Fix avx512ne2ps2bf16 wrong code [PR 111127]
Checks
Commit Message
Hi,
For PR111127, the wrong code was caused by wrong expander for maskz.
correct the parameter order for avx512ne2ps2bf16_maskz expander
Bootstrapped/regtested on x86-64-pc-linux-gnu{m32,}.
OK for master and backport to GCC13?
gcc/ChangeLog:
PR target/111127
* config/i386/sse.md (avx512f_cvtne2ps2bf16_<mode>_maskz):
Adjust paramter order.
gcc/testsuite/ChangeLog:
PR target/111127
* gcc.target/i386/pr111127.c: New test.
---
gcc/config/i386/sse.md | 4 ++--
gcc/testsuite/gcc.target/i386/pr111127.c | 24 ++++++++++++++++++++++++
2 files changed, 26 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr111127.c
Comments
On Thu, Aug 24, 2023 at 5:05 PM Hongyu Wang via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Hi,
>
> For PR111127, the wrong code was caused by wrong expander for maskz.
> correct the parameter order for avx512ne2ps2bf16_maskz expander
>
> Bootstrapped/regtested on x86-64-pc-linux-gnu{m32,}.
> OK for master and backport to GCC13?
Ok.
>
> gcc/ChangeLog:
>
> PR target/111127
> * config/i386/sse.md (avx512f_cvtne2ps2bf16_<mode>_maskz):
> Adjust paramter order.
>
> gcc/testsuite/ChangeLog:
>
> PR target/111127
> * gcc.target/i386/pr111127.c: New test.
> ---
> gcc/config/i386/sse.md | 4 ++--
> gcc/testsuite/gcc.target/i386/pr111127.c | 24 ++++++++++++++++++++++++
> 2 files changed, 26 insertions(+), 2 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr111127.c
>
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index da85223a9b4..194dab9a9d0 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -30006,8 +30006,8 @@ (define_expand "avx512f_cvtne2ps2bf16_<mode>_maskz"
> (match_operand:<avx512fmaskmode> 3 "register_operand")]
> "TARGET_AVX512BF16"
> {
> - emit_insn (gen_avx512f_cvtne2ps2bf16_<mode>_mask(operands[0], operands[2],
> - operands[1], CONST0_RTX(<MODE>mode), operands[3]));
> + emit_insn (gen_avx512f_cvtne2ps2bf16_<mode>_mask(operands[0], operands[1],
> + operands[2], CONST0_RTX(<MODE>mode), operands[3]));
> DONE;
> })
>
> diff --git a/gcc/testsuite/gcc.target/i386/pr111127.c b/gcc/testsuite/gcc.target/i386/pr111127.c
> new file mode 100644
> index 00000000000..c124bc18bc4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr111127.c
> @@ -0,0 +1,24 @@
> +/* PR target/111127 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mavx512bf16 -mavx512vl" } */
> +/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%zmm1, %zmm0, %zmm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
> +/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%ymm1, %ymm0, %ymm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
> +/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%xmm1, %xmm0, %xmm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
> +
> +#include <immintrin.h>
> +
> +__m512bh cvttest(__mmask32 k, __m512 a, __m512 b)
> +{
> + return _mm512_maskz_cvtne2ps_pbh (k,a,b);
> +}
> +
> +__m256bh cvttest2(__mmask16 k, __m256 a, __m256 b)
> +{
> + return _mm256_maskz_cvtne2ps_pbh (k,a,b);
> +}
> +
> +__m128bh cvttest3(__mmask8 k, __m128 a, __m128 b)
> +{
> + return _mm_maskz_cvtne2ps_pbh (k,a,b);
> +}
> +
> --
> 2.31.1
>
@@ -30006,8 +30006,8 @@ (define_expand "avx512f_cvtne2ps2bf16_<mode>_maskz"
(match_operand:<avx512fmaskmode> 3 "register_operand")]
"TARGET_AVX512BF16"
{
- emit_insn (gen_avx512f_cvtne2ps2bf16_<mode>_mask(operands[0], operands[2],
- operands[1], CONST0_RTX(<MODE>mode), operands[3]));
+ emit_insn (gen_avx512f_cvtne2ps2bf16_<mode>_mask(operands[0], operands[1],
+ operands[2], CONST0_RTX(<MODE>mode), operands[3]));
DONE;
})
new file mode 100644
@@ -0,0 +1,24 @@
+/* PR target/111127 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512bf16 -mavx512vl" } */
+/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%zmm1, %zmm0, %zmm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%ymm1, %ymm0, %ymm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtne2ps2bf16\[ \\t\]+\[^\{\n\]*%xmm1, %xmm0, %xmm0\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+
+#include <immintrin.h>
+
+__m512bh cvttest(__mmask32 k, __m512 a, __m512 b)
+{
+ return _mm512_maskz_cvtne2ps_pbh (k,a,b);
+}
+
+__m256bh cvttest2(__mmask16 k, __m256 a, __m256 b)
+{
+ return _mm256_maskz_cvtne2ps_pbh (k,a,b);
+}
+
+__m128bh cvttest3(__mmask8 k, __m128 a, __m128 b)
+{
+ return _mm_maskz_cvtne2ps_pbh (k,a,b);
+}
+