motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-06 01:03:55 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Implement SVE2 signed saturating doubling multiply high

Browse source 
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-59-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:03:24 -07:00 • committed by Peter Maydell
parent b95f5eebf6
commit 169d7c5825
4 changed files with 116 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

84
target/arm/vec_helper.c
View file

@ -81,6 +81,26 @@ void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_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] = do_sqrdmlah_b(n[i], m[i], 0, false, false);
}
}
void HELPER(sve2_sqrdmulh_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] = do_sqrdmlah_b(n[i], m[i], 0, false, true);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */
int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3,
bool neg, bool round, uint32_t *sat)
@ -198,6 +218,28 @@ void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_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;
uint32_t discard;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, false, &discard);
}
}
void HELPER(sve2_sqrdmulh_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;
uint32_t discard;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, true, &discard);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
bool neg, bool round, uint32_t *sat)
@ -309,6 +351,28 @@ void HELPER(sve2_sqrdmlsh_s)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_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;
uint32_t discard;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, false, &discard);
}
}
void HELPER(sve2_sqrdmulh_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;
uint32_t discard;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, true, &discard);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */
static int64_t do_sat128_d(Int128 r)
{
@ -368,6 +432,26 @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int64_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 8; ++i) {
d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, false);
}
}
void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int64_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 8; ++i) {
d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, true);
}
}
/* Integer 8 and 16-bit dot-product.
*
* Note that for the loops herein, host endianness does not matter