On Sat, 25 May 2024 at 00:27, Richard Henderson
<richard.hender...@linaro.org> wrote:
>
> These are the last instructions within disas_simd_three_reg_same
> and disas_simd_scalar_three_reg_same, so remove them.
>
> Signed-off-by: Richard Henderson <richard.hender...@linaro.org>
> diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
> index d8e96386be..b05922b425 100644
> --- a/target/arm/tcg/vec_helper.c
> +++ b/target/arm/tcg/vec_helper.c
> @@ -311,6 +311,38 @@ void HELPER(neon_sqrdmulh_h)(void *vd, void *vn, void
> *vm,
> clear_tail(d, opr_sz, simd_maxsz(desc));
> }
>
> +void HELPER(neon_sqdmulh_idx_h)(void *vd, void *vn, void *vm,
> + void *vq, uint32_t desc)
> +{
> + intptr_t i, j, opr_sz = simd_oprsz(desc);
> + int idx = simd_data(desc);
> + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
> +
> + for (i = 0; i < opr_sz / 2; i += 16 / 2) {
> + int16_t mm = m[i];
> + for (j = 0; j < 16 / 2; ++j) {
> + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, vq);
> + }
> + }
> + clear_tail(d, opr_sz, simd_maxsz(desc));
> +}
> +
> +void HELPER(neon_sqrdmulh_idx_h)(void *vd, void *vn, void *vm,
> + void *vq, uint32_t desc)
> +{
> + intptr_t i, j, opr_sz = simd_oprsz(desc);
> + int idx = simd_data(desc);
> + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
> +
> + for (i = 0; i < opr_sz / 2; i += 16 / 2) {
> + int16_t mm = m[i];
> + for (j = 0; j < 16 / 2; ++j) {
> + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, vq);
> + }
> + }
> + clear_tail(d, opr_sz, simd_maxsz(desc));
> +}
> +
> void HELPER(sve2_sqrdmlah_h)(void *vd, void *vn, void *vm,
> void *va, uint32_t desc)
> {
> @@ -474,6 +506,38 @@ void HELPER(neon_sqrdmulh_s)(void *vd, void *vn, void
> *vm,
> clear_tail(d, opr_sz, simd_maxsz(desc));
> }
>
> +void HELPER(neon_sqdmulh_idx_s)(void *vd, void *vn, void *vm,
> + void *vq, uint32_t desc)
> +{
> + intptr_t i, j, opr_sz = simd_oprsz(desc);
> + int idx = simd_data(desc);
> + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
> +
> + for (i = 0; i < opr_sz / 4; i += 16 / 4) {
> + int32_t mm = m[i];
> + for (j = 0; j < 16 / 4; ++j) {
> + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, vq);
> + }
> + }
> + clear_tail(d, opr_sz, simd_maxsz(desc));
> +}
> +
> +void HELPER(neon_sqrdmulh_idx_s)(void *vd, void *vn, void *vm,
> + void *vq, uint32_t desc)
> +{
> + intptr_t i, j, opr_sz = simd_oprsz(desc);
> + int idx = simd_data(desc);
> + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
> +
> + for (i = 0; i < opr_sz / 4; i += 16 / 4) {
> + int32_t mm = m[i];
> + for (j = 0; j < 16 / 4; ++j) {
> + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, vq);
> + }
> + }
> + clear_tail(d, opr_sz, simd_maxsz(desc));
> +}
Missing H macros in these helpers ?
thanks
-- PMM
