maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] In LowerEXTEND_VECTOR_INREG, emit a vector shuffle instead of directly using X86ISD::UNPCKL 

The majority of the changes are because the rest of shuffle lowering/combining prefers to replace the undef input with the other operand. Using UNPCKL directly seemed to avoid this and just grabbed a randomish register for the undef which can create false dependencies.

llvm-svn: 346050
This commit is contained in:
Craig Topper 2018-11-02 22:48:02 +00:00
parent 50bc1ed290
commit f7108aef14
4 changed files with 134 additions and 140 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -19820,7 +19820,7 @@ static SDValue LowerEXTEND_VECTOR_INREG(SDValue Op,
// As SRAI is only available on i16/i32 types, we expand only up to i32
// and handle i64 separately.
while (CurrVT != VT && CurrVT.getVectorElementType() != MVT::i32) {
Curr = DAG.getNode(X86ISD::UNPCKL, dl, CurrVT, DAG.getUNDEF(CurrVT), Curr);
Curr = getUnpackl(DAG, dl, CurrVT, DAG.getUNDEF(CurrVT), Curr);
MVT CurrSVT = MVT::getIntegerVT(CurrVT.getScalarSizeInBits() * 2);
CurrVT = MVT::getVectorVT(CurrSVT, CurrVT.getVectorNumElements() / 2);
Curr = DAG.getBitcast(CurrVT, Curr);

36
llvm/test/CodeGen/X86/madd.ll
View File

@ -954,38 +954,38 @@ define i32 @_Z9test_charPcS_i_1024(i8* nocapture readonly, i8* nocapture readonl
; SSE2-NEXT: .p2align 4, 0x90
; SSE2-NEXT: .LBB7_1: # %vector.body
; SSE2-NEXT: # =>This Inner Loop Header: Depth=1
; SSE2-NEXT: movq {{.*#+}} xmm5 = mem[0],zero
; 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: movq {{.*#+}} xmm6 = mem[0],zero
; 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: movq {{.*#+}} xmm7 = mem[0],zero
; 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: movq {{.*#+}} xmm0 = mem[0],zero
; 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: movq {{.*#+}} xmm2 = mem[0],zero
; 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: pmaddwd %xmm5, %xmm2
; SSE2-NEXT: paddd %xmm2, %xmm9
; SSE2-NEXT: movq {{.*#+}} xmm2 = mem[0],zero
; 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: pmaddwd %xmm6, %xmm2
; SSE2-NEXT: paddd %xmm2, %xmm4
; SSE2-NEXT: movq {{.*#+}} xmm6 = mem[0],zero
; 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: movq {{.*#+}} xmm5 = mem[0],zero
; 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: movq {{.*#+}} xmm2 = mem[0],zero
; 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: pmaddwd %xmm7, %xmm2
; SSE2-NEXT: paddd %xmm2, %xmm1
; SSE2-NEXT: paddd %xmm2, %xmm9
; SSE2-NEXT: movq {{.*#+}} xmm2 = mem[0],zero
; 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: pmaddwd %xmm0, %xmm2
; SSE2-NEXT: paddd %xmm2, %xmm3
; SSE2-NEXT: paddd %xmm2, %xmm4
; SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; 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: pmaddwd %xmm6, %xmm0
; SSE2-NEXT: paddd %xmm0, %xmm1
; SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; 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: pmaddwd %xmm5, %xmm0
; SSE2-NEXT: paddd %xmm0, %xmm3
; SSE2-NEXT: addq $32, %rcx
; SSE2-NEXT: cmpq %rcx, %rax
; SSE2-NEXT: jne .LBB7_1

16
llvm/test/CodeGen/X86/vec_int_to_fp.ll
View File

@ -1726,13 +1726,11 @@ define <8 x float> @sitofp_8i16_to_8f32(<8 x i16> %a) {
define <8 x float> @sitofp_8i8_to_8f32(<16 x i8> %a) {
; SSE2-LABEL: sitofp_8i8_to_8f32:
; SSE2: # %bb.0:
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: psrad $24, %xmm1
; SSE2-NEXT: cvtdq2ps %xmm1, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; SSE2-NEXT: psrad $24, %xmm0
; SSE2-NEXT: cvtdq2ps %xmm0, %xmm1
; SSE2-NEXT: movaps %xmm2, %xmm0
@ -1776,13 +1774,11 @@ define <8 x float> @sitofp_8i8_to_8f32(<16 x i8> %a) {
define <8 x float> @sitofp_16i8_to_8f32(<16 x i8> %a) {
; SSE2-LABEL: sitofp_16i8_to_8f32:
; SSE2: # %bb.0:
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: psrad $24, %xmm1
; SSE2-NEXT: cvtdq2ps %xmm1, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; SSE2-NEXT: psrad $24, %xmm0
; SSE2-NEXT: cvtdq2ps %xmm0, %xmm1
; SSE2-NEXT: movaps %xmm2, %xmm0

220
llvm/test/CodeGen/X86/vector-sext.ll
View File

@ -46,20 +46,20 @@ entry:
define <16 x i16> @sext_16i8_to_16i16(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_16i8_to_16i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: psraw $8, %xmm2
; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
; SSE2-NEXT: movdqa %xmm0, %xmm1
; 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: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: psraw $8, %xmm1
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: sext_16i8_to_16i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSSE3-NEXT: psraw $8, %xmm2
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: psraw $8, %xmm0
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSSE3-NEXT: psraw $8, %xmm1
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_16i8_to_16i16:
@ -103,30 +103,32 @@ entry:
define <32 x i16> @sext_32i8_to_32i16(<32 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_32i8_to_32i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSE2-NEXT: psraw $8, %xmm4
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm0[8],xmm5[9],xmm0[9],xmm5[10],xmm0[10],xmm5[11],xmm0[11],xmm5[12],xmm0[12],xmm5[13],xmm0[13],xmm5[14],xmm0[14],xmm5[15],xmm0[15]
; SSE2-NEXT: psraw $8, %xmm5
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: movdqa %xmm0, %xmm1
; 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: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: psraw $8, %xmm1
; SSE2-NEXT: movdqa %xmm3, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
; SSE2-NEXT: psraw $8, %xmm2
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15]
; 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: movdqa %xmm4, %xmm0
; SSE2-NEXT: movdqa %xmm5, %xmm1
; SSE2-NEXT: retq
;
; SSSE3-LABEL: sext_32i8_to_32i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSSE3-NEXT: psraw $8, %xmm4
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm0[8],xmm5[9],xmm0[9],xmm5[10],xmm0[10],xmm5[11],xmm0[11],xmm5[12],xmm0[12],xmm5[13],xmm0[13],xmm5[14],xmm0[14],xmm5[15],xmm0[15]
; SSSE3-NEXT: psraw $8, %xmm5
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSSE3-NEXT: movdqa %xmm1, %xmm3
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: psraw $8, %xmm0
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSSE3-NEXT: psraw $8, %xmm1
; SSSE3-NEXT: movdqa %xmm3, %xmm2
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
; SSSE3-NEXT: psraw $8, %xmm2
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15]
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSSE3-NEXT: psraw $8, %xmm3
; SSSE3-NEXT: movdqa %xmm4, %xmm0
; SSSE3-NEXT: movdqa %xmm5, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_32i8_to_32i16:
@ -230,24 +232,22 @@ entry:
define <8 x i32> @sext_16i8_to_8i32(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_16i8_to_8i32:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: psrad $24, %xmm1
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: sext_16i8_to_8i32:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSSE3-NEXT: psrad $24, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[u,u,u,4,u,u,u,5,u,u,u,6,u,u,u,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSSE3-NEXT: psrad $24, %xmm2
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSSE3-NEXT: psrad $24, %xmm1
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_16i8_to_8i32:
@ -292,37 +292,34 @@ entry:
define <16 x i32> @sext_16i8_to_16i32(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_16i8_to_16i32:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
; SSE2-NEXT: psrad $24, %xmm4
; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
; SSE2-NEXT: psrad $24, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSE2-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: psrad $24, %xmm3
; SSE2-NEXT: movdqa %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: sext_16i8_to_16i32:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSSE3-NEXT: psrad $24, %xmm0
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm3[8],xmm1[9],xmm3[9],xmm1[10],xmm3[10],xmm1[11],xmm3[11],xmm1[12],xmm3[12],xmm1[13],xmm3[13],xmm1[14],xmm3[14],xmm1[15],xmm3[15]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSSE3-NEXT: psrad $24, %xmm2
; SSSE3-NEXT: movdqa %xmm3, %xmm1
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[u,u,u,4,u,u,u,5,u,u,u,6,u,u,u,7]
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
; SSSE3-NEXT: psrad $24, %xmm4
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
; SSSE3-NEXT: psrad $24, %xmm1
; SSSE3-NEXT: pshufb {{.*#+}} xmm3 = xmm3[u,u,u,12,u,u,u,13,u,u,u,14,u,u,u,15]
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSSE3-NEXT: psrad $24, %xmm2
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSSE3-NEXT: psrad $24, %xmm3
; SSSE3-NEXT: movdqa %xmm4, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_16i8_to_16i32:
@ -424,14 +421,13 @@ entry:
define <4 x i64> @sext_16i8_to_4i64(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_16i8_to_4i64:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm2, %xmm1
; SSE2-NEXT: psrad $31, %xmm1
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: psrld $16, %xmm0
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: psrad $31, %xmm0
@ -442,18 +438,19 @@ define <4 x i64> @sext_16i8_to_4i64(<16 x i8> %A) nounwind uwtable readnone ssp
;
; SSSE3-LABEL: sext_16i8_to_4i64:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: psrad $31, %xmm2
; SSSE3-NEXT: psrad $24, %xmm0
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[u,u,u,2,u,u,u,3,u,u,u,u,u,u,u,u]
; SSSE3-NEXT: movdqa %xmm1, %xmm2
; SSSE3-NEXT: psrad $31, %xmm2
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm2, %xmm1
; SSSE3-NEXT: psrad $31, %xmm1
; SSSE3-NEXT: psrad $24, %xmm2
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: psrad $31, %xmm0
; SSSE3-NEXT: psrad $24, %xmm1
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_16i8_to_4i64:
@ -498,63 +495,62 @@ entry:
define <8 x i64> @sext_16i8_to_8i64(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: sext_16i8_to_8i64:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: psrad $31, %xmm2
; SSE2-NEXT: psrad $24, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
; SSE2-NEXT: psrld $16, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; 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: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm4, %xmm1
; SSE2-NEXT: psrad $31, %xmm1
; SSE2-NEXT: psrad $24, %xmm4
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: psrad $31, %xmm0
; SSE2-NEXT: psrad $24, %xmm1
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3]
; SSE2-NEXT: movdqa %xmm2, %xmm4
; SSE2-NEXT: psrad $31, %xmm4
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE2-NEXT: psrld $16, %xmm3
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3]
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: psrad $31, %xmm4
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: psrad $31, %xmm0
; SSE2-NEXT: psrad $24, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm3, %xmm0
; SSE2-NEXT: psrad $31, %xmm0
; SSE2-NEXT: psrad $24, %xmm3
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
; SSE2-NEXT: movdqa %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: sext_16i8_to_8i64:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <u,u,u,2,u,u,u,3,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm4, %xmm1
; SSSE3-NEXT: psrad $31, %xmm1
; SSSE3-NEXT: psrad $24, %xmm4
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: psrad $31, %xmm0
; SSSE3-NEXT: psrad $24, %xmm1
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; SSSE3-NEXT: movdqa %xmm0, %xmm4
; SSSE3-NEXT: psrad $31, %xmm4
; SSSE3-NEXT: psrad $24, %xmm0
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSSE3-NEXT: pshufb %xmm2, %xmm3
; SSSE3-NEXT: movdqa %xmm3, %xmm2
; SSSE3-NEXT: psrad $31, %xmm2
; SSSE3-NEXT: psrad $24, %xmm3
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; SSSE3-NEXT: movdqa %xmm2, %xmm4
; SSSE3-NEXT: psrad $31, %xmm4
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: psrad $31, %xmm0
; SSSE3-NEXT: psrad $24, %xmm2
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm3, %xmm0
; SSSE3-NEXT: psrad $31, %xmm0
; SSSE3-NEXT: psrad $24, %xmm3
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
; SSSE3-NEXT: movdqa %xmm4, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: sext_16i8_to_8i64:
@ -1291,7 +1287,8 @@ define <2 x i64> @load_sext_2i8_to_2i64(<2 x i8> *%ptr) {
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movzwl (%rdi), %eax
; SSSE3-NEXT: movd %eax, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[u,u,u,0,u,u,u,1,u,u,u,u,u,u,u,u]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: psrad $31, %xmm1
; SSSE3-NEXT: psrad $24, %xmm0
@ -5064,7 +5061,8 @@ define <2 x i32> @sext_2i8_to_2i32(<2 x i8>* %addr) {
; SSSE3: # %bb.0:
; SSSE3-NEXT: movzwl (%rdi), %eax
; SSSE3-NEXT: movd %eax, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[u,u,u,0,u,u,u,1,u,u,u,u,u,u,u,u]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSSE3-NEXT: psrad $24, %xmm0
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; SSSE3-NEXT: paddq %xmm0, %xmm0