diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2021-05-25 15:58:12 -0700 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-06-03 16:43:26 +0100 |
| commit | 839144784b613998edf7a7277ed2ed2015b0b4d7 (patch) | |
| tree | 88bf3487c95aaf2b1add57c80d1954e008796050 /target/arm/vec_helper.c | |
| parent | cb8657f7f9fcc2ebe8dfb1cbc9e572670d2af568 (diff) | |
| download | qemu-839144784b613998edf7a7277ed2ed2015b0b4d7.zip qemu-839144784b613998edf7a7277ed2ed2015b0b4d7.tar.gz qemu-839144784b613998edf7a7277ed2ed2015b0b4d7.tar.bz2 | |
target/arm: Implement bfloat16 dot product (indexed)
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>
Diffstat (limited to 'target/arm/vec_helper.c')
| -rw-r--r-- | target/arm/vec_helper.c | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 7eefcd0..74a497f 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -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)); +} |