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

[ARM] Prevent parallel macs for unsigned values 

Both zext and sext are currently allowed during the search for narrow
sequences and sexts operands are later added to the mac candidates.
But operands of muls are also added, without checking whether they're
sext or zext, which means we can generate a signed smlad when we
shouldn't.

Differential Revision: https://reviews.llvm.org/D54790

llvm-svn: 347542
This commit is contained in:
Sam Parker 2018-11-26 10:22:55 +00:00
parent 8cd9d1b5ce
commit 5338f7aae4
4 changed files with 214 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Target/ARM/ARMParallelDSP.cpp
View File

@ -525,26 +525,20 @@ static void MatchParallelMACSequences(Reduction &R,
if (!I)
return false;
Value *MulOp0, *MulOp1;
switch (I->getOpcode()) {
case Instruction::Add:
if (Match(I->getOperand(0)) || (Match(I->getOperand(1))))
return true;
break;
case Instruction::Mul:
if (match (I, (m_Mul(m_Value(MulOp0), m_Value(MulOp1))))) {
case Instruction::Mul: {
Value *MulOp0 = I->getOperand(0);
Value *MulOp1 = I->getOperand(1);
if (isa<SExtInst>(MulOp0) && isa<SExtInst>(MulOp1))
AddMACCandidate(Candidates, I, MulOp0, MulOp1);
return false;
}
break;
return false;
}
case Instruction::SExt:
if (match (I, (m_SExt(m_Mul(m_Value(MulOp0), m_Value(MulOp1)))))) {
Instruction *Mul = cast<Instruction>(I->getOperand(0));
AddMACCandidate(Candidates, Mul, MulOp0, MulOp1);
return false;
}
break;
return Match(I->getOperand(0));
}
return false;
};

80
llvm/test/CodeGen/ARM/smlad0.ll
View File

@ -130,3 +130,83 @@ for.body:
%cmp = icmp slt i32 %add29, %arg
br i1 %cmp, label %for.body, label %for.cond.cleanup
}
define i32 @one_zext(i32 %arg, i32* nocapture readnone %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
; CHECK-LABEL: @one_zext
; CHECK-NOT: call i32 @llvm.arm.smlad
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = zext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = zext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
define i32 @two_zext(i32 %arg, i32* nocapture readnone %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
; CHECK-LABEL: @two_zext
; CHECK-NOT: call i32 @llvm.arm.smlad
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = zext i16 %2 to i32
%conv4 = zext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = zext i16 %3 to i32
%conv8 = zext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}

41
llvm/test/CodeGen/ARM/smlald0.ll
View File

@ -130,3 +130,44 @@ for.body:
%cmp = icmp slt i32 %add29, %arg
br i1 %cmp, label %for.body, label %for.cond.cleanup
}
define i64 @reduction_zext(i32 %arg, i32* nocapture readnone %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
; CHECK-LABEL: @reduction_zext
; CHECK-NOT: call i64 @llvm.arm.smlald
; CHECK-NOT: call i32 @llvm.arm.smlad
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i64 [ 0, %entry ], [ %add11, %for.body ]
ret i64 %mac1.0.lcssa
for.body:
%mac1.026 = phi i64 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i64
%conv4 = zext i16 %0 to i64
%mul = mul nsw i64 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i64
%conv8 = zext i16 %1 to i64
%mul9 = mul nsw i64 %conv7, %conv8
%add10 = add i64 %mul, %mac1.026
%add11 = add i64 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}

86
llvm/test/CodeGen/ARM/smlald2.ll
View File

@ -136,3 +136,89 @@ for.body:
%cmp = icmp slt i32 %add29, %arg
br i1 %cmp, label %for.body, label %for.cond.cleanup
}
define i64 @zext_mul_reduction(i32 %arg, i32* nocapture readnone %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
; CHECK-LABEL: @zext_mul_reduction
; CHECK-NOT: call i64 @llvm.arm.smlald
; CHECK-NOT: call i32 @llvm.arm.smlad
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i64 [ 0, %entry ], [ %add11, %for.body ]
ret i64 %mac1.0.lcssa
for.body:
%mac1.026 = phi i64 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = zext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%sext0 = sext i32 %mul to i64
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = zext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%sext1 = sext i32 %mul9 to i64
%add10 = add i64 %sext0, %mac1.026
%add11 = add i64 %sext1, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
define i64 @zext_add_reduction(i32 %arg, i32* nocapture readnone %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
; CHECK-LABEL: @zext_add_reduction
; CHECK-NOT: call i64 @llvm.arm.smlald
; CHECK-NOT: call i32 @llvm.arm.smlad
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i64 [ 0, %entry ], [ %add11, %for.body ]
ret i64 %mac1.0.lcssa
for.body:
%mac1.026 = phi i64 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%sext0 = zext i32 %mul to i64
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%sext1 = zext i32 %mul9 to i64
%add10 = add i64 %sext0, %mac1.026
%add11 = add i64 %sext1, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}