riscv
/
qemu
mirror of https://gitea.goldendeliverer.com/riscv/qemu.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

target/arm: Convert VCMLA, VCADD size field to MO_* in decode 

The VCMLA and VCADD insns have a size field which is 0 for fp16
and 1 for fp32 (note that this is the reverse of the Neon 3-same
encoding!). Convert it to MO_* values in decode for consistency.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200903133209.5141-4-peter.maydell@linaro.org
pull/99/head
Peter Maydell 6 years ago
parent
0ae715c658
commit
d186a4854c
2 changed files with 24 additions and 16 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 18
      target/arm/neon-shared.decode
  2. 22
      target/arm/translate-neon.c.inc

18
target/arm/neon-shared.decode
View File

@ -34,11 +34,17 @@
%vd_dp 22:1 12:4
%vd_sp 12:4 22:1
VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp
# For VCMLA/VCADD insns, convert the single-bit size field
# which is 0 for fp16 and 1 for fp32 into a MO_* constant.
# (Note that this is the reverse of the sense of the 1-bit size
# field in the 3same_fp Neon insns.)
%vcadd_size 20:1 !function=plus1
VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp
VCMLA 1111 110 rot:2 . 1 . .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size
VCADD 1111 110 rot:1 1 . 0 . .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size
# VUDOT and VSDOT
VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \
@ -51,9 +57,9 @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1
VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
vn=%vn_dp vd=%vd_dp size=0
vn=%vn_dp vd=%vd_dp size=1
VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=2 index=0
VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \
vm=%vm_dp vn=%vn_dp vd=%vd_dp

22
target/arm/translate-neon.c.inc
View File

@ -168,7 +168,7 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
gen_helper_gvec_3_ptr *fn_gvec_ptr;
if (!dc_isar_feature(aa32_vcma, s)
|| (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) {
|| (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) {
return false;
}
@ -187,8 +187,9 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
}
opr_sz = (1 + a->q) * 8;
fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD);
fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah;
fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
fn_gvec_ptr = (a->size == MO_16) ?
gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas;
tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
vfp_reg_offset(1, a->vn),
vfp_reg_offset(1, a->vm),
@ -205,7 +206,7 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
gen_helper_gvec_3_ptr *fn_gvec_ptr;
if (!dc_isar_feature(aa32_vcma, s)
|| (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) {
|| (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) {
return false;
}
@ -224,8 +225,9 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
}
opr_sz = (1 + a->q) * 8;
fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD);
fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh;
fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
fn_gvec_ptr = (a->size == MO_16) ?
gen_helper_gvec_fcaddh : gen_helper_gvec_fcadds;
tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
vfp_reg_offset(1, a->vn),
vfp_reg_offset(1, a->vm),
@ -307,7 +309,7 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
if (!dc_isar_feature(aa32_vcma, s)) {
return false;
}
if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) {
if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) {
return false;
}
@ -325,10 +327,10 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
return true;
}
fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx
: gen_helper_gvec_fcmlah_idx);
fn_gvec_ptr = (a->size == MO_16) ?
gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx;
opr_sz = (1 + a->q) * 8;
fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD);
fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
vfp_reg_offset(1, a->vn),
vfp_reg_offset(1, a->vm),

Write Preview
Loading…
Cancel
Save