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

[DagCombiner] Generalized BuildVector Vector Concatenation 

The CONCAT_VECTORS combiner pass can transform the concat of two BUILD_VECTOR nodes into a single BUILD_VECTOR node.

This patch generalises this to support any number of BUILD_VECTOR nodes, and also permits UNDEF nodes to be included as well.

This was noticed as AVX vec128 -> vec256 canonicalization sometimes creates a CONCAT_VECTOR with a real vec128 lower and an vec128 UNDEF upper.

Differential Revision: http://reviews.llvm.org/D7816

llvm-svn: 230177
This commit is contained in:
Simon Pilgrim 2015-02-22 18:17:28 +00:00
parent e2dd84e42f
commit 4e30d9b6d8
2 changed files with 48 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -11430,36 +11430,51 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
}
}
// Fold any combination of BUILD_VECTOR or UNDEF nodes into one BUILD_VECTOR.
// We have already tested above for an UNDEF only concatenation.
// fold (concat_vectors (BUILD_VECTOR A, B, ...), (BUILD_VECTOR C, D, ...))
// -> (BUILD_VECTOR A, B, ..., C, D, ...)
if (N->getNumOperands() == 2 &&
N->getOperand(0).getOpcode() == ISD::BUILD_VECTOR &&
N->getOperand(1).getOpcode() == ISD::BUILD_VECTOR) {
EVT VT = N->getValueType(0);
SDValue N0 = N->getOperand(0);
SDValue N1 = N->getOperand(1);
auto IsBuildVectorOrUndef = [](const SDValue &Op) {
return ISD::UNDEF == Op.getOpcode() || ISD::BUILD_VECTOR == Op.getOpcode();
};
bool AllBuildVectorsOrUndefs =
std::all_of(N->op_begin(), N->op_end(), IsBuildVectorOrUndef);
if (AllBuildVectorsOrUndefs) {
SmallVector<SDValue, 8> Opnds;
unsigned BuildVecNumElts = N0.getNumOperands();
EVT SVT = VT.getScalarType();
EVT SclTy0 = N0.getOperand(0)->getValueType(0);
EVT SclTy1 = N1.getOperand(0)->getValueType(0);
if (SclTy0.isFloatingPoint()) {
for (unsigned i = 0; i != BuildVecNumElts; ++i)
Opnds.push_back(N0.getOperand(i));
for (unsigned i = 0; i != BuildVecNumElts; ++i)
Opnds.push_back(N1.getOperand(i));
} else {
EVT MinVT = SVT;
if (!SVT.isFloatingPoint())
// If BUILD_VECTOR are from built from integer, they may have different
// operand types. Get the smaller type and truncate all operands to it.
EVT MinTy = SclTy0.bitsLE(SclTy1) ? SclTy0 : SclTy1;
for (unsigned i = 0; i != BuildVecNumElts; ++i)
Opnds.push_back(DAG.getNode(ISD::TRUNCATE, SDLoc(N), MinTy,
N0.getOperand(i)));
for (unsigned i = 0; i != BuildVecNumElts; ++i)
Opnds.push_back(DAG.getNode(ISD::TRUNCATE, SDLoc(N), MinTy,
N1.getOperand(i)));
for (const SDValue &Op : N->ops()) {
EVT OpSVT = Op.getValueType().getScalarType();
MinVT = MinVT.bitsLE(OpSVT) ? MinVT : OpSVT;
}
for (const SDValue &Op : N->ops()) {
EVT OpVT = Op.getValueType();
unsigned NumElts = OpVT.getVectorNumElements();
if (ISD::UNDEF == Op.getOpcode())
for (unsigned i = 0; i != NumElts; ++i)
Opnds.push_back(DAG.getUNDEF(MinVT));
if (ISD::BUILD_VECTOR == Op.getOpcode()) {
if (SVT.isFloatingPoint()) {
assert(SVT == OpVT.getScalarType() && "Concat vector type mismatch");
for (unsigned i = 0; i != NumElts; ++i)
Opnds.push_back(Op.getOperand(i));
} else {
for (unsigned i = 0; i != NumElts; ++i)
Opnds.push_back(
DAG.getNode(ISD::TRUNCATE, SDLoc(N), MinVT, Op.getOperand(i)));
}
}
}
assert(VT.getVectorNumElements() == Opnds.size() &&
"Concat vector type mismatch");
return DAG.getNode(ISD::BUILD_VECTOR, SDLoc(N), VT, Opnds);
}

33
llvm/test/CodeGen/X86/vector-zext.ll
View File

@ -358,22 +358,16 @@ define <8 x i32> @shuf_zext_8i16_to_8i32(<8 x i16> %A) nounwind uwtable readnone
;
; AVX1-LABEL: shuf_zext_8i16_to_8i32:
; AVX1: # BB#0: # %entry
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuf_zext_8i16_to_8i32:
; AVX2: # BB#0: # %entry
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; AVX2-NEXT: vpunpcklwd{{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
; AVX2-NEXT: # kill
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: retq
entry:
%B = shufflevector <8 x i16> %A, <8 x i16> zeroinitializer, <16 x i32> <i32 0, i32 8, i32 1, i32 8, i32 2, i32 8, i32 3, i32 8, i32 4, i32 8, i32 5, i32 8, i32 6, i32 8, i32 7, i32 8>
@ -410,22 +404,17 @@ define <4 x i64> @shuf_zext_4i32_to_4i64(<4 x i32> %A) nounwind uwtable readnone
;
; AVX1-LABEL: shuf_zext_4i32_to_4i64:
; AVX1: # BB#0: # %entry
; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm0[0,1],xmm1[0,0]
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
; AVX1-NEXT: vblendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,0,3,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero
; AVX1-NEXT: vxorpd %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vblendpd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,0,3,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuf_zext_4i32_to_4i64:
; AVX2: # BB#0: # %entry
; AVX2-NEXT: # kill
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX2-NEXT: xorl %eax, %eax
; AVX2-NEXT: vmovd %eax, %xmm1
; AVX2-NEXT: vpbroadcastd %xmm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX2-NEXT: retq
entry:
%B = shufflevector <4 x i32> %A, <4 x i32> zeroinitializer, <8 x i32> <i32 0, i32 4, i32 1, i32 4, i32 2, i32 4, i32 3, i32 4>