RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-02-11 07:15:26 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[SLP] Treat SelectInsts as reduction values.

Browse Source 
Summary:
Certain workloads, in particular sum-of-absdiff loops, can be vectorized using SLP if it can treat select instructions as reduction values.

The test case is a bit awkward. The AArch64 cost model needs some tuning to not be so pessimistic about selects. I've had to tweak the SLP threshold here.

Reviewers: jmolloy, mzolotukhin, spatel, nadav

Subscribers: nadav, mssimpso, aemerson, llvm-commits

Differential Revision: http://reviews.llvm.org/D13949

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251424 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Charlie Turner 2015-10-27 17:49:11 +00:00
parent 2d323d4ed2
commit b13834ec71
2 changed files with 80 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -3714,11 +3714,11 @@ public:
return false;
// Post order traverse the reduction tree starting at B. We only handle true
// trees containing only binary operators.
SmallVector<std::pair<BinaryOperator *, unsigned>, 32> Stack;
// trees containing only binary operators or selects.
SmallVector<std::pair<Instruction *, unsigned>, 32> Stack;
Stack.push_back(std::make_pair(B, 0));
while (!Stack.empty()) {
BinaryOperator *TreeN = Stack.back().first;
Instruction *TreeN = Stack.back().first;
unsigned EdgeToVist = Stack.back().second++;
bool IsReducedValue = TreeN->getOpcode() != ReductionOpcode;
@ -3754,9 +3754,10 @@ public:
// Visit left or right.
Value *NextV = TreeN->getOperand(EdgeToVist);
BinaryOperator *Next = dyn_cast<BinaryOperator>(NextV);
if (Next)
Stack.push_back(std::make_pair(Next, 0));
// We currently only allow BinaryOperator's and SelectInst's as reduction
// values in our tree.
if (isa<BinaryOperator>(NextV) || isa<SelectInst>(NextV))
Stack.push_back(std::make_pair(cast<Instruction>(NextV), 0));
else if (NextV != Phi)
return false;
}

73
test/Transforms/SLPVectorizer/AArch64/horizontal.ll Normal file
View File

@ -0,0 +1,73 @@
; RUN: opt -slp-vectorizer -slp-threshold=-6 -slp-vectorize-hor -S < %s | FileCheck %s
; FIXME: The threshold is changed to keep this test case a bit smaller.
; The AArch64 cost model should not give such high costs to select statements.
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux"
; CHECK-LABEL: test_select
; CHECK: load <4 x i32>
; CHECK: load <4 x i32>
; CHECK: select <4 x i1>
define i32 @test_select(i32* noalias nocapture readonly %blk1, i32* noalias nocapture readonly %blk2, i32 %lx, i32 %h) {
entry:
%cmp.22 = icmp sgt i32 %h, 0
br i1 %cmp.22, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%idx.ext = sext i32 %lx to i64
br label %for.body
for.body: ; preds = %for.body, %for.body.lr.ph
%s.026 = phi i32 [ 0, %for.body.lr.ph ], [ %add27, %for.body ]
%j.025 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
%p2.024 = phi i32* [ %blk2, %for.body.lr.ph ], [ %add.ptr29, %for.body ]
%p1.023 = phi i32* [ %blk1, %for.body.lr.ph ], [ %add.ptr, %for.body ]
%0 = load i32, i32* %p1.023, align 4
%1 = load i32, i32* %p2.024, align 4
%sub = sub nsw i32 %0, %1
%cmp2 = icmp slt i32 %sub, 0
%sub3 = sub nsw i32 0, %sub
%sub3.sub = select i1 %cmp2, i32 %sub3, i32 %sub
%add = add nsw i32 %sub3.sub, %s.026
%arrayidx4 = getelementptr inbounds i32, i32* %p1.023, i64 1
%2 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %p2.024, i64 1
%3 = load i32, i32* %arrayidx5, align 4
%sub6 = sub nsw i32 %2, %3
%cmp7 = icmp slt i32 %sub6, 0
%sub9 = sub nsw i32 0, %sub6
%v.1 = select i1 %cmp7, i32 %sub9, i32 %sub6
%add11 = add nsw i32 %add, %v.1
%arrayidx12 = getelementptr inbounds i32, i32* %p1.023, i64 2
%4 = load i32, i32* %arrayidx12, align 4
%arrayidx13 = getelementptr inbounds i32, i32* %p2.024, i64 2
%5 = load i32, i32* %arrayidx13, align 4
%sub14 = sub nsw i32 %4, %5
%cmp15 = icmp slt i32 %sub14, 0
%sub17 = sub nsw i32 0, %sub14
%sub17.sub14 = select i1 %cmp15, i32 %sub17, i32 %sub14
%add19 = add nsw i32 %add11, %sub17.sub14
%arrayidx20 = getelementptr inbounds i32, i32* %p1.023, i64 3
%6 = load i32, i32* %arrayidx20, align 4
%arrayidx21 = getelementptr inbounds i32, i32* %p2.024, i64 3
%7 = load i32, i32* %arrayidx21, align 4
%sub22 = sub nsw i32 %6, %7
%cmp23 = icmp slt i32 %sub22, 0
%sub25 = sub nsw i32 0, %sub22
%v.3 = select i1 %cmp23, i32 %sub25, i32 %sub22
%add27 = add nsw i32 %add19, %v.3
%add.ptr = getelementptr inbounds i32, i32* %p1.023, i64 %idx.ext
%add.ptr29 = getelementptr inbounds i32, i32* %p2.024, i64 %idx.ext
%inc = add nuw nsw i32 %j.025, 1
%exitcond = icmp eq i32 %inc, %h
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
%s.0.lcssa = phi i32 [ 0, %entry ], [ %add27, %for.end.loopexit ]
ret i32 %s.0.lcssa
}