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:
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);
Res = WidenVecRes_Shift(N);
break;
+ case ISD::ANY_EXTEND_VECTOR_INREG:
+ case ISD::SIGN_EXTEND_VECTOR_INREG:
+ case ISD::ZERO_EXTEND_VECTOR_INREG:
+ Res = WidenVecRes_EXTEND_VECTOR_INREG(N);
+ break;
+
case ISD::ANY_EXTEND:
case ISD::FP_EXTEND:
case ISD::FP_ROUND:
return DAG.getNode(ISD::BUILD_VECTOR, DL, WidenVT, Ops);
}
+SDValue DAGTypeLegalizer::WidenVecRes_EXTEND_VECTOR_INREG(SDNode *N) {
+ unsigned Opcode = N->getOpcode();
+ SDValue InOp = N->getOperand(0);
+ SDLoc DL(N);
+
+ EVT WidenVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
+ EVT WidenSVT = WidenVT.getVectorElementType();
+ unsigned WidenNumElts = WidenVT.getVectorNumElements();
+
+ EVT InVT = InOp.getValueType();
+ EVT InSVT = InVT.getVectorElementType();
+ unsigned InVTNumElts = InVT.getVectorNumElements();
+
+ if (getTypeAction(InVT) == TargetLowering::TypeWidenVector) {
+ InOp = GetWidenedVector(InOp);
+ InVT = InOp.getValueType();
+ if (InVT.getSizeInBits() == WidenVT.getSizeInBits()) {
+ switch (Opcode) {
+ case ISD::ANY_EXTEND_VECTOR_INREG:
+ return DAG.getAnyExtendVectorInReg(InOp, DL, WidenVT);
+ case ISD::SIGN_EXTEND_VECTOR_INREG:
+ return DAG.getSignExtendVectorInReg(InOp, DL, WidenVT);
+ case ISD::ZERO_EXTEND_VECTOR_INREG:
+ return DAG.getZeroExtendVectorInReg(InOp, DL, WidenVT);
+ }
+ }
+ }
+
+ // Unroll, extend the scalars and rebuild the vector.
+ SmallVector<SDValue, 16> Ops;
+ for (unsigned i = 0, e = std::min(InVTNumElts, WidenNumElts); i != e; ++i) {
+ SDValue Val = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, InSVT, InOp,
+ DAG.getConstant(i, DL, TLI.getVectorIdxTy(DAG.getDataLayout())));
+ switch (Opcode) {
+ case ISD::ANY_EXTEND_VECTOR_INREG:
+ Val = DAG.getNode(ISD::ANY_EXTEND, DL, WidenSVT, Val);
+ break;
+ case ISD::SIGN_EXTEND_VECTOR_INREG:
+ Val = DAG.getNode(ISD::SIGN_EXTEND, DL, WidenSVT, Val);
+ break;
+ case ISD::ZERO_EXTEND_VECTOR_INREG:
+ Val = DAG.getNode(ISD::ZERO_EXTEND, DL, WidenSVT, Val);
+ break;
+ default:
+ llvm_unreachable("A *_EXTEND_VECTOR_INREG node was expected");
+ }
+ Ops.push_back(Val);
+ }
+
+ while (Ops.size() != WidenNumElts)
+ Ops.push_back(DAG.getUNDEF(WidenSVT));
+
+ return DAG.getNode(ISD::BUILD_VECTOR, DL, WidenVT, Ops);
+}
+
SDValue DAGTypeLegalizer::WidenVecRes_FCOPYSIGN(SDNode *N) {
// If this is an FCOPYSIGN with same input types, we can treat it as a
// normal (can trap) binary op.
; 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:
; 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:
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:
; 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:
define void @convert_v3i8_to_v3f32(<3 x float>* %dst.addr, <3 x i8>* %src.addr) nounwind {
; X86-SSE2-LABEL: convert_v3i8_to_v3f32:
; X86-SSE2: # BB#0: # %entry
-; X86-SSE2-NEXT: pushl %eax
-; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE2-NEXT: pushl %ebp
+; X86-SSE2-NEXT: movl %esp, %ebp
+; X86-SSE2-NEXT: pushl %esi
+; X86-SSE2-NEXT: andl $-16, %esp
+; X86-SSE2-NEXT: subl $32, %esp
+; X86-SSE2-NEXT: movl 8(%ebp), %eax
+; X86-SSE2-NEXT: movl 12(%ebp), %ecx
; X86-SSE2-NEXT: movzwl (%ecx), %edx
; X86-SSE2-NEXT: movd %edx, %xmm0
; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; X86-SSE2-NEXT: movdqa %xmm0, (%esp)
+; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-SSE2-NEXT: shll $8, %edx
+; X86-SSE2-NEXT: movzbl (%esp), %esi
+; X86-SSE2-NEXT: orl %edx, %esi
+; X86-SSE2-NEXT: pinsrw $0, %esi, %xmm0
; X86-SSE2-NEXT: movzbl 2(%ecx), %ecx
-; X86-SSE2-NEXT: movd %ecx, %xmm1
-; X86-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
-; X86-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
-; X86-SSE2-NEXT: pslld $24, %xmm0
+; X86-SSE2-NEXT: pinsrw $1, %ecx, %xmm0
+; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; X86-SSE2-NEXT: psrad $24, %xmm0
; X86-SSE2-NEXT: cvtdq2ps %xmm0, %xmm0
; X86-SSE2-NEXT: movss %xmm0, (%eax)
; X86-SSE2-NEXT: movss %xmm1, 8(%eax)
; X86-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
; X86-SSE2-NEXT: movss %xmm0, 4(%eax)
-; X86-SSE2-NEXT: popl %eax
+; X86-SSE2-NEXT: leal -4(%ebp), %esp
+; X86-SSE2-NEXT: popl %esi
+; X86-SSE2-NEXT: popl %ebp
; X86-SSE2-NEXT: retl
;
; X86-SSE42-LABEL: convert_v3i8_to_v3f32:
; X64-SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; X64-SSE2-NEXT: movdqa %xmm0, -{{[0-9]+}}(%rsp)
+; X64-SSE2-NEXT: movl -{{[0-9]+}}(%rsp), %eax
+; X64-SSE2-NEXT: shll $8, %eax
+; X64-SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
+; X64-SSE2-NEXT: orl %eax, %ecx
+; X64-SSE2-NEXT: pinsrw $0, %ecx, %xmm0
; X64-SSE2-NEXT: movzbl 2(%rsi), %eax
-; X64-SSE2-NEXT: movd %eax, %xmm1
-; X64-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
-; X64-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
-; X64-SSE2-NEXT: pslld $24, %xmm0
+; X64-SSE2-NEXT: pinsrw $1, %eax, %xmm0
+; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; X64-SSE2-NEXT: psrad $24, %xmm0
; X64-SSE2-NEXT: cvtdq2ps %xmm0, %xmm0
; X64-SSE2-NEXT: movlps %xmm0, (%rdi)
define void @convert_v3i8_to_v3f32(<3 x float>* %dst.addr, <3 x i8>* %src.addr) nounwind {
; X86-SSE2-LABEL: convert_v3i8_to_v3f32:
; X86-SSE2: # BB#0: # %entry
-; X86-SSE2-NEXT: pushl %eax
-; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE2-NEXT: pushl %ebp
+; X86-SSE2-NEXT: movl %esp, %ebp
+; X86-SSE2-NEXT: pushl %esi
+; X86-SSE2-NEXT: andl $-16, %esp
+; X86-SSE2-NEXT: subl $32, %esp
+; X86-SSE2-NEXT: movl 8(%ebp), %eax
+; X86-SSE2-NEXT: movl 12(%ebp), %ecx
; X86-SSE2-NEXT: movzwl (%ecx), %edx
; X86-SSE2-NEXT: movd %edx, %xmm0
; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; X86-SSE2-NEXT: movdqa %xmm0, (%esp)
+; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-SSE2-NEXT: shll $8, %edx
+; X86-SSE2-NEXT: movzbl (%esp), %esi
+; X86-SSE2-NEXT: orl %edx, %esi
+; X86-SSE2-NEXT: pinsrw $0, %esi, %xmm0
; X86-SSE2-NEXT: movzbl 2(%ecx), %ecx
-; X86-SSE2-NEXT: movd %ecx, %xmm1
-; X86-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
-; X86-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
-; X86-SSE2-NEXT: andps .LCPI1_0, %xmm0
+; X86-SSE2-NEXT: pinsrw $1, %ecx, %xmm0
+; X86-SSE2-NEXT: pxor %xmm1, %xmm1
+; X86-SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; X86-SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-SSE2-NEXT: cvtdq2ps %xmm0, %xmm0
; X86-SSE2-NEXT: movss %xmm0, (%eax)
; X86-SSE2-NEXT: movaps %xmm0, %xmm1
; X86-SSE2-NEXT: movss %xmm1, 8(%eax)
; X86-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
; X86-SSE2-NEXT: movss %xmm0, 4(%eax)
-; X86-SSE2-NEXT: popl %eax
+; X86-SSE2-NEXT: leal -4(%ebp), %esp
+; X86-SSE2-NEXT: popl %esi
+; X86-SSE2-NEXT: popl %ebp
; X86-SSE2-NEXT: retl
;
; X86-SSE42-LABEL: convert_v3i8_to_v3f32:
; X64-SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; 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: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; X64-SSE2-NEXT: movdqa %xmm0, -{{[0-9]+}}(%rsp)
+; X64-SSE2-NEXT: movl -{{[0-9]+}}(%rsp), %eax
+; X64-SSE2-NEXT: shll $8, %eax
+; X64-SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
+; X64-SSE2-NEXT: orl %eax, %ecx
+; X64-SSE2-NEXT: pinsrw $0, %ecx, %xmm0
; X64-SSE2-NEXT: movzbl 2(%rsi), %eax
-; X64-SSE2-NEXT: movd %eax, %xmm1
-; X64-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
-; X64-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
-; X64-SSE2-NEXT: andps {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT: pinsrw $1, %eax, %xmm0
+; X64-SSE2-NEXT: pxor %xmm1, %xmm1
+; X64-SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; X64-SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-SSE2-NEXT: cvtdq2ps %xmm0, %xmm0
; X64-SSE2-NEXT: movlps %xmm0, (%rdi)
; X64-SSE2-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1,0]