER_2(neon_tst_u16, i32, i32, i32)
+DEF_HELPER_2(neon_tst_u32, i32, i32, i32)
+
+DEF_HELPER_1(neon_clz_u8, i32, i32)
+DEF_HELPER_1(neon_clz_u16, i32, i32)
+DEF_HELPER_1(neon_cls_s8, i32, i32)
+DEF_HELPER_1(neon_cls_s16, i32, i32)
+DEF_HELPER_1(neon_cls_s32, i32, i32)
+DEF_HELPER_1(neon_cnt_u8, i32, i32)
+DEF_HELPER_FLAGS_1(neon_rbit_u8, TCG_CALL_NO_RWG_SE, i32, i32)
+
+DEF_HELPER_3(neon_qdmulh_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrdmulh_s16, i32, env, i32, i32)
+DEF_HELPER_4(neon_qrdmlah_s16, i32, env, i32, i32, i32)
+DEF_HELPER_4(neon_qrdmlsh_s16, i32, env, i32, i32, i32)
+DEF_HELPER_3(neon_qdmulh_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrdmulh_s32, i32, env, i32, i32)
+DEF_HELPER_4(neon_qrdmlah_s32, i32, env, s32, s32, s32)
+DEF_HELPER_4(neon_qrdmlsh_s32, i32, env, s32, s32, s32)
+
+DEF_HELPER_1(neon_narrow_u8, i32, i64)
+DEF_HELPER_1(neon_narrow_u16, i32, i64)
+DEF_HELPER_2(neon_unarrow_sat8, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u8, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s8, i32, env, i64)
+DEF_HELPER_2(neon_unarrow_sat16, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u16, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s16, i32, env, i64)
+DEF_HELPER_2(neon_unarrow_sat32, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u32, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s32, i32, env, i64)
+DEF_HELPER_1(neon_narrow_high_u8, i32, i64)
+DEF_HELPER_1(neon_narrow_high_u16, i32, i64)
+DEF_HELPER_1(neon_narrow_round_high_u8, i32, i64)
+DEF_HELPER_1(neon_narrow_round_high_u16, i32, i64)
+DEF_HELPER_1(neon_widen_u8, i64, i32)
+DEF_HELPER_1(neon_widen_s8, i64, i32)
+DEF_HELPER_1(neon_widen_u16, i64, i32)
+DEF_HELPER_1(neon_widen_s16, i64, i32)
+
+DEF_HELPER_2(neon_addl_u16, i64, i64, i64)
+DEF_HELPER_2(neon_addl_u32, i64, i64, i64)
+DEF_HELPER_2(neon_paddl_u16, i64, i64, i64)
+DEF_HELPER_2(neon_paddl_u32, i64, i64, i64)
+DEF_HELPER_2(neon_subl_u16, i64, i64, i64)
+DEF_HELPER_2(neon_subl_u32, i64, i64, i64)
+DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64)
+DEF_HELPER_3(neon_addl_saturate_s64, i64, env, i64, i64)
+DEF_HELPER_2(neon_abdl_u16, i64, i32, i32)
+DEF_HELPER_2(neon_abdl_s16, i64, i32, i32)
+DEF_HELPER_2(neon_abdl_u32, i64, i32, i32)
+DEF_HELPER_2(neon_abdl_s32, i64, i32, i32)
+DEF_HELPER_2(neon_abdl_u64, i64, i32, i32)
+DEF_HELPER_2(neon_abdl_s64, i64, i32, i32)
+DEF_HELPER_2(neon_mull_u8, i64, i32, i32)
+DEF_HELPER_2(neon_mull_s8, i64, i32, i32)
+DEF_HELPER_2(neon_mull_u16, i64, i32, i32)
+DEF_HELPER_2(neon_mull_s16, i64, i32, i32)
+
+DEF_HELPER_1(neon_negl_u16, i64, i64)
+DEF_HELPER_1(neon_negl_u32, i64, i64)
+
+DEF_HELPER_FLAGS_2(neon_qabs_s8, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s16, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s32, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s64, TCG_CALL_NO_RWG, i64, env, i64)
+DEF_HELPER_FLAGS_2(neon_qneg_s8, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64)
+
+DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acge_f64, i64, i64, i64, ptr)
+DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, ptr)
+
+DEF_HELPER_FLAGS_2(neon_unzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_unzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qunzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qunzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qunzip32, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_zip8, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_zip16, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qzip8, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qzip16, TCG_CALL_NO_RWG, void, ptr, ptr)
+DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr)
+
+DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(neon_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(neon_sqdmulh_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_sqdmulh_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+#ifdef TARGET_AARCH64
+DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64)
+DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64)
+DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64)
+DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64)
+
+DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
+DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
+DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
+#endif
--
2.38.1
Instead of including helper-neon.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 1 -
target/arm/tcg/neon_helper.c | 5 ++++-
target/arm/tcg/translate-a64.c | 4 ++++
target/arm/tcg/translate-neon.c | 6 ++++++
target/arm/tcg/translate-sme.c | 4 ++++
target/arm/tcg/translate.c | 4 ++++
target/arm/tcg/vec_helper.c | 4 ++++
7 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 2600c150f4..819d27d597 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -577,5 +577,4 @@ DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG,
#include "tcg/helper-sme.h.inc"
#endif
-#include "tcg/helper-neon.h.inc"
#include "tcg/helper-mve.h.inc"
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index cd668eb43a..6a4b3a8abf 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -9,10 +9,13 @@
#include "qemu/osdep.h"
#include "cpu.h"
-#include "exec/helper-proto.h"
#include "fpu/softfloat.h"
#include "vec_internal.h"
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
#define SIGNBIT (uint32_t)0x80000000
#define SIGNBIT64 ((uint64_t)1 << 63)
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index c0727c900f..22caf89bb0 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -30,6 +30,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 497aba2e39..9a1831f849 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -28,6 +28,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
/* Include the generated Neon decoder */
#include "decode-neon-dp.c.inc"
#include "decode-neon-ls.c.inc"
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index d0054e3f77..24796e5d9e 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -21,6 +21,10 @@
#include "translate.h"
#include "translate-a64.h"
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
/*
* Include the generated decoder.
*/
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index a352fced6e..2b3951cece 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -29,6 +29,10 @@
#include "cpregs.h"
#include "exec/helper-proto.h"
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "helper.h"
#include "exec/helper-info.c.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 013ca1b05f..af325577f0 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -29,6 +29,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/*
* Data for expanding active predicate bits to bytes, for byte elements.
*
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > Instead of including helper-neon.h.inc via helper.h which > is included by all TCG files, restrict it to the few files > that require it. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 1 - > target/arm/tcg/neon_helper.c | 5 ++++- > target/arm/tcg/translate-a64.c | 4 ++++ > target/arm/tcg/translate-neon.c | 6 ++++++ > target/arm/tcg/translate-sme.c | 4 ++++ > target/arm/tcg/translate.c | 4 ++++ > target/arm/tcg/vec_helper.c | 4 ++++ > 7 files changed, 26 insertions(+), 2 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
We want to extract gvec helpers to a new translate-gvec.c
file. Some helpers will still be accessed out of it, from
the current translate.c. Expose their prototype.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/translate.h | 5 +++++
target/arm/tcg/translate.c | 8 ++++----
2 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index d2a98b9f3a..7d57a71b67 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -418,6 +418,11 @@ void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
+void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh);
+void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh);
+void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh);
+void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh);
+
void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index 2b3951cece..adefa737c9 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -1925,7 +1925,7 @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
tcg_gen_vec_add16_i64(d, d, t);
}
-static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
{
TCGv_i32 t;
@@ -1940,7 +1940,7 @@ static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
tcg_gen_add_i32(d, d, t);
}
-static void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
{
TCGv_i64 t = tcg_temp_new_i64();
@@ -2120,7 +2120,7 @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
tcg_gen_vec_add16_i64(d, d, t);
}
-static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
{
TCGv_i32 t;
@@ -2135,7 +2135,7 @@ static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
tcg_gen_add_i32(d, d, t);
}
-static void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
{
TCGv_i64 t = tcg_temp_new_i64();
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > We want to extract gvec helpers to a new translate-gvec.c > file. Some helpers will still be accessed out of it, from > the current translate.c. Expose their prototype. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/tcg/translate.h | 5 +++++ > target/arm/tcg/translate.c | 8 ++++---- > 2 files changed, 9 insertions(+), 4 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Extract 1600 lines from the big enough translate.c.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/translate-gvec.c | 1644 +++++++++++++++++++++++++++++++
target/arm/tcg/translate.c | 1630 ------------------------------
target/arm/tcg/meson.build | 1 +
3 files changed, 1645 insertions(+), 1630 deletions(-)
create mode 100644 target/arm/tcg/translate-gvec.c
diff --git a/target/arm/tcg/translate-gvec.c b/target/arm/tcg/translate-gvec.c
new file mode 100644
index 0000000000..8b1d5e283c
--- /dev/null
+++ b/target/arm/tcg/translate-gvec.c
@@ -0,0 +1,1644 @@
+/*
+ * ARM AdvSIMD / SVE Vector Helpers
+ *
+ * Copyright (c) 2020 Linaro
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "translate.h"
+
+#define HELPER_H "tcg/helper-neon.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
+static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
+ uint32_t opr_sz, uint32_t max_sz,
+ gen_helper_gvec_3_ptr *fn)
+{
+ TCGv_ptr qc_ptr = tcg_temp_new_ptr();
+
+ tcg_gen_addi_ptr(qc_ptr, cpu_env, offsetof(CPUARMState, vfp.qc));
+ tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr,
+ opr_sz, max_sz, 0, fn);
+}
+
+void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3_ptr * const fns[2] = {
+ gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32
+ };
+ tcg_debug_assert(vece >= 1 && vece <= 2);
+ gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
+void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3_ptr * const fns[2] = {
+ gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32
+ };
+ tcg_debug_assert(vece >= 1 && vece <= 2);
+ gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
+#define GEN_CMP0(NAME, COND) \
+ static void gen_##NAME##0_i32(TCGv_i32 d, TCGv_i32 a) \
+ { \
+ tcg_gen_setcondi_i32(COND, d, a, 0); \
+ tcg_gen_neg_i32(d, d); \
+ } \
+ static void gen_##NAME##0_i64(TCGv_i64 d, TCGv_i64 a) \
+ { \
+ tcg_gen_setcondi_i64(COND, d, a, 0); \
+ tcg_gen_neg_i64(d, d); \
+ } \
+ static void gen_##NAME##0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) \
+ { \
+ TCGv_vec zero = tcg_constant_vec_matching(d, vece, 0); \
+ tcg_gen_cmp_vec(COND, vece, d, a, zero); \
+ } \
+ void gen_gvec_##NAME##0(unsigned vece, uint32_t d, uint32_t m, \
+ uint32_t opr_sz, uint32_t max_sz) \
+ { \
+ const GVecGen2 op[4] = { \
+ { .fno = gen_helper_gvec_##NAME##0_b, \
+ .fniv = gen_##NAME##0_vec, \
+ .opt_opc = vecop_list_cmp, \
+ .vece = MO_8 }, \
+ { .fno = gen_helper_gvec_##NAME##0_h, \
+ .fniv = gen_##NAME##0_vec, \
+ .opt_opc = vecop_list_cmp, \
+ .vece = MO_16 }, \
+ { .fni4 = gen_##NAME##0_i32, \
+ .fniv = gen_##NAME##0_vec, \
+ .opt_opc = vecop_list_cmp, \
+ .vece = MO_32 }, \
+ { .fni8 = gen_##NAME##0_i64, \
+ .fniv = gen_##NAME##0_vec, \
+ .opt_opc = vecop_list_cmp, \
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64, \
+ .vece = MO_64 }, \
+ }; \
+ tcg_gen_gvec_2(d, m, opr_sz, max_sz, &op[vece]); \
+ }
+
+static const TCGOpcode vecop_list_cmp[] = {
+ INDEX_op_cmp_vec, 0
+};
+
+GEN_CMP0(ceq, TCG_COND_EQ)
+GEN_CMP0(cle, TCG_COND_LE)
+GEN_CMP0(cge, TCG_COND_GE)
+GEN_CMP0(clt, TCG_COND_LT)
+GEN_CMP0(cgt, TCG_COND_GT)
+
+#undef GEN_CMP0
+
+static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_vec_sar8i_i64(a, a, shift);
+ tcg_gen_vec_add8_i64(d, d, a);
+}
+
+static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_vec_sar16i_i64(a, a, shift);
+ tcg_gen_vec_add16_i64(d, d, a);
+}
+
+static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
+{
+ tcg_gen_sari_i32(a, a, shift);
+ tcg_gen_add_i32(d, d, a);
+}
+
+static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_sari_i64(a, a, shift);
+ tcg_gen_add_i64(d, d, a);
+}
+
+static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ tcg_gen_sari_vec(vece, a, a, sh);
+ tcg_gen_add_vec(vece, d, d, a);
+}
+
+void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sari_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_ssra8_i64,
+ .fniv = gen_ssra_vec,
+ .fno = gen_helper_gvec_ssra_b,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni8 = gen_ssra16_i64,
+ .fniv = gen_ssra_vec,
+ .fno = gen_helper_gvec_ssra_h,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_ssra32_i32,
+ .fniv = gen_ssra_vec,
+ .fno = gen_helper_gvec_ssra_s,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_ssra64_i64,
+ .fniv = gen_ssra_vec,
+ .fno = gen_helper_gvec_ssra_b,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize]. */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ /*
+ * Shifts larger than the element size are architecturally valid.
+ * Signed results in all sign bits.
+ */
+ shift = MIN(shift, (8 << vece) - 1);
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+}
+
+static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_vec_shr8i_i64(a, a, shift);
+ tcg_gen_vec_add8_i64(d, d, a);
+}
+
+static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_vec_shr16i_i64(a, a, shift);
+ tcg_gen_vec_add16_i64(d, d, a);
+}
+
+static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
+{
+ tcg_gen_shri_i32(a, a, shift);
+ tcg_gen_add_i32(d, d, a);
+}
+
+static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_shri_i64(a, a, shift);
+ tcg_gen_add_i64(d, d, a);
+}
+
+static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ tcg_gen_shri_vec(vece, a, a, sh);
+ tcg_gen_add_vec(vece, d, d, a);
+}
+
+void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shri_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_usra8_i64,
+ .fniv = gen_usra_vec,
+ .fno = gen_helper_gvec_usra_b,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8, },
+ { .fni8 = gen_usra16_i64,
+ .fniv = gen_usra_vec,
+ .fno = gen_helper_gvec_usra_h,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16, },
+ { .fni4 = gen_usra32_i32,
+ .fniv = gen_usra_vec,
+ .fno = gen_helper_gvec_usra_s,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32, },
+ { .fni8 = gen_usra64_i64,
+ .fniv = gen_usra_vec,
+ .fno = gen_helper_gvec_usra_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64, },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize]. */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ /*
+ * Shifts larger than the element size are architecturally valid.
+ * Unsigned results in all zeros as input to accumulate: nop.
+ */
+ if (shift < (8 << vece)) {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ } else {
+ /* Nop, but we do need to clear the tail. */
+ tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
+ }
+}
+
+/*
+ * Shift one less than the requested amount, and the low bit is
+ * the rounding bit. For the 8 and 16-bit operations, because we
+ * mask the low bit, we can perform a normal integer shift instead
+ * of a vector shift.
+ */
+static void gen_srshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, sh - 1);
+ tcg_gen_andi_i64(t, t, dup_const(MO_8, 1));
+ tcg_gen_vec_sar8i_i64(d, a, sh);
+ tcg_gen_vec_add8_i64(d, d, t);
+}
+
+static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, sh - 1);
+ tcg_gen_andi_i64(t, t, dup_const(MO_16, 1));
+ tcg_gen_vec_sar16i_i64(d, a, sh);
+ tcg_gen_vec_add16_i64(d, d, t);
+}
+
+void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+{
+ TCGv_i32 t;
+
+ /* Handle shift by the input size for the benefit of trans_SRSHR_ri */
+ if (sh == 32) {
+ tcg_gen_movi_i32(d, 0);
+ return;
+ }
+ t = tcg_temp_new_i32();
+ tcg_gen_extract_i32(t, a, sh - 1, 1);
+ tcg_gen_sari_i32(d, a, sh);
+ tcg_gen_add_i32(d, d, t);
+}
+
+void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_extract_i64(t, a, sh - 1, 1);
+ tcg_gen_sari_i64(d, a, sh);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ TCGv_vec ones = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_shri_vec(vece, t, a, sh - 1);
+ tcg_gen_dupi_vec(vece, ones, 1);
+ tcg_gen_and_vec(vece, t, t, ones);
+ tcg_gen_sari_vec(vece, d, a, sh);
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_srshr8_i64,
+ .fniv = gen_srshr_vec,
+ .fno = gen_helper_gvec_srshr_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni8 = gen_srshr16_i64,
+ .fniv = gen_srshr_vec,
+ .fno = gen_helper_gvec_srshr_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_srshr32_i32,
+ .fniv = gen_srshr_vec,
+ .fno = gen_helper_gvec_srshr_s,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_srshr64_i64,
+ .fniv = gen_srshr_vec,
+ .fno = gen_helper_gvec_srshr_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize] */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ if (shift == (8 << vece)) {
+ /*
+ * Shifts larger than the element size are architecturally valid.
+ * Signed results in all sign bits. With rounding, this produces
+ * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0.
+ * I.e. always zero.
+ */
+ tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0);
+ } else {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ }
+}
+
+static void gen_srsra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ gen_srshr8_i64(t, a, sh);
+ tcg_gen_vec_add8_i64(d, d, t);
+}
+
+static void gen_srsra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ gen_srshr16_i64(t, a, sh);
+ tcg_gen_vec_add16_i64(d, d, t);
+}
+
+static void gen_srsra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+
+ gen_srshr32_i32(t, a, sh);
+ tcg_gen_add_i32(d, d, t);
+}
+
+static void gen_srsra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ gen_srshr64_i64(t, a, sh);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_srsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+
+ gen_srshr_vec(vece, t, a, sh);
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_srsra8_i64,
+ .fniv = gen_srsra_vec,
+ .fno = gen_helper_gvec_srsra_b,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_8 },
+ { .fni8 = gen_srsra16_i64,
+ .fniv = gen_srsra_vec,
+ .fno = gen_helper_gvec_srsra_h,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_16 },
+ { .fni4 = gen_srsra32_i32,
+ .fniv = gen_srsra_vec,
+ .fno = gen_helper_gvec_srsra_s,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_32 },
+ { .fni8 = gen_srsra64_i64,
+ .fniv = gen_srsra_vec,
+ .fno = gen_helper_gvec_srsra_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize] */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ /*
+ * Shifts larger than the element size are architecturally valid.
+ * Signed results in all sign bits. With rounding, this produces
+ * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0.
+ * I.e. always zero. With accumulation, this leaves D unchanged.
+ */
+ if (shift == (8 << vece)) {
+ /* Nop, but we do need to clear the tail. */
+ tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
+ } else {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ }
+}
+
+static void gen_urshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, sh - 1);
+ tcg_gen_andi_i64(t, t, dup_const(MO_8, 1));
+ tcg_gen_vec_shr8i_i64(d, a, sh);
+ tcg_gen_vec_add8_i64(d, d, t);
+}
+
+static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, sh - 1);
+ tcg_gen_andi_i64(t, t, dup_const(MO_16, 1));
+ tcg_gen_vec_shr16i_i64(d, a, sh);
+ tcg_gen_vec_add16_i64(d, d, t);
+}
+
+void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+{
+ TCGv_i32 t;
+
+ /* Handle shift by the input size for the benefit of trans_URSHR_ri */
+ if (sh == 32) {
+ tcg_gen_extract_i32(d, a, sh - 1, 1);
+ return;
+ }
+ t = tcg_temp_new_i32();
+ tcg_gen_extract_i32(t, a, sh - 1, 1);
+ tcg_gen_shri_i32(d, a, sh);
+ tcg_gen_add_i32(d, d, t);
+}
+
+void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_extract_i64(t, a, sh - 1, 1);
+ tcg_gen_shri_i64(d, a, sh);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ TCGv_vec ones = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_shri_vec(vece, t, a, shift - 1);
+ tcg_gen_dupi_vec(vece, ones, 1);
+ tcg_gen_and_vec(vece, t, t, ones);
+ tcg_gen_shri_vec(vece, d, a, shift);
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shri_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_urshr8_i64,
+ .fniv = gen_urshr_vec,
+ .fno = gen_helper_gvec_urshr_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni8 = gen_urshr16_i64,
+ .fniv = gen_urshr_vec,
+ .fno = gen_helper_gvec_urshr_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_urshr32_i32,
+ .fniv = gen_urshr_vec,
+ .fno = gen_helper_gvec_urshr_s,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_urshr64_i64,
+ .fniv = gen_urshr_vec,
+ .fno = gen_helper_gvec_urshr_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize] */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ if (shift == (8 << vece)) {
+ /*
+ * Shifts larger than the element size are architecturally valid.
+ * Unsigned results in zero. With rounding, this produces a
+ * copy of the most significant bit.
+ */
+ tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift - 1, opr_sz, max_sz);
+ } else {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ }
+}
+
+static void gen_ursra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ if (sh == 8) {
+ tcg_gen_vec_shr8i_i64(t, a, 7);
+ } else {
+ gen_urshr8_i64(t, a, sh);
+ }
+ tcg_gen_vec_add8_i64(d, d, t);
+}
+
+static void gen_ursra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ if (sh == 16) {
+ tcg_gen_vec_shr16i_i64(t, a, 15);
+ } else {
+ gen_urshr16_i64(t, a, sh);
+ }
+ tcg_gen_vec_add16_i64(d, d, t);
+}
+
+static void gen_ursra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+
+ if (sh == 32) {
+ tcg_gen_shri_i32(t, a, 31);
+ } else {
+ gen_urshr32_i32(t, a, sh);
+ }
+ tcg_gen_add_i32(d, d, t);
+}
+
+static void gen_ursra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ if (sh == 64) {
+ tcg_gen_shri_i64(t, a, 63);
+ } else {
+ gen_urshr64_i64(t, a, sh);
+ }
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_ursra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+
+ if (sh == (8 << vece)) {
+ tcg_gen_shri_vec(vece, t, a, sh - 1);
+ } else {
+ gen_urshr_vec(vece, t, a, sh);
+ }
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shri_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen2i ops[4] = {
+ { .fni8 = gen_ursra8_i64,
+ .fniv = gen_ursra_vec,
+ .fno = gen_helper_gvec_ursra_b,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_8 },
+ { .fni8 = gen_ursra16_i64,
+ .fniv = gen_ursra_vec,
+ .fno = gen_helper_gvec_ursra_h,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_16 },
+ { .fni4 = gen_ursra32_i32,
+ .fniv = gen_ursra_vec,
+ .fno = gen_helper_gvec_ursra_s,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_32 },
+ { .fni8 = gen_ursra64_i64,
+ .fniv = gen_ursra_vec,
+ .fno = gen_helper_gvec_ursra_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize] */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+}
+
+static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ uint64_t mask = dup_const(MO_8, 0xff >> shift);
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, shift);
+ tcg_gen_andi_i64(t, t, mask);
+ tcg_gen_andi_i64(d, d, ~mask);
+ tcg_gen_or_i64(d, d, t);
+}
+
+static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ uint64_t mask = dup_const(MO_16, 0xffff >> shift);
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shri_i64(t, a, shift);
+ tcg_gen_andi_i64(t, t, mask);
+ tcg_gen_andi_i64(d, d, ~mask);
+ tcg_gen_or_i64(d, d, t);
+}
+
+static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
+{
+ tcg_gen_shri_i32(a, a, shift);
+ tcg_gen_deposit_i32(d, d, a, 0, 32 - shift);
+}
+
+static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_shri_i64(a, a, shift);
+ tcg_gen_deposit_i64(d, d, a, 0, 64 - shift);
+}
+
+static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ TCGv_vec m = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh));
+ tcg_gen_shri_vec(vece, t, a, sh);
+ tcg_gen_and_vec(vece, d, d, m);
+ tcg_gen_or_vec(vece, d, d, t);
+}
+
+void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 };
+ const GVecGen2i ops[4] = {
+ { .fni8 = gen_shr8_ins_i64,
+ .fniv = gen_shr_ins_vec,
+ .fno = gen_helper_gvec_sri_b,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni8 = gen_shr16_ins_i64,
+ .fniv = gen_shr_ins_vec,
+ .fno = gen_helper_gvec_sri_h,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_shr32_ins_i32,
+ .fniv = gen_shr_ins_vec,
+ .fno = gen_helper_gvec_sri_s,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_shr64_ins_i64,
+ .fniv = gen_shr_ins_vec,
+ .fno = gen_helper_gvec_sri_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [1..esize]. */
+ tcg_debug_assert(shift > 0);
+ tcg_debug_assert(shift <= (8 << vece));
+
+ /* Shift of esize leaves destination unchanged. */
+ if (shift < (8 << vece)) {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ } else {
+ /* Nop, but we do need to clear the tail. */
+ tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
+ }
+}
+
+static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ uint64_t mask = dup_const(MO_8, 0xff << shift);
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shli_i64(t, a, shift);
+ tcg_gen_andi_i64(t, t, mask);
+ tcg_gen_andi_i64(d, d, ~mask);
+ tcg_gen_or_i64(d, d, t);
+}
+
+static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ uint64_t mask = dup_const(MO_16, 0xffff << shift);
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_shli_i64(t, a, shift);
+ tcg_gen_andi_i64(t, t, mask);
+ tcg_gen_andi_i64(d, d, ~mask);
+ tcg_gen_or_i64(d, d, t);
+}
+
+static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
+{
+ tcg_gen_deposit_i32(d, d, a, shift, 32 - shift);
+}
+
+static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
+{
+ tcg_gen_deposit_i64(d, d, a, shift, 64 - shift);
+}
+
+static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ TCGv_vec m = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_shli_vec(vece, t, a, sh);
+ tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh));
+ tcg_gen_and_vec(vece, d, d, m);
+ tcg_gen_or_vec(vece, d, d, t);
+}
+
+void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 };
+ const GVecGen2i ops[4] = {
+ { .fni8 = gen_shl8_ins_i64,
+ .fniv = gen_shl_ins_vec,
+ .fno = gen_helper_gvec_sli_b,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni8 = gen_shl16_ins_i64,
+ .fniv = gen_shl_ins_vec,
+ .fno = gen_helper_gvec_sli_h,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_shl32_ins_i32,
+ .fniv = gen_shl_ins_vec,
+ .fno = gen_helper_gvec_sli_s,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_shl64_ins_i64,
+ .fniv = gen_shl_ins_vec,
+ .fno = gen_helper_gvec_sli_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+
+ /* tszimm encoding produces immediates in the range [0..esize-1]. */
+ tcg_debug_assert(shift >= 0);
+ tcg_debug_assert(shift < (8 << vece));
+
+ if (shift == 0) {
+ tcg_gen_gvec_mov(vece, rd_ofs, rm_ofs, opr_sz, max_sz);
+ } else {
+ tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
+ }
+}
+
+static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ gen_helper_neon_mul_u8(a, a, b);
+ gen_helper_neon_add_u8(d, d, a);
+}
+
+static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ gen_helper_neon_mul_u8(a, a, b);
+ gen_helper_neon_sub_u8(d, d, a);
+}
+
+static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ gen_helper_neon_mul_u16(a, a, b);
+ gen_helper_neon_add_u16(d, d, a);
+}
+
+static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ gen_helper_neon_mul_u16(a, a, b);
+ gen_helper_neon_sub_u16(d, d, a);
+}
+
+static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ tcg_gen_mul_i32(a, a, b);
+ tcg_gen_add_i32(d, d, a);
+}
+
+static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ tcg_gen_mul_i32(a, a, b);
+ tcg_gen_sub_i32(d, d, a);
+}
+
+static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ tcg_gen_mul_i64(a, a, b);
+ tcg_gen_add_i64(d, d, a);
+}
+
+static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ tcg_gen_mul_i64(a, a, b);
+ tcg_gen_sub_i64(d, d, a);
+}
+
+static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ tcg_gen_mul_vec(vece, a, a, b);
+ tcg_gen_add_vec(vece, d, d, a);
+}
+
+static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ tcg_gen_mul_vec(vece, a, a, b);
+ tcg_gen_sub_vec(vece, d, d, a);
+}
+
+/* Note that while NEON does not support VMLA and VMLS as 64-bit ops,
+ * these tables are shared with AArch64 which does support them.
+ */
+void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_mul_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fni4 = gen_mla8_i32,
+ .fniv = gen_mla_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni4 = gen_mla16_i32,
+ .fniv = gen_mla_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_mla32_i32,
+ .fniv = gen_mla_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_mla64_i64,
+ .fniv = gen_mla_vec,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_mul_vec, INDEX_op_sub_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fni4 = gen_mls8_i32,
+ .fniv = gen_mls_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni4 = gen_mls16_i32,
+ .fniv = gen_mls_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_mls32_i32,
+ .fniv = gen_mls_vec,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_mls64_i64,
+ .fniv = gen_mls_vec,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .load_dest = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+/* CMTST : test is "if (X & Y != 0)". */
+static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ tcg_gen_and_i32(d, a, b);
+ tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0);
+ tcg_gen_neg_i32(d, d);
+}
+
+void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ tcg_gen_and_i64(d, a, b);
+ tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0);
+ tcg_gen_neg_i64(d, d);
+}
+
+static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ tcg_gen_and_vec(vece, d, a, b);
+ tcg_gen_dupi_vec(vece, a, 0);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a);
+}
+
+void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = { INDEX_op_cmp_vec, 0 };
+ static const GVecGen3 ops[4] = {
+ { .fni4 = gen_helper_neon_tst_u8,
+ .fniv = gen_cmtst_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fni4 = gen_helper_neon_tst_u16,
+ .fniv = gen_cmtst_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_cmtst_i32,
+ .fniv = gen_cmtst_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_cmtst_i64,
+ .fniv = gen_cmtst_vec,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift)
+{
+ TCGv_i32 lval = tcg_temp_new_i32();
+ TCGv_i32 rval = tcg_temp_new_i32();
+ TCGv_i32 lsh = tcg_temp_new_i32();
+ TCGv_i32 rsh = tcg_temp_new_i32();
+ TCGv_i32 zero = tcg_constant_i32(0);
+ TCGv_i32 max = tcg_constant_i32(32);
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_ext8s_i32(lsh, shift);
+ tcg_gen_neg_i32(rsh, lsh);
+ tcg_gen_shl_i32(lval, src, lsh);
+ tcg_gen_shr_i32(rval, src, rsh);
+ tcg_gen_movcond_i32(TCG_COND_LTU, dst, lsh, max, lval, zero);
+ tcg_gen_movcond_i32(TCG_COND_LTU, dst, rsh, max, rval, dst);
+}
+
+void gen_ushl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift)
+{
+ TCGv_i64 lval = tcg_temp_new_i64();
+ TCGv_i64 rval = tcg_temp_new_i64();
+ TCGv_i64 lsh = tcg_temp_new_i64();
+ TCGv_i64 rsh = tcg_temp_new_i64();
+ TCGv_i64 zero = tcg_constant_i64(0);
+ TCGv_i64 max = tcg_constant_i64(64);
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_ext8s_i64(lsh, shift);
+ tcg_gen_neg_i64(rsh, lsh);
+ tcg_gen_shl_i64(lval, src, lsh);
+ tcg_gen_shr_i64(rval, src, rsh);
+ tcg_gen_movcond_i64(TCG_COND_LTU, dst, lsh, max, lval, zero);
+ tcg_gen_movcond_i64(TCG_COND_LTU, dst, rsh, max, rval, dst);
+}
+
+static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
+ TCGv_vec src, TCGv_vec shift)
+{
+ TCGv_vec lval = tcg_temp_new_vec_matching(dst);
+ TCGv_vec rval = tcg_temp_new_vec_matching(dst);
+ TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
+ TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
+ TCGv_vec msk, max;
+
+ tcg_gen_neg_vec(vece, rsh, shift);
+ if (vece == MO_8) {
+ tcg_gen_mov_vec(lsh, shift);
+ } else {
+ msk = tcg_temp_new_vec_matching(dst);
+ tcg_gen_dupi_vec(vece, msk, 0xff);
+ tcg_gen_and_vec(vece, lsh, shift, msk);
+ tcg_gen_and_vec(vece, rsh, rsh, msk);
+ }
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_shlv_vec(vece, lval, src, lsh);
+ tcg_gen_shrv_vec(vece, rval, src, rsh);
+
+ max = tcg_temp_new_vec_matching(dst);
+ tcg_gen_dupi_vec(vece, max, 8 << vece);
+
+ /*
+ * The choice of LT (signed) and GEU (unsigned) are biased toward
+ * the instructions of the x86_64 host. For MO_8, the whole byte
+ * is significant so we must use an unsigned compare; otherwise we
+ * have already masked to a byte and so a signed compare works.
+ * Other tcg hosts have a full set of comparisons and do not care.
+ */
+ if (vece == MO_8) {
+ tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max);
+ tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max);
+ tcg_gen_andc_vec(vece, lval, lval, lsh);
+ tcg_gen_andc_vec(vece, rval, rval, rsh);
+ } else {
+ tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max);
+ tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max);
+ tcg_gen_and_vec(vece, lval, lval, lsh);
+ tcg_gen_and_vec(vece, rval, rval, rsh);
+ }
+ tcg_gen_or_vec(vece, dst, lval, rval);
+}
+
+void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_neg_vec, INDEX_op_shlv_vec,
+ INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_ushl_vec,
+ .fno = gen_helper_gvec_ushl_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fniv = gen_ushl_vec,
+ .fno = gen_helper_gvec_ushl_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_ushl_i32,
+ .fniv = gen_ushl_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_ushl_i64,
+ .fniv = gen_ushl_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift)
+{
+ TCGv_i32 lval = tcg_temp_new_i32();
+ TCGv_i32 rval = tcg_temp_new_i32();
+ TCGv_i32 lsh = tcg_temp_new_i32();
+ TCGv_i32 rsh = tcg_temp_new_i32();
+ TCGv_i32 zero = tcg_constant_i32(0);
+ TCGv_i32 max = tcg_constant_i32(31);
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_ext8s_i32(lsh, shift);
+ tcg_gen_neg_i32(rsh, lsh);
+ tcg_gen_shl_i32(lval, src, lsh);
+ tcg_gen_umin_i32(rsh, rsh, max);
+ tcg_gen_sar_i32(rval, src, rsh);
+ tcg_gen_movcond_i32(TCG_COND_LEU, lval, lsh, max, lval, zero);
+ tcg_gen_movcond_i32(TCG_COND_LT, dst, lsh, zero, rval, lval);
+}
+
+void gen_sshl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift)
+{
+ TCGv_i64 lval = tcg_temp_new_i64();
+ TCGv_i64 rval = tcg_temp_new_i64();
+ TCGv_i64 lsh = tcg_temp_new_i64();
+ TCGv_i64 rsh = tcg_temp_new_i64();
+ TCGv_i64 zero = tcg_constant_i64(0);
+ TCGv_i64 max = tcg_constant_i64(63);
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_ext8s_i64(lsh, shift);
+ tcg_gen_neg_i64(rsh, lsh);
+ tcg_gen_shl_i64(lval, src, lsh);
+ tcg_gen_umin_i64(rsh, rsh, max);
+ tcg_gen_sar_i64(rval, src, rsh);
+ tcg_gen_movcond_i64(TCG_COND_LEU, lval, lsh, max, lval, zero);
+ tcg_gen_movcond_i64(TCG_COND_LT, dst, lsh, zero, rval, lval);
+}
+
+static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
+ TCGv_vec src, TCGv_vec shift)
+{
+ TCGv_vec lval = tcg_temp_new_vec_matching(dst);
+ TCGv_vec rval = tcg_temp_new_vec_matching(dst);
+ TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
+ TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
+ TCGv_vec tmp = tcg_temp_new_vec_matching(dst);
+
+ /*
+ * Rely on the TCG guarantee that out of range shifts produce
+ * unspecified results, not undefined behaviour (i.e. no trap).
+ * Discard out-of-range results after the fact.
+ */
+ tcg_gen_neg_vec(vece, rsh, shift);
+ if (vece == MO_8) {
+ tcg_gen_mov_vec(lsh, shift);
+ } else {
+ tcg_gen_dupi_vec(vece, tmp, 0xff);
+ tcg_gen_and_vec(vece, lsh, shift, tmp);
+ tcg_gen_and_vec(vece, rsh, rsh, tmp);
+ }
+
+ /* Bound rsh so out of bound right shift gets -1. */
+ tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1);
+ tcg_gen_umin_vec(vece, rsh, rsh, tmp);
+ tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp);
+
+ tcg_gen_shlv_vec(vece, lval, src, lsh);
+ tcg_gen_sarv_vec(vece, rval, src, rsh);
+
+ /* Select in-bound left shift. */
+ tcg_gen_andc_vec(vece, lval, lval, tmp);
+
+ /* Select between left and right shift. */
+ if (vece == MO_8) {
+ tcg_gen_dupi_vec(vece, tmp, 0);
+ tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval);
+ } else {
+ tcg_gen_dupi_vec(vece, tmp, 0x80);
+ tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval);
+ }
+}
+
+void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec,
+ INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_sshl_vec,
+ .fno = gen_helper_gvec_sshl_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fniv = gen_sshl_vec,
+ .fno = gen_helper_gvec_sshl_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_sshl_i32,
+ .fniv = gen_sshl_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_sshl_i64,
+ .fniv = gen_sshl_vec,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec x = tcg_temp_new_vec_matching(t);
+ tcg_gen_add_vec(vece, x, a, b);
+ tcg_gen_usadd_vec(vece, t, a, b);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
+ tcg_gen_or_vec(vece, sat, sat, x);
+}
+
+void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_uqadd_vec,
+ .fno = gen_helper_gvec_uqadd_b,
+ .write_aofs = true,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fniv = gen_uqadd_vec,
+ .fno = gen_helper_gvec_uqadd_h,
+ .write_aofs = true,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fniv = gen_uqadd_vec,
+ .fno = gen_helper_gvec_uqadd_s,
+ .write_aofs = true,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fniv = gen_uqadd_vec,
+ .fno = gen_helper_gvec_uqadd_d,
+ .write_aofs = true,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+ rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec x = tcg_temp_new_vec_matching(t);
+ tcg_gen_add_vec(vece, x, a, b);
+ tcg_gen_ssadd_vec(vece, t, a, b);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
+ tcg_gen_or_vec(vece, sat, sat, x);
+}
+
+void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_sqadd_vec,
+ .fno = gen_helper_gvec_sqadd_b,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_8 },
+ { .fniv = gen_sqadd_vec,
+ .fno = gen_helper_gvec_sqadd_h,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_16 },
+ { .fniv = gen_sqadd_vec,
+ .fno = gen_helper_gvec_sqadd_s,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_32 },
+ { .fniv = gen_sqadd_vec,
+ .fno = gen_helper_gvec_sqadd_d,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+ rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec x = tcg_temp_new_vec_matching(t);
+ tcg_gen_sub_vec(vece, x, a, b);
+ tcg_gen_ussub_vec(vece, t, a, b);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
+ tcg_gen_or_vec(vece, sat, sat, x);
+}
+
+void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_uqsub_vec,
+ .fno = gen_helper_gvec_uqsub_b,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_8 },
+ { .fniv = gen_uqsub_vec,
+ .fno = gen_helper_gvec_uqsub_h,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_16 },
+ { .fniv = gen_uqsub_vec,
+ .fno = gen_helper_gvec_uqsub_s,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_32 },
+ { .fniv = gen_uqsub_vec,
+ .fno = gen_helper_gvec_uqsub_d,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+ rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec x = tcg_temp_new_vec_matching(t);
+ tcg_gen_sub_vec(vece, x, a, b);
+ tcg_gen_sssub_vec(vece, t, a, b);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
+ tcg_gen_or_vec(vece, sat, sat, x);
+}
+
+void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_sqsub_vec,
+ .fno = gen_helper_gvec_sqsub_b,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_8 },
+ { .fniv = gen_sqsub_vec,
+ .fno = gen_helper_gvec_sqsub_h,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_16 },
+ { .fniv = gen_sqsub_vec,
+ .fno = gen_helper_gvec_sqsub_s,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_32 },
+ { .fniv = gen_sqsub_vec,
+ .fno = gen_helper_gvec_sqsub_d,
+ .opt_opc = vecop_list,
+ .write_aofs = true,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+ rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_sabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+
+ tcg_gen_sub_i32(t, a, b);
+ tcg_gen_sub_i32(d, b, a);
+ tcg_gen_movcond_i32(TCG_COND_LT, d, a, b, d, t);
+}
+
+static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_sub_i64(t, a, b);
+ tcg_gen_sub_i64(d, b, a);
+ tcg_gen_movcond_i64(TCG_COND_LT, d, a, b, d, t);
+}
+
+static void gen_sabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_smin_vec(vece, t, a, b);
+ tcg_gen_smax_vec(vece, d, a, b);
+ tcg_gen_sub_vec(vece, d, d, t);
+}
+
+void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sub_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_sabd_vec,
+ .fno = gen_helper_gvec_sabd_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fniv = gen_sabd_vec,
+ .fno = gen_helper_gvec_sabd_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_sabd_i32,
+ .fniv = gen_sabd_vec,
+ .fno = gen_helper_gvec_sabd_s,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_sabd_i64,
+ .fniv = gen_sabd_vec,
+ .fno = gen_helper_gvec_sabd_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_uabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+
+ tcg_gen_sub_i32(t, a, b);
+ tcg_gen_sub_i32(d, b, a);
+ tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, d, t);
+}
+
+static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_sub_i64(t, a, b);
+ tcg_gen_sub_i64(d, b, a);
+ tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, d, t);
+}
+
+static void gen_uabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+
+ tcg_gen_umin_vec(vece, t, a, b);
+ tcg_gen_umax_vec(vece, d, a, b);
+ tcg_gen_sub_vec(vece, d, d, t);
+}
+
+void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sub_vec, INDEX_op_umin_vec, INDEX_op_umax_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_uabd_vec,
+ .fno = gen_helper_gvec_uabd_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8 },
+ { .fniv = gen_uabd_vec,
+ .fno = gen_helper_gvec_uabd_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16 },
+ { .fni4 = gen_uabd_i32,
+ .fniv = gen_uabd_vec,
+ .fno = gen_helper_gvec_uabd_s,
+ .opt_opc = vecop_list,
+ .vece = MO_32 },
+ { .fni8 = gen_uabd_i64,
+ .fniv = gen_uabd_vec,
+ .fno = gen_helper_gvec_uabd_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+ gen_sabd_i32(t, a, b);
+ tcg_gen_add_i32(d, d, t);
+}
+
+static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+ gen_sabd_i64(t, a, b);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ gen_sabd_vec(vece, t, a, b);
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sub_vec, INDEX_op_add_vec,
+ INDEX_op_smin_vec, INDEX_op_smax_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_saba_vec,
+ .fno = gen_helper_gvec_saba_b,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_8 },
+ { .fniv = gen_saba_vec,
+ .fno = gen_helper_gvec_saba_h,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_16 },
+ { .fni4 = gen_saba_i32,
+ .fniv = gen_saba_vec,
+ .fno = gen_helper_gvec_saba_s,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_32 },
+ { .fni8 = gen_saba_i64,
+ .fniv = gen_saba_vec,
+ .fno = gen_helper_gvec_saba_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
+
+static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+ TCGv_i32 t = tcg_temp_new_i32();
+ gen_uabd_i32(t, a, b);
+ tcg_gen_add_i32(d, d, t);
+}
+
+static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+ gen_uabd_i64(t, a, b);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ gen_uabd_vec(vece, t, a, b);
+ tcg_gen_add_vec(vece, d, d, t);
+}
+
+void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_sub_vec, INDEX_op_add_vec,
+ INDEX_op_umin_vec, INDEX_op_umax_vec, 0
+ };
+ static const GVecGen3 ops[4] = {
+ { .fniv = gen_uaba_vec,
+ .fno = gen_helper_gvec_uaba_b,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_8 },
+ { .fniv = gen_uaba_vec,
+ .fno = gen_helper_gvec_uaba_h,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_16 },
+ { .fni4 = gen_uaba_i32,
+ .fniv = gen_uaba_vec,
+ .fno = gen_helper_gvec_uaba_s,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_32 },
+ { .fni8 = gen_uaba_i64,
+ .fniv = gen_uaba_vec,
+ .fno = gen_helper_gvec_uaba_d,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .opt_opc = vecop_list,
+ .load_dest = true,
+ .vece = MO_64 },
+ };
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index adefa737c9..ddc9baeafb 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -1659,1636 +1659,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
gen_rfe(s, pc, load_cpu_field(spsr));
}
-static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
- uint32_t opr_sz, uint32_t max_sz,
- gen_helper_gvec_3_ptr *fn)
-{
- TCGv_ptr qc_ptr = tcg_temp_new_ptr();
-
- tcg_gen_addi_ptr(qc_ptr, cpu_env, offsetof(CPUARMState, vfp.qc));
- tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr,
- opr_sz, max_sz, 0, fn);
-}
-
-void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static gen_helper_gvec_3_ptr * const fns[2] = {
- gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32
- };
- tcg_debug_assert(vece >= 1 && vece <= 2);
- gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
-}
-
-void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static gen_helper_gvec_3_ptr * const fns[2] = {
- gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32
- };
- tcg_debug_assert(vece >= 1 && vece <= 2);
- gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
-}
-
-#define GEN_CMP0(NAME, COND) \
- static void gen_##NAME##0_i32(TCGv_i32 d, TCGv_i32 a) \
- { \
- tcg_gen_setcondi_i32(COND, d, a, 0); \
- tcg_gen_neg_i32(d, d); \
- } \
- static void gen_##NAME##0_i64(TCGv_i64 d, TCGv_i64 a) \
- { \
- tcg_gen_setcondi_i64(COND, d, a, 0); \
- tcg_gen_neg_i64(d, d); \
- } \
- static void gen_##NAME##0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) \
- { \
- TCGv_vec zero = tcg_constant_vec_matching(d, vece, 0); \
- tcg_gen_cmp_vec(COND, vece, d, a, zero); \
- } \
- void gen_gvec_##NAME##0(unsigned vece, uint32_t d, uint32_t m, \
- uint32_t opr_sz, uint32_t max_sz) \
- { \
- const GVecGen2 op[4] = { \
- { .fno = gen_helper_gvec_##NAME##0_b, \
- .fniv = gen_##NAME##0_vec, \
- .opt_opc = vecop_list_cmp, \
- .vece = MO_8 }, \
- { .fno = gen_helper_gvec_##NAME##0_h, \
- .fniv = gen_##NAME##0_vec, \
- .opt_opc = vecop_list_cmp, \
- .vece = MO_16 }, \
- { .fni4 = gen_##NAME##0_i32, \
- .fniv = gen_##NAME##0_vec, \
- .opt_opc = vecop_list_cmp, \
- .vece = MO_32 }, \
- { .fni8 = gen_##NAME##0_i64, \
- .fniv = gen_##NAME##0_vec, \
- .opt_opc = vecop_list_cmp, \
- .prefer_i64 = TCG_TARGET_REG_BITS == 64, \
- .vece = MO_64 }, \
- }; \
- tcg_gen_gvec_2(d, m, opr_sz, max_sz, &op[vece]); \
- }
-
-static const TCGOpcode vecop_list_cmp[] = {
- INDEX_op_cmp_vec, 0
-};
-
-GEN_CMP0(ceq, TCG_COND_EQ)
-GEN_CMP0(cle, TCG_COND_LE)
-GEN_CMP0(cge, TCG_COND_GE)
-GEN_CMP0(clt, TCG_COND_LT)
-GEN_CMP0(cgt, TCG_COND_GT)
-
-#undef GEN_CMP0
-
-static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_vec_sar8i_i64(a, a, shift);
- tcg_gen_vec_add8_i64(d, d, a);
-}
-
-static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_vec_sar16i_i64(a, a, shift);
- tcg_gen_vec_add16_i64(d, d, a);
-}
-
-static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
-{
- tcg_gen_sari_i32(a, a, shift);
- tcg_gen_add_i32(d, d, a);
-}
-
-static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_sari_i64(a, a, shift);
- tcg_gen_add_i64(d, d, a);
-}
-
-static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- tcg_gen_sari_vec(vece, a, a, sh);
- tcg_gen_add_vec(vece, d, d, a);
-}
-
-void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sari_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_ssra8_i64,
- .fniv = gen_ssra_vec,
- .fno = gen_helper_gvec_ssra_b,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni8 = gen_ssra16_i64,
- .fniv = gen_ssra_vec,
- .fno = gen_helper_gvec_ssra_h,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_ssra32_i32,
- .fniv = gen_ssra_vec,
- .fno = gen_helper_gvec_ssra_s,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_ssra64_i64,
- .fniv = gen_ssra_vec,
- .fno = gen_helper_gvec_ssra_b,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize]. */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- /*
- * Shifts larger than the element size are architecturally valid.
- * Signed results in all sign bits.
- */
- shift = MIN(shift, (8 << vece) - 1);
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
-}
-
-static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_vec_shr8i_i64(a, a, shift);
- tcg_gen_vec_add8_i64(d, d, a);
-}
-
-static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_vec_shr16i_i64(a, a, shift);
- tcg_gen_vec_add16_i64(d, d, a);
-}
-
-static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
-{
- tcg_gen_shri_i32(a, a, shift);
- tcg_gen_add_i32(d, d, a);
-}
-
-static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_shri_i64(a, a, shift);
- tcg_gen_add_i64(d, d, a);
-}
-
-static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- tcg_gen_shri_vec(vece, a, a, sh);
- tcg_gen_add_vec(vece, d, d, a);
-}
-
-void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_shri_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_usra8_i64,
- .fniv = gen_usra_vec,
- .fno = gen_helper_gvec_usra_b,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8, },
- { .fni8 = gen_usra16_i64,
- .fniv = gen_usra_vec,
- .fno = gen_helper_gvec_usra_h,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16, },
- { .fni4 = gen_usra32_i32,
- .fniv = gen_usra_vec,
- .fno = gen_helper_gvec_usra_s,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32, },
- { .fni8 = gen_usra64_i64,
- .fniv = gen_usra_vec,
- .fno = gen_helper_gvec_usra_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_64, },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize]. */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- /*
- * Shifts larger than the element size are architecturally valid.
- * Unsigned results in all zeros as input to accumulate: nop.
- */
- if (shift < (8 << vece)) {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- } else {
- /* Nop, but we do need to clear the tail. */
- tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
- }
-}
-
-/*
- * Shift one less than the requested amount, and the low bit is
- * the rounding bit. For the 8 and 16-bit operations, because we
- * mask the low bit, we can perform a normal integer shift instead
- * of a vector shift.
- */
-static void gen_srshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, sh - 1);
- tcg_gen_andi_i64(t, t, dup_const(MO_8, 1));
- tcg_gen_vec_sar8i_i64(d, a, sh);
- tcg_gen_vec_add8_i64(d, d, t);
-}
-
-static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, sh - 1);
- tcg_gen_andi_i64(t, t, dup_const(MO_16, 1));
- tcg_gen_vec_sar16i_i64(d, a, sh);
- tcg_gen_vec_add16_i64(d, d, t);
-}
-
-void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
-{
- TCGv_i32 t;
-
- /* Handle shift by the input size for the benefit of trans_SRSHR_ri */
- if (sh == 32) {
- tcg_gen_movi_i32(d, 0);
- return;
- }
- t = tcg_temp_new_i32();
- tcg_gen_extract_i32(t, a, sh - 1, 1);
- tcg_gen_sari_i32(d, a, sh);
- tcg_gen_add_i32(d, d, t);
-}
-
-void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_extract_i64(t, a, sh - 1, 1);
- tcg_gen_sari_i64(d, a, sh);
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- TCGv_vec ones = tcg_temp_new_vec_matching(d);
-
- tcg_gen_shri_vec(vece, t, a, sh - 1);
- tcg_gen_dupi_vec(vece, ones, 1);
- tcg_gen_and_vec(vece, t, t, ones);
- tcg_gen_sari_vec(vece, d, a, sh);
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_srshr8_i64,
- .fniv = gen_srshr_vec,
- .fno = gen_helper_gvec_srshr_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni8 = gen_srshr16_i64,
- .fniv = gen_srshr_vec,
- .fno = gen_helper_gvec_srshr_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_srshr32_i32,
- .fniv = gen_srshr_vec,
- .fno = gen_helper_gvec_srshr_s,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_srshr64_i64,
- .fniv = gen_srshr_vec,
- .fno = gen_helper_gvec_srshr_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize] */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- if (shift == (8 << vece)) {
- /*
- * Shifts larger than the element size are architecturally valid.
- * Signed results in all sign bits. With rounding, this produces
- * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0.
- * I.e. always zero.
- */
- tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0);
- } else {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- }
-}
-
-static void gen_srsra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- gen_srshr8_i64(t, a, sh);
- tcg_gen_vec_add8_i64(d, d, t);
-}
-
-static void gen_srsra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- gen_srshr16_i64(t, a, sh);
- tcg_gen_vec_add16_i64(d, d, t);
-}
-
-static void gen_srsra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
-{
- TCGv_i32 t = tcg_temp_new_i32();
-
- gen_srshr32_i32(t, a, sh);
- tcg_gen_add_i32(d, d, t);
-}
-
-static void gen_srsra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- gen_srshr64_i64(t, a, sh);
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_srsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
-
- gen_srshr_vec(vece, t, a, sh);
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_srsra8_i64,
- .fniv = gen_srsra_vec,
- .fno = gen_helper_gvec_srsra_b,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_8 },
- { .fni8 = gen_srsra16_i64,
- .fniv = gen_srsra_vec,
- .fno = gen_helper_gvec_srsra_h,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_16 },
- { .fni4 = gen_srsra32_i32,
- .fniv = gen_srsra_vec,
- .fno = gen_helper_gvec_srsra_s,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_32 },
- { .fni8 = gen_srsra64_i64,
- .fniv = gen_srsra_vec,
- .fno = gen_helper_gvec_srsra_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize] */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- /*
- * Shifts larger than the element size are architecturally valid.
- * Signed results in all sign bits. With rounding, this produces
- * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0.
- * I.e. always zero. With accumulation, this leaves D unchanged.
- */
- if (shift == (8 << vece)) {
- /* Nop, but we do need to clear the tail. */
- tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
- } else {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- }
-}
-
-static void gen_urshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, sh - 1);
- tcg_gen_andi_i64(t, t, dup_const(MO_8, 1));
- tcg_gen_vec_shr8i_i64(d, a, sh);
- tcg_gen_vec_add8_i64(d, d, t);
-}
-
-static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, sh - 1);
- tcg_gen_andi_i64(t, t, dup_const(MO_16, 1));
- tcg_gen_vec_shr16i_i64(d, a, sh);
- tcg_gen_vec_add16_i64(d, d, t);
-}
-
-void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
-{
- TCGv_i32 t;
-
- /* Handle shift by the input size for the benefit of trans_URSHR_ri */
- if (sh == 32) {
- tcg_gen_extract_i32(d, a, sh - 1, 1);
- return;
- }
- t = tcg_temp_new_i32();
- tcg_gen_extract_i32(t, a, sh - 1, 1);
- tcg_gen_shri_i32(d, a, sh);
- tcg_gen_add_i32(d, d, t);
-}
-
-void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_extract_i64(t, a, sh - 1, 1);
- tcg_gen_shri_i64(d, a, sh);
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- TCGv_vec ones = tcg_temp_new_vec_matching(d);
-
- tcg_gen_shri_vec(vece, t, a, shift - 1);
- tcg_gen_dupi_vec(vece, ones, 1);
- tcg_gen_and_vec(vece, t, t, ones);
- tcg_gen_shri_vec(vece, d, a, shift);
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_shri_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_urshr8_i64,
- .fniv = gen_urshr_vec,
- .fno = gen_helper_gvec_urshr_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni8 = gen_urshr16_i64,
- .fniv = gen_urshr_vec,
- .fno = gen_helper_gvec_urshr_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_urshr32_i32,
- .fniv = gen_urshr_vec,
- .fno = gen_helper_gvec_urshr_s,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_urshr64_i64,
- .fniv = gen_urshr_vec,
- .fno = gen_helper_gvec_urshr_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize] */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- if (shift == (8 << vece)) {
- /*
- * Shifts larger than the element size are architecturally valid.
- * Unsigned results in zero. With rounding, this produces a
- * copy of the most significant bit.
- */
- tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift - 1, opr_sz, max_sz);
- } else {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- }
-}
-
-static void gen_ursra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- if (sh == 8) {
- tcg_gen_vec_shr8i_i64(t, a, 7);
- } else {
- gen_urshr8_i64(t, a, sh);
- }
- tcg_gen_vec_add8_i64(d, d, t);
-}
-
-static void gen_ursra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- if (sh == 16) {
- tcg_gen_vec_shr16i_i64(t, a, 15);
- } else {
- gen_urshr16_i64(t, a, sh);
- }
- tcg_gen_vec_add16_i64(d, d, t);
-}
-
-static void gen_ursra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
-{
- TCGv_i32 t = tcg_temp_new_i32();
-
- if (sh == 32) {
- tcg_gen_shri_i32(t, a, 31);
- } else {
- gen_urshr32_i32(t, a, sh);
- }
- tcg_gen_add_i32(d, d, t);
-}
-
-static void gen_ursra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- if (sh == 64) {
- tcg_gen_shri_i64(t, a, 63);
- } else {
- gen_urshr64_i64(t, a, sh);
- }
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_ursra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
-
- if (sh == (8 << vece)) {
- tcg_gen_shri_vec(vece, t, a, sh - 1);
- } else {
- gen_urshr_vec(vece, t, a, sh);
- }
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_shri_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen2i ops[4] = {
- { .fni8 = gen_ursra8_i64,
- .fniv = gen_ursra_vec,
- .fno = gen_helper_gvec_ursra_b,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_8 },
- { .fni8 = gen_ursra16_i64,
- .fniv = gen_ursra_vec,
- .fno = gen_helper_gvec_ursra_h,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_16 },
- { .fni4 = gen_ursra32_i32,
- .fniv = gen_ursra_vec,
- .fno = gen_helper_gvec_ursra_s,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_32 },
- { .fni8 = gen_ursra64_i64,
- .fniv = gen_ursra_vec,
- .fno = gen_helper_gvec_ursra_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize] */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
-}
-
-static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- uint64_t mask = dup_const(MO_8, 0xff >> shift);
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, shift);
- tcg_gen_andi_i64(t, t, mask);
- tcg_gen_andi_i64(d, d, ~mask);
- tcg_gen_or_i64(d, d, t);
-}
-
-static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- uint64_t mask = dup_const(MO_16, 0xffff >> shift);
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shri_i64(t, a, shift);
- tcg_gen_andi_i64(t, t, mask);
- tcg_gen_andi_i64(d, d, ~mask);
- tcg_gen_or_i64(d, d, t);
-}
-
-static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
-{
- tcg_gen_shri_i32(a, a, shift);
- tcg_gen_deposit_i32(d, d, a, 0, 32 - shift);
-}
-
-static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_shri_i64(a, a, shift);
- tcg_gen_deposit_i64(d, d, a, 0, 64 - shift);
-}
-
-static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- TCGv_vec m = tcg_temp_new_vec_matching(d);
-
- tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh));
- tcg_gen_shri_vec(vece, t, a, sh);
- tcg_gen_and_vec(vece, d, d, m);
- tcg_gen_or_vec(vece, d, d, t);
-}
-
-void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 };
- const GVecGen2i ops[4] = {
- { .fni8 = gen_shr8_ins_i64,
- .fniv = gen_shr_ins_vec,
- .fno = gen_helper_gvec_sri_b,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni8 = gen_shr16_ins_i64,
- .fniv = gen_shr_ins_vec,
- .fno = gen_helper_gvec_sri_h,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_shr32_ins_i32,
- .fniv = gen_shr_ins_vec,
- .fno = gen_helper_gvec_sri_s,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_shr64_ins_i64,
- .fniv = gen_shr_ins_vec,
- .fno = gen_helper_gvec_sri_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [1..esize]. */
- tcg_debug_assert(shift > 0);
- tcg_debug_assert(shift <= (8 << vece));
-
- /* Shift of esize leaves destination unchanged. */
- if (shift < (8 << vece)) {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- } else {
- /* Nop, but we do need to clear the tail. */
- tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz);
- }
-}
-
-static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- uint64_t mask = dup_const(MO_8, 0xff << shift);
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shli_i64(t, a, shift);
- tcg_gen_andi_i64(t, t, mask);
- tcg_gen_andi_i64(d, d, ~mask);
- tcg_gen_or_i64(d, d, t);
-}
-
-static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- uint64_t mask = dup_const(MO_16, 0xffff << shift);
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_shli_i64(t, a, shift);
- tcg_gen_andi_i64(t, t, mask);
- tcg_gen_andi_i64(d, d, ~mask);
- tcg_gen_or_i64(d, d, t);
-}
-
-static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift)
-{
- tcg_gen_deposit_i32(d, d, a, shift, 32 - shift);
-}
-
-static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
-{
- tcg_gen_deposit_i64(d, d, a, shift, 64 - shift);
-}
-
-static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- TCGv_vec m = tcg_temp_new_vec_matching(d);
-
- tcg_gen_shli_vec(vece, t, a, sh);
- tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh));
- tcg_gen_and_vec(vece, d, d, m);
- tcg_gen_or_vec(vece, d, d, t);
-}
-
-void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 };
- const GVecGen2i ops[4] = {
- { .fni8 = gen_shl8_ins_i64,
- .fniv = gen_shl_ins_vec,
- .fno = gen_helper_gvec_sli_b,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni8 = gen_shl16_ins_i64,
- .fniv = gen_shl_ins_vec,
- .fno = gen_helper_gvec_sli_h,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_shl32_ins_i32,
- .fniv = gen_shl_ins_vec,
- .fno = gen_helper_gvec_sli_s,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_shl64_ins_i64,
- .fniv = gen_shl_ins_vec,
- .fno = gen_helper_gvec_sli_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
-
- /* tszimm encoding produces immediates in the range [0..esize-1]. */
- tcg_debug_assert(shift >= 0);
- tcg_debug_assert(shift < (8 << vece));
-
- if (shift == 0) {
- tcg_gen_gvec_mov(vece, rd_ofs, rm_ofs, opr_sz, max_sz);
- } else {
- tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]);
- }
-}
-
-static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- gen_helper_neon_mul_u8(a, a, b);
- gen_helper_neon_add_u8(d, d, a);
-}
-
-static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- gen_helper_neon_mul_u8(a, a, b);
- gen_helper_neon_sub_u8(d, d, a);
-}
-
-static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- gen_helper_neon_mul_u16(a, a, b);
- gen_helper_neon_add_u16(d, d, a);
-}
-
-static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- gen_helper_neon_mul_u16(a, a, b);
- gen_helper_neon_sub_u16(d, d, a);
-}
-
-static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- tcg_gen_mul_i32(a, a, b);
- tcg_gen_add_i32(d, d, a);
-}
-
-static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- tcg_gen_mul_i32(a, a, b);
- tcg_gen_sub_i32(d, d, a);
-}
-
-static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- tcg_gen_mul_i64(a, a, b);
- tcg_gen_add_i64(d, d, a);
-}
-
-static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- tcg_gen_mul_i64(a, a, b);
- tcg_gen_sub_i64(d, d, a);
-}
-
-static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- tcg_gen_mul_vec(vece, a, a, b);
- tcg_gen_add_vec(vece, d, d, a);
-}
-
-static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- tcg_gen_mul_vec(vece, a, a, b);
- tcg_gen_sub_vec(vece, d, d, a);
-}
-
-/* Note that while NEON does not support VMLA and VMLS as 64-bit ops,
- * these tables are shared with AArch64 which does support them.
- */
-void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_mul_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fni4 = gen_mla8_i32,
- .fniv = gen_mla_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni4 = gen_mla16_i32,
- .fniv = gen_mla_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_mla32_i32,
- .fniv = gen_mla_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_mla64_i64,
- .fniv = gen_mla_vec,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_mul_vec, INDEX_op_sub_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fni4 = gen_mls8_i32,
- .fniv = gen_mls_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni4 = gen_mls16_i32,
- .fniv = gen_mls_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_mls32_i32,
- .fniv = gen_mls_vec,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_mls64_i64,
- .fniv = gen_mls_vec,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .load_dest = true,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-/* CMTST : test is "if (X & Y != 0)". */
-static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- tcg_gen_and_i32(d, a, b);
- tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0);
- tcg_gen_neg_i32(d, d);
-}
-
-void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- tcg_gen_and_i64(d, a, b);
- tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0);
- tcg_gen_neg_i64(d, d);
-}
-
-static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- tcg_gen_and_vec(vece, d, a, b);
- tcg_gen_dupi_vec(vece, a, 0);
- tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a);
-}
-
-void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = { INDEX_op_cmp_vec, 0 };
- static const GVecGen3 ops[4] = {
- { .fni4 = gen_helper_neon_tst_u8,
- .fniv = gen_cmtst_vec,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fni4 = gen_helper_neon_tst_u16,
- .fniv = gen_cmtst_vec,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_cmtst_i32,
- .fniv = gen_cmtst_vec,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_cmtst_i64,
- .fniv = gen_cmtst_vec,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift)
-{
- TCGv_i32 lval = tcg_temp_new_i32();
- TCGv_i32 rval = tcg_temp_new_i32();
- TCGv_i32 lsh = tcg_temp_new_i32();
- TCGv_i32 rsh = tcg_temp_new_i32();
- TCGv_i32 zero = tcg_constant_i32(0);
- TCGv_i32 max = tcg_constant_i32(32);
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_ext8s_i32(lsh, shift);
- tcg_gen_neg_i32(rsh, lsh);
- tcg_gen_shl_i32(lval, src, lsh);
- tcg_gen_shr_i32(rval, src, rsh);
- tcg_gen_movcond_i32(TCG_COND_LTU, dst, lsh, max, lval, zero);
- tcg_gen_movcond_i32(TCG_COND_LTU, dst, rsh, max, rval, dst);
-}
-
-void gen_ushl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift)
-{
- TCGv_i64 lval = tcg_temp_new_i64();
- TCGv_i64 rval = tcg_temp_new_i64();
- TCGv_i64 lsh = tcg_temp_new_i64();
- TCGv_i64 rsh = tcg_temp_new_i64();
- TCGv_i64 zero = tcg_constant_i64(0);
- TCGv_i64 max = tcg_constant_i64(64);
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_ext8s_i64(lsh, shift);
- tcg_gen_neg_i64(rsh, lsh);
- tcg_gen_shl_i64(lval, src, lsh);
- tcg_gen_shr_i64(rval, src, rsh);
- tcg_gen_movcond_i64(TCG_COND_LTU, dst, lsh, max, lval, zero);
- tcg_gen_movcond_i64(TCG_COND_LTU, dst, rsh, max, rval, dst);
-}
-
-static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
- TCGv_vec src, TCGv_vec shift)
-{
- TCGv_vec lval = tcg_temp_new_vec_matching(dst);
- TCGv_vec rval = tcg_temp_new_vec_matching(dst);
- TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
- TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
- TCGv_vec msk, max;
-
- tcg_gen_neg_vec(vece, rsh, shift);
- if (vece == MO_8) {
- tcg_gen_mov_vec(lsh, shift);
- } else {
- msk = tcg_temp_new_vec_matching(dst);
- tcg_gen_dupi_vec(vece, msk, 0xff);
- tcg_gen_and_vec(vece, lsh, shift, msk);
- tcg_gen_and_vec(vece, rsh, rsh, msk);
- }
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_shlv_vec(vece, lval, src, lsh);
- tcg_gen_shrv_vec(vece, rval, src, rsh);
-
- max = tcg_temp_new_vec_matching(dst);
- tcg_gen_dupi_vec(vece, max, 8 << vece);
-
- /*
- * The choice of LT (signed) and GEU (unsigned) are biased toward
- * the instructions of the x86_64 host. For MO_8, the whole byte
- * is significant so we must use an unsigned compare; otherwise we
- * have already masked to a byte and so a signed compare works.
- * Other tcg hosts have a full set of comparisons and do not care.
- */
- if (vece == MO_8) {
- tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max);
- tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max);
- tcg_gen_andc_vec(vece, lval, lval, lsh);
- tcg_gen_andc_vec(vece, rval, rval, rsh);
- } else {
- tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max);
- tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max);
- tcg_gen_and_vec(vece, lval, lval, lsh);
- tcg_gen_and_vec(vece, rval, rval, rsh);
- }
- tcg_gen_or_vec(vece, dst, lval, rval);
-}
-
-void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_neg_vec, INDEX_op_shlv_vec,
- INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_ushl_vec,
- .fno = gen_helper_gvec_ushl_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fniv = gen_ushl_vec,
- .fno = gen_helper_gvec_ushl_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_ushl_i32,
- .fniv = gen_ushl_vec,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_ushl_i64,
- .fniv = gen_ushl_vec,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift)
-{
- TCGv_i32 lval = tcg_temp_new_i32();
- TCGv_i32 rval = tcg_temp_new_i32();
- TCGv_i32 lsh = tcg_temp_new_i32();
- TCGv_i32 rsh = tcg_temp_new_i32();
- TCGv_i32 zero = tcg_constant_i32(0);
- TCGv_i32 max = tcg_constant_i32(31);
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_ext8s_i32(lsh, shift);
- tcg_gen_neg_i32(rsh, lsh);
- tcg_gen_shl_i32(lval, src, lsh);
- tcg_gen_umin_i32(rsh, rsh, max);
- tcg_gen_sar_i32(rval, src, rsh);
- tcg_gen_movcond_i32(TCG_COND_LEU, lval, lsh, max, lval, zero);
- tcg_gen_movcond_i32(TCG_COND_LT, dst, lsh, zero, rval, lval);
-}
-
-void gen_sshl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift)
-{
- TCGv_i64 lval = tcg_temp_new_i64();
- TCGv_i64 rval = tcg_temp_new_i64();
- TCGv_i64 lsh = tcg_temp_new_i64();
- TCGv_i64 rsh = tcg_temp_new_i64();
- TCGv_i64 zero = tcg_constant_i64(0);
- TCGv_i64 max = tcg_constant_i64(63);
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_ext8s_i64(lsh, shift);
- tcg_gen_neg_i64(rsh, lsh);
- tcg_gen_shl_i64(lval, src, lsh);
- tcg_gen_umin_i64(rsh, rsh, max);
- tcg_gen_sar_i64(rval, src, rsh);
- tcg_gen_movcond_i64(TCG_COND_LEU, lval, lsh, max, lval, zero);
- tcg_gen_movcond_i64(TCG_COND_LT, dst, lsh, zero, rval, lval);
-}
-
-static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
- TCGv_vec src, TCGv_vec shift)
-{
- TCGv_vec lval = tcg_temp_new_vec_matching(dst);
- TCGv_vec rval = tcg_temp_new_vec_matching(dst);
- TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
- TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
- TCGv_vec tmp = tcg_temp_new_vec_matching(dst);
-
- /*
- * Rely on the TCG guarantee that out of range shifts produce
- * unspecified results, not undefined behaviour (i.e. no trap).
- * Discard out-of-range results after the fact.
- */
- tcg_gen_neg_vec(vece, rsh, shift);
- if (vece == MO_8) {
- tcg_gen_mov_vec(lsh, shift);
- } else {
- tcg_gen_dupi_vec(vece, tmp, 0xff);
- tcg_gen_and_vec(vece, lsh, shift, tmp);
- tcg_gen_and_vec(vece, rsh, rsh, tmp);
- }
-
- /* Bound rsh so out of bound right shift gets -1. */
- tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1);
- tcg_gen_umin_vec(vece, rsh, rsh, tmp);
- tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp);
-
- tcg_gen_shlv_vec(vece, lval, src, lsh);
- tcg_gen_sarv_vec(vece, rval, src, rsh);
-
- /* Select in-bound left shift. */
- tcg_gen_andc_vec(vece, lval, lval, tmp);
-
- /* Select between left and right shift. */
- if (vece == MO_8) {
- tcg_gen_dupi_vec(vece, tmp, 0);
- tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval);
- } else {
- tcg_gen_dupi_vec(vece, tmp, 0x80);
- tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval);
- }
-}
-
-void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec,
- INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_sshl_vec,
- .fno = gen_helper_gvec_sshl_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fniv = gen_sshl_vec,
- .fno = gen_helper_gvec_sshl_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_sshl_i32,
- .fniv = gen_sshl_vec,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_sshl_i64,
- .fniv = gen_sshl_vec,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
- TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec x = tcg_temp_new_vec_matching(t);
- tcg_gen_add_vec(vece, x, a, b);
- tcg_gen_usadd_vec(vece, t, a, b);
- tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
- tcg_gen_or_vec(vece, sat, sat, x);
-}
-
-void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen4 ops[4] = {
- { .fniv = gen_uqadd_vec,
- .fno = gen_helper_gvec_uqadd_b,
- .write_aofs = true,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fniv = gen_uqadd_vec,
- .fno = gen_helper_gvec_uqadd_h,
- .write_aofs = true,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fniv = gen_uqadd_vec,
- .fno = gen_helper_gvec_uqadd_s,
- .write_aofs = true,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fniv = gen_uqadd_vec,
- .fno = gen_helper_gvec_uqadd_d,
- .write_aofs = true,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
- rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
- TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec x = tcg_temp_new_vec_matching(t);
- tcg_gen_add_vec(vece, x, a, b);
- tcg_gen_ssadd_vec(vece, t, a, b);
- tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
- tcg_gen_or_vec(vece, sat, sat, x);
-}
-
-void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
- };
- static const GVecGen4 ops[4] = {
- { .fniv = gen_sqadd_vec,
- .fno = gen_helper_gvec_sqadd_b,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_8 },
- { .fniv = gen_sqadd_vec,
- .fno = gen_helper_gvec_sqadd_h,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_16 },
- { .fniv = gen_sqadd_vec,
- .fno = gen_helper_gvec_sqadd_s,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_32 },
- { .fniv = gen_sqadd_vec,
- .fno = gen_helper_gvec_sqadd_d,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_64 },
- };
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
- rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
- TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec x = tcg_temp_new_vec_matching(t);
- tcg_gen_sub_vec(vece, x, a, b);
- tcg_gen_ussub_vec(vece, t, a, b);
- tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
- tcg_gen_or_vec(vece, sat, sat, x);
-}
-
-void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
- };
- static const GVecGen4 ops[4] = {
- { .fniv = gen_uqsub_vec,
- .fno = gen_helper_gvec_uqsub_b,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_8 },
- { .fniv = gen_uqsub_vec,
- .fno = gen_helper_gvec_uqsub_h,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_16 },
- { .fniv = gen_uqsub_vec,
- .fno = gen_helper_gvec_uqsub_s,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_32 },
- { .fniv = gen_uqsub_vec,
- .fno = gen_helper_gvec_uqsub_d,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_64 },
- };
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
- rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
- TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec x = tcg_temp_new_vec_matching(t);
- tcg_gen_sub_vec(vece, x, a, b);
- tcg_gen_sssub_vec(vece, t, a, b);
- tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
- tcg_gen_or_vec(vece, sat, sat, x);
-}
-
-void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
- };
- static const GVecGen4 ops[4] = {
- { .fniv = gen_sqsub_vec,
- .fno = gen_helper_gvec_sqsub_b,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_8 },
- { .fniv = gen_sqsub_vec,
- .fno = gen_helper_gvec_sqsub_h,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_16 },
- { .fniv = gen_sqsub_vec,
- .fno = gen_helper_gvec_sqsub_s,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_32 },
- { .fniv = gen_sqsub_vec,
- .fno = gen_helper_gvec_sqsub_d,
- .opt_opc = vecop_list,
- .write_aofs = true,
- .vece = MO_64 },
- };
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
- rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_sabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- TCGv_i32 t = tcg_temp_new_i32();
-
- tcg_gen_sub_i32(t, a, b);
- tcg_gen_sub_i32(d, b, a);
- tcg_gen_movcond_i32(TCG_COND_LT, d, a, b, d, t);
-}
-
-static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_sub_i64(t, a, b);
- tcg_gen_sub_i64(d, b, a);
- tcg_gen_movcond_i64(TCG_COND_LT, d, a, b, d, t);
-}
-
-static void gen_sabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
-
- tcg_gen_smin_vec(vece, t, a, b);
- tcg_gen_smax_vec(vece, d, a, b);
- tcg_gen_sub_vec(vece, d, d, t);
-}
-
-void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sub_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_sabd_vec,
- .fno = gen_helper_gvec_sabd_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fniv = gen_sabd_vec,
- .fno = gen_helper_gvec_sabd_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_sabd_i32,
- .fniv = gen_sabd_vec,
- .fno = gen_helper_gvec_sabd_s,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_sabd_i64,
- .fniv = gen_sabd_vec,
- .fno = gen_helper_gvec_sabd_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_uabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- TCGv_i32 t = tcg_temp_new_i32();
-
- tcg_gen_sub_i32(t, a, b);
- tcg_gen_sub_i32(d, b, a);
- tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, d, t);
-}
-
-static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- TCGv_i64 t = tcg_temp_new_i64();
-
- tcg_gen_sub_i64(t, a, b);
- tcg_gen_sub_i64(d, b, a);
- tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, d, t);
-}
-
-static void gen_uabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
-
- tcg_gen_umin_vec(vece, t, a, b);
- tcg_gen_umax_vec(vece, d, a, b);
- tcg_gen_sub_vec(vece, d, d, t);
-}
-
-void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sub_vec, INDEX_op_umin_vec, INDEX_op_umax_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_uabd_vec,
- .fno = gen_helper_gvec_uabd_b,
- .opt_opc = vecop_list,
- .vece = MO_8 },
- { .fniv = gen_uabd_vec,
- .fno = gen_helper_gvec_uabd_h,
- .opt_opc = vecop_list,
- .vece = MO_16 },
- { .fni4 = gen_uabd_i32,
- .fniv = gen_uabd_vec,
- .fno = gen_helper_gvec_uabd_s,
- .opt_opc = vecop_list,
- .vece = MO_32 },
- { .fni8 = gen_uabd_i64,
- .fniv = gen_uabd_vec,
- .fno = gen_helper_gvec_uabd_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- TCGv_i32 t = tcg_temp_new_i32();
- gen_sabd_i32(t, a, b);
- tcg_gen_add_i32(d, d, t);
-}
-
-static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- TCGv_i64 t = tcg_temp_new_i64();
- gen_sabd_i64(t, a, b);
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- gen_sabd_vec(vece, t, a, b);
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sub_vec, INDEX_op_add_vec,
- INDEX_op_smin_vec, INDEX_op_smax_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_saba_vec,
- .fno = gen_helper_gvec_saba_b,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_8 },
- { .fniv = gen_saba_vec,
- .fno = gen_helper_gvec_saba_h,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_16 },
- { .fni4 = gen_saba_i32,
- .fniv = gen_saba_vec,
- .fno = gen_helper_gvec_saba_s,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_32 },
- { .fni8 = gen_saba_i64,
- .fniv = gen_saba_vec,
- .fno = gen_helper_gvec_saba_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
-static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
- TCGv_i32 t = tcg_temp_new_i32();
- gen_uabd_i32(t, a, b);
- tcg_gen_add_i32(d, d, t);
-}
-
-static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
- TCGv_i64 t = tcg_temp_new_i64();
- gen_uabd_i64(t, a, b);
- tcg_gen_add_i64(d, d, t);
-}
-
-static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
-{
- TCGv_vec t = tcg_temp_new_vec_matching(d);
- gen_uabd_vec(vece, t, a, b);
- tcg_gen_add_vec(vece, d, d, t);
-}
-
-void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
- uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
-{
- static const TCGOpcode vecop_list[] = {
- INDEX_op_sub_vec, INDEX_op_add_vec,
- INDEX_op_umin_vec, INDEX_op_umax_vec, 0
- };
- static const GVecGen3 ops[4] = {
- { .fniv = gen_uaba_vec,
- .fno = gen_helper_gvec_uaba_b,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_8 },
- { .fniv = gen_uaba_vec,
- .fno = gen_helper_gvec_uaba_h,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_16 },
- { .fni4 = gen_uaba_i32,
- .fniv = gen_uaba_vec,
- .fno = gen_helper_gvec_uaba_s,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_32 },
- { .fni8 = gen_uaba_i64,
- .fniv = gen_uaba_vec,
- .fno = gen_helper_gvec_uaba_d,
- .prefer_i64 = TCG_TARGET_REG_BITS == 64,
- .opt_opc = vecop_list,
- .load_dest = true,
- .vece = MO_64 },
- };
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
-}
-
static void do_coproc_insn(DisasContext *s, int cpnum, int is64,
int opc1, int crn, int crm, int opc2,
bool isread, int rt, int rt2)
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index fca9912a0a..0a9b4be332 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -21,6 +21,7 @@ arm_ss.add(gen)
arm_ss.add(files(
'cpu32.c',
'translate.c',
+ 'translate-gvec.c',
'translate-iwmmxt.c',
'translate-m-nocp.c',
'translate-mve.c',
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > Extract 1600 lines from the big enough translate.c. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/tcg/translate-gvec.c | 1644 +++++++++++++++++++++++++++++++ > target/arm/tcg/translate.c | 1630 ------------------------------ > target/arm/tcg/meson.build | 1 + > 3 files changed, 1645 insertions(+), 1630 deletions(-) > create mode 100644 target/arm/tcg/translate-gvec.c Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the generic
vector definitions. Move them to a new header; the next commit
will remove it from the common helper.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 380 +------------------------------
target/arm/tcg/helper-gvec.h.inc | 378 ++++++++++++++++++++++++++++++
2 files changed, 379 insertions(+), 379 deletions(-)
create mode 100644 target/arm/tcg/helper-gvec.h.inc
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 819d27d597..df22f1a117 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -146,15 +146,6 @@ DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
-DEF_HELPER_FLAGS_5(gvec_qrdmlah_s16, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s16, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_qrdmlah_s32, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s32, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_5(sve2_sqrdmlah_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_b, TCG_CALL_NO_RWG,
@@ -172,336 +163,6 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmul_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqadd_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqadd_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqadd_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqadd_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqadd_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqadd_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqadd_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqsub_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqsub_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqsub_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uqsub_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqsub_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqsub_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqsub_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sqsub_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_fmlal_a32, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmlal_a64, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a32, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a64, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_clt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_clt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cle0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cgt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_smulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_smulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_smulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_smulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_umulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_umulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_umulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_umulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_ushl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_pmul_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_ssra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ssra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ssra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ssra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_usra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_usra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_usra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_usra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_srsra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srsra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srsra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_srsra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_ursra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ursra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ursra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_ursra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_sri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_3(gvec_sli_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sli_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sli_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(gvec_sli_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_sabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_uabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_saba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_saba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_saba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_saba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_uaba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uaba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uaba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_uaba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(gvec_mul_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_mul_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_mul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_mla_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_mla_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_mla_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_mls_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_mls_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_mls_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
@@ -531,50 +192,11 @@ DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_smmla_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_ummla_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usmmla_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_bfdot, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_bfdot_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_bfmmla, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
#include "tcg/helper-sve.h.inc"
#include "tcg/helper-sme.h.inc"
#endif
+#include "tcg/helper-gvec.h.inc"
#include "tcg/helper-mve.h.inc"
diff --git a/target/arm/tcg/helper-gvec.h.inc b/target/arm/tcg/helper-gvec.h.inc
new file mode 100644
index 0000000000..6143221428
--- /dev/null
+++ b/target/arm/tcg/helper-gvec.h.inc
@@ -0,0 +1,378 @@
+DEF_HELPER_FLAGS_5(gvec_qrdmlah_s16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_qrdmlah_s32, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s32, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmul_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqadd_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqadd_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqadd_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqadd_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqadd_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqadd_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqadd_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqsub_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqsub_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqsub_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uqsub_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqsub_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqsub_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqsub_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sqsub_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmlal_a32, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmlal_a64, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a32, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a64, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_clt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_clt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cle0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cgt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_smulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_umulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_ushl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_pmul_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_ssra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ssra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ssra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ssra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_usra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_usra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_usra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_usra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_srsra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srsra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srsra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_srsra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_ursra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ursra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ursra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ursra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_sri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(gvec_sli_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sli_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sli_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_sli_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_sabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_uabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_saba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_saba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_saba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_saba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_uaba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uaba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uaba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uaba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_mul_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_mul_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_mul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_mla_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mla_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mla_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_mls_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mls_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mls_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_smmla_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_ummla_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usmmla_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_bfdot, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_bfdot_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_bfmmla, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > helper.h is used by all units, but not all require the generic > vector definitions. Move them to a new header; the next commit > will remove it from the common helper.h. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 380 +------------------------------ > target/arm/tcg/helper-gvec.h.inc | 378 ++++++++++++++++++++++++++++++ > 2 files changed, 379 insertions(+), 379 deletions(-) > create mode 100644 target/arm/tcg/helper-gvec.h.inc Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Instead of including helper-gvec.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 1 -
target/arm/tcg/translate-a64.c | 4 ++++
target/arm/tcg/translate-gvec.c | 6 ++++++
target/arm/tcg/translate-neon.c | 4 ++++
target/arm/tcg/translate-sve.c | 3 +++
target/arm/tcg/vec_helper.c | 4 ++++
6 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index df22f1a117..6d61694f5e 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -198,5 +198,4 @@ DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG,
#include "tcg/helper-sme.h.inc"
#endif
-#include "tcg/helper-gvec.h.inc"
#include "tcg/helper-mve.h.inc"
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 22caf89bb0..924bbdbf1d 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -26,6 +26,10 @@
#include "semihosting/semihost.h"
#include "cpregs.h"
+#define HELPER_H "tcg/helper-gvec.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-vfp.h.inc"
#include "exec/helper-gen.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/translate-gvec.c b/target/arm/tcg/translate-gvec.c
index 8b1d5e283c..1ae346c5a8 100644
--- a/target/arm/tcg/translate-gvec.c
+++ b/target/arm/tcg/translate-gvec.c
@@ -13,6 +13,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-gvec.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t opr_sz, uint32_t max_sz,
gen_helper_gvec_3_ptr *fn)
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 9a1831f849..fa13e7e8cb 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -24,6 +24,10 @@
#include "translate.h"
#include "translate-a32.h"
+#define HELPER_H "tcg/helper-gvec.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-vfp.h.inc"
#include "exec/helper-gen.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index ff050626e6..605cce0979 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -22,6 +22,9 @@
#include "translate-a64.h"
#include "fpu/softfloat.h"
+#define HELPER_H "tcg/helper-gvec.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t,
TCGv_i64, uint32_t, uint32_t);
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index af325577f0..b0aaca38e7 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -25,6 +25,10 @@
#include "qemu/int128.h"
#include "vec_internal.h"
+#define HELPER_H "tcg/helper-gvec.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-vfp.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > Instead of including helper-gvec.h.inc via helper.h which > is included by all TCG files, restrict it to the few files > that require it. > > Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> > --- > target/arm/helper.h | 1 - > target/arm/tcg/translate-a64.c | 4 ++++ > target/arm/tcg/translate-gvec.c | 6 ++++++ > target/arm/tcg/translate-neon.c | 4 ++++ > target/arm/tcg/translate-sve.c | 3 +++ > target/arm/tcg/vec_helper.c | 4 ++++ > 6 files changed, 21 insertions(+), 1 deletion(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the
SVE2 definitions. We already have helper-sve.h.inc for
SVE* definitions, move them there. The next commit will
remove it from the common helper.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper.h | 46 ---------------------------------
target/arm/tcg/helper-sve.h.inc | 46 +++++++++++++++++++++++++++++++++
2 files changed, 46 insertions(+), 46 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6d61694f5e..f347305c0f 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -146,52 +146,6 @@ DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlah_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_b, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlah_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlah_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, ptr, i32)
-
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
#include "tcg/helper-sve.h.inc"
diff --git a/target/arm/tcg/helper-sve.h.inc b/target/arm/tcg/helper-sve.h.inc
index cc4e1d8948..042a29d76a 100644
--- a/target/arm/tcg/helper-sve.h.inc
+++ b/target/arm/tcg/helper-sve.h.inc
@@ -2802,3 +2802,49 @@ DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
--
2.38.1
Instead of including helper-sve.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 1 -
target/arm/tcg/sve_helper.c | 4 ++++
target/arm/tcg/translate-sme.c | 4 ++++
target/arm/tcg/translate-sve.c | 6 ++++++
target/arm/tcg/vec_helper.c | 4 ++++
5 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index f347305c0f..38d3d1a2f3 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -148,7 +148,6 @@ DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
-#include "tcg/helper-sve.h.inc"
#include "tcg/helper-sme.h.inc"
#endif
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 8a0d966aae..79a42af591 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -33,6 +33,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sve.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/* Return a value for NZCV as per the ARM PredTest pseudofunction.
*
* The return value has bit 31 set if N is set, bit 1 set if Z is clear,
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 24796e5d9e..e63b9883a9 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -25,6 +25,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sve.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
/*
* Include the generated decoder.
*/
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 605cce0979..87f92b4d1d 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -26,6 +26,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sve.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t,
TCGv_i64, uint32_t, uint32_t);
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index b0aaca38e7..99f81df9e1 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -37,6 +37,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sve.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/*
* Data for expanding active predicate bits to bytes, for byte elements.
*
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > Instead of including helper-sve.h.inc via helper.h which > is included by all TCG files, restrict it to the few files > that require it. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 1 - > target/arm/tcg/sve_helper.c | 4 ++++ > target/arm/tcg/translate-sme.c | 4 ++++ > target/arm/tcg/translate-sve.c | 6 ++++++ > target/arm/tcg/vec_helper.c | 4 ++++ > 5 files changed, 18 insertions(+), 1 deletion(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the crypto
definitions. Move them to a new header; the next commit will
remove it from the common helper.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 37 ++------------------------
target/arm/tcg/helper-crypto.h.inc | 42 ++++++++++++++++++++++++++++++
2 files changed, 44 insertions(+), 35 deletions(-)
create mode 100644 target/arm/tcg/helper-crypto.h.inc
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 38d3d1a2f3..175589cbb4 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -108,44 +108,11 @@ DEF_HELPER_3(shr_cc, i32, env, i32, i32)
DEF_HELPER_3(sar_cc, i32, env, i32, i32)
DEF_HELPER_3(ror_cc, i32, env, i32, i32)
-DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_sha1su0, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha1c, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha1p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha1m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_sm3tt1a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm3tt1b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm3tt2a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm3tt2b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
-DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
+#include "tcg/helper-crypto.h.inc"
+
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
#include "tcg/helper-sme.h.inc"
diff --git a/target/arm/tcg/helper-crypto.h.inc b/target/arm/tcg/helper-crypto.h.inc
new file mode 100644
index 0000000000..d86f5002c4
--- /dev/null
+++ b/target/arm/tcg/helper-crypto.h.inc
@@ -0,0 +1,42 @@
+/*
+ * crypto_helper.c - emulate v8 Crypto Extensions instructions
+ *
+ * Copyright (C) 2013 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+
+DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_sha1su0, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha1c, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha1p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha1m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_sm3tt1a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3tt1b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3tt2a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3tt2b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > helper.h is used by all units, but not all require the crypto > definitions. Move them to a new header; the next commit will > remove it from the common helper.h. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 37 ++------------------------ > target/arm/tcg/helper-crypto.h.inc | 42 ++++++++++++++++++++++++++++++ > 2 files changed, 44 insertions(+), 35 deletions(-) > create mode 100644 target/arm/tcg/helper-crypto.h.inc Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Instead of including helper-crypto.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 2 --
target/arm/tcg/crypto_helper.c | 7 ++++++-
target/arm/tcg/translate-a64.c | 4 ++++
target/arm/tcg/translate-neon.c | 4 ++++
target/arm/tcg/translate-sve.c | 4 ++++
5 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 175589cbb4..e132969837 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -111,8 +111,6 @@ DEF_HELPER_3(ror_cc, i32, env, i32, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
-#include "tcg/helper-crypto.h.inc"
-
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
#include "tcg/helper-sme.h.inc"
diff --git a/target/arm/tcg/crypto_helper.c b/target/arm/tcg/crypto_helper.c
index d28690321f..75d9e57e3d 100644
--- a/target/arm/tcg/crypto_helper.c
+++ b/target/arm/tcg/crypto_helper.c
@@ -12,12 +12,17 @@
#include "qemu/osdep.h"
#include "cpu.h"
-#include "exec/helper-proto.h"
#include "tcg/tcg-gvec-desc.h"
#include "crypto/aes.h"
#include "crypto/sm4.h"
#include "vec_internal.h"
+#define HELPER_H "tcg/helper-crypto.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
union CRYPTO_STATE {
uint8_t bytes[16];
uint32_t words[4];
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 924bbdbf1d..46428ef034 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -38,6 +38,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-crypto.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index fa13e7e8cb..ba9f1a9801 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -32,6 +32,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-crypto.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-neon.h.inc"
#include "exec/helper-proto.h.inc"
#include "exec/helper-gen.h.inc"
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 87f92b4d1d..0fa3a14512 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -26,6 +26,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-crypto.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-sve.h.inc"
#include "exec/helper-proto.h.inc"
#include "exec/helper-gen.h.inc"
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > +++ b/target/arm/tcg/crypto_helper.c > @@ -12,12 +12,17 @@ > #include "qemu/osdep.h" > > #include "cpu.h" > -#include "exec/helper-proto.h" > #include "tcg/tcg-gvec-desc.h" > #include "crypto/aes.h" > #include "crypto/sm4.h" > #include "vec_internal.h" > > +#define HELPER_H "tcg/helper-crypto.h.inc" > +#include "exec/helper-proto.h.inc" > +#include "exec/helper-gen.h.inc" > +#include "exec/helper-info.c.inc" > +#undef HELPER_H > + foo_helper.c does not require helper-gen.h.inc. Usually we put helper-info.c.inc into one of the translate*.c files; probably translate-neon.c in this case. r~
On 20/6/23 12:38, Richard Henderson wrote: > On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: >> +++ b/target/arm/tcg/crypto_helper.c >> @@ -12,12 +12,17 @@ >> #include "qemu/osdep.h" >> #include "cpu.h" >> -#include "exec/helper-proto.h" >> #include "tcg/tcg-gvec-desc.h" >> #include "crypto/aes.h" >> #include "crypto/sm4.h" >> #include "vec_internal.h" >> +#define HELPER_H "tcg/helper-crypto.h.inc" >> +#include "exec/helper-proto.h.inc" >> +#include "exec/helper-gen.h.inc" >> +#include "exec/helper-info.c.inc" >> +#undef HELPER_H >> + > > foo_helper.c does not require helper-gen.h.inc. Right. > Usually we put helper-info.c.inc into one of the translate*.c files; > probably translate-neon.c in this case. Yes.
Instead of including helper-mve.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 2 --
target/arm/tcg/mve_helper.c | 5 ++++-
target/arm/tcg/translate-mve.c | 6 ++++++
target/arm/tcg/translate.c | 4 ++++
4 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index e132969837..6ea6384855 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -115,5 +115,3 @@ DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
#include "tcg/helper-a64.h.inc"
#include "tcg/helper-sme.h.inc"
#endif
-
-#include "tcg/helper-mve.h.inc"
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index d8ba5a9e60..a3fca486e0 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -21,7 +21,6 @@
#include "cpu.h"
#include "internals.h"
#include "vec_internal.h"
-#include "exec/helper-proto.h"
#include "exec/cpu_ldst.h"
#include "exec/exec-all.h"
#include "tcg/tcg.h"
@@ -31,6 +30,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-mve.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
static uint16_t mve_eci_mask(CPUARMState *env)
{
/*
diff --git a/target/arm/tcg/translate-mve.c b/target/arm/tcg/translate-mve.c
index bbc7b3f4ce..8577dc4377 100644
--- a/target/arm/tcg/translate-mve.c
+++ b/target/arm/tcg/translate-mve.c
@@ -21,6 +21,12 @@
#include "translate.h"
#include "translate-a32.h"
+#define HELPER_H "tcg/helper-mve.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
static inline int vidup_imm(DisasContext *s, int x)
{
return 1 << x;
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index ddc9baeafb..a71c60f4fb 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -33,6 +33,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-mve.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "helper.h"
#include "exec/helper-info.c.inc"
#undef HELPER_H
--
2.38.1
On 6/19/23 17:54, Philippe Mathieu-Daudé wrote: > Instead of including helper-mve.h.inc via helper.h which > is included by all TCG files, restrict it to the few files > that require it. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 2 -- > target/arm/tcg/mve_helper.c | 5 ++++- > target/arm/tcg/translate-mve.c | 6 ++++++ > target/arm/tcg/translate.c | 4 ++++ > 4 files changed, 14 insertions(+), 3 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Instead of including helper-sme.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 1 -
target/arm/tcg/sme_helper.c | 5 ++++-
target/arm/tcg/translate-a64.c | 4 ++++
target/arm/tcg/translate-sme.c | 6 ++++++
4 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6ea6384855..159ed9664f 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -113,5 +113,4 @@ DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
#ifdef TARGET_AARCH64
#include "tcg/helper-a64.h.inc"
-#include "tcg/helper-sme.h.inc"
#endif
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 1e67fcac30..04170ad18d 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -21,7 +21,6 @@
#include "cpu.h"
#include "internals.h"
#include "tcg/tcg-gvec-desc.h"
-#include "exec/helper-proto.h"
#include "exec/cpu_ldst.h"
#include "exec/exec-all.h"
#include "qemu/int128.h"
@@ -29,6 +28,10 @@
#include "vec_internal.h"
#include "sve_ldst_internal.h"
+#define HELPER_H "tcg/helper-sme.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
void helper_set_svcr(CPUARMState *env, uint32_t val, uint32_t mask)
{
aarch64_set_svcr(env, val, mask);
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 46428ef034..f4c9448582 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -42,6 +42,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sme.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index e63b9883a9..fa0dc20bf2 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -29,6 +29,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-sme.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
/*
* Include the generated decoder.
*/
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote: > Instead of including helper-sme.h.inc via helper.h which > is included by all TCG files, restrict it to the few files > that require it. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 1 - > target/arm/tcg/sme_helper.c | 5 ++++- > target/arm/tcg/translate-a64.c | 4 ++++ > target/arm/tcg/translate-sme.c | 6 ++++++ > 4 files changed, 14 insertions(+), 2 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the crypto
definitions. Move them to a new header, which we only include
where necessary, removing the need for "exec/helper-proto.h".
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/helper-a64.h.inc | 12 ------------
target/arm/tcg/helper-pauth.h.inc | 19 +++++++++++++++++++
target/arm/tcg/pauth_helper.c | 4 +++-
target/arm/tcg/translate-a64.c | 6 ++++++
4 files changed, 28 insertions(+), 13 deletions(-)
create mode 100644 target/arm/tcg/helper-pauth.h.inc
diff --git a/target/arm/tcg/helper-a64.h.inc b/target/arm/tcg/helper-a64.h.inc
index adff15600d..2f1aeb3ea5 100644
--- a/target/arm/tcg/helper-a64.h.inc
+++ b/target/arm/tcg/helper-a64.h.inc
@@ -69,18 +69,6 @@ DEF_HELPER_2(sqrt_f16, f16, f16, ptr)
DEF_HELPER_2(exception_return, void, env, i64)
DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64)
-DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(pacdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(pacga, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(autia, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(autib, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(autda, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64)
-DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64)
-
DEF_HELPER_FLAGS_3(mte_check, TCG_CALL_NO_WG, i64, env, i32, i64)
DEF_HELPER_FLAGS_3(mte_check_zva, TCG_CALL_NO_WG, i64, env, i32, i64)
DEF_HELPER_FLAGS_3(irg, TCG_CALL_NO_RWG, i64, env, i64, i64)
diff --git a/target/arm/tcg/helper-pauth.h.inc b/target/arm/tcg/helper-pauth.h.inc
new file mode 100644
index 0000000000..b5bf8aae24
--- /dev/null
+++ b/target/arm/tcg/helper-pauth.h.inc
@@ -0,0 +1,19 @@
+/*
+ * ARM v8.3-PAuth helper definitions
+ *
+ * Copyright (c) 2019 Linaro, Ltd.
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+
+DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(pacdb, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(pacga, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(autia, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(autib, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(autda, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64)
+DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64)
diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c
index 62af569341..c872f7e337 100644
--- a/target/arm/tcg/pauth_helper.c
+++ b/target/arm/tcg/pauth_helper.c
@@ -22,10 +22,12 @@
#include "internals.h"
#include "exec/exec-all.h"
#include "exec/cpu_ldst.h"
-#include "exec/helper-proto.h"
#include "tcg/tcg-gvec-desc.h"
#include "qemu/xxhash.h"
+#define HELPER_H "tcg/helper-pauth.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
static uint64_t pac_cell_shuffle(uint64_t i)
{
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index f4c9448582..0d74e5b6e4 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -46,6 +46,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-pauth.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote: > helper.h is used by all units, but not all require the crypto > definitions. Move them to a new header, which we only include > where necessary, removing the need for "exec/helper-proto.h". > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/tcg/helper-a64.h.inc | 12 ------------ > target/arm/tcg/helper-pauth.h.inc | 19 +++++++++++++++++++ > target/arm/tcg/pauth_helper.c | 4 +++- > target/arm/tcg/translate-a64.c | 6 ++++++ > 4 files changed, 28 insertions(+), 13 deletions(-) > create mode 100644 target/arm/tcg/helper-pauth.h.inc Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the crypto
definitions. Move them to a new header, which we only include
where necessary, removing the need for "exec/helper-proto.h".
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/helper-a64.h.inc | 16 ----------------
target/arm/tcg/helper-mte.h.inc | 23 +++++++++++++++++++++++
target/arm/tcg/mte_helper.c | 4 +++-
target/arm/tcg/translate-a64.c | 6 ++++++
4 files changed, 32 insertions(+), 17 deletions(-)
create mode 100644 target/arm/tcg/helper-mte.h.inc
diff --git a/target/arm/tcg/helper-a64.h.inc b/target/arm/tcg/helper-a64.h.inc
index 2f1aeb3ea5..e975f44bef 100644
--- a/target/arm/tcg/helper-a64.h.inc
+++ b/target/arm/tcg/helper-a64.h.inc
@@ -68,21 +68,5 @@ DEF_HELPER_2(sqrt_f16, f16, f16, ptr)
DEF_HELPER_2(exception_return, void, env, i64)
DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64)
-
-DEF_HELPER_FLAGS_3(mte_check, TCG_CALL_NO_WG, i64, env, i32, i64)
-DEF_HELPER_FLAGS_3(mte_check_zva, TCG_CALL_NO_WG, i64, env, i32, i64)
-DEF_HELPER_FLAGS_3(irg, TCG_CALL_NO_RWG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_4(addsubg, TCG_CALL_NO_RWG_SE, i64, env, i64, s32, i32)
-DEF_HELPER_FLAGS_3(ldg, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(stg, TCG_CALL_NO_WG, void, env, i64, i64)
-DEF_HELPER_FLAGS_3(stg_parallel, TCG_CALL_NO_WG, void, env, i64, i64)
-DEF_HELPER_FLAGS_2(stg_stub, TCG_CALL_NO_WG, void, env, i64)
-DEF_HELPER_FLAGS_3(st2g, TCG_CALL_NO_WG, void, env, i64, i64)
-DEF_HELPER_FLAGS_3(st2g_parallel, TCG_CALL_NO_WG, void, env, i64, i64)
-DEF_HELPER_FLAGS_2(st2g_stub, TCG_CALL_NO_WG, void, env, i64)
-DEF_HELPER_FLAGS_2(ldgm, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_3(stgm, TCG_CALL_NO_WG, void, env, i64, i64)
-DEF_HELPER_FLAGS_3(stzgm_tags, TCG_CALL_NO_WG, void, env, i64, i64)
-
DEF_HELPER_FLAGS_4(unaligned_access, TCG_CALL_NO_WG,
noreturn, env, i64, i32, i32)
diff --git a/target/arm/tcg/helper-mte.h.inc b/target/arm/tcg/helper-mte.h.inc
new file mode 100644
index 0000000000..dc954d49a0
--- /dev/null
+++ b/target/arm/tcg/helper-mte.h.inc
@@ -0,0 +1,23 @@
+/*
+ * ARM v8.5-MemTag helper definitions
+ *
+ * Copyright (c) 2020 Linaro, Ltd.
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+
+DEF_HELPER_FLAGS_3(mte_check, TCG_CALL_NO_WG, i64, env, i32, i64)
+DEF_HELPER_FLAGS_3(mte_check_zva, TCG_CALL_NO_WG, i64, env, i32, i64)
+
+DEF_HELPER_FLAGS_3(irg, TCG_CALL_NO_RWG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_4(addsubg, TCG_CALL_NO_RWG_SE, i64, env, i64, s32, i32)
+DEF_HELPER_FLAGS_3(ldg, TCG_CALL_NO_WG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_3(stg, TCG_CALL_NO_WG, void, env, i64, i64)
+DEF_HELPER_FLAGS_3(stg_parallel, TCG_CALL_NO_WG, void, env, i64, i64)
+DEF_HELPER_FLAGS_2(stg_stub, TCG_CALL_NO_WG, void, env, i64)
+DEF_HELPER_FLAGS_3(st2g, TCG_CALL_NO_WG, void, env, i64, i64)
+DEF_HELPER_FLAGS_3(st2g_parallel, TCG_CALL_NO_WG, void, env, i64, i64)
+DEF_HELPER_FLAGS_2(st2g_stub, TCG_CALL_NO_WG, void, env, i64)
+DEF_HELPER_FLAGS_2(ldgm, TCG_CALL_NO_WG, i64, env, i64)
+DEF_HELPER_FLAGS_3(stgm, TCG_CALL_NO_WG, void, env, i64, i64)
+DEF_HELPER_FLAGS_3(stzgm_tags, TCG_CALL_NO_WG, void, env, i64, i64)
diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c
index 9c64def081..89840c6f7e 100644
--- a/target/arm/tcg/mte_helper.c
+++ b/target/arm/tcg/mte_helper.c
@@ -24,11 +24,13 @@
#include "exec/exec-all.h"
#include "exec/ram_addr.h"
#include "exec/cpu_ldst.h"
-#include "exec/helper-proto.h"
#include "hw/core/tcg-cpu-ops.h"
#include "qapi/error.h"
#include "qemu/guest-random.h"
+#define HELPER_H "tcg/helper-mte.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
static int choose_nonexcluded_tag(int tag, int offset, uint16_t exclude)
{
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 0d74e5b6e4..a3d4265f85 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -46,6 +46,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-mte.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-pauth.h.inc"
#include "exec/helper-proto.h.inc"
#include "exec/helper-gen.h.inc"
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote: > helper.h is used by all units, but not all require the crypto > definitions. Move them to a new header, which we only include > where necessary, removing the need for "exec/helper-proto.h". > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/tcg/helper-a64.h.inc | 16 ---------------- > target/arm/tcg/helper-mte.h.inc | 23 +++++++++++++++++++++++ > target/arm/tcg/mte_helper.c | 4 +++- > target/arm/tcg/translate-a64.c | 6 ++++++ > 4 files changed, 32 insertions(+), 17 deletions(-) > create mode 100644 target/arm/tcg/helper-mte.h.inc Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Instead of including helper-a64.h.inc via helper.h which
is included by all TCG files, restrict it to the few files
that require it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 4 ----
target/arm/tcg/helper-a64.c | 4 ++++
target/arm/tcg/sve_helper.c | 5 ++++-
target/arm/tcg/translate-a64.c | 6 ++++++
target/arm/tcg/vec_helper.c | 5 ++++-
5 files changed, 18 insertions(+), 6 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 159ed9664f..aae2a38407 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -110,7 +110,3 @@ DEF_HELPER_3(ror_cc, i32, env, i32, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
-
-#ifdef TARGET_AARCH64
-#include "tcg/helper-a64.h.inc"
-#endif
diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 6312238676..782b6b6e94 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -35,6 +35,10 @@
#include "fpu/softfloat.h"
#include <zlib.h> /* For crc32 */
+#define HELPER_H "tcg/helper-a64.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/* C2.4.7 Multiply and divide */
/* special cases for 0 and LLONG_MIN are mandated by the standard */
uint64_t HELPER(udiv64)(uint64_t num, uint64_t den)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 79a42af591..64f744bf6a 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -21,7 +21,6 @@
#include "cpu.h"
#include "internals.h"
#include "exec/exec-all.h"
-#include "exec/helper-proto.h"
#include "tcg/tcg-gvec-desc.h"
#include "fpu/softfloat.h"
#include "tcg/tcg.h"
@@ -37,6 +36,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-a64.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/* Return a value for NZCV as per the ARM PredTest pseudofunction.
*
* The return value has bit 31 set if N is set, bit 1 set if Z is clear,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index a3d4265f85..73697f0cc9 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -58,6 +58,12 @@
#include "exec/helper-info.c.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-a64.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 99f81df9e1..dcfb3cfc96 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -19,7 +19,6 @@
#include "qemu/osdep.h"
#include "cpu.h"
-#include "exec/helper-proto.h"
#include "tcg/tcg-gvec-desc.h"
#include "fpu/softfloat.h"
#include "qemu/int128.h"
@@ -41,6 +40,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-a64.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/*
* Data for expanding active predicate bits to bytes, for byte elements.
*
--
2.38.1
No need to have the v8m_stackcheck() helper in the generic
op_helper.c, move it with the rest of the M-profile helpers.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/m_helper.c | 16 ++++++++++++++++
target/arm/tcg/op_helper.c | 16 ----------------
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 0891acc29c..0780bb3dea 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -2893,3 +2893,19 @@ uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure, bool threadmode,
}
}
}
+
+void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue)
+{
+ /*
+ * Perform the v8M stack limit check for SP updates from translated code,
+ * raising an exception if the limit is breached.
+ */
+ if (newvalue < v7m_sp_limit(env)) {
+ /*
+ * Stack limit exceptions are a rare case, so rather than syncing
+ * PC/condbits before the call, we use raise_exception_ra() so
+ * that cpu_restore_state() will sort them out.
+ */
+ raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC());
+ }
+}
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index 70a9c37b74..04a90e3e3a 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -82,22 +82,6 @@ void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome,
raise_exception(env, excp, syndrome, target_el);
}
-void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue)
-{
- /*
- * Perform the v8M stack limit check for SP updates from translated code,
- * raising an exception if the limit is breached.
- */
- if (newvalue < v7m_sp_limit(env)) {
- /*
- * Stack limit exceptions are a rare case, so rather than syncing
- * PC/condbits before the call, we use raise_exception_ra() so
- * that cpu_restore_state() will sort them out.
- */
- raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC());
- }
-}
-
uint32_t HELPER(add_setq)(CPUARMState *env, uint32_t a, uint32_t b)
{
uint32_t res = a + b;
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote: > No need to have the v8m_stackcheck() helper in the generic > op_helper.c, move it with the rest of the M-profile helpers. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/tcg/m_helper.c | 16 ++++++++++++++++ > target/arm/tcg/op_helper.c | 16 ---------------- > 2 files changed, 16 insertions(+), 16 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
helper.h is used by all units, but not all require the
M-profile definitions. Move them to a new header; the next
commit will remove it from the common helper.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 17 ++---------------
target/arm/tcg/helper-m.h.inc | 23 +++++++++++++++++++++++
2 files changed, 25 insertions(+), 15 deletions(-)
create mode 100644 target/arm/tcg/helper-m.h.inc
diff --git a/target/arm/helper.h b/target/arm/helper.h
index aae2a38407..70ae3513e5 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -62,21 +62,6 @@ DEF_HELPER_3(cpsr_write, void, env, i32, i32)
DEF_HELPER_2(cpsr_write_eret, void, env, i32)
DEF_HELPER_1(cpsr_read, i32, env)
-DEF_HELPER_3(v7m_msr, void, env, i32, i32)
-DEF_HELPER_2(v7m_mrs, i32, env, i32)
-
-DEF_HELPER_2(v7m_bxns, void, env, i32)
-DEF_HELPER_2(v7m_blxns, void, env, i32)
-
-DEF_HELPER_3(v7m_tt, i32, env, i32, i32)
-
-DEF_HELPER_1(v7m_preserve_fp_state, void, env)
-
-DEF_HELPER_2(v7m_vlstm, void, env, i32)
-DEF_HELPER_2(v7m_vlldm, void, env, i32)
-
-DEF_HELPER_2(v8m_stackcheck, void, env, i32)
-
DEF_HELPER_FLAGS_2(check_bxj_trap, TCG_CALL_NO_WG, void, env, i32)
DEF_HELPER_4(access_check_cp_reg, cptr, env, i32, i32, i32)
@@ -110,3 +95,5 @@ DEF_HELPER_3(ror_cc, i32, env, i32, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
+
+#include "tcg/helper-m.h.inc"
diff --git a/target/arm/tcg/helper-m.h.inc b/target/arm/tcg/helper-m.h.inc
new file mode 100644
index 0000000000..122311b6d0
--- /dev/null
+++ b/target/arm/tcg/helper-m.h.inc
@@ -0,0 +1,23 @@
+/*
+ * ARM M-profile helper definitions
+ *
+ * Copyright (c) 2007 CodeSourcery.
+ * Written by Paul Brook
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+DEF_HELPER_3(v7m_msr, void, env, i32, i32)
+DEF_HELPER_2(v7m_mrs, i32, env, i32)
+
+DEF_HELPER_2(v7m_bxns, void, env, i32)
+DEF_HELPER_2(v7m_blxns, void, env, i32)
+
+DEF_HELPER_3(v7m_tt, i32, env, i32, i32)
+
+DEF_HELPER_1(v7m_preserve_fp_state, void, env)
+
+DEF_HELPER_2(v7m_vlstm, void, env, i32)
+DEF_HELPER_2(v7m_vlldm, void, env, i32)
+
+DEF_HELPER_2(v8m_stackcheck, void, env, i32)
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote: > helper.h is used by all units, but not all require the > M-profile definitions. Move them to a new header; the next > commit will remove it from the common helper.h. > > Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org> > --- > target/arm/helper.h | 17 ++--------------- > target/arm/tcg/helper-m.h.inc | 23 +++++++++++++++++++++++ > 2 files changed, 25 insertions(+), 15 deletions(-) > create mode 100644 target/arm/tcg/helper-m.h.inc Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
Instead of including helper-m.h.inc via helper.h which is
included by all TCG files, restrict it to the few files
that require it.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/helper.h | 2 --
target/arm/tcg/m_helper.c | 4 ++++
target/arm/tcg/translate-m-nocp.c | 6 ++++++
target/arm/tcg/translate-vfp.c | 4 ++++
target/arm/tcg/translate.c | 4 ++++
5 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 70ae3513e5..77c004a70c 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -95,5 +95,3 @@ DEF_HELPER_3(ror_cc, i32, env, i32, i32)
DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
-
-#include "tcg/helper-m.h.inc"
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 0780bb3dea..45568d96bb 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -21,6 +21,10 @@
#include "hw/intc/armv7m_nvic.h"
#endif
+#define HELPER_H "tcg/helper-m.h.inc"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
static void v7m_msr_xpsr(CPUARMState *env, uint32_t mask,
uint32_t reg, uint32_t val)
{
diff --git a/target/arm/tcg/translate-m-nocp.c b/target/arm/tcg/translate-m-nocp.c
index 7343945b41..ee9c296a98 100644
--- a/target/arm/tcg/translate-m-nocp.c
+++ b/target/arm/tcg/translate-m-nocp.c
@@ -25,6 +25,12 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-m.h.inc"
+#include "exec/helper-proto.h.inc"
+#include "exec/helper-gen.h.inc"
+#include "exec/helper-info.c.inc"
+#undef HELPER_H
+
/* Include the generated decoder */
#include "decode-m-nocp.c.inc"
diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c
index b890c7ed01..ff61c53db2 100644
--- a/target/arm/tcg/translate-vfp.c
+++ b/target/arm/tcg/translate-vfp.c
@@ -24,6 +24,10 @@
#include "translate.h"
#include "translate-a32.h"
+#define HELPER_H "tcg/helper-m.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-vfp.h.inc"
#include "exec/helper-proto.h.inc"
#include "exec/helper-gen.h.inc"
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index a71c60f4fb..4b54e177d1 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -37,6 +37,10 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
+#define HELPER_H "tcg/helper-m.h.inc"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
+
#define HELPER_H "helper.h"
#include "exec/helper-info.c.inc"
#undef HELPER_H
--
2.38.1
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/translate.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 7d57a71b67..13d59d8417 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -6,9 +6,11 @@
#include "tcg/tcg-op-gvec.h"
#include "exec/exec-all.h"
#include "exec/translator.h"
-#include "exec/helper-gen.h"
#include "internals.h"
+#define HELPER_H "helper.h"
+#include "exec/helper-gen.h.inc"
+#undef HELPER_H
/* internal defines */
--
2.38.1
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/debug_helper.c | 6 +++++-
target/arm/helper.c | 6 +++++-
target/arm/tcg/helper-a64.c | 5 ++++-
target/arm/tcg/hflags.c | 5 ++++-
target/arm/tcg/m_helper.c | 5 ++++-
target/arm/tcg/op_helper.c | 5 ++++-
target/arm/tcg/psci.c | 5 ++++-
target/arm/tcg/tlb_helper.c | 4 +++-
target/arm/tcg/translate.c | 2 +-
9 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index 8362462a07..31165b92a5 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -11,10 +11,14 @@
#include "internals.h"
#include "cpregs.h"
#include "exec/exec-all.h"
-#include "exec/helper-proto.h"
#include "sysemu/tcg.h"
#ifdef CONFIG_TCG
+
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
/* Return the Exception Level targeted by debug exceptions. */
static int arm_debug_target_el(CPUARMState *env)
{
diff --git a/target/arm/helper.c b/target/arm/helper.c
index d4bee43bd0..63ed29b841 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -11,7 +11,6 @@
#include "trace.h"
#include "cpu.h"
#include "internals.h"
-#include "exec/helper-proto.h"
#include "qemu/main-loop.h"
#include "qemu/timer.h"
#include "qemu/bitops.h"
@@ -26,6 +25,11 @@
#include "qapi/error.h"
#include "qemu/guest-random.h"
#ifdef CONFIG_TCG
+
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
#include "semihosting/common-semi.h"
#endif
#include "cpregs.h"
diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 782b6b6e94..58a573e21d 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -21,7 +21,6 @@
#include "qemu/units.h"
#include "cpu.h"
#include "gdbstub/helpers.h"
-#include "exec/helper-proto.h"
#include "qemu/host-utils.h"
#include "qemu/log.h"
#include "qemu/main-loop.h"
@@ -35,6 +34,10 @@
#include "fpu/softfloat.h"
#include <zlib.h> /* For crc32 */
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
#define HELPER_H "tcg/helper-a64.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index 616c5fa723..83a1aa08e4 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -8,9 +8,12 @@
#include "qemu/osdep.h"
#include "cpu.h"
#include "internals.h"
-#include "exec/helper-proto.h"
#include "cpregs.h"
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
static inline bool fgt_svc(CPUARMState *env, int el)
{
/*
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 45568d96bb..1991eafe05 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -10,7 +10,6 @@
#include "cpu.h"
#include "internals.h"
#include "gdbstub/helpers.h"
-#include "exec/helper-proto.h"
#include "qemu/main-loop.h"
#include "qemu/bitops.h"
#include "qemu/log.h"
@@ -25,6 +24,10 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
static void v7m_msr_xpsr(CPUARMState *env, uint32_t mask,
uint32_t reg, uint32_t val)
{
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index 04a90e3e3a..24205074cc 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -19,12 +19,15 @@
#include "qemu/osdep.h"
#include "qemu/main-loop.h"
#include "cpu.h"
-#include "exec/helper-proto.h"
#include "internals.h"
#include "exec/exec-all.h"
#include "exec/cpu_ldst.h"
#include "cpregs.h"
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
#define SIGNBIT (uint32_t)0x80000000
#define SIGNBIT64 ((uint64_t)1 << 63)
diff --git a/target/arm/tcg/psci.c b/target/arm/tcg/psci.c
index 6c1239bb96..2822a6b96a 100644
--- a/target/arm/tcg/psci.c
+++ b/target/arm/tcg/psci.c
@@ -18,13 +18,16 @@
#include "qemu/osdep.h"
#include "cpu.h"
-#include "exec/helper-proto.h"
#include "kvm-consts.h"
#include "qemu/main-loop.h"
#include "sysemu/runstate.h"
#include "internals.h"
#include "arm-powerctl.h"
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
+
bool arm_is_psci_call(ARMCPU *cpu, int excp_type)
{
/*
diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
index 8df36c2cbf..e663aef2fd 100644
--- a/target/arm/tcg/tlb_helper.c
+++ b/target/arm/tcg/tlb_helper.c
@@ -9,8 +9,10 @@
#include "cpu.h"
#include "internals.h"
#include "exec/exec-all.h"
-#include "exec/helper-proto.h"
+#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
+#undef HELPER_H
/*
* Returns true if the stage 1 translation regime is using LPAE format page
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index 4b54e177d1..bb8756d0ff 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -27,7 +27,6 @@
#include "arm_ldst.h"
#include "semihosting/semihost.h"
#include "cpregs.h"
-#include "exec/helper-proto.h"
#define HELPER_H "tcg/helper-neon.h.inc"
#include "exec/helper-gen.h.inc"
@@ -42,6 +41,7 @@
#undef HELPER_H
#define HELPER_H "helper.h"
+#include "exec/helper-proto.h.inc"
#include "exec/helper-info.c.inc"
#undef HELPER_H
--
2.38.1
Since commit 139c1837db ("meson: rename included C source files
to .c.inc"), QEMU standard procedure for included C files is to
use *.c.inc.
Besides, since commit 6a0057aa22 ("docs/devel: make a statement
about includes") this is documented as the Coding Style:
If you do use template header files they should be named with
the ``.c.inc`` or ``.h.inc`` suffix to make it clear they are
being included for expansion.
Therefore rename 'helper.h' as 'helper.h.inc'. Since this file
is TCG-specific, move it to the tcg/ directory.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
target/arm/tcg/translate.h | 2 +-
target/arm/{helper.h => tcg/helper.h.inc} | 0
target/arm/debug_helper.c | 2 +-
target/arm/helper.c | 2 +-
target/arm/tcg/helper-a64.c | 2 +-
target/arm/tcg/hflags.c | 2 +-
target/arm/tcg/m_helper.c | 2 +-
target/arm/tcg/op_helper.c | 2 +-
target/arm/tcg/psci.c | 2 +-
target/arm/tcg/tlb_helper.c | 2 +-
target/arm/tcg/translate.c | 2 +-
11 files changed, 10 insertions(+), 10 deletions(-)
rename target/arm/{helper.h => tcg/helper.h.inc} (100%)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 13d59d8417..6516852c06 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -8,7 +8,7 @@
#include "exec/translator.h"
#include "internals.h"
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-gen.h.inc"
#undef HELPER_H
diff --git a/target/arm/helper.h b/target/arm/tcg/helper.h.inc
similarity index 100%
rename from target/arm/helper.h
rename to target/arm/tcg/helper.h.inc
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index 31165b92a5..b32852e947 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -15,7 +15,7 @@
#ifdef CONFIG_TCG
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 63ed29b841..425cc86c7a 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -26,7 +26,7 @@
#include "qemu/guest-random.h"
#ifdef CONFIG_TCG
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 58a573e21d..5573c0c15e 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -34,7 +34,7 @@
#include "fpu/softfloat.h"
#include <zlib.h> /* For crc32 */
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index 83a1aa08e4..e75cb0100e 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -10,7 +10,7 @@
#include "internals.h"
#include "cpregs.h"
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 1991eafe05..4100161775 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -24,7 +24,7 @@
#include "exec/helper-proto.h.inc"
#undef HELPER_H
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index 24205074cc..e1aadd63f0 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -24,7 +24,7 @@
#include "exec/cpu_ldst.h"
#include "cpregs.h"
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/psci.c b/target/arm/tcg/psci.c
index 2822a6b96a..e00b9b1493 100644
--- a/target/arm/tcg/psci.c
+++ b/target/arm/tcg/psci.c
@@ -24,7 +24,7 @@
#include "internals.h"
#include "arm-powerctl.h"
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
index e663aef2fd..3f8cb358a6 100644
--- a/target/arm/tcg/tlb_helper.c
+++ b/target/arm/tcg/tlb_helper.c
@@ -10,7 +10,7 @@
#include "internals.h"
#include "exec/exec-all.h"
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#undef HELPER_H
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index bb8756d0ff..00b73c9151 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -40,7 +40,7 @@
#include "exec/helper-gen.h.inc"
#undef HELPER_H
-#define HELPER_H "helper.h"
+#define HELPER_H "tcg/helper.h.inc"
#include "exec/helper-proto.h.inc"
#include "exec/helper-info.c.inc"
#undef HELPER_H
--
2.38.1
On 6/19/23 17:55, Philippe Mathieu-Daudé wrote:
> Since commit 139c1837db ("meson: rename included C source files
> to .c.inc"), QEMU standard procedure for included C files is to
> use *.c.inc.
>
> Besides, since commit 6a0057aa22 ("docs/devel: make a statement
> about includes") this is documented as the Coding Style:
>
> If you do use template header files they should be named with
> the ``.c.inc`` or ``.h.inc`` suffix to make it clear they are
> being included for expansion.
>
> Therefore rename 'helper.h' as 'helper.h.inc'. Since this file
> is TCG-specific, move it to the tcg/ directory.
>
> Signed-off-by: Philippe Mathieu-Daudé<philmd@linaro.org>
> ---
> target/arm/tcg/translate.h | 2 +-
> target/arm/{helper.h => tcg/helper.h.inc} | 0
> target/arm/debug_helper.c | 2 +-
> target/arm/helper.c | 2 +-
> target/arm/tcg/helper-a64.c | 2 +-
> target/arm/tcg/hflags.c | 2 +-
> target/arm/tcg/m_helper.c | 2 +-
> target/arm/tcg/op_helper.c | 2 +-
> target/arm/tcg/psci.c | 2 +-
> target/arm/tcg/tlb_helper.c | 2 +-
> target/arm/tcg/translate.c | 2 +-
> 11 files changed, 10 insertions(+), 10 deletions(-)
> rename target/arm/{helper.h => tcg/helper.h.inc} (100%)
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
r~
Since commit 139c1837db ("meson: rename included C source files
to .c.inc"), QEMU standard procedure for included C files is to
use *.c.inc.
Besides, since commit 6a0057aa22 ("docs/devel: make a statement
about includes") this is documented as the Coding Style:
If you do use template header files they should be named with
the ``.c.inc`` or ``.h.inc`` suffix to make it clear they are
being included for expansion.
Therefore rename 'bti-crt.inc.c' as 'bti-crt.c.inc'.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
---
tests/tcg/aarch64/bti-1.c | 2 +-
tests/tcg/aarch64/bti-3.c | 2 +-
tests/tcg/aarch64/{bti-crt.inc.c => bti-crt.c.inc} | 0
3 files changed, 2 insertions(+), 2 deletions(-)
rename tests/tcg/aarch64/{bti-crt.inc.c => bti-crt.c.inc} (100%)
diff --git a/tests/tcg/aarch64/bti-1.c b/tests/tcg/aarch64/bti-1.c
index 61924f0d7a..99a879af23 100644
--- a/tests/tcg/aarch64/bti-1.c
+++ b/tests/tcg/aarch64/bti-1.c
@@ -2,7 +2,7 @@
* Branch target identification, basic notskip cases.
*/
-#include "bti-crt.inc.c"
+#include "bti-crt.c.inc"
static void skip2_sigill(int sig, siginfo_t *info, ucontext_t *uc)
{
diff --git a/tests/tcg/aarch64/bti-3.c b/tests/tcg/aarch64/bti-3.c
index a852856d9a..8c534c09d7 100644
--- a/tests/tcg/aarch64/bti-3.c
+++ b/tests/tcg/aarch64/bti-3.c
@@ -2,7 +2,7 @@
* BTI vs PACIASP
*/
-#include "bti-crt.inc.c"
+#include "bti-crt.c.inc"
static void skip2_sigill(int sig, siginfo_t *info, ucontext_t *uc)
{
diff --git a/tests/tcg/aarch64/bti-crt.inc.c b/tests/tcg/aarch64/bti-crt.c.inc
similarity index 100%
rename from tests/tcg/aarch64/bti-crt.inc.c
rename to tests/tcg/aarch64/bti-crt.c.inc
--
2.38.1
© 2016 - 2025 Red Hat, Inc.