yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2025-01-11 01:15:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/arm: Implement VFP vp16 VCVT-with-specified-rounding-mode

Browse source 
Implement the fp16 versions of the VFP VCVT instruction forms
which convert between floating point and integer with a specified
rounding mode.

Backports c505bc6a9d50a48f9d89d6cf930e863838a5b367
This commit is contained in:
Peter Maydell 2021-02-28 05:18:06 -05:00 committed by Lioncash
parent 74a6af4e23
commit beee4ad7f3
2 changed files with 28 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
qemu/target/arm/translate-vfp.inc.c
View file

@ -402,7 +402,7 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
{ {
TCGContext *tcg_ctx = s->uc->tcg_ctx; TCGContext *tcg_ctx = s->uc->tcg_ctx;
uint32_t rd, rm; uint32_t rd, rm;
bool dp = a->dp; int sz = a->sz;
TCGv_ptr fpst; TCGv_ptr fpst;
TCGv_i32 tcg_rmode, tcg_shift; TCGv_i32 tcg_rmode, tcg_shift;
int rounding = fp_decode_rm[a->rm]; int rounding = fp_decode_rm[a->rm];
@ -412,12 +412,16 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
return false; return false;
} }
if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) {
return false;
}
if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) {
return false; return false;
} }
/* UNDEF accesses to D16-D31 if they don't exist */ /* UNDEF accesses to D16-D31 if they don't exist */
if (dp && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) {
return false; return false;
} }
@ -428,14 +432,18 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
return true; return true;
} }
fpst = fpstatus_ptr(tcg_ctx, FPST_FPCR); if (sz == 1) {
fpst = fpstatus_ptr(tcg_ctx, FPST_FPCR_F16);
} else {
fpst = fpstatus_ptr(tcg_ctx, FPST_FPCR);
}
tcg_shift = tcg_const_i32(tcg_ctx, 0); tcg_shift = tcg_const_i32(tcg_ctx, 0);
tcg_rmode = tcg_const_i32(tcg_ctx, arm_rmode_to_sf(rounding)); tcg_rmode = tcg_const_i32(tcg_ctx, arm_rmode_to_sf(rounding));
gen_helper_set_rmode(tcg_ctx, tcg_rmode, tcg_rmode, fpst); gen_helper_set_rmode(tcg_ctx, tcg_rmode, tcg_rmode, fpst);
if (dp) { if (sz == 3) {
TCGv_i64 tcg_double, tcg_res; TCGv_i64 tcg_double, tcg_res;
TCGv_i32 tcg_tmp; TCGv_i32 tcg_tmp;
tcg_double = tcg_temp_new_i64(tcg_ctx); tcg_double = tcg_temp_new_i64(tcg_ctx);
@ -457,10 +465,18 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
tcg_single = tcg_temp_new_i32(tcg_ctx); tcg_single = tcg_temp_new_i32(tcg_ctx);
tcg_res = tcg_temp_new_i32(tcg_ctx); tcg_res = tcg_temp_new_i32(tcg_ctx);
neon_load_reg32(s, tcg_single, rm); neon_load_reg32(s, tcg_single, rm);
if (is_signed) { if (sz == 1) {
gen_helper_vfp_tosls(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst); if (is_signed) {
gen_helper_vfp_toslh(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst);
} else {
gen_helper_vfp_toulh(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst);
}
} else { } else {
gen_helper_vfp_touls(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst); if (is_signed) {
gen_helper_vfp_tosls(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst);
} else {
gen_helper_vfp_touls(tcg_ctx, tcg_res, tcg_single, tcg_shift, fpst);
}
} }
neon_store_reg32(s, tcg_res, rd); neon_store_reg32(s, tcg_res, rd);
tcg_temp_free_i32(tcg_ctx, tcg_res); tcg_temp_free_i32(tcg_ctx, tcg_res);

6
qemu/target/arm/vfp-uncond.decode
View file

@ -64,7 +64,9 @@ VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \
vm=%vm_dp vd=%vd_dp dp=1 vm=%vm_dp vd=%vd_dp dp=1
# VCVT float to int with specified rounding mode; Vd is always single-precision # VCVT float to int with specified rounding mode; Vd is always single-precision
VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \
vm=%vm_sp vd=%vd_sp sz=1
VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \
vm=%vm_sp vd=%vd_sp dp=0 vm=%vm_sp vd=%vd_sp sz=2
VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \
vm=%vm_dp vd=%vd_sp dp=1 vm=%vm_dp vd=%vd_sp sz=3