diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2021-09-01 09:02:36 +0100 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-09-01 11:08:16 +0100 |
| commit | abfe39b263595a47f42219aa3a3fc63804a12a35 (patch) | |
| tree | 9515d6eda16b3832c87489a354b3cbdbc30b763b /target/arm/mve_helper.c | |
| parent | 90257a4f35efef15380f45339fecc348e762acc6 (diff) | |
target/arm: Implement MVE scalar fp insns
Implement the MVE scalar floating point insns VADD, VSUB and VMUL.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'target/arm/mve_helper.c')
| -rw-r--r-- | target/arm/mve_helper.c | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index a6ad894414..b49975fdc0 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -3040,3 +3040,38 @@ DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH) DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS) DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH) DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) + +#define DO_2OP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_SCALAR_ALL(OP, FN) \ + DO_2OP_FP_SCALAR(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP_SCALAR(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add) +DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub) +DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul) |