On Fri, Nov 22, 2024 at 4:08 PM Haochen Jiang <haochen.ji...@intel.com> wrote:
>
> Hi all,
>
> Under FP8, we should not use AVX512F_LEN_HALF to get the mask size since
> it will get 16 instead of 8 and drop into wrong if condition. Correct
> the usage for vcvtneph2[b,h]f8[,s] runtime test.
>
> Tested under sde. Ok for trunk?
Ok.
>
> Thx,
> Haochen
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/i386/avx10_2-512-vcvtneph2bf8-2.c: Correct 128bit
> mask usage.
> * gcc.target/i386/avx10_2-512-vcvtneph2bf8s-2.c: Ditto.
> * gcc.target/i386/avx10_2-512-vcvtneph2hf8-2.c: Ditto.
> * gcc.target/i386/avx10_2-512-vcvtneph2hf8s-2.c: Ditto.
> ---
> .../i386/avx10_2-512-vcvtneph2bf8-2.c | 25 +++++++++++--------
> .../i386/avx10_2-512-vcvtneph2bf8s-2.c | 25 +++++++++++--------
> .../i386/avx10_2-512-vcvtneph2hf8-2.c | 23 ++++++++++-------
> .../i386/avx10_2-512-vcvtneph2hf8s-2.c | 23 ++++++++++-------
> 4 files changed, 58 insertions(+), 38 deletions(-)
>
> diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8-2.c
> b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8-2.c
> index d5ba911334c..96ca7e80c4d 100644
> --- a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8-2.c
> +++ b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8-2.c
> @@ -11,8 +11,8 @@
> #include "avx10-helper.h"
> #include "fp8-helper.h"
>
> -#define SIZE_SRC (AVX512F_LEN / 16)
> -#define SIZE (AVX512F_LEN_HALF / 8)
> +#define SIZE (AVX512F_LEN / 16)
> +#define SIZE_DST (AVX512F_LEN_HALF / 8)
> #include "avx512f-mask-type.h"
>
> void
> @@ -23,14 +23,14 @@ CALC (unsigned char *r, _Float16 *s)
> hf8_bf8 = 1;
> saturate = 0;
>
> - for (i = 0; i < SIZE; i++)
> + for (i = 0; i < SIZE_DST; i++)
> {
> r[i] = 0;
> - if (i < SIZE_SRC)
> + if (i < SIZE)
> {
> Float16Union usrc = {.f16 = s[i]};
> r[i] = convert_fp16_to_fp8(usrc.f16, 0, hf8_bf8, saturate);
> }
> }
> }
>
> @@ -41,17 +41,22 @@ TEST (void)
> UNION_TYPE (AVX512F_LEN_HALF, i_b) res1, res2, res3;
> UNION_TYPE (AVX512F_LEN, h) src;
> MASK_TYPE mask = MASK_VALUE;
> - unsigned char res_ref[SIZE];
> + unsigned char res_ref[SIZE_DST];
>
> sign = 1;
> - for (i = 0; i < SIZE_SRC; i++)
> + for (i = 0; i < SIZE; i++)
> {
> src.a[i] = (_Float16)(sign * (2.5 * (1 << (i % 3))));
> sign = -sign;
> }
>
> +#if AVX512F_LEN > 128
> + for (i = 0; i < SIZE_DST; i++)
> + res2.a[i] = DEFAULT_VALUE;
> +#else
> for (i = 0; i < SIZE; i++)
> res2.a[i] = DEFAULT_VALUE;
> +#endif
>
> CALC(res_ref, src.a);
>
> diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8s-2.c
> b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8s-2.c
> index 49e170aa428..c458f1ebb77 100644
> --- a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8s-2.c
> +++ b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2bf8s-2.c
> @@ -11,8 +11,8 @@
> #include "avx10-helper.h"
> #include "fp8-helper.h"
>
> -#define SIZE_SRC (AVX512F_LEN / 16)
> -#define SIZE (AVX512F_LEN_HALF / 8)
> +#define SIZE (AVX512F_LEN / 16)
> +#define SIZE_DST (AVX512F_LEN_HALF / 8)
> #include "avx512f-mask-type.h"
>
> void
> @@ -23,14 +23,14 @@ CALC (unsigned char *r, _Float16 *s)
> hf8_bf8 = 1;
> saturate = 1;
>
> - for (i = 0; i < SIZE; i++)
> + for (i = 0; i < SIZE_DST; i++)
> {
> r[i] = 0;
> - if (i < SIZE_SRC)
> + if (i < SIZE)
> {
> Float16Union usrc = {.f16 = s[i]};
> r[i] = convert_fp16_to_fp8(usrc.f16, 0, hf8_bf8, saturate);
> }
> }
> }
>
> @@ -41,17 +41,22 @@ TEST (void)
> UNION_TYPE (AVX512F_LEN_HALF, i_b) res1, res2, res3;
> UNION_TYPE (AVX512F_LEN, h) src;
> MASK_TYPE mask = MASK_VALUE;
> - unsigned char res_ref[SIZE];
> + unsigned char res_ref[SIZE_DST];
>
> sign = 1;
> - for (i = 0; i < SIZE_SRC; i++)
> + for (i = 0; i < SIZE; i++)
> {
> src.a[i] = (_Float16)(sign * (2.5 * (1 << (i % 3))));
> sign = -sign;
> }
>
> +#if AVX512F_LEN > 128
> + for (i = 0; i < SIZE_DST; i++)
> + res2.a[i] = DEFAULT_VALUE;
> +#else
> for (i = 0; i < SIZE; i++)
> res2.a[i] = DEFAULT_VALUE;
> +#endif
>
> CALC(res_ref, src.a);
>
> diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8-2.c
> b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8-2.c
> index f481b72cc71..cb9cdbb89c1 100644
> --- a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8-2.c
> +++ b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8-2.c
> @@ -11,8 +11,8 @@
> #include "avx10-helper.h"
> #include "fp8-helper.h"
>
> -#define SIZE_SRC (AVX512F_LEN / 16)
> -#define SIZE (AVX512F_LEN_HALF / 8)
> +#define SIZE (AVX512F_LEN / 16)
> +#define SIZE_DST (AVX512F_LEN_HALF / 8)
> #include "avx512f-mask-type.h"
>
> void
> @@ -23,14 +23,14 @@ CALC (unsigned char *r, _Float16 *s)
> hf8_bf8 = 0;
> saturate = 0;
>
> - for (i = 0; i < SIZE; i++)
> + for (i = 0; i < SIZE_DST; i++)
> {
> r[i] = 0;
> - if (i < SIZE_SRC)
> + if (i < SIZE)
> {
> Float16Union usrc = {.f16 = s[i]};
> r[i] = convert_fp16_to_fp8(usrc.f16, 0, hf8_bf8, saturate);
> }
> }
> }
>
> @@ -44,14 +44,19 @@ TEST (void)
> unsigned char res_ref[SIZE];
>
> sign = 1;
> - for (i = 0; i < SIZE_SRC; i++)
> + for (i = 0; i < SIZE; i++)
> {
> src.a[i] = (_Float16)(sign * (2.5 * (1 << (i % 3))));
> sign = -sign;
> }
>
> +#if AVX512F_LEN > 128
> + for (i = 0; i < SIZE_DST; i++)
> + res2.a[i] = DEFAULT_VALUE;
> +#else
> for (i = 0; i < SIZE; i++)
> res2.a[i] = DEFAULT_VALUE;
> +#endif
>
> CALC(res_ref, src.a);
>
> diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8s-2.c
> b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8s-2.c
> index 4782b038f3b..4827af4df53 100644
> --- a/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8s-2.c
> +++ b/gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtneph2hf8s-2.c
> @@ -11,8 +11,8 @@
> #include "avx10-helper.h"
> #include "fp8-helper.h"
>
> -#define SIZE_SRC (AVX512F_LEN / 16)
> -#define SIZE (AVX512F_LEN_HALF / 8)
> +#define SIZE (AVX512F_LEN / 16)
> +#define SIZE_DST (AVX512F_LEN_HALF / 8)
> #include "avx512f-mask-type.h"
>
> void
> @@ -23,14 +23,14 @@ CALC (unsigned char *r, _Float16 *s)
> hf8_bf8 = 0;
> saturate = 1;
>
> - for (i = 0; i < SIZE; i++)
> + for (i = 0; i < SIZE_DST; i++)
> {
> r[i] = 0;
> - if (i < SIZE_SRC)
> + if (i < SIZE)
> {
> Float16Union usrc = {.f16 = s[i]};
> r[i] = convert_fp16_to_fp8(usrc.f16, 0, hf8_bf8, saturate);
> }
> }
> }
>
> @@ -44,14 +44,19 @@ TEST (void)
> unsigned char res_ref[SIZE];
>
> sign = 1;
> - for (i = 0; i < SIZE_SRC; i++)
> + for (i = 0; i < SIZE; i++)
> {
> src.a[i] = (_Float16)(sign * (2.5 * (1 << (i % 3))));
> sign = -sign;
> }
>
> +#if AVX512F_LEN > 128
> + for (i = 0; i < SIZE_DST; i++)
> + res2.a[i] = DEFAULT_VALUE;
> +#else
> for (i = 0; i < SIZE; i++)
> res2.a[i] = DEFAULT_VALUE;
> +#endif
>
> CALC(res_ref, src.a);
>
> --
> 2.31.1
>
--
BR,
Hongtao
