[Bug target/95488] Suboptimal multiplication codegen for v16qi

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95488

--- Comment #9 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to H.J. Lu from comment #8)
>  -march=skylake-avx512 gave:
> 
> [hjl@gnu-cfl-2 gcc]$
> /export/build/gnu/tools-build/gcc-debug/build-x86_64-linux/gcc/xgcc
> -B/export/build/gnu/tools-build/gcc-debug/build-x86_64-linux/gcc/
> /export/gnu/import/git/sources/gcc/gcc/testsuite/gcc.target/i386/avx512bw-
> pr95488-1.c  -march=skylake-avx512   -fno-diagnostics-show-caret
> -fno-diagnostics-show-line-numbers -fdiagnostics-color=never 
> -fdiagnostics-urls=never  -O2  -ffat-lto-objects -fno-ident -S -o
> avx512bw-pr95488-1.s
> [hjl@gnu-cfl-2 gcc]$ cat avx512bw-pr95488-1.s
> 	.file	"avx512bw-pr95488-1.c"
> 	.text
> 	.p2align 4
> 	.globl	mul_512
> 	.type	mul_512, @function
> mul_512:
> .LFB0:
> 	.cfi_startproc
> 	vpunpcklbw	%ymm0, %ymm0, %ymm3
> 	vpunpcklbw	%ymm1, %ymm1, %ymm2
> 	vpunpckhbw	%ymm0, %ymm0, %ymm0
> 	vpunpckhbw	%ymm1, %ymm1, %ymm1
> 	vpmullw	%ymm3, %ymm2, %ymm2
> 	vpmullw	%ymm0, %ymm1, %ymm1
> 	vpshufb	.LC0(%rip), %ymm2, %ymm0
> 	vpshufb	.LC1(%rip), %ymm1, %ymm1
> 	vpor	%ymm1, %ymm0, %ymm0
> 	ret
> 	.cfi_endproc
> .LFE0:
> 	.size	mul_512, .-mul_512
> 	.p2align 4
> 	.globl	umul_512
> 	.type	umul_512, @function
> umul_512:
> .LFB1:
> 	.cfi_startproc
> 	vpunpcklbw	%ymm0, %ymm0, %ymm3
> 	vpunpcklbw	%ymm1, %ymm1, %ymm2
> 	vpunpckhbw	%ymm0, %ymm0, %ymm0
> 	vpunpckhbw	%ymm1, %ymm1, %ymm1
> 	vpmullw	%ymm3, %ymm2, %ymm2
> 	vpmullw	%ymm0, %ymm1, %ymm1
> 	vpshufb	.LC0(%rip), %ymm2, %ymm0
> 	vpshufb	.LC1(%rip), %ymm1, %ymm1
> 	vpor	%ymm1, %ymm0, %ymm0
> 	ret
> 	.cfi_endproc
> .LFE1:
> 	.size	umul_512, .-umul_512

It's on purpose, maybe I'll add -mprefer-vector-with=512 to testcase.
----
19498  /* Not generate zmm instruction when prefer 128/256 bit vector width. 
*/
19499  if (qimode == V32QImode 
19500      && (TARGET_PREFER_AVX128 || TARGET_PREFER_AVX256))
19501    return false;
----