i386: Support vectorized BF16 smaxmin with AVX10.2 instructions

gcc/ChangeLog:

	* config/i386/sse.md
	(<code><mode>3): New define expand pattern for BF smaxmin.

gcc/testsuite/ChangeLog:
	* gcc.target/i386/avx10_2-512-bf-vector-smaxmin-1.c: New test.
	* gcc.target/i386/avx10_2-bf-vector-smaxmin-1.c: New test.
This commit is contained in:
Levy Hsu 2024-09-02 10:24:47 +08:00 committed by Haochen Jiang
parent 6d294fb8ac
commit 29ef601973
3 changed files with 63 additions and 0 deletions

View file

@ -31901,6 +31901,13 @@
"vscalefpbf16\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
[(set_attr "prefix" "evex")])
(define_expand "<code><mode>3"
[(set (match_operand:VBF_AVX10_2 0 "register_operand")
(smaxmin:VBF_AVX10_2
(match_operand:VBF_AVX10_2 1 "register_operand")
(match_operand:VBF_AVX10_2 2 "nonimmediate_operand")))]
"TARGET_AVX10_2_256")
(define_insn "avx10_2_<code>pbf16_<mode><mask_name>"
[(set (match_operand:VBF_AVX10_2 0 "register_operand" "=v")
(smaxmin:VBF_AVX10_2

View file

@ -0,0 +1,20 @@
/* { dg-do compile } */
/* { dg-options "-mavx10.2-512 -mprefer-vector-width=512 -Ofast" } */
/* /* { dg-final { scan-assembler-times "vmaxpbf16" 1 } } */
/* /* { dg-final { scan-assembler-times "vminpbf16" 1 } } */
void
maxpbf16_512 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 32; i++)
dest[i] = src1[i] > src2[i] ? src1[i] : src2[i];
}
void
minpbf16_512 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 32; i++)
dest[i] = src1[i] < src2[i] ? src1[i] : src2[i];
}

View file

@ -0,0 +1,36 @@
/* { dg-do compile } */
/* { dg-options "-mavx10.2 -Ofast" } */
/* /* { dg-final { scan-assembler-times "vmaxpbf16" 2 } } */
/* /* { dg-final { scan-assembler-times "vminpbf16" 2 } } */
void
maxpbf16_256 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 16; i++)
dest[i] = src1[i] > src2[i] ? src1[i] : src2[i];
}
void
minpbf16_256 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 16; i++)
dest[i] = src1[i] < src2[i] ? src1[i] : src2[i];
}
void
maxpbf16_128 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 16; i++)
dest[i] = src1[i] > src2[i] ? src1[i] : src2[i];
}
void
minpbf16_128 (__bf16* dest, __bf16* src1, __bf16* src2)
{
int i;
for (i = 0; i < 16; i++)
dest[i] = src1[i] < src2[i] ? src1[i] : src2[i];
}