Proxmox-Port/qemu
1
0
Fork 0
mirror of https://github.com/qemu/qemu.git synced 2025-08-10 12:46:22 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

target/arm: Implement fp16 for Neon VMAXNM, VMINNM

Browse Source 
Convert the Neon floating point VMAXNM and VMINNM insns to
using a gvec helper and use this to implement the fp16 case.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-30-peter.maydell@linaro.org
This commit is contained in:
Peter Maydell 2020-08-28 19:33:38 +01:00
parent e43268c54b
commit e22705bb94
3 changed files with 27 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
target/arm/helper.h
View File

@ -653,6 +653,12 @@ 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_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_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_ftsmul_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32) void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,

23
target/arm/translate-neon.c.inc
View File

@ -1151,6 +1151,11 @@ static void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
DO_3S_FP(VMLA, gen_VMLA_fp_3s, true) DO_3S_FP(VMLA, gen_VMLA_fp_3s, true)
DO_3S_FP(VMLS, gen_VMLS_fp_3s, true) DO_3S_FP(VMLS, gen_VMLS_fp_3s, true)
WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s)
WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h)
WRAP_FP_GVEC(gen_VMINNM_fp32_3s, FPST_STD, gen_helper_gvec_fminnum_s)
WRAP_FP_GVEC(gen_VMINNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fminnum_h)
static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a)
{ {
if (!arm_dc_feature(s, ARM_FEATURE_V8)) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
@ -1158,11 +1163,12 @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a)
} }
if (a->size != 0) { if (a->size != 0) {
/* TODO fp16 support */ if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false; return false;
}
return do_3same(s, a, gen_VMAXNM_fp16_3s);
} }
return do_3same(s, a, gen_VMAXNM_fp32_3s);
return do_3same_fp(s, a, gen_helper_vfp_maxnums, false);
} }
static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a)
@ -1172,11 +1178,12 @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a)
} }
if (a->size != 0) { if (a->size != 0) {
/* TODO fp16 support */ if (!dc_isar_feature(aa32_fp16_arith, s)) {
return false; return false;
}
return do_3same(s, a, gen_VMINNM_fp16_3s);
} }
return do_3same(s, a, gen_VMINNM_fp32_3s);
return do_3same_fp(s, a, gen_helper_vfp_minnums, false);
} }
WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32)

6
target/arm/vec_helper.c
View File

@ -823,6 +823,12 @@ DO_3OP(gvec_fmax_s, float32_max, float32)
DO_3OP(gvec_fmin_h, float16_min, float16) DO_3OP(gvec_fmin_h, float16_min, float16)
DO_3OP(gvec_fmin_s, float32_min, float32) DO_3OP(gvec_fmin_s, float32_min, float32)
DO_3OP(gvec_fmaxnum_h, float16_maxnum, float16)
DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32)
DO_3OP(gvec_fminnum_h, float16_minnum, float16)
DO_3OP(gvec_fminnum_s, float32_minnum, float32)
#ifdef TARGET_AARCH64 #ifdef TARGET_AARCH64
DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)