yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2025-02-25 14:26:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree

Browse source 
Convert the Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS 3-reg-same
insns to decodetree. (These are all the remaining non-accumulation
instructions in this group.)

Backports commit d5fdf9e9e1c6f2bbb0a4bcaafd85d344cce9c298 from qemu
This commit is contained in:
Peter Maydell 2020-05-15 23:44:50 -04:00 committed by Lioncash
parent a593866af6
commit 82484db863
3 changed files with 78 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
qemu/target/arm/neon-dp.decode
View file

@ -188,5 +188,11 @@ VCGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 0 .... @3same_fp
VACGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 1 .... @3same_fp
VCGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 0 .... @3same_fp
VACGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 1 .... @3same_fp
VMAX_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 0 .... @3same_fp
VMIN_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 0 .... @3same_fp
VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0
VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0
VRECPS_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
VRSQRTS_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
VMAXNM_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp

70
qemu/target/arm/translate-neon.inc.c
View file

@ -1138,6 +1138,8 @@ DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false)
DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false)
DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false)
DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false)
DO_3S_FP(VMAX, gen_helper_vfp_maxs, false)
DO_3S_FP(VMIN, gen_helper_vfp_mins, false)
static void gen_VMLA_fp_3s(TCGContext *s, TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
TCGv_ptr fpstatus)
@ -1156,6 +1158,74 @@ static void gen_VMLS_fp_3s(TCGContext *s, TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm,
DO_3S_FP(VMLA, gen_VMLA_fp_3s, true)
DO_3S_FP(VMLS, gen_VMLS_fp_3s, true)
static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a)
{
if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
return false;
}
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same_fp(s, a, gen_helper_vfp_maxnums, false);
}
static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a)
{
if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
return false;
}
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same_fp(s, a, gen_helper_vfp_minnums, false);
}
WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32)
static void gen_VRECPS_fp_3s(TCGContext *s, unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
static const GVecGen3 ops = { .fni4 = gen_VRECPS_tramp };
tcg_gen_gvec_3(s, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops);
}
static bool trans_VRECPS_fp_3s(DisasContext *s, arg_3same *a)
{
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same(s, a, gen_VRECPS_fp_3s);
}
WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32)
static void gen_VRSQRTS_fp_3s(TCGContext *s, unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
static const GVecGen3 ops = { .fni4 = gen_VRSQRTS_tramp };
tcg_gen_gvec_3(s, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops);
}
static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a)
{
if (a->size != 0) {
/* TODO fp16 support */
return false;
}
return do_3same(s, a, gen_VRSQRTS_fp_3s);
}
static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
{
/* FP operations handled pairwise 32 bits at a time */

42
qemu/target/arm/translate.c
View file

@ -5562,6 +5562,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
case NEON_3R_FLOAT_MULTIPLY:
case NEON_3R_FLOAT_CMP:
case NEON_3R_FLOAT_ACMP:
case NEON_3R_FLOAT_MINMAX:
case NEON_3R_FLOAT_MISC:
/* Already handled by decodetree */
return 1;
}
@ -5571,17 +5573,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
return 1;
}
switch (op) {
case NEON_3R_FLOAT_MINMAX:
if (u) {
return 1; /* VPMIN/VPMAX handled by decodetree */
}
break;
case NEON_3R_FLOAT_MISC:
/* VMAXNM/VMINNM in ARMv8 */
if (u && !arm_dc_feature(s, ARM_FEATURE_V8)) {
return 1;
}
break;
case NEON_3R_VFM_VQRDMLSH:
if (!dc_isar_feature(aa32_simdfmac, s)) {
return 1;
@ -5597,35 +5588,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
tmp = neon_load_reg(s, rn, pass);
tmp2 = neon_load_reg(s, rm, pass);
switch (op) {
case NEON_3R_FLOAT_MINMAX:
{
TCGv_ptr fpstatus = get_fpstatus_ptr(tcg_ctx, 1);
if (size == 0) {
gen_helper_vfp_maxs(tcg_ctx, tmp, tmp, tmp2, fpstatus);
} else {
gen_helper_vfp_mins(tcg_ctx, tmp, tmp, tmp2, fpstatus);
}
tcg_temp_free_ptr(tcg_ctx, fpstatus);
break;
}
case NEON_3R_FLOAT_MISC:
if (u) {
/* VMAXNM/VMINNM */
TCGv_ptr fpstatus = get_fpstatus_ptr(tcg_ctx, 1);
if (size == 0) {
gen_helper_vfp_maxnums(tcg_ctx, tmp, tmp, tmp2, fpstatus);
} else {
gen_helper_vfp_minnums(tcg_ctx, tmp, tmp, tmp2, fpstatus);
}
tcg_temp_free_ptr(tcg_ctx, fpstatus);
} else {
if (size == 0) {
gen_helper_recps_f32(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
} else {
gen_helper_rsqrts_f32(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
}
}
break;
case NEON_3R_VFM_VQRDMLSH:
{
/* VFMA, VFMS: fused multiply-add */