[X86] Add slow/fast pmulld test coverage to vector-mul.ll

This commit is contained in:
Simon Pilgrim 2021-09-27 21:42:08 +01:00
parent 04f5913395
commit 540ed354d3
1 changed files with 391 additions and 166 deletions

View File

@ -1,6 +1,9 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,X86-SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,X64-SSE
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X86-SSE,X86-SSE2
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE,X86-SSE4
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X64-SSE,X64-SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2,-slow-pmulld | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE,X64-SSE4
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2,+slow-pmulld | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE,X64-SSE4
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop | FileCheck %s --check-prefixes=X64-AVX,X64-XOP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=X64-AVX,X64-AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefixes=X64-AVX,X64-AVX512DQ
@ -89,13 +92,21 @@ define <16 x i8> @mul_v16i8_32(<16 x i8> %a0) nounwind {
;
define <2 x i64> @mul_v2i64_32_8(<2 x i64> %a0) nounwind {
; SSE-LABEL: mul_v2i64_32_8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psllq $3, %xmm1
; SSE-NEXT: psllq $5, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE-NEXT: ret{{[l|q]}}
; SSE2-LABEL: mul_v2i64_32_8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: psllq $5, %xmm1
; SSE2-NEXT: psllq $3, %xmm0
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE2-NEXT: ret{{[l|q]}}
;
; SSE4-LABEL: mul_v2i64_32_8:
; SSE4: # %bb.0:
; SSE4-NEXT: movdqa %xmm0, %xmm1
; SSE4-NEXT: psllq $3, %xmm1
; SSE4-NEXT: psllq $5, %xmm0
; SSE4-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-XOP-LABEL: mul_v2i64_32_8:
; X64-XOP: # %bb.0:
@ -116,15 +127,27 @@ define <2 x i64> @mul_v2i64_32_8(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_1_2_4_8(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_1_2_4_8:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_1_2_4_8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [1,2,4,8]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_1_2_4_8:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_1_2_4_8:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_1_2_4_8:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i32_1_2_4_8:
; X64-XOP: # %bb.0:
@ -174,19 +197,33 @@ define <8 x i16> @mul_v8i16_1_2_4_8_16_32_64_128(<8 x i16> %a0) nounwind {
}
define <16 x i8> @mul_v16i8_1_2_4_8_1_2_4_8_1_2_4_8_1_2_4_8(<16 x i8> %a0) nounwind {
; SSE-LABEL: mul_v16i8_1_2_4_8_1_2_4_8_1_2_4_8_1_2_4_8:
; SSE: # %bb.0:
; SSE-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; SSE-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [1,2,4,8,1,2,4,8]
; SSE-NEXT: pmullw %xmm2, %xmm0
; SSE-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm3, %xmm0
; SSE-NEXT: pmullw %xmm2, %xmm1
; SSE-NEXT: pand %xmm3, %xmm1
; SSE-NEXT: packuswb %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: ret{{[l|q]}}
; SSE2-LABEL: mul_v16i8_1_2_4_8_1_2_4_8_1_2_4_8_1_2_4_8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [1,2,4,8,1,2,4,8]
; SSE2-NEXT: pmullw %xmm2, %xmm1
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm3, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pmullw %xmm2, %xmm0
; SSE2-NEXT: pand %xmm3, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; SSE4-LABEL: mul_v16i8_1_2_4_8_1_2_4_8_1_2_4_8_1_2_4_8:
; SSE4: # %bb.0:
; SSE4-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; SSE4-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE4-NEXT: movdqa {{.*#+}} xmm2 = [1,2,4,8,1,2,4,8]
; SSE4-NEXT: pmullw %xmm2, %xmm0
; SSE4-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE4-NEXT: pand %xmm3, %xmm0
; SSE4-NEXT: pmullw %xmm2, %xmm1
; SSE4-NEXT: pand %xmm3, %xmm1
; SSE4-NEXT: packuswb %xmm0, %xmm1
; SSE4-NEXT: movdqa %xmm1, %xmm0
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-XOP-LABEL: mul_v16i8_1_2_4_8_1_2_4_8_1_2_4_8_1_2_4_8:
; X64-XOP: # %bb.0:
@ -248,15 +285,23 @@ define <2 x i64> @mul_v2i64_17(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_17(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_17:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_17:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pslld $4, %xmm1
; SSE2-NEXT: paddd %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_17:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_17:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_17:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i32_17:
; X64-XOP: # %bb.0:
@ -376,12 +421,24 @@ define <4 x i64> @mul_v4i64_17(<4 x i64> %a0) nounwind {
}
define <8 x i32> @mul_v8i32_17(<8 x i32> %a0) nounwind {
; SSE-LABEL: mul_v8i32_17:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [17,17,17,17]
; SSE-NEXT: pmulld %xmm2, %xmm0
; SSE-NEXT: pmulld %xmm2, %xmm1
; SSE-NEXT: ret{{[l|q]}}
; SSE2-LABEL: mul_v8i32_17:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: pslld $4, %xmm2
; SSE2-NEXT: paddd %xmm0, %xmm2
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: pslld $4, %xmm3
; SSE2-NEXT: paddd %xmm1, %xmm3
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm1
; SSE2-NEXT: ret{{[l|q]}}
;
; SSE4-LABEL: mul_v8i32_17:
; SSE4: # %bb.0:
; SSE4-NEXT: movdqa {{.*#+}} xmm2 = [17,17,17,17]
; SSE4-NEXT: pmulld %xmm2, %xmm0
; SSE4-NEXT: pmulld %xmm2, %xmm1
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-XOP-LABEL: mul_v8i32_17:
; X64-XOP: # %bb.0:
@ -521,15 +578,24 @@ define <2 x i64> @mul_v2i64_neg1025(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_neg33(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_neg33:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_neg33:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pslld $5, %xmm1
; SSE2-NEXT: paddd %xmm0, %xmm1
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_neg33:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_neg33:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_neg33:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i32_neg33:
; X64-XOP: # %bb.0:
@ -665,12 +731,27 @@ define <4 x i64> @mul_v4i64_neg1025(<4 x i64> %a0) nounwind {
}
define <8 x i32> @mul_v8i32_neg33(<8 x i32> %a0) nounwind {
; SSE-LABEL: mul_v8i32_neg33:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [4294967263,4294967263,4294967263,4294967263]
; SSE-NEXT: pmulld %xmm2, %xmm0
; SSE-NEXT: pmulld %xmm2, %xmm1
; SSE-NEXT: ret{{[l|q]}}
; SSE2-LABEL: mul_v8i32_neg33:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pslld $5, %xmm3
; SSE2-NEXT: paddd %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: psubd %xmm3, %xmm0
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: pslld $5, %xmm3
; SSE2-NEXT: paddd %xmm1, %xmm3
; SSE2-NEXT: psubd %xmm3, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm1
; SSE2-NEXT: ret{{[l|q]}}
;
; SSE4-LABEL: mul_v8i32_neg33:
; SSE4: # %bb.0:
; SSE4-NEXT: movdqa {{.*#+}} xmm2 = [4294967263,4294967263,4294967263,4294967263]
; SSE4-NEXT: pmulld %xmm2, %xmm0
; SSE4-NEXT: pmulld %xmm2, %xmm1
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-XOP-LABEL: mul_v8i32_neg33:
; X64-XOP: # %bb.0:
@ -843,15 +924,27 @@ define <2 x i64> @mul_v2i64_17_65(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_5_17_33_65(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_5_17_33_65:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_5_17_33_65:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [5,17,33,65]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_5_17_33_65:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_5_17_33_65:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_5_17_33_65:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-AVX-LABEL: mul_v4i32_5_17_33_65:
; X64-AVX: # %bb.0:
@ -881,31 +974,57 @@ define <8 x i16> @mul_v8i16_2_3_9_17_33_65_129_257(<8 x i16> %a0) nounwind {
}
define <16 x i8> @mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3(<16 x i8> %a0) nounwind {
; X86-SSE-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; X86-SSE-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X86-SSE-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X86-SSE-NEXT: pand %xmm2, %xmm0
; X86-SSE-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm1
; X86-SSE-NEXT: pand %xmm2, %xmm1
; X86-SSE-NEXT: packuswb %xmm0, %xmm1
; X86-SSE-NEXT: movdqa %xmm1, %xmm0
; X86-SSE-NEXT: retl
; X86-SSE2-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X86-SSE2: # %bb.0:
; X86-SSE2-NEXT: movdqa %xmm0, %xmm1
; X86-SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X86-SSE2-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm1
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X86-SSE2-NEXT: pand %xmm2, %xmm1
; X86-SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-SSE2-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE2-NEXT: pand %xmm2, %xmm0
; X86-SSE2-NEXT: packuswb %xmm1, %xmm0
; X86-SSE2-NEXT: retl
;
; X64-SSE-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; X64-SSE-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X64-SSE-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X64-SSE-NEXT: pand %xmm2, %xmm0
; X64-SSE-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; X64-SSE-NEXT: pand %xmm2, %xmm1
; X64-SSE-NEXT: packuswb %xmm0, %xmm1
; X64-SSE-NEXT: movdqa %xmm1, %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; X86-SSE4-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X86-SSE4-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X86-SSE4-NEXT: pand %xmm2, %xmm0
; X86-SSE4-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}, %xmm1
; X86-SSE4-NEXT: pand %xmm2, %xmm1
; X86-SSE4-NEXT: packuswb %xmm0, %xmm1
; X86-SSE4-NEXT: movdqa %xmm1, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE2-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: movdqa %xmm0, %xmm1
; X64-SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X64-SSE2-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X64-SSE2-NEXT: pand %xmm2, %xmm1
; X64-SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-SSE2-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE2-NEXT: pand %xmm2, %xmm0
; X64-SSE2-NEXT: packuswb %xmm1, %xmm0
; X64-SSE2-NEXT: retq
;
; X64-SSE4-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; X64-SSE4-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; X64-SSE4-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; X64-SSE4-NEXT: pand %xmm2, %xmm0
; X64-SSE4-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; X64-SSE4-NEXT: pand %xmm2, %xmm1
; X64-SSE4-NEXT: packuswb %xmm0, %xmm1
; X64-SSE4-NEXT: movdqa %xmm1, %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v16i8_2_3_9_17_33_65_129_2_3_9_17_33_65_129_2_3:
; X64-XOP: # %bb.0:
@ -972,15 +1091,23 @@ define <2 x i64> @mul_v2i64_7(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_7(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_7:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_7:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pslld $3, %xmm1
; SSE2-NEXT: psubd %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_7:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_7:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_7:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i32_7:
; X64-XOP: # %bb.0:
@ -1095,15 +1222,22 @@ define <2 x i64> @mul_v2i64_neg7(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_neg63(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_neg63:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_neg63:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pslld $6, %xmm1
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_neg63:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_neg63:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_neg63:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i32_neg63:
; X64-XOP: # %bb.0:
@ -1361,11 +1495,24 @@ define <2 x i64> @mul_v2i64_neg_17_65(<2 x i64> %a0) nounwind {
}
define <2 x i64> @mul_v2i64_0_1(<2 x i64> %a0) nounwind {
; SSE-LABEL: mul_v2i64_0_1:
; SSE: # %bb.0:
; SSE-NEXT: xorps %xmm1, %xmm1
; SSE-NEXT: blendps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; SSE-NEXT: ret{{[l|q]}}
; X86-SSE2-LABEL: mul_v2i64_0_1:
; X86-SSE2: # %bb.0:
; X86-SSE2-NEXT: xorpd %xmm1, %xmm1
; X86-SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; X86-SSE2-NEXT: retl
;
; SSE4-LABEL: mul_v2i64_0_1:
; SSE4: # %bb.0:
; SSE4-NEXT: xorps %xmm1, %xmm1
; SSE4-NEXT: blendps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-SSE2-LABEL: mul_v2i64_0_1:
; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: xorps %xmm1, %xmm1
; X64-SSE2-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; X64-SSE2-NEXT: movaps %xmm1, %xmm0
; X64-SSE2-NEXT: retq
;
; X64-AVX-LABEL: mul_v2i64_0_1:
; X64-AVX: # %bb.0:
@ -1501,15 +1648,27 @@ define <2 x i64> @mul_v2i64_15_neg_63(<2 x i64> %a0) nounwind {
}
define <4 x i32> @mul_v4i32_0_15_31_7(<4 x i32> %a0) nounwind {
; X86-SSE-LABEL: mul_v4i32_0_15_31_7:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE-NEXT: retl
; SSE2-LABEL: mul_v4i32_0_15_31_7:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,15,31,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: ret{{[l|q]}}
;
; X64-SSE-LABEL: mul_v4i32_0_15_31_7:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i32_0_15_31_7:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE4-LABEL: mul_v4i32_0_15_31_7:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; X64-SSE4-NEXT: retq
;
; X64-AVX-LABEL: mul_v4i32_0_15_31_7:
; X64-AVX: # %bb.0:
@ -1539,19 +1698,33 @@ define <8 x i16> @mul_v8i16_0_1_7_15_31_63_127_255(<8 x i16> %a0) nounwind {
}
define <16 x i8> @mul_v16i8_0_1_3_7_15_31_63_127_0_1_3_7_15_31_63_127(<16 x i8> %a0) nounwind {
; SSE-LABEL: mul_v16i8_0_1_3_7_15_31_63_127_0_1_3_7_15_31_63_127:
; SSE: # %bb.0:
; SSE-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; SSE-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [0,1,3,7,15,31,63,127]
; SSE-NEXT: pmullw %xmm2, %xmm0
; SSE-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm3, %xmm0
; SSE-NEXT: pmullw %xmm2, %xmm1
; SSE-NEXT: pand %xmm3, %xmm1
; SSE-NEXT: packuswb %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: ret{{[l|q]}}
; SSE2-LABEL: mul_v16i8_0_1_3_7_15_31_63_127_0_1_3_7_15_31_63_127:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [0,1,3,7,15,31,63,127]
; SSE2-NEXT: pmullw %xmm2, %xmm1
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm3, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pmullw %xmm2, %xmm0
; SSE2-NEXT: pand %xmm3, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: ret{{[l|q]}}
;
; SSE4-LABEL: mul_v16i8_0_1_3_7_15_31_63_127_0_1_3_7_15_31_63_127:
; SSE4: # %bb.0:
; SSE4-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; SSE4-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE4-NEXT: movdqa {{.*#+}} xmm2 = [0,1,3,7,15,31,63,127]
; SSE4-NEXT: pmullw %xmm2, %xmm0
; SSE4-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE4-NEXT: pand %xmm3, %xmm0
; SSE4-NEXT: pmullw %xmm2, %xmm1
; SSE4-NEXT: pand %xmm3, %xmm1
; SSE4-NEXT: packuswb %xmm0, %xmm1
; SSE4-NEXT: movdqa %xmm1, %xmm0
; SSE4-NEXT: ret{{[l|q]}}
;
; X64-XOP-LABEL: mul_v16i8_0_1_3_7_15_31_63_127_0_1_3_7_15_31_63_127:
; X64-XOP: # %bb.0:
@ -1693,21 +1866,43 @@ define <2 x i64> @mul_v2i64_60_120(<2 x i64> %x) nounwind {
; multiply inputs is loop invariant.
; FIXME: We should be able to insert an AssertZExt for this.
define <2 x i64> @mul_v2i64_zext_cross_bb(<2 x i32>* %in, <2 x i32>* %y) {
; X86-SSE-LABEL: mul_v2i64_zext_cross_bb:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmuludq %xmm1, %xmm0
; X86-SSE-NEXT: retl
; X86-SSE2-LABEL: mul_v2i64_zext_cross_bb:
; X86-SSE2: # %bb.0:
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X86-SSE2-NEXT: pxor %xmm1, %xmm1
; X86-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X86-SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0,0,1,1]
; X86-SSE2-NEXT: pmuludq %xmm1, %xmm0
; X86-SSE2-NEXT: retl
;
; X64-SSE-LABEL: mul_v2i64_zext_cross_bb:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmuludq %xmm1, %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v2i64_zext_cross_bb:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE4-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmuludq %xmm1, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE2-LABEL: mul_v2i64_zext_cross_bb:
; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X64-SSE2-NEXT: pxor %xmm1, %xmm1
; X64-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X64-SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
; X64-SSE2-NEXT: pmuludq %xmm1, %xmm0
; X64-SSE2-NEXT: retq
;
; X64-SSE4-LABEL: mul_v2i64_zext_cross_bb:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmuludq %xmm1, %xmm0
; X64-SSE4-NEXT: retq
;
; X64-AVX-LABEL: mul_v2i64_zext_cross_bb:
; X64-AVX: # %bb.0:
@ -1727,27 +1922,57 @@ foo:
}
define <4 x i64> @mul_v4i64_zext_cross_bb(<4 x i32>* %in, <4 x i32>* %y) {
; X86-SSE-LABEL: mul_v4i64_zext_cross_bb:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmuludq %xmm2, %xmm1
; X86-SSE-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X86-SSE-NEXT: pmuludq %xmm2, %xmm0
; X86-SSE-NEXT: retl
; X86-SSE2-LABEL: mul_v4i64_zext_cross_bb:
; X86-SSE2: # %bb.0:
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE2-NEXT: movdqa (%ecx), %xmm0
; X86-SSE2-NEXT: pxor %xmm2, %xmm2
; X86-SSE2-NEXT: movdqa %xmm0, %xmm1
; X86-SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X86-SSE2-NEXT: movdqa (%eax), %xmm2
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[2,1,3,3]
; X86-SSE2-NEXT: pmuludq %xmm3, %xmm1
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,1,1,3]
; X86-SSE2-NEXT: pmuludq %xmm2, %xmm0
; X86-SSE2-NEXT: retl
;
; X64-SSE-LABEL: mul_v4i64_zext_cross_bb:
; X64-SSE: # %bb.0:
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmuludq %xmm2, %xmm1
; X64-SSE-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X64-SSE-NEXT: pmuludq %xmm2, %xmm0
; X64-SSE-NEXT: retq
; X86-SSE4-LABEL: mul_v4i64_zext_cross_bb:
; X86-SSE4: # %bb.0:
; X86-SSE4-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE4-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmuludq %xmm2, %xmm1
; X86-SSE4-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X86-SSE4-NEXT: pmuludq %xmm2, %xmm0
; X86-SSE4-NEXT: retl
;
; X64-SSE2-LABEL: mul_v4i64_zext_cross_bb:
; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: movdqa (%rdi), %xmm0
; X64-SSE2-NEXT: pxor %xmm2, %xmm2
; X64-SSE2-NEXT: movdqa %xmm0, %xmm1
; X64-SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X64-SSE2-NEXT: movdqa (%rsi), %xmm2
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[2,1,3,3]
; X64-SSE2-NEXT: pmuludq %xmm3, %xmm1
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,1,1,3]
; X64-SSE2-NEXT: pmuludq %xmm2, %xmm0
; X64-SSE2-NEXT: retq
;
; X64-SSE4-LABEL: mul_v4i64_zext_cross_bb:
; X64-SSE4: # %bb.0:
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm1 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm0 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmuludq %xmm2, %xmm1
; X64-SSE4-NEXT: pmovzxdq {{.*#+}} xmm2 = mem[0],zero,mem[1],zero
; X64-SSE4-NEXT: pmuludq %xmm2, %xmm0
; X64-SSE4-NEXT: retq
;
; X64-XOP-LABEL: mul_v4i64_zext_cross_bb:
; X64-XOP: # %bb.0: