motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-04 16:23:55 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Implement bfloat16 dot product (indexed)

Browse source 
This is BFDOT for both AArch64 AdvSIMD and SVE,
and VDOT.BF16 for AArch32 NEON.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-8-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-25 15:58:12 -07:00 • committed by Peter Maydell
parent cb8657f7f9
commit 839144784b
7 changed files with 80 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

20
target/arm/vec_helper.c
View file

@ -2452,3 +2452,23 @@ void HELPER(gvec_bfdot)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
void *va, uint32_t desc)
{
intptr_t i, j, opr_sz = simd_oprsz(desc);
intptr_t index = simd_data(desc);
intptr_t elements = opr_sz / 4;
intptr_t eltspersegment = MIN(16 / 4, elements);
float32 *d = vd, *a = va;
uint32_t *n = vn, *m = vm;
for (i = 0; i < elements; i += eltspersegment) {
uint32_t m_idx = m[i + H4(index)];
for (j = i; j < i + eltspersegment; j++) {
d[j] = bfdotadd(a[j], n[j], m_idx);
}
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}