motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-07-29 05:13:54 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Implement SVE2 Integer Multiply - Unpredicated

Browse source 
For MUL, we can rely on generic support.  For SMULH and UMULH,
create some trivial helpers.  For PMUL, back in a21bb78e58,
we organized helper_gvec_pmul_b in preparation for this use.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:02:28 -07:00 • committed by Peter Maydell
parent 2dc10fa2f9
commit 5dad1ba52f
4 changed files with 166 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

96
target/arm/vec_helper.c
View file

@ -1985,3 +1985,99 @@ void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc)
clear_tail(vd, oprsz, simd_maxsz(desc));
}
#endif
/*
* NxN -> N highpart multiply
*
* TODO: expose this as a generic vector operation.
*/
void HELPER(gvec_smulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int8_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz; ++i) {
d[i] = ((int32_t)n[i] * m[i]) >> 8;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_smulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int16_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = ((int32_t)n[i] * m[i]) >> 16;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_smulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int32_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = ((int64_t)n[i] * m[i]) >> 32;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_smulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
uint64_t *d = vd, *n = vn, *m = vm;
uint64_t discard;
for (i = 0; i < opr_sz / 8; ++i) {
muls64(&discard, &d[i], n[i], m[i]);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_umulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
uint8_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz; ++i) {
d[i] = ((uint32_t)n[i] * m[i]) >> 8;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_umulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
uint16_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = ((uint32_t)n[i] * m[i]) >> 16;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_umulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
uint32_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = ((uint64_t)n[i] * m[i]) >> 32;
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
uint64_t *d = vd, *n = vn, *m = vm;
uint64_t discard;
for (i = 0; i < opr_sz / 8; ++i) {
mulu64(&discard, &d[i], n[i], m[i]);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}