motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-07 17:53:56 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Handle FPCR.AH in SVE FMLSL (indexed)

Browse source 
Handle FPCR.AH's requirement to not negate the sign of a NaN in SVE
FMLSL (indexed), using the usual trick of negating by XOR when AH=0
and by muladd flags when AH=1.

Since we have the CPUARMState* in the helper anyway, we can
look directly at env->vfp.fpcr and don't need toa pass in the
FPCR.AH value via the SIMD data word.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250129013857.135256-32-richard.henderson@linaro.org
[PMM: commit message tweaked]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2025-02-01 16:39:53 +00:00 • committed by Peter Maydell
parent 0fa4b7afd4
commit f67a16e7d7
1 changed files with 12 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

15
target/arm/tcg/vec_helper.c
View file

@ -2250,23 +2250,32 @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va,
CPUARMState *env, uint32_t desc)
{
intptr_t i, j, oprsz = simd_oprsz(desc);
uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15;
bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16);
float_status *status = &env->vfp.fp_status_a64;
bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a64);
int negx = 0, negf = 0;
if (is_s) {
if (env->vfp.fpcr & FPCR_AH) {
negf = float_muladd_negate_product;
} else {
negx = 0x8000;
}
}
for (i = 0; i < oprsz; i += 16) {
float16 mm_16 = *(float16 *)(vm + i + idx);
float32 mm = float16_to_float32_by_bits(mm_16, fz16);
for (j = 0; j < 16; j += sizeof(float32)) {
float16 nn_16 = *(float16 *)(vn + H1_2(i + j + sel)) ^ negn;
float16 nn_16 = *(float16 *)(vn + H1_2(i + j + sel)) ^ negx;
float32 nn = float16_to_float32_by_bits(nn_16, fz16);
float32 aa = *(float32 *)(va + H1_4(i + j));
*(float32 *)(vd + H1_4(i + j)) =
float32_muladd(nn, mm, aa, 0, status);
float32_muladd(nn, mm, aa, negf, status);
}
}
}