Generalise the existing SIGN_EXTEND to SIGN_EXTEND_VECTOR_INREG combine to support zero extension as well and get rid of a lot of unnecessary ANY_EXTEND + mask patterns.
Reapplied with a fix for PR26870 (avoid premature use of TargetConstant in ZERO_EXTEND_VECTOR_INREG expansion).
Differential Revision: http://reviews.llvm.org/D17691
llvm-svn: 263159
SDValue visitANY_EXTEND(SDNode *N);
SDValue visitSIGN_EXTEND_INREG(SDNode *N);
SDValue visitSIGN_EXTEND_VECTOR_INREG(SDNode *N);
+ SDValue visitZERO_EXTEND_VECTOR_INREG(SDNode *N);
SDValue visitTRUNCATE(SDNode *N);
SDValue visitBITCAST(SDNode *N);
SDValue visitBUILD_PAIR(SDNode *N);
case ISD::ANY_EXTEND: return visitANY_EXTEND(N);
case ISD::SIGN_EXTEND_INREG: return visitSIGN_EXTEND_INREG(N);
case ISD::SIGN_EXTEND_VECTOR_INREG: return visitSIGN_EXTEND_VECTOR_INREG(N);
+ case ISD::ZERO_EXTEND_VECTOR_INREG: return visitZERO_EXTEND_VECTOR_INREG(N);
case ISD::TRUNCATE: return visitTRUNCATE(N);
case ISD::BITCAST: return visitBITCAST(N);
case ISD::BUILD_PAIR: return visitBUILD_PAIR(N);
EVT VT = N->getValueType(0);
assert((Opcode == ISD::SIGN_EXTEND || Opcode == ISD::ZERO_EXTEND ||
- Opcode == ISD::ANY_EXTEND || Opcode == ISD::SIGN_EXTEND_VECTOR_INREG)
+ Opcode == ISD::ANY_EXTEND || Opcode == ISD::SIGN_EXTEND_VECTOR_INREG ||
+ Opcode == ISD::ZERO_EXTEND_VECTOR_INREG)
&& "Expected EXTEND dag node in input!");
// fold (sext c1) -> c1
return SDValue();
}
+SDValue DAGCombiner::visitZERO_EXTEND_VECTOR_INREG(SDNode *N) {
+ SDValue N0 = N->getOperand(0);
+ EVT VT = N->getValueType(0);
+
+ if (N0.getOpcode() == ISD::UNDEF)
+ return DAG.getUNDEF(VT);
+
+ if (SDNode *Res = tryToFoldExtendOfConstant(N, TLI, DAG, LegalTypes,
+ LegalOperations))
+ return SDValue(Res, 0);
+
+ return SDValue();
+}
+
SDValue DAGCombiner::visitTRUNCATE(SDNode *N) {
SDValue N0 = N->getOperand(0);
EVT VT = N->getValueType(0);
int NumSrcElements = SrcVT.getVectorNumElements();
// Build up a zero vector to blend into this one.
- SDValue Zero = DAG.getTargetConstant(0, DL, SrcVT);
+ SDValue Zero = DAG.getConstant(0, DL, SrcVT);
// Shuffle the incoming lanes into the correct position, and pull all other
// lanes from the zero vector.
return R.getValue(1);
}
-/// Convert a SEXT of a vector to a SIGN_EXTEND_VECTOR_INREG, this requires
-/// the splitting (or concatenating with UNDEFs) of the input to vectors of the
-/// same size as the target type which then extends the lowest elements.
+/// Convert a SEXT or ZEXT of a vector to a SIGN_EXTEND_VECTOR_INREG or
+/// ZERO_EXTEND_VECTOR_INREG, this requires the splitting (or concatenating
+/// with UNDEFs) of the input to vectors of the same size as the target type
+/// which then extends the lowest elements.
static SDValue combineToExtendVectorInReg(SDNode *N, SelectionDAG &DAG,
TargetLowering::DAGCombinerInfo &DCI,
const X86Subtarget &Subtarget) {
- if (N->getOpcode() != ISD::SIGN_EXTEND)
+ unsigned Opcode = N->getOpcode();
+ if (Opcode != ISD::SIGN_EXTEND && Opcode != ISD::ZERO_EXTEND)
return SDValue();
if (!DCI.isBeforeLegalizeOps())
return SDValue();
if (InSVT != MVT::i32 && InSVT != MVT::i16 && InSVT != MVT::i8)
return SDValue();
+ // On AVX2+ targets, if the input/output types are both legal then we will be
+ // able to use SIGN_EXTEND/ZERO_EXTEND directly.
+ if (Subtarget.hasInt256() && DAG.getTargetLoweringInfo().isTypeLegal(VT) &&
+ DAG.getTargetLoweringInfo().isTypeLegal(InVT))
+ return SDValue();
+
SDLoc DL(N);
auto ExtendVecSize = [&DAG](SDLoc DL, SDValue N, unsigned Size) {
EVT ExVT =
EVT::getVectorVT(*DAG.getContext(), SVT, 128 / SVT.getSizeInBits());
SDValue Ex = ExtendVecSize(DL, N0, Scale * InVT.getSizeInBits());
- SDValue SExt = DAG.getNode(ISD::SIGN_EXTEND, DL, ExVT, Ex);
+ SDValue SExt = DAG.getNode(Opcode, DL, ExVT, Ex);
return DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VT, SExt,
DAG.getIntPtrConstant(0, DL));
}
// If target-size is 128-bits (or 256-bits on AVX2 target), then convert to
- // ISD::SIGN_EXTEND_VECTOR_INREG which ensures lowering to X86ISD::VSEXT.
+ // ISD::*_EXTEND_VECTOR_INREG which ensures lowering to X86ISD::V*EXT.
if (VT.is128BitVector() || (VT.is256BitVector() && Subtarget.hasInt256())) {
SDValue ExOp = ExtendVecSize(DL, N0, VT.getSizeInBits());
- return DAG.getSignExtendVectorInReg(ExOp, DL, VT);
+ return Opcode == ISD::SIGN_EXTEND
+ ? DAG.getSignExtendVectorInReg(ExOp, DL, VT)
+ : DAG.getZeroExtendVectorInReg(ExOp, DL, VT);
}
// On pre-AVX2 targets, split into 128-bit nodes of
- // ISD::SIGN_EXTEND_VECTOR_INREG.
+ // ISD::*_EXTEND_VECTOR_INREG.
if (!Subtarget.hasInt256() && !(VT.getSizeInBits() % 128)) {
unsigned NumVecs = VT.getSizeInBits() / 128;
unsigned NumSubElts = 128 / SVT.getSizeInBits();
SDValue SrcVec = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, InSubVT, N0,
DAG.getIntPtrConstant(Offset, DL));
SrcVec = ExtendVecSize(DL, SrcVec, 128);
- SrcVec = DAG.getSignExtendVectorInReg(SrcVec, DL, SubVT);
+ SrcVec = Opcode == ISD::SIGN_EXTEND
+ ? DAG.getSignExtendVectorInReg(SrcVec, DL, SubVT)
+ : DAG.getZeroExtendVectorInReg(SrcVec, DL, SubVT);
Opnds.push_back(SrcVec);
}
return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Opnds);
}
}
+ if (SDValue V = combineToExtendVectorInReg(N, DAG, DCI, Subtarget))
+ return V;
+
if (VT.is256BitVector())
if (SDValue R = WidenMaskArithmetic(N, DAG, DCI, Subtarget))
return R;
--- /dev/null
+; RUN: llc < %s -mtriple=i686-pc-windows-msvc18.0.0 -mcpu=pentium4
+
+define x86_thiscallcc i32* @fn4(i32* %this, i8* dereferenceable(1) %p1) {
+entry:
+ %DL = getelementptr inbounds i32, i32* %this, i32 0
+ %call.i = tail call x86_thiscallcc i64 @fn1(i32* %DL)
+ %getTypeAllocSize___trans_tmp_2.i = getelementptr inbounds i32, i32* %this, i32 0
+ %0 = load i32, i32* %getTypeAllocSize___trans_tmp_2.i, align 4
+ %call.i8 = tail call x86_thiscallcc i64 @fn1(i32* %DL)
+ %1 = insertelement <2 x i64> undef, i64 %call.i, i32 0
+ %2 = insertelement <2 x i64> %1, i64 %call.i8, i32 1
+ %3 = add nsw <2 x i64> %2, <i64 7, i64 7>
+ %4 = sdiv <2 x i64> %3, <i64 8, i64 8>
+ %5 = add nsw <2 x i64> %4, <i64 1, i64 1>
+ %6 = load i32, i32* %getTypeAllocSize___trans_tmp_2.i, align 4
+ %7 = insertelement <2 x i32> undef, i32 %0, i32 0
+ %8 = insertelement <2 x i32> %7, i32 %6, i32 1
+ %9 = zext <2 x i32> %8 to <2 x i64>
+ %10 = srem <2 x i64> %5, %9
+ %11 = sub <2 x i64> %5, %10
+ %12 = trunc <2 x i64> %11 to <2 x i32>
+ %13 = extractelement <2 x i32> %12, i32 0
+ %14 = extractelement <2 x i32> %12, i32 1
+ %cmp = icmp eq i32 %13, %14
+ br i1 %cmp, label %if.then, label %cleanup
+
+if.then:
+ %call4 = tail call x86_thiscallcc i32* @fn3(i8* nonnull %p1)
+ br label %cleanup
+
+cleanup:
+ %retval.0 = phi i32* [ %call4, %if.then ], [ undef, %entry ]
+ ret i32* %retval.0
+}
+
+declare x86_thiscallcc i32* @fn3(i8*)
+declare x86_thiscallcc i64 @fn1(i32*)
;
; AVX1-LABEL: uitofp_16i8_to_4f32:
; AVX1: # BB#0:
-; AVX1-NEXT: vpmovzxbw {{.*#+}} 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
-; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX1-LABEL: uitofp_8i8_to_8f32:
; AVX1: # BB#0:
-; AVX1-NEXT: vpmovzxbw {{.*#+}} 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
-; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: uitofp_8i8_to_8f32:
; AVX2: # BB#0:
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX2-NEXT: retq
%shuf = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
;
; AVX1-LABEL: uitofp_16i8_to_8f32:
; AVX1: # BB#0:
-; AVX1-NEXT: vpmovzxbw {{.*#+}} 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
-; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX1-NEXT: retq
;
;
; AVX1-LABEL: zext_16i8_to_8i32:
; AVX1: # BB#0: # %entry
-; AVX1-NEXT: vpmovzxbw {{.*#+}} 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
-; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: zext_16i8_to_8i32:
; AVX2: # BB#0: # %entry
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: zext_16i8_to_8i32:
; AVX512: # BB#0: # %entry
; AVX512-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX512-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
entry:
%B = shufflevector <16 x i8> %A, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
;
; AVX1-LABEL: zext_16i8_to_4i64:
; AVX1: # BB#0: # %entry
-; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,2,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: zext_16i8_to_4i64:
; AVX2: # BB#0: # %entry
; AVX2-NEXT: vpmovzxbq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero
-; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: zext_16i8_to_4i64:
; AVX512: # BB#0: # %entry
; AVX512-NEXT: vpmovzxbq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero
-; AVX512-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
entry:
%B = shufflevector <16 x i8> %A, <16 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
;
; AVX1-LABEL: zext_8i16_to_4i64:
; AVX1: # BB#0: # %entry
-; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
-; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,2,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: zext_8i16_to_4i64:
; AVX2: # BB#0: # %entry
; AVX2-NEXT: vpmovzxwq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX2-NEXT: vpxor %ymm1, %ymm1, %ymm1
-; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7],ymm0[8],ymm1[9,10,11],ymm0[12],ymm1[13,14,15]
; AVX2-NEXT: retq
;
; AVX512-LABEL: zext_8i16_to_4i64:
; AVX512: # BB#0: # %entry
; AVX512-NEXT: vpmovzxwq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX512-NEXT: vpxor %ymm1, %ymm1, %ymm1
-; AVX512-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7],ymm0[8],ymm1[9,10,11],ymm0[12],ymm1[13,14,15]
; AVX512-NEXT: retq
entry:
%B = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>