yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2025-01-22 19:40:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/i386: fix packusdw in-place operation

Browse source 
The SSE4.1 packusdw instruction combines source and destination
vectors of signed 32-bit integers into a single vector of unsigned
16-bit integers, with unsigned saturation. When the source and
destination are the same register, this means each 32-bit element of
that register is used twice as an input, to produce two of the 16-bit
output elements, and so if the operation is carried out
element-by-element in-place, no matter what the order in which it is
applied to the elements, the first element's operation will overwrite
some future input. The helper for packssdw avoids this issue by
computing the result in a local temporary and copying it to the
destination at the end; this patch fixes the packusdw helper to do
likewise. This fixes three gcc test failures in my GCC 6-based
testing.

Backports commit 80e19606215d4df370dfe8fe21c558a129f00f0b from qemu
This commit is contained in:
Joseph Myers 2018-03-04 23:57:53 -05:00 committed by Lioncash
parent 84b3c54b18
commit 59df0bae12
No known key found for this signature in database
GPG key ID: 4E3C3CC1031BA9C7
1 changed files with 11 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
qemu/target/i386/ops_sse.h
View file

@ -1655,14 +1655,17 @@ SSE_HELPER_Q(helper_pcmpeqq, FCMPEQQ)
void glue(helper_packusdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) void glue(helper_packusdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{ {
d->W(0) = satuw((int32_t) d->L(0)); Reg r;
d->W(1) = satuw((int32_t) d->L(1));
d->W(2) = satuw((int32_t) d->L(2)); r.W(0) = satuw((int32_t) d->L(0));
d->W(3) = satuw((int32_t) d->L(3)); r.W(1) = satuw((int32_t) d->L(1));
d->W(4) = satuw((int32_t) s->L(0)); r.W(2) = satuw((int32_t) d->L(2));
d->W(5) = satuw((int32_t) s->L(1)); r.W(3) = satuw((int32_t) d->L(3));
d->W(6) = satuw((int32_t) s->L(2)); r.W(4) = satuw((int32_t) s->L(0));
d->W(7) = satuw((int32_t) s->L(3)); r.W(5) = satuw((int32_t) s->L(1));
r.W(6) = satuw((int32_t) s->L(2));
r.W(7) = satuw((int32_t) s->L(3));
*d = r;
} }
#define FMINSB(d, s) MIN((int8_t)d, (int8_t)s) #define FMINSB(d, s) MIN((int8_t)d, (int8_t)s)