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

[X86][SSE] Simplify vector LOAD + EXTEND on pre-SSE41 hardware 

Improve vector extension of vectors on hardware without dedicated VSEXT/VZEXT instructions.

We already convert these to SIGN_EXTEND_VECTOR_INREG/ZERO_EXTEND_VECTOR_INREG but can further improve this by using the legalizer instead of prematurely splitting into legal vectors in the combine as this only properly helps for lowering to VSEXT/VZEXT.

Removes a lot of unnecessary any_extend + mask pattern - (Fix for PR25718).

Differential Revision: http://reviews.llvm.org/D17932

llvm-svn: 263303
This commit is contained in:
Simon Pilgrim 2016-03-11 22:18:05 +00:00
parent be50836514
commit 33d57c7547
4 changed files with 90 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
View File

@ -653,6 +653,7 @@ private:
void SplitVecRes_UnaryOp(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_ExtendOp(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_InregOp(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_ExtVecInRegOp(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_BITCAST(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_BUILD_VECTOR(SDNode *N, SDValue &Lo, SDValue &Hi);

39
llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
View File

@ -621,6 +621,12 @@ void DAGTypeLegalizer::SplitVectorResult(SDNode *N, unsigned ResNo) {
SplitVecRes_VECTOR_SHUFFLE(cast<ShuffleVectorSDNode>(N), Lo, Hi);
break;
case ISD::ANY_EXTEND_VECTOR_INREG:
case ISD::SIGN_EXTEND_VECTOR_INREG:
case ISD::ZERO_EXTEND_VECTOR_INREG:
SplitVecRes_ExtVecInRegOp(N, Lo, Hi);
break;
case ISD::BITREVERSE:
case ISD::BSWAP:
case ISD::CONVERT_RNDSAT:
@ -917,6 +923,39 @@ void DAGTypeLegalizer::SplitVecRes_InregOp(SDNode *N, SDValue &Lo,
DAG.getValueType(HiVT));
}
void DAGTypeLegalizer::SplitVecRes_ExtVecInRegOp(SDNode *N, SDValue &Lo,
SDValue &Hi) {
unsigned Opcode = N->getOpcode();
SDValue N0 = N->getOperand(0);
SDLoc dl(N);
SDValue InLo, InHi;
GetSplitVector(N0, InLo, InHi);
EVT InLoVT = InLo.getValueType();
unsigned InNumElements = InLoVT.getVectorNumElements();
EVT OutLoVT, OutHiVT;
std::tie(OutLoVT, OutHiVT) = DAG.GetSplitDestVTs(N->getValueType(0));
unsigned OutNumElements = OutLoVT.getVectorNumElements();
assert((2 * OutNumElements) <= InNumElements &&
"Illegal extend vector in reg split");
// *_EXTEND_VECTOR_INREG instructions extend the lowest elements of the
// input vector (i.e. we only use InLo):
// OutLo will extend the first OutNumElements from InLo.
// OutHi will extend the next OutNumElements from InLo.
// Shuffle the elements from InLo for OutHi into the bottom elements to
// create a 'fake' InHi.
SmallVector<int, 8> SplitHi(InNumElements, -1);
for (unsigned i = 0; i != OutNumElements; ++i)
SplitHi[i] = i + OutNumElements;
InHi = DAG.getVectorShuffle(InLoVT, dl, InLo, DAG.getUNDEF(InLoVT), SplitHi);
Lo = DAG.getNode(Opcode, dl, OutLoVT, InLo);
Hi = DAG.getNode(Opcode, dl, OutHiVT, InHi);
}
void DAGTypeLegalizer::SplitVecRes_INSERT_VECTOR_ELT(SDNode *N, SDValue &Lo,
SDValue &Hi) {
SDValue Vec = N->getOperand(0);

4
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -28534,7 +28534,9 @@ static SDValue combineToExtendVectorInReg(SDNode *N, SelectionDAG &DAG,
// If target-size is 128-bits (or 256-bits on AVX2 target), then convert to
// ISD::*_EXTEND_VECTOR_INREG which ensures lowering to X86ISD::V*EXT.
if (VT.is128BitVector() || (VT.is256BitVector() && Subtarget.hasInt256())) {
// Also use this if we don't have SSE41 to allow the legalizer do its job.
if (!Subtarget.hasSSE41() || VT.is128BitVector() ||
(VT.is256BitVector() && Subtarget.hasInt256())) {
SDValue ExOp = ExtendVecSize(DL, N0, VT.getSizeInBits());
return Opcode == ISD::SIGN_EXTEND
? DAG.getSignExtendVectorInReg(ExOp, DL, VT)

99
llvm/test/CodeGen/X86/vector-zext.ll
View File

@ -544,23 +544,20 @@ define <4 x i64> @load_zext_4i8_to_4i64(<4 x i8> *%ptr) {
; SSE2-LABEL: load_zext_4i8_to_4i64:
; SSE2: # BB#0: # %entry
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; 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],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: load_zext_4i8_to_4i64:
; SSSE3: # BB#0: # %entry
; SSSE3-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; 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 {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[4],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[8],zero,zero,zero,zero,zero,zero,zero,xmm1[12],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[2],zero,zero,zero,zero,zero,zero,zero,xmm1[3],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: retq
;
; SSE41-LABEL: load_zext_4i8_to_4i64:
@ -625,22 +622,21 @@ define <8 x i32> @load_zext_8i8_to_8i32(<8 x i8> *%ptr) {
; SSE2-LABEL: load_zext_8i8_to_8i32:
; SSE2: # BB#0: # %entry
; SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; 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: pxor %xmm2, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: load_zext_8i8_to_8i32:
; SSSE3: # BB#0: # %entry
; SSSE3-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; 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: pxor %xmm2, %xmm2
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[6],zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[8],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[14],zero,zero,zero
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: load_zext_8i8_to_8i32:
@ -674,34 +670,33 @@ entry:
define <8 x i64> @load_zext_8i8_to_8i64(<8 x i8> *%ptr) {
; SSE2-LABEL: load_zext_8i8_to_8i64:
; SSE2: # BB#0: # %entry
; SSE2-NEXT: movq {{.*#+}} xmm3 = mem[0],zero
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,1,0,3]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,6,7]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm3[1,1,1,3]
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,5,5,6,7]
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[2,1,2,3]
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,5,5,6,7]
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[3,1,3,3]
; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,5,5,6,7]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm3, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: load_zext_8i8_to_8i64:
; SSSE3: # BB#0: # %entry
; SSSE3-NEXT: movq {{.*#+}} xmm3 = mem[0],zero
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSSE3-NEXT: movdqa %xmm3, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: movdqa %xmm3, %xmm1
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[4],zero,zero,zero,zero,zero,zero,zero,xmm1[6],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [0,128,128,128,128,128,128,128,1,128,128,128,128,128,128,128]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: pshufb %xmm4, %xmm0
; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [2,128,128,128,128,128,128,128,3,128,128,128,128,128,128,128]
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
; SSSE3-NEXT: pshufb %xmm5, %xmm1
; SSSE3-NEXT: movdqa %xmm3, %xmm2
; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = xmm2[8],zero,zero,zero,zero,zero,zero,zero,xmm2[10],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm3 = xmm3[12],zero,zero,zero,zero,zero,zero,zero,xmm3[14],zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb %xmm4, %xmm2
; SSSE3-NEXT: pshufb %xmm5, %xmm3
; SSSE3-NEXT: retq
;
; SSE41-LABEL: load_zext_8i8_to_8i64:
@ -851,21 +846,21 @@ define <4 x i64> @load_zext_4i16_to_4i64(<4 x i16> *%ptr) {
; SSE2-LABEL: load_zext_4i16_to_4i64:
; SSE2: # BB#0: # %entry
; SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [65535,0,0,0,65535,0,0,0]
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: load_zext_4i16_to_4i64:
; SSSE3: # BB#0: # %entry
; SSSE3-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT: pxor %xmm2, %xmm2
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1],zero,zero,zero,zero,zero,zero,xmm0[4,5],zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[8,9],zero,zero,zero,zero,zero,zero,xmm1[12,13],zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: load_zext_4i16_to_4i64: