2015-11-25 06:09:31 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
|
2016-03-26 17:35:48 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW
|
2008-05-24 01:49:40 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <16 x i8> @mul_v16i8c(<16 x i8> %i) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v16i8c:
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: pmullw %xmm1, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm3, %xmm2
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm1, %xmm0
|
|
|
|
; SSE2-NEXT: pand %xmm3, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-LABEL: mul_v16i8c:
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm1
|
2016-10-25 22:29:25 +08:00
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [117,117,117,117,117,117,117,117]
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm1
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm3, %xmm1
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: pand %xmm3, %xmm0
|
|
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm1
|
|
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: retq
|
2015-11-25 06:09:31 +08:00
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX2-LABEL: mul_v16i8c:
|
2015-11-25 06:09:31 +08:00
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
|
2015-11-25 06:09:31 +08:00
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
|
|
; AVX2-NEXT: vzeroupper
|
|
|
|
; AVX2-NEXT: retq
|
2016-03-26 17:35:48 +08:00
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v16i8c:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512F-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v16i8c:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %xmm0, %ymm0
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512BW-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
2016-07-09 08:19:07 +08:00
|
|
|
; AVX512BW-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512BW-NEXT: retq
|
2015-04-27 15:55:46 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <16 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
|
|
|
|
ret <16 x i8> %A
|
|
|
|
}
|
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <8 x i16> @mul_v8i16c(<8 x i16> %i) nounwind {
|
|
|
|
; SSE-LABEL: mul_v8i16c:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm0
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v8i16c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2015-04-27 15:55:46 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <8 x i16> %i, < i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117 >
|
|
|
|
ret <8 x i16> %A
|
|
|
|
}
|
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <4 x i32> @mul_v4i32c(<4 x i32> %i) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v4i32c:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [117,117,117,117]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
2015-02-16 20:28:18 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm2
|
2015-02-16 20:28:18 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-LABEL: mul_v4i32c:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmulld {{.*}}(%rip), %xmm0
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE41-NEXT: retq
|
2015-11-25 06:09:31 +08:00
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v4i32c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpbroadcastd {{.*}}(%rip), %xmm1
|
|
|
|
; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <4 x i32> %i, < i32 117, i32 117, i32 117, i32 117 >
|
|
|
|
ret <4 x i32> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <2 x i64> @mul_v2i64c(<2 x i64> %i) nounwind {
|
|
|
|
; SSE-LABEL: mul_v2i64c:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [117,117]
|
|
|
|
; SSE-NEXT: movdqa %xmm0, %xmm2
|
|
|
|
; SSE-NEXT: pmuludq %xmm1, %xmm2
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE-NEXT: pmuludq %xmm1, %xmm0
|
|
|
|
; SSE-NEXT: psllq $32, %xmm0
|
|
|
|
; SSE-NEXT: paddq %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v2i64c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [117,117]
|
|
|
|
; AVX-NEXT: vpmuludq %xmm1, %xmm0, %xmm2
|
|
|
|
; AVX-NEXT: vpsrlq $32, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: vpsllq $32, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: vpaddq %xmm0, %xmm2, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <2 x i64> %i, < i64 117, i64 117 >
|
|
|
|
ret <2 x i64> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <16 x i8> @mul_v16i8(<16 x i8> %i, <16 x i8> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v16i8:
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2: # BB#0: # %entry
|
2015-04-30 16:23:16 +08:00
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
2015-04-30 16:23:16 +08:00
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
2015-04-30 16:23:16 +08:00
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm1, %xmm0
|
2015-04-30 16:23:16 +08:00
|
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm3, %xmm0
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-LABEL: mul_v16i8:
|
2015-04-27 15:55:46 +08:00
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm3
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: pmullw %xmm3, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm3, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm1
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: pand %xmm3, %xmm0
|
|
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: retq
|
2015-11-25 06:09:31 +08:00
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX2-LABEL: mul_v16i8:
|
2015-11-25 06:09:31 +08:00
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
|
|
; AVX2-NEXT: vzeroupper
|
|
|
|
; AVX2-NEXT: retq
|
2016-03-26 17:35:48 +08:00
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v16i8:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v16i8:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
2016-07-09 08:19:07 +08:00
|
|
|
; AVX512BW-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512BW-NEXT: retq
|
2015-04-27 15:55:46 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <16 x i8> %i, %j
|
|
|
|
ret <16 x i8> %A
|
|
|
|
}
|
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <8 x i16> @mul_v8i16(<8 x i16> %i, <8 x i16> %j) nounwind {
|
|
|
|
; SSE-LABEL: mul_v8i16:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: pmullw %xmm1, %xmm0
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v8i16:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmullw %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2015-04-27 15:55:46 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <8 x i16> %i, %j
|
|
|
|
ret <8 x i16> %A
|
|
|
|
}
|
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <4 x i32> @mul_v4i32(<4 x i32> %i, <4 x i32> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v4i32:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
2015-02-16 20:28:18 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
2015-02-16 20:28:18 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-LABEL: mul_v4i32:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmulld %xmm1, %xmm0
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE41-NEXT: retq
|
2015-11-25 06:09:31 +08:00
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v4i32:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <4 x i32> %i, %j
|
|
|
|
ret <4 x i32> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <2 x i64> @mul_v2i64(<2 x i64> %i, <2 x i64> %j) nounwind {
|
|
|
|
; SSE-LABEL: mul_v2i64:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: movdqa %xmm0, %xmm2
|
|
|
|
; SSE-NEXT: pmuludq %xmm1, %xmm2
|
|
|
|
; SSE-NEXT: movdqa %xmm1, %xmm3
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm3
|
|
|
|
; SSE-NEXT: pmuludq %xmm0, %xmm3
|
|
|
|
; SSE-NEXT: psllq $32, %xmm3
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE-NEXT: pmuludq %xmm1, %xmm0
|
|
|
|
; SSE-NEXT: psllq $32, %xmm0
|
2016-07-18 14:14:54 +08:00
|
|
|
; SSE-NEXT: paddq %xmm3, %xmm0
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE-NEXT: paddq %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v2i64:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmuludq %xmm1, %xmm0, %xmm2
|
|
|
|
; AVX-NEXT: vpsrlq $32, %xmm1, %xmm3
|
|
|
|
; AVX-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
|
|
|
|
; AVX-NEXT: vpsllq $32, %xmm3, %xmm3
|
|
|
|
; AVX-NEXT: vpsrlq $32, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: vpsllq $32, %xmm0, %xmm0
|
2016-07-18 14:14:54 +08:00
|
|
|
; AVX-NEXT: vpaddq %xmm0, %xmm3, %xmm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-NEXT: vpaddq %xmm0, %xmm2, %xmm0
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <2 x i64> %i, %j
|
|
|
|
ret <2 x i64> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2008-05-24 01:49:40 +08:00
|
|
|
declare void @foo()
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <4 x i32> @mul_v4i32spill(<4 x i32> %i, <4 x i32> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v4i32spill:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: subq $40, %rsp
|
|
|
|
; SSE2-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
|
|
|
|
; SSE2-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
|
|
|
; SSE2-NEXT: callq foo
|
|
|
|
; SSE2-NEXT: movdqa (%rsp), %xmm0 # 16-byte Reload
|
2015-02-16 20:28:18 +08:00
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
|
|
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 # 16-byte Reload
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm2
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE2-NEXT: addq $40, %rsp
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-LABEL: mul_v4i32spill:
|
2015-02-16 20:23:22 +08:00
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: subq $40, %rsp
|
|
|
|
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
|
|
|
|
; SSE41-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
|
|
|
; SSE41-NEXT: callq foo
|
|
|
|
; SSE41-NEXT: movdqa (%rsp), %xmm0 # 16-byte Reload
|
|
|
|
; SSE41-NEXT: pmulld {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
|
|
|
|
; SSE41-NEXT: addq $40, %rsp
|
2014-07-26 09:11:10 +08:00
|
|
|
; SSE41-NEXT: retq
|
2015-11-25 06:09:31 +08:00
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v4i32spill:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: subq $40, %rsp
|
|
|
|
; AVX-NEXT: vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
|
|
|
|
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
|
|
|
|
; AVX-NEXT: callq foo
|
|
|
|
; AVX-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
|
|
|
|
; AVX-NEXT: vpmulld {{[0-9]+}}(%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
|
|
; AVX-NEXT: addq $40, %rsp
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
; Use a call to force spills.
|
|
|
|
call void @foo()
|
|
|
|
%A = mul <4 x i32> %i, %j
|
|
|
|
ret <4 x i32> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2014-07-26 07:59:20 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <2 x i64> @mul_v2i64spill(<2 x i64> %i, <2 x i64> %j) nounwind {
|
|
|
|
; SSE-LABEL: mul_v2i64spill:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: subq $40, %rsp
|
|
|
|
; SSE-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
|
|
|
|
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
|
|
|
; SSE-NEXT: callq foo
|
|
|
|
; SSE-NEXT: movdqa (%rsp), %xmm0 # 16-byte Reload
|
|
|
|
; SSE-NEXT: movdqa %xmm0, %xmm2
|
|
|
|
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 # 16-byte Reload
|
|
|
|
; SSE-NEXT: pmuludq %xmm3, %xmm2
|
|
|
|
; SSE-NEXT: movdqa %xmm3, %xmm1
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE-NEXT: pmuludq %xmm0, %xmm1
|
|
|
|
; SSE-NEXT: psllq $32, %xmm1
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE-NEXT: pmuludq %xmm3, %xmm0
|
|
|
|
; SSE-NEXT: psllq $32, %xmm0
|
2016-07-18 14:14:54 +08:00
|
|
|
; SSE-NEXT: paddq %xmm1, %xmm0
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE-NEXT: paddq %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: addq $40, %rsp
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-09-05 14:43:06 +08:00
|
|
|
; AVX-LABEL: mul_v2i64spill:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: subq $40, %rsp
|
|
|
|
; AVX-NEXT: vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
|
|
|
|
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
|
|
|
|
; AVX-NEXT: callq foo
|
|
|
|
; AVX-NEXT: vmovdqa {{[0-9]+}}(%rsp), %xmm2 # 16-byte Reload
|
|
|
|
; AVX-NEXT: vmovdqa (%rsp), %xmm4 # 16-byte Reload
|
|
|
|
; AVX-NEXT: vpmuludq %xmm2, %xmm4, %xmm0
|
|
|
|
; AVX-NEXT: vpsrlq $32, %xmm2, %xmm1
|
|
|
|
; AVX-NEXT: vmovdqa %xmm2, %xmm3
|
|
|
|
; AVX-NEXT: vpmuludq %xmm1, %xmm4, %xmm1
|
|
|
|
; AVX-NEXT: vpsllq $32, %xmm1, %xmm1
|
|
|
|
; AVX-NEXT: vpsrlq $32, %xmm4, %xmm2
|
|
|
|
; AVX-NEXT: vpmuludq %xmm3, %xmm2, %xmm2
|
|
|
|
; AVX-NEXT: vpsllq $32, %xmm2, %xmm2
|
|
|
|
; AVX-NEXT: vpaddq %xmm2, %xmm1, %xmm1
|
|
|
|
; AVX-NEXT: vpaddq %xmm1, %xmm0, %xmm0
|
|
|
|
; AVX-NEXT: addq $40, %rsp
|
|
|
|
; AVX-NEXT: retq
|
2014-07-26 07:59:20 +08:00
|
|
|
entry:
|
|
|
|
; Use a call to force spills.
|
|
|
|
call void @foo()
|
|
|
|
%A = mul <2 x i64> %i, %j
|
|
|
|
ret <2 x i64> %A
|
2008-05-24 01:49:40 +08:00
|
|
|
}
|
2015-06-16 14:07:24 +08:00
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <32 x i8> @mul_v32i8c(<32 x i8> %i) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v32i8c:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm3
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm3, %xmm0
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm3
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm3
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm1
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: packuswb %xmm3, %xmm1
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v32i8c:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm2
|
2016-10-25 22:29:25 +08:00
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [117,117,117,117,117,117,117,117]
|
2016-03-26 17:35:48 +08:00
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm0
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm0
|
|
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm3
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm3
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm3
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm0
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm0
|
|
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm3
|
|
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm1
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v32i8c:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm1, %ymm1
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm3, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v32i8c:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm1
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm1, %zmm1
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v32i8c:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
2016-03-26 17:44:27 +08:00
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512BW-NEXT: vpmullw {{.*}}(%rip), %zmm0, %zmm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <32 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
|
|
|
|
ret <32 x i8> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x i16> @mul_v16i16c(<16 x i16> %i) nounwind {
|
|
|
|
; SSE-LABEL: mul_v16i16c:
|
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [117,117,117,117,117,117,117,117]
|
|
|
|
; SSE-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: pmullw %xmm2, %xmm1
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX-LABEL: mul_v16i16c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <16 x i16> %i, < i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117 >
|
|
|
|
ret <16 x i16> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i32> @mul_v8i32c(<8 x i32> %i) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v8i32c:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [117,117,117,117]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v8i32c:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [117,117,117,117]
|
|
|
|
; SSE41-NEXT: pmulld %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: pmulld %xmm2, %xmm1
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX-LABEL: mul_v8i32c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
|
|
|
|
; AVX-NEXT: vpmulld %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <8 x i32> %i, < i32 117, i32 117, i32 117, i32 117, i32 117, i32 117, i32 117, i32 117 >
|
|
|
|
ret <8 x i32> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i64> @mul_v4i64c(<4 x i64> %i) nounwind {
|
|
|
|
; SSE-LABEL: mul_v4i64c:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [117,117]
|
|
|
|
; SSE-NEXT: movdqa %xmm0, %xmm3
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: psllq $32, %xmm0
|
|
|
|
; SSE-NEXT: paddq %xmm3, %xmm0
|
|
|
|
; SSE-NEXT: movdqa %xmm1, %xmm3
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm1
|
|
|
|
; SSE-NEXT: psllq $32, %xmm1
|
|
|
|
; SSE-NEXT: paddq %xmm3, %xmm1
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v4i64c:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpbroadcastq {{.*}}(%rip), %ymm1
|
|
|
|
; AVX-NEXT: vpmuludq %ymm1, %ymm0, %ymm2
|
|
|
|
; AVX-NEXT: vpsrlq $32, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: vpsllq $32, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: vpaddq %ymm0, %ymm2, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
2015-06-16 14:07:24 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <4 x i64> %i, < i64 117, i64 117, i64 117, i64 117 >
|
|
|
|
ret <4 x i64> %A
|
|
|
|
}
|
|
|
|
|
2016-03-26 17:35:48 +08:00
|
|
|
define <32 x i8> @mul_v32i8(<32 x i8> %i, <32 x i8> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v32i8:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm5, %xmm0
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm2
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm5
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm5
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
|
|
|
; SSE2-NEXT: pmullw %xmm3, %xmm1
|
|
|
|
; SSE2-NEXT: pand %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: packuswb %xmm5, %xmm1
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v32i8:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm5
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm4
|
|
|
|
; SSE41-NEXT: pmullw %xmm5, %xmm4
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm4
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm0
|
|
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm4
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm3, %xmm0
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm2
|
|
|
|
; SSE41-NEXT: pmullw %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm1
|
|
|
|
; SSE41-NEXT: pmullw %xmm0, %xmm1
|
|
|
|
; SSE41-NEXT: pand %xmm5, %xmm1
|
|
|
|
; SSE41-NEXT: packuswb %xmm1, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm1
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v32i8:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm3, %ymm3
|
|
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm3, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v32i8:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm3
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm2, %zmm2
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm1
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm2, %ymm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v32i8:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
2016-03-26 17:44:27 +08:00
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm1, %zmm1
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
|
|
|
|
; AVX512BW-NEXT: vpmullw %zmm1, %zmm0, %zmm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <32 x i8> %i, %j
|
|
|
|
ret <32 x i8> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x i16> @mul_v16i16(<16 x i16> %i, <16 x i16> %j) nounwind {
|
|
|
|
; SSE-LABEL: mul_v16i16:
|
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: pmullw %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: pmullw %xmm3, %xmm1
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX-LABEL: mul_v16i16:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <16 x i16> %i, %j
|
|
|
|
ret <16 x i16> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i32> @mul_v8i32(<8 x i32> %i, <8 x i32> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v8i32:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm0
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm2
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm1
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v8i32:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: pmulld %xmm2, %xmm0
|
|
|
|
; SSE41-NEXT: pmulld %xmm3, %xmm1
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX-LABEL: mul_v8i32:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmulld %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <8 x i32> %i, %j
|
|
|
|
ret <8 x i32> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i64> @mul_v4i64(<4 x i64> %i, <4 x i64> %j) nounwind {
|
|
|
|
; SSE-LABEL: mul_v4i64:
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE: # BB#0: # %entry
|
|
|
|
; SSE-NEXT: movdqa %xmm0, %xmm4
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm4
|
|
|
|
; SSE-NEXT: movdqa %xmm2, %xmm5
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm5
|
|
|
|
; SSE-NEXT: pmuludq %xmm0, %xmm5
|
|
|
|
; SSE-NEXT: psllq $32, %xmm5
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE-NEXT: pmuludq %xmm2, %xmm0
|
|
|
|
; SSE-NEXT: psllq $32, %xmm0
|
2016-07-18 14:14:54 +08:00
|
|
|
; SSE-NEXT: paddq %xmm5, %xmm0
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE-NEXT: paddq %xmm4, %xmm0
|
|
|
|
; SSE-NEXT: movdqa %xmm1, %xmm2
|
|
|
|
; SSE-NEXT: pmuludq %xmm3, %xmm2
|
|
|
|
; SSE-NEXT: movdqa %xmm3, %xmm4
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm4
|
|
|
|
; SSE-NEXT: pmuludq %xmm1, %xmm4
|
|
|
|
; SSE-NEXT: psllq $32, %xmm4
|
|
|
|
; SSE-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE-NEXT: pmuludq %xmm3, %xmm1
|
|
|
|
; SSE-NEXT: psllq $32, %xmm1
|
2016-07-18 14:14:54 +08:00
|
|
|
; SSE-NEXT: paddq %xmm4, %xmm1
|
2015-11-25 06:09:31 +08:00
|
|
|
; SSE-NEXT: paddq %xmm2, %xmm1
|
|
|
|
; SSE-NEXT: retq
|
|
|
|
;
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-LABEL: mul_v4i64:
|
|
|
|
; AVX: # BB#0: # %entry
|
|
|
|
; AVX-NEXT: vpmuludq %ymm1, %ymm0, %ymm2
|
|
|
|
; AVX-NEXT: vpsrlq $32, %ymm1, %ymm3
|
|
|
|
; AVX-NEXT: vpmuludq %ymm3, %ymm0, %ymm3
|
|
|
|
; AVX-NEXT: vpsllq $32, %ymm3, %ymm3
|
|
|
|
; AVX-NEXT: vpsrlq $32, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX-NEXT: vpsllq $32, %ymm0, %ymm0
|
2016-07-18 14:14:54 +08:00
|
|
|
; AVX-NEXT: vpaddq %ymm0, %ymm3, %ymm0
|
2016-03-26 17:35:48 +08:00
|
|
|
; AVX-NEXT: vpaddq %ymm0, %ymm2, %ymm0
|
|
|
|
; AVX-NEXT: retq
|
2015-06-16 14:07:24 +08:00
|
|
|
entry:
|
|
|
|
%A = mul <4 x i64> %i, %j
|
|
|
|
ret <4 x i64> %A
|
|
|
|
}
|
2016-03-26 17:50:06 +08:00
|
|
|
|
|
|
|
define <64 x i8> @mul_v64i8c(<64 x i8> %i) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v64i8c:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm6
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm6
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm6, %xmm0
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm6
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm6
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm1
|
|
|
|
; SSE2-NEXT: packuswb %xmm6, %xmm1
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm6
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm6
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm6
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm2
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm2
|
|
|
|
; SSE2-NEXT: packuswb %xmm6, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm6
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm6
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm6
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm3
|
|
|
|
; SSE2-NEXT: pand %xmm5, %xmm3
|
|
|
|
; SSE2-NEXT: packuswb %xmm6, %xmm3
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v64i8c:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm1
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm0
|
2016-10-25 22:29:25 +08:00
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm6 = [117,117,117,117,117,117,117,117]
|
2016-03-26 17:50:06 +08:00
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm0
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm7 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm0
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm1
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm1
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm1
|
|
|
|
; SSE41-NEXT: packuswb %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm4, %xmm1
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm1
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm1
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm4, %xmm4
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm4
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm4
|
|
|
|
; SSE41-NEXT: packuswb %xmm4, %xmm1
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm4
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm4
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm4
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm2
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm2
|
|
|
|
; SSE41-NEXT: packuswb %xmm2, %xmm4
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm3, %xmm5
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm5
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm5
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm3[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pmullw %xmm6, %xmm2
|
|
|
|
; SSE41-NEXT: pand %xmm7, %xmm2
|
|
|
|
; SSE41-NEXT: packuswb %xmm2, %xmm5
|
|
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm3
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v64i8c:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX2-NEXT: vpmullw %ymm3, %ymm2, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm4
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm4, %xmm4
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm4[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmullw %ymm3, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm4
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm4, %xmm4
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
|
|
|
; AVX2-NEXT: vpmullw %ymm3, %ymm2, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm4
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm4, %xmm4
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm4[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX2-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm3, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm5, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v64i8c:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm2
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm3 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512F-NEXT: vpmullw %ymm3, %ymm2, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm2, %zmm2
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm3, %ymm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm2, %ymm0
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm3, %ymm2, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm2, %zmm2
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm1
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm1, %zmm1
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm2, %ymm1
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v64i8c:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
2016-10-10 07:08:39 +08:00
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm1
|
2016-10-25 22:29:25 +08:00
|
|
|
; AVX512BW-NEXT: vmovdqu16 {{.*#+}} zmm2 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
|
2016-10-10 07:08:39 +08:00
|
|
|
; AVX512BW-NEXT: vpmullw %zmm2, %zmm1, %zmm1
|
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
|
2016-04-11 01:02:48 +08:00
|
|
|
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
|
2016-10-10 07:08:39 +08:00
|
|
|
; AVX512BW-NEXT: vpmullw %zmm2, %zmm0, %zmm0
|
2016-04-11 01:02:48 +08:00
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
2016-10-10 07:08:39 +08:00
|
|
|
; AVX512BW-NEXT: vinserti64x4 $1, %ymm0, %zmm1, %zmm0
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512BW-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <64 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
|
|
|
|
ret <64 x i8> %A
|
|
|
|
}
|
|
|
|
|
|
|
|
define <64 x i8> @mul_v64i8(<64 x i8> %i, <64 x i8> %j) nounwind {
|
|
|
|
; SSE2-LABEL: mul_v64i8:
|
|
|
|
; SSE2: # BB#0: # %entry
|
|
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm8
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm8 = xmm8[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm8
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm9
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm9 = xmm9[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm9
|
|
|
|
; SSE2-NEXT: pmullw %xmm8, %xmm9
|
|
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm9
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm0
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm0
|
|
|
|
; SSE2-NEXT: packuswb %xmm9, %xmm0
|
|
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm9
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm9 = xmm9[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm9
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: pmullw %xmm9, %xmm4
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm4
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm1
|
|
|
|
; SSE2-NEXT: pmullw %xmm5, %xmm1
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm1
|
|
|
|
; SSE2-NEXT: packuswb %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: movdqa %xmm6, %xmm4
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm5
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm2
|
|
|
|
; SSE2-NEXT: pmullw %xmm6, %xmm2
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm2
|
|
|
|
; SSE2-NEXT: packuswb %xmm5, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm7, %xmm4
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm5
|
|
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
|
|
; SSE2-NEXT: pmullw %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm5
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm7
|
|
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
|
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
|
|
; SSE2-NEXT: pmullw %xmm7, %xmm3
|
|
|
|
; SSE2-NEXT: pand %xmm8, %xmm3
|
|
|
|
; SSE2-NEXT: packuswb %xmm5, %xmm3
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v64i8:
|
|
|
|
; SSE41: # BB#0: # %entry
|
|
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm8
|
|
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm1
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm4, %xmm9
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: pmullw %xmm9, %xmm0
|
|
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm9 = [255,255,255,255,255,255,255,255]
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm0
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm4, %xmm4
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm1
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm1
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm1
|
|
|
|
; SSE41-NEXT: packuswb %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm5, %xmm4
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm8, %xmm1
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm1
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm1
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm5[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm4, %xmm4
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm8[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm5, %xmm5
|
|
|
|
; SSE41-NEXT: pmullw %xmm4, %xmm5
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm5
|
|
|
|
; SSE41-NEXT: packuswb %xmm5, %xmm1
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm6, %xmm5
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm4
|
|
|
|
; SSE41-NEXT: pmullw %xmm5, %xmm4
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm4
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm6[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm5, %xmm5
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pmullw %xmm5, %xmm2
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm2
|
|
|
|
; SSE41-NEXT: packuswb %xmm2, %xmm4
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm7, %xmm2
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm3, %xmm5
|
|
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm5
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm5
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm7[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxbw %xmm3, %xmm3
|
|
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm3
|
|
|
|
; SSE41-NEXT: pand %xmm9, %xmm3
|
|
|
|
; SSE41-NEXT: packuswb %xmm3, %xmm5
|
|
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm2
|
|
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm3
|
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v64i8:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm4
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm4, %ymm4
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm5
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm5, %ymm5
|
|
|
|
; AVX2-NEXT: vpmullw %ymm4, %ymm5, %ymm5
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm5, %xmm6
|
|
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm6, %xmm6
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm5, %xmm5
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm6[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm0, %xmm0
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm2
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm5
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm5, %ymm5
|
|
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm5, %ymm2
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm5
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm5, %xmm5
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm2, %xmm2
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm5[0]
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm3, %ymm3
|
|
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX2-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm3, %xmm3
|
|
|
|
; AVX2-NEXT: vpshufb %xmm4, %xmm1, %xmm1
|
|
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
|
|
|
|
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512F-LABEL: mul_v64i8:
|
|
|
|
; AVX512F: # BB#0: # %entry
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm2, %ymm4
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm5
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm4, %ymm5, %ymm4
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm4, %zmm4
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm4, %xmm4
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm2, %xmm2
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm2, %ymm2
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm0, %ymm0
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm4, %ymm0
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm3, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm4
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm4, %ymm2
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm2, %zmm2
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm3, %xmm3
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm3, %ymm3
|
|
|
|
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm1
|
|
|
|
; AVX512F-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
|
|
|
; AVX512F-NEXT: vpmovsxwd %ymm1, %zmm1
|
|
|
|
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
2016-07-22 13:46:44 +08:00
|
|
|
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm2, %ymm1
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512F-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512BW-LABEL: mul_v64i8:
|
|
|
|
; AVX512BW: # BB#0: # %entry
|
2016-04-11 01:02:48 +08:00
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm1, %zmm2
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm3
|
|
|
|
; AVX512BW-NEXT: vpmullw %zmm2, %zmm3, %zmm2
|
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm2, %ymm2
|
|
|
|
; AVX512BW-NEXT: vextracti64x4 $1, %zmm1, %ymm1
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm1, %zmm1
|
|
|
|
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
|
|
|
|
; AVX512BW-NEXT: vpmullw %zmm1, %zmm0, %zmm0
|
|
|
|
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
|
|
|
; AVX512BW-NEXT: vinserti64x4 $1, %ymm0, %zmm2, %zmm0
|
2016-03-26 17:50:06 +08:00
|
|
|
; AVX512BW-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%A = mul <64 x i8> %i, %j
|
|
|
|
ret <64 x i8> %A
|
|
|
|
}
|
|
|
|
|
2016-11-13 07:44:58 +08:00
|
|
|
; PR30845
|
|
|
|
define <4 x i32> @mul_v4i64_zero_upper(<4 x i32> %val1, <4 x i32> %val2) {
|
|
|
|
; SSE2-LABEL: mul_v4i64_zero_upper:
|
|
|
|
; SSE2: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm3[2],xmm1[3],xmm3[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm2
|
|
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm1[1,3]
|
|
|
|
; SSE2-NEXT: movaps %xmm2, %xmm0
|
2016-11-13 07:44:58 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v4i64_zero_upper:
|
|
|
|
; SSE41: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: pxor %xmm3, %xmm3
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm4 = xmm0[0],zero,xmm0[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm3[2],xmm1[3],xmm3[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE41-NEXT: pmuludq %xmm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: pmuludq %xmm4, %xmm2
|
|
|
|
; SSE41-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm1[1,3]
|
|
|
|
; SSE41-NEXT: movaps %xmm2, %xmm0
|
2016-11-13 07:44:58 +08:00
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v4i64_zero_upper:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
|
|
|
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX2-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 07:44:58 +08:00
|
|
|
; AVX2-NEXT: vzeroupper
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512-LABEL: mul_v4i64_zero_upper:
|
|
|
|
; AVX512: # BB#0: # %entry
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
|
|
|
; AVX512-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 07:44:58 +08:00
|
|
|
; AVX512-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%val1a = zext <4 x i32> %val1 to <4 x i64>
|
|
|
|
%val2a = zext <4 x i32> %val2 to <4 x i64>
|
|
|
|
%res64 = mul <4 x i64> %val1a, %val2a
|
|
|
|
%rescast = bitcast <4 x i64> %res64 to <8 x i32>
|
|
|
|
%res = shufflevector <8 x i32> %rescast, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <4 x i32> %res
|
|
|
|
}
|
2016-11-13 22:57:52 +08:00
|
|
|
|
|
|
|
define <4 x i32> @mul_v4i64_zero_upper_left(<4 x i32> %val1, <4 x i64> %val2) {
|
|
|
|
; SSE2-LABEL: mul_v4i64_zero_upper_left:
|
|
|
|
; SSE2: # BB#0: # %entry
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
2016-11-13 22:57:52 +08:00
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm4
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm3
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: psrlq $32, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm0, %xmm2
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: psllq $32, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: paddq %xmm3, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm1
|
|
|
|
; SSE2-NEXT: paddq %xmm1, %xmm0
|
|
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
|
2016-11-13 22:57:52 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v4i64_zero_upper_left:
|
|
|
|
; SSE41: # BB#0: # %entry
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE41-NEXT: pxor %xmm3, %xmm3
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm4 = xmm0[0],zero,xmm0[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
|
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm3
|
|
|
|
; SSE41-NEXT: pmuludq %xmm2, %xmm3
|
|
|
|
; SSE41-NEXT: psrlq $32, %xmm2
|
|
|
|
; SSE41-NEXT: pmuludq %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: psllq $32, %xmm2
|
|
|
|
; SSE41-NEXT: paddq %xmm3, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
|
|
; SSE41-NEXT: pmuludq %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE41-NEXT: pmuludq %xmm4, %xmm1
|
|
|
|
; SSE41-NEXT: psllq $32, %xmm1
|
|
|
|
; SSE41-NEXT: paddq %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
|
2016-11-13 22:57:52 +08:00
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v4i64_zero_upper_left:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
|
|
|
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm2
|
2016-11-17 20:14:49 +08:00
|
|
|
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm1
|
2016-11-13 22:57:52 +08:00
|
|
|
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpsllq $32, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpaddq %ymm0, %ymm2, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX2-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 22:57:52 +08:00
|
|
|
; AVX2-NEXT: vzeroupper
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512-LABEL: mul_v4i64_zero_upper_left:
|
|
|
|
; AVX512: # BB#0: # %entry
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
|
|
|
; AVX512-NEXT: vpmuludq %ymm1, %ymm0, %ymm2
|
2016-11-17 20:14:49 +08:00
|
|
|
; AVX512-NEXT: vpsrlq $32, %ymm1, %ymm1
|
2016-11-13 22:57:52 +08:00
|
|
|
; AVX512-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512-NEXT: vpsllq $32, %ymm0, %ymm0
|
|
|
|
; AVX512-NEXT: vpaddq %ymm0, %ymm2, %ymm0
|
|
|
|
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 22:57:52 +08:00
|
|
|
; AVX512-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%val1a = zext <4 x i32> %val1 to <4 x i64>
|
|
|
|
%res64 = mul <4 x i64> %val1a, %val2
|
|
|
|
%rescast = bitcast <4 x i64> %res64 to <8 x i32>
|
|
|
|
%res = shufflevector <8 x i32> %rescast, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <4 x i32> %res
|
|
|
|
}
|
|
|
|
|
2016-11-13 23:32:11 +08:00
|
|
|
define <4 x i32> @mul_v4i64_zero_lower(<4 x i32> %val1, <4 x i64> %val2) {
|
|
|
|
; SSE2-LABEL: mul_v4i64_zero_lower:
|
|
|
|
; SSE2: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: psrlq $32, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm0, %xmm2
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: psllq $32, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm3
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm3
|
|
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,3],xmm2[1,3]
|
|
|
|
; SSE2-NEXT: movaps %xmm3, %xmm0
|
2016-11-13 23:32:11 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v4i64_zero_lower:
|
|
|
|
; SSE41: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: pxor %xmm4, %xmm4
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
2016-12-12 21:33:58 +08:00
|
|
|
; SSE41-NEXT: psrlq $32, %xmm2
|
|
|
|
; SSE41-NEXT: pmuludq %xmm0, %xmm2
|
|
|
|
; SSE41-NEXT: psllq $32, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE41-NEXT: pmuludq %xmm1, %xmm3
|
|
|
|
; SSE41-NEXT: psllq $32, %xmm3
|
|
|
|
; SSE41-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,3],xmm2[1,3]
|
|
|
|
; SSE41-NEXT: movaps %xmm3, %xmm0
|
2016-11-13 23:32:11 +08:00
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v4i64_zero_lower:
|
|
|
|
; AVX2: # BB#0: # %entry
|
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
2016-11-17 20:14:49 +08:00
|
|
|
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm1
|
2016-11-13 23:32:11 +08:00
|
|
|
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpsllq $32, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX2-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 23:32:11 +08:00
|
|
|
; AVX2-NEXT: vzeroupper
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512-LABEL: mul_v4i64_zero_lower:
|
|
|
|
; AVX512: # BB#0: # %entry
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
2016-11-17 20:14:49 +08:00
|
|
|
; AVX512-NEXT: vpsrlq $32, %ymm1, %ymm1
|
2016-11-13 23:32:11 +08:00
|
|
|
; AVX512-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX512-NEXT: vpsllq $32, %ymm0, %ymm0
|
|
|
|
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
|
2016-11-13 23:32:11 +08:00
|
|
|
; AVX512-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%val1a = zext <4 x i32> %val1 to <4 x i64>
|
|
|
|
%val2a = and <4 x i64> %val2, <i64 -4294967296, i64 -4294967296, i64 -4294967296, i64 -4294967296>
|
|
|
|
%res64 = mul <4 x i64> %val1a, %val2a
|
|
|
|
%rescast = bitcast <4 x i64> %res64 to <8 x i32>
|
|
|
|
%res = shufflevector <8 x i32> %rescast, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <4 x i32> %res
|
|
|
|
}
|
2016-11-18 19:00:36 +08:00
|
|
|
|
|
|
|
define <8 x i32> @mul_v8i64_zero_upper(<8 x i32> %val1, <8 x i32> %val2) {
|
|
|
|
; SSE2-LABEL: mul_v8i64_zero_upper:
|
|
|
|
; SSE2: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pxor %xmm6, %xmm6
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm4
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm6[2],xmm0[3],xmm6[3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm5
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm6[2],xmm1[3],xmm6[3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm8
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm8 = xmm8[0],xmm6[0],xmm8[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm6[2],xmm2[3],xmm6[3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm6[0],xmm7[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm6[2],xmm3[3],xmm6[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm3
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm7, %xmm5
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm0, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE2-NEXT: pmuludq %xmm8, %xmm4
|
|
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[1,3],xmm2[1,3]
|
|
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[1,3],xmm3[1,3]
|
|
|
|
; SSE2-NEXT: movaps %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: movaps %xmm5, %xmm1
|
2016-11-18 19:00:36 +08:00
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v8i64_zero_upper:
|
|
|
|
; SSE41: # BB#0: # %entry
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: pxor %xmm6, %xmm6
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm8 = xmm0[0],zero,xmm0[1],zero
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm6[2],xmm0[3],xmm6[3]
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm7 = xmm1[0],zero,xmm1[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm6[2],xmm1[3],xmm6[3]
|
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm4 = xmm2[0],zero,xmm2[1],zero
|
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm6[2],xmm2[3],xmm6[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm5 = xmm3[0],zero,xmm3[1],zero
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm6[2],xmm3[3],xmm6[3]
|
2016-12-09 18:13:45 +08:00
|
|
|
; SSE41-NEXT: pmuludq %xmm1, %xmm3
|
|
|
|
; SSE41-NEXT: pmuludq %xmm0, %xmm2
|
[x86] use a single shufps when it can save instructions
This is a tiny patch with a big pile of test changes.
This partially fixes PR27885:
https://llvm.org/bugs/show_bug.cgi?id=27885
My motivating case looks like this:
- vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
- vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
- vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+ vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
And this happens several times in the diffs. For chips with domain-crossing penalties,
the instruction count and size reduction should usually overcome any potential
domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such
as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so
using shufps is a pure win.
So the test case diffs all appear to be improvements except one test in
vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate
zero elements and one test in combine-sra.ll where multiple uses prevent the expected
shuffle combining.
Differential Revision: https://reviews.llvm.org/D27692
llvm-svn: 289837
2016-12-16 02:03:38 +08:00
|
|
|
; SSE41-NEXT: pmuludq %xmm7, %xmm5
|
|
|
|
; SSE41-NEXT: pmuludq %xmm8, %xmm4
|
|
|
|
; SSE41-NEXT: shufps {{.*#+}} xmm4 = xmm4[1,3],xmm2[1,3]
|
|
|
|
; SSE41-NEXT: shufps {{.*#+}} xmm5 = xmm5[1,3],xmm3[1,3]
|
|
|
|
; SSE41-NEXT: movaps %xmm4, %xmm0
|
|
|
|
; SSE41-NEXT: movaps %xmm5, %xmm1
|
2016-11-18 19:00:36 +08:00
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v8i64_zero_upper:
|
|
|
|
; AVX2: # BB#0: # %entry
|
2016-12-16 02:43:46 +08:00
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
|
2016-11-18 19:00:36 +08:00
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
2016-12-16 02:43:46 +08:00
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
|
2016-11-18 19:00:36 +08:00
|
|
|
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
|
|
|
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmuludq %ymm3, %ymm2, %ymm1
|
2016-12-16 02:43:46 +08:00
|
|
|
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm1[1,3],ymm0[1,3],ymm1[5,7],ymm0[5,7]
|
2016-11-18 19:00:36 +08:00
|
|
|
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512-LABEL: mul_v8i64_zero_upper:
|
|
|
|
; AVX512: # BB#0: # %entry
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
|
|
|
|
; AVX512-NEXT: vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
|
|
|
|
; AVX512-NEXT: vpmuludq %zmm1, %zmm0, %zmm0
|
|
|
|
; AVX512-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
2016-12-16 02:43:46 +08:00
|
|
|
; AVX512-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
|
2016-11-18 19:00:36 +08:00
|
|
|
; AVX512-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
|
|
|
; AVX512-NEXT: retq
|
|
|
|
entry:
|
|
|
|
%val1a = zext <8 x i32> %val1 to <8 x i64>
|
|
|
|
%val2a = zext <8 x i32> %val2 to <8 x i64>
|
|
|
|
%res64 = mul <8 x i64> %val1a, %val2a
|
|
|
|
%rescast = bitcast <8 x i64> %res64 to <16 x i32>
|
|
|
|
%res = shufflevector <16 x i32> %rescast, <16 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7,i32 9, i32 11, i32 13, i32 15 >
|
|
|
|
ret <8 x i32> %res
|
|
|
|
}
|
2016-12-11 06:02:36 +08:00
|
|
|
|
|
|
|
define <8 x i64> @mul_v8i64_sext(<8 x i16> %val1, <8 x i32> %val2) {
|
|
|
|
; SSE2-LABEL: mul_v8i64_sext:
|
|
|
|
; SSE2: # BB#0:
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm9
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[3,1,2,3]
|
|
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
|
|
; SSE2-NEXT: psrad $16, %xmm3
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm2
|
|
|
|
; SSE2-NEXT: psrad $16, %xmm1
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm6
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm6
|
|
|
|
; SSE2-NEXT: psrad $16, %xmm2
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm6[0],xmm2[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm6
|
|
|
|
; SSE2-NEXT: psrad $16, %xmm0
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm8 = xmm9[2,3,0,1]
|
|
|
|
; SSE2-NEXT: movdqa %xmm8, %xmm7
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm7
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm8 = xmm8[0],xmm7[0],xmm8[1],xmm7[1]
|
|
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1]
|
|
|
|
; SSE2-NEXT: movdqa %xmm6, %xmm7
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm7
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
|
|
|
|
; SSE2-NEXT: movdqa %xmm9, %xmm7
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm7
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm7[0],xmm9[1],xmm7[1]
|
|
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm7
|
|
|
|
; SSE2-NEXT: psrad $31, %xmm7
|
|
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1]
|
|
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm7
|
|
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm7
|
|
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm5
|
|
|
|
; SSE2-NEXT: pmuludq %xmm0, %xmm5
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm0
|
|
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm0
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm0
|
|
|
|
; SSE2-NEXT: paddq %xmm5, %xmm0
|
|
|
|
; SSE2-NEXT: paddq %xmm7, %xmm0
|
|
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
|
|
; SSE2-NEXT: pmuludq %xmm9, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm9, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm5
|
|
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm5
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm2
|
|
|
|
; SSE2-NEXT: pmuludq %xmm9, %xmm2
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm2
|
|
|
|
; SSE2-NEXT: paddq %xmm5, %xmm2
|
|
|
|
; SSE2-NEXT: paddq %xmm4, %xmm2
|
|
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
|
|
; SSE2-NEXT: pmuludq %xmm6, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm6, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm5
|
|
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm5
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm1
|
|
|
|
; SSE2-NEXT: pmuludq %xmm6, %xmm1
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm1
|
|
|
|
; SSE2-NEXT: paddq %xmm5, %xmm1
|
|
|
|
; SSE2-NEXT: paddq %xmm4, %xmm1
|
|
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm4
|
|
|
|
; SSE2-NEXT: pmuludq %xmm8, %xmm4
|
|
|
|
; SSE2-NEXT: movdqa %xmm8, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm5
|
|
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm5
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm5
|
|
|
|
; SSE2-NEXT: psrlq $32, %xmm3
|
|
|
|
; SSE2-NEXT: pmuludq %xmm8, %xmm3
|
|
|
|
; SSE2-NEXT: psllq $32, %xmm3
|
|
|
|
; SSE2-NEXT: paddq %xmm5, %xmm3
|
|
|
|
; SSE2-NEXT: paddq %xmm4, %xmm3
|
|
|
|
; SSE2-NEXT: retq
|
|
|
|
;
|
|
|
|
; SSE41-LABEL: mul_v8i64_sext:
|
|
|
|
; SSE41: # BB#0:
|
2016-12-12 18:49:15 +08:00
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[3,1,2,3]
|
|
|
|
; SSE41-NEXT: pmovsxwq %xmm3, %xmm8
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxwq %xmm3, %xmm6
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
|
|
|
|
; SSE41-NEXT: pmovsxwq %xmm3, %xmm7
|
|
|
|
; SSE41-NEXT: pmovsxwq %xmm0, %xmm5
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxdq %xmm0, %xmm3
|
|
|
|
; SSE41-NEXT: pmovsxdq %xmm2, %xmm2
|
|
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
|
|
; SSE41-NEXT: pmovsxdq %xmm0, %xmm4
|
|
|
|
; SSE41-NEXT: pmovsxdq %xmm1, %xmm0
|
|
|
|
; SSE41-NEXT: pmuldq %xmm5, %xmm0
|
|
|
|
; SSE41-NEXT: pmuldq %xmm7, %xmm4
|
|
|
|
; SSE41-NEXT: pmuldq %xmm6, %xmm2
|
|
|
|
; SSE41-NEXT: pmuldq %xmm8, %xmm3
|
|
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm1
|
2016-12-11 06:02:36 +08:00
|
|
|
; SSE41-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX2-LABEL: mul_v8i64_sext:
|
|
|
|
; AVX2: # BB#0:
|
|
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
|
|
|
|
; AVX2-NEXT: vpmovsxwq %xmm2, %ymm2
|
|
|
|
; AVX2-NEXT: vpmovsxwq %xmm0, %ymm0
|
|
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
|
|
|
|
; AVX2-NEXT: vpmovsxdq %xmm3, %ymm3
|
|
|
|
; AVX2-NEXT: vpmovsxdq %xmm1, %ymm1
|
2016-12-12 18:49:15 +08:00
|
|
|
; AVX2-NEXT: vpmuldq %ymm1, %ymm0, %ymm0
|
|
|
|
; AVX2-NEXT: vpmuldq %ymm3, %ymm2, %ymm1
|
2016-12-11 06:02:36 +08:00
|
|
|
; AVX2-NEXT: retq
|
|
|
|
;
|
|
|
|
; AVX512-LABEL: mul_v8i64_sext:
|
|
|
|
; AVX512: # BB#0:
|
|
|
|
; AVX512-NEXT: vpmovsxwq %xmm0, %zmm0
|
|
|
|
; AVX512-NEXT: vpmovsxdq %ymm1, %zmm1
|
2016-12-12 18:49:15 +08:00
|
|
|
; AVX512-NEXT: vpmuldq %zmm1, %zmm0, %zmm0
|
2016-12-11 06:02:36 +08:00
|
|
|
; AVX512-NEXT: retq
|
|
|
|
%1 = sext <8 x i16> %val1 to <8 x i64>
|
|
|
|
%2 = sext <8 x i32> %val2 to <8 x i64>
|
|
|
|
%3 = mul <8 x i64> %1, %2
|
|
|
|
ret <8 x i64> %3
|
|
|
|
}
|