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

[X86][SSE] Attempt to convert SSE shift-by-var to shift-by-imm. 

Prep work for PR40203

llvm-svn: 356249
This commit is contained in:
Simon Pilgrim 2019-03-15 11:05:42 +00:00
parent 8b0a15b0ef
commit 0ad17402a9
3 changed files with 35 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -36527,11 +36527,22 @@ static SDValue combineVectorShiftVar(SDNode *N, SelectionDAG &DAG,
X86ISD::VSRL == N->getOpcode()) &&
"Unexpected shift opcode");
EVT VT = N->getValueType(0);
SDValue N0 = N->getOperand(0);
SDValue N1 = N->getOperand(1);
// Shift zero -> zero.
if (ISD::isBuildVectorAllZeros(N->getOperand(0).getNode()))
if (ISD::isBuildVectorAllZeros(N0.getNode()))
return DAG.getConstant(0, SDLoc(N), VT);
// Detect constant shift amounts.
APInt UndefElts;
SmallVector<APInt, 32> EltBits;
if (getTargetConstantBitsFromNode(N1, 64, UndefElts, EltBits, true, false)) {
unsigned X86Opc = getTargetVShiftUniformOpcode(N->getOpcode(), false);
return getTargetVShiftByConstNode(X86Opc, SDLoc(N), VT.getSimpleVT(), N0,
EltBits[0].getZExtValue(), DAG);
}
APInt KnownUndef, KnownZero;
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
APInt DemandedElts = APInt::getAllOnesValue(VT.getVectorNumElements());

8
llvm/test/CodeGen/X86/vec_shift2.ll
View File

@ -5,16 +5,12 @@
define <2 x i64> @t1(<2 x i64> %b1, <2 x i64> %c) nounwind {
; X32-LABEL: t1:
; X32: # %bb.0:
; X32-NEXT: movl $14, %eax
; X32-NEXT: movd %eax, %xmm1
; X32-NEXT: psrlw %xmm1, %xmm0
; X32-NEXT: psrlw $14, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: t1:
; X64: # %bb.0:
; X64-NEXT: movl $14, %eax
; X64-NEXT: movd %eax, %xmm1
; X64-NEXT: psrlw %xmm1, %xmm0
; X64-NEXT: psrlw $14, %xmm0
; X64-NEXT: retq
%tmp1 = bitcast <2 x i64> %b1 to <8 x i16>
%tmp2 = tail call <8 x i16> @llvm.x86.sse2.psrl.w( <8 x i16> %tmp1, <8 x i16> bitcast (<4 x i32> < i32 14, i32 undef, i32 undef, i32 undef > to <8 x i16>) ) nounwind readnone

51
llvm/test/CodeGen/X86/vector-idiv-v2i32.ll
View File

@ -618,37 +618,28 @@ define void @test_sdiv_pow2_v2i32(<2 x i32>* %x, <2 x i32>* %y) nounwind {
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X86-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-NEXT: psrad $31, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,3,2,3]
; X86-NEXT: movdqa %xmm1, %xmm0
; X86-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X86-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1,1,3]
; X86-NEXT: movdqa {{.*#+}} xmm2 = [31,0,31,0]
; X86-NEXT: movdqa {{.*#+}} xmm3 = [0,2147483648,0,2147483648]
; X86-NEXT: movdqa %xmm3, %xmm4
; X86-NEXT: psrlq %xmm2, %xmm4
; X86-NEXT: movl $31, %ecx
; X86-NEXT: movd %ecx, %xmm5
; X86-NEXT: psrlq %xmm5, %xmm3
; X86-NEXT: movsd {{.*#+}} xmm3 = xmm4[0],xmm3[1]
; X86-NEXT: movdqa %xmm0, %xmm4
; X86-NEXT: psrlq %xmm2, %xmm4
; X86-NEXT: psrlq %xmm5, %xmm0
; X86-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; X86-NEXT: xorpd %xmm3, %xmm0
; X86-NEXT: psubq %xmm3, %xmm0
; X86-NEXT: pand {{\.LCPI.*}}, %xmm0
; X86-NEXT: psrlq $29, %xmm0
; X86-NEXT: paddq %xmm1, %xmm0
; X86-NEXT: psllq $32, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,3,2,3]
; X86-NEXT: psrad $31, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; X86-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X86-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; X86-NEXT: psrlq $3, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
; X86-NEXT: psrad $31, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X86-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X86-NEXT: psrlq $31, %xmm2
; X86-NEXT: movsd {{.*#+}} xmm2 = xmm2[0,1]
; X86-NEXT: movapd {{.*#+}} xmm1 = [2.1219957909652723E-314,2.1219957909652723E-314]
; X86-NEXT: xorpd %xmm1, %xmm2
; X86-NEXT: psubq %xmm1, %xmm2
; X86-NEXT: pand {{\.LCPI.*}}, %xmm2
; X86-NEXT: psrlq $29, %xmm2
; X86-NEXT: paddq %xmm0, %xmm2
; X86-NEXT: psllq $32, %xmm2
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,3,2,3]
; X86-NEXT: psrad $31, %xmm2
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; X86-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-NEXT: psrlq $3, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X86-NEXT: movq %xmm0, (%eax)
; X86-NEXT: retl
;