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

[DAGCombiner][X86] Teach SimplifyVBinOp to fold VBinOp (concat X, undef/constant), (concat Y, undef/constant) -> concat (VBinOp X, Y), VecC 

This improves the combine I included in D66504 to handle constants in the upper operands of the concat. If we can constant fold them away we can pull the concat after the bin op. This helps with chains of madd reductions on X86 from loop unrolling. The loop madd reduction pattern creates pmaddwd with half the width of the add that follows it using zeroes to fill the upper bits. If we have two of these added together we can pull the zeroes through the accumulating add and then shrink it.

Differential Revision: https://reviews.llvm.org/D66680

llvm-svn: 369937
This commit is contained in:
Craig Topper 2019-08-26 17:59:11 +00:00
parent a4a308cc25
commit 846429de74
2 changed files with 40 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -19448,33 +19448,35 @@ SDValue DAGCombiner::SimplifyVBinOp(SDNode *N) {
}
}
// Make sure all but the first op are undef.
auto ConcatWithUndef = [](SDValue Concat) {
// Make sure all but the first op are undef or constant.
auto ConcatWithConstantOrUndef = [](SDValue Concat) {
return Concat.getOpcode() == ISD::CONCAT_VECTORS &&
std::all_of(std::next(Concat->op_begin()), Concat->op_end(),
[](const SDValue &Op) {
return Op.isUndef();
return Op.isUndef() ||
ISD::isBuildVectorOfConstantSDNodes(Op.getNode());
});
};
// The following pattern is likely to emerge with vector reduction ops. Moving
// the binary operation ahead of the concat may allow using a narrower vector
// instruction that has better performance than the wide version of the op:
// VBinOp (concat X, undef), (concat Y, undef) --> concat (VBinOp X, Y), VecC
if (ConcatWithUndef(LHS) && ConcatWithUndef(RHS) &&
// VBinOp (concat X, undef/constant), (concat Y, undef/constant) -->
// concat (VBinOp X, Y), VecC
if (ConcatWithConstantOrUndef(LHS) && ConcatWithConstantOrUndef(RHS) &&
(LHS.hasOneUse() || RHS.hasOneUse())) {
SDValue X = LHS.getOperand(0);
SDValue Y = RHS.getOperand(0);
EVT NarrowVT = X.getValueType();
if (NarrowVT == Y.getValueType() &&
EVT NarrowVT = LHS.getOperand(0).getValueType();
if (NarrowVT == RHS.getOperand(0).getValueType() &&
TLI.isOperationLegalOrCustomOrPromote(Opcode, NarrowVT)) {
// (binop undef, undef) may not return undef, so compute that result.
SDLoc DL(N);
SDValue VecC =
DAG.getNode(Opcode, DL, NarrowVT, DAG.getUNDEF(NarrowVT),
DAG.getUNDEF(NarrowVT));
SmallVector<SDValue, 4> Ops(LHS.getNumOperands(), VecC);
Ops[0] = DAG.getNode(Opcode, DL, NarrowVT, X, Y);
unsigned NumOperands = LHS.getNumOperands();
SmallVector<SDValue, 4> Ops;
for (unsigned i = 0; i != NumOperands; ++i) {
// This constant fold for operands 1 and up.
Ops.push_back(DAG.getNode(Opcode, DL, NarrowVT, LHS.getOperand(i),
RHS.getOperand(i)));
}
return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Ops);
}
}

67
llvm/test/CodeGen/X86/madd.ll
View File

@ -2720,52 +2720,27 @@ define i32 @madd_quad_reduction(<8 x i16>* %arg, <8 x i16>* %arg1, <8 x i16>* %a
; SSE2-NEXT: movd %xmm1, %eax
; SSE2-NEXT: retq
;
; AVX1-LABEL: madd_quad_reduction:
; AVX1: # %bb.0:
; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %r10
; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: vmovdqu (%rdi), %xmm0
; AVX1-NEXT: vmovdqu (%rdx), %xmm1
; AVX1-NEXT: vpmaddwd (%rcx), %xmm1, %xmm1
; AVX1-NEXT: vpmaddwd (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vmovdqu (%r8), %xmm2
; AVX1-NEXT: vpmaddwd (%r9), %xmm2, %xmm2
; AVX1-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vmovdqu (%rax), %xmm2
; AVX1-NEXT: vpmaddwd (%r10), %xmm2, %xmm2
; AVX1-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX1-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX1-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovd %xmm0, %eax
; AVX1-NEXT: retq
;
; AVX256-LABEL: madd_quad_reduction:
; AVX256: # %bb.0:
; AVX256-NEXT: movq {{[0-9]+}}(%rsp), %r10
; AVX256-NEXT: movq {{[0-9]+}}(%rsp), %rax
; AVX256-NEXT: vmovdqu (%rdi), %xmm0
; AVX256-NEXT: vmovdqu (%rdx), %xmm1
; AVX256-NEXT: vpmaddwd (%rcx), %xmm1, %xmm1
; AVX256-NEXT: vpmaddwd (%rsi), %xmm0, %xmm0
; AVX256-NEXT: vmovdqu (%r8), %xmm2
; AVX256-NEXT: vpmaddwd (%r9), %xmm2, %xmm2
; AVX256-NEXT: vpaddd %ymm2, %ymm1, %ymm1
; AVX256-NEXT: vmovdqu (%rax), %xmm2
; AVX256-NEXT: vpmaddwd (%r10), %xmm2, %xmm2
; AVX256-NEXT: vpaddd %ymm2, %ymm1, %ymm1
; AVX256-NEXT: vpaddd %ymm1, %ymm0, %ymm0
; AVX256-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX256-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX256-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX256-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT: vmovd %xmm0, %eax
; AVX256-NEXT: vzeroupper
; AVX256-NEXT: retq
; AVX-LABEL: madd_quad_reduction:
; AVX: # %bb.0:
; AVX-NEXT: movq {{[0-9]+}}(%rsp), %r10
; AVX-NEXT: movq {{[0-9]+}}(%rsp), %rax
; AVX-NEXT: vmovdqu (%rdi), %xmm0
; AVX-NEXT: vmovdqu (%rdx), %xmm1
; AVX-NEXT: vpmaddwd (%rcx), %xmm1, %xmm1
; AVX-NEXT: vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT: vmovdqu (%r8), %xmm2
; AVX-NEXT: vpmaddwd (%r9), %xmm2, %xmm2
; AVX-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX-NEXT: vmovdqu (%rax), %xmm2
; AVX-NEXT: vpmaddwd (%r10), %xmm2, %xmm2
; AVX-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovd %xmm0, %eax
; AVX-NEXT: retq
%tmp = load <8 x i16>, <8 x i16>* %arg, align 1
%tmp6 = load <8 x i16>, <8 x i16>* %arg1, align 1
%tmp7 = sext <8 x i16> %tmp to <8 x i32>