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

[InstCombine] use m_APInt to allow icmp (shl X, Y), C folds for splat constant vectors, part 4 

This concludes the fixes for icmp+shl in this series:
https://reviews.llvm.org/rL279339
https://reviews.llvm.org/rL279398
https://reviews.llvm.org/rL279399

llvm-svn: 279401
This commit is contained in:
Sanjay Patel 2016-08-21 17:10:07 +00:00
parent 163a5ab799
commit 643d21a62c
2 changed files with 12 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
View File

@ -2042,23 +2042,20 @@ Instruction *InstCombiner::foldICmpShlConstant(ICmpInst &Cmp, Instruction *Shl,
And, Constant::getNullValue(And->getType()));
}
// FIXME: This check restricts all folds under here to scalar types.
ConstantInt *RHS = dyn_cast<ConstantInt>(Cmp.getOperand(1));
if (!RHS)
return nullptr;
// Transform (icmp pred iM (shl iM %v, N), CI)
// -> (icmp pred i(M-N) (trunc %v iM to i(M-N)), (trunc (CI>>N))
// Transform the shl to a trunc if (trunc (CI>>N)) has no loss and M-N.
// This enables to get rid of the shift in favor of a trunc which can be
// Transform (icmp pred iM (shl iM %v, N), C)
// -> (icmp pred i(M-N) (trunc %v iM to i(M-N)), (trunc (C>>N))
// Transform the shl to a trunc if (trunc (C>>N)) has no loss and M-N.
// This enables us to get rid of the shift in favor of a trunc which can be
// free on the target. It has the additional benefit of comparing to a
// smaller constant, which will be target friendly.
unsigned Amt = ShiftAmt->getLimitedValue(TypeBits - 1);
if (Shl->hasOneUse() && Amt != 0 && C->countTrailingZeros() >= Amt) {
Type *NTy = IntegerType::get(Cmp.getContext(), TypeBits - Amt);
Constant *NCI = ConstantExpr::getTrunc(
ConstantExpr::getAShr(RHS, ConstantInt::get(RHS->getType(), Amt)), NTy);
return new ICmpInst(Pred, Builder->CreateTrunc(X, NTy), NCI);
Type *TruncTy = IntegerType::get(Cmp.getContext(), TypeBits - Amt);
if (X->getType()->isVectorTy())
TruncTy = VectorType::get(TruncTy, X->getType()->getVectorNumElements());
Constant *NewC =
ConstantInt::get(TruncTy, C->ashr(*ShiftAmt).trunc(TypeBits - Amt));
return new ICmpInst(Pred, Builder->CreateTrunc(X, TruncTy), NewC);
}
return nullptr;

5
llvm/test/Transforms/InstCombine/icmp.ll
View File

@ -1105,11 +1105,10 @@ define i1 @icmp_shl16(i32 %x) {
ret i1 %cmp
}
; FIXME: Vectors should fold the same way.
define <2 x i1> @icmp_shl16_vec(<2 x i32> %x) {
; CHECK-LABEL: @icmp_shl16_vec(
; CHECK-NEXT: [[SHL:%.*]] = shl <2 x i32> %x, <i32 16, i32 16>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i32> [[SHL]], <i32 2359296, i32 2359296>
; CHECK-NEXT: [[TMP1:%.*]] = trunc <2 x i32> %x to <2 x i16>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i16> [[TMP1]], <i16 36, i16 36>
; CHECK-NEXT: ret <2 x i1> [[CMP]]
;
%shl = shl <2 x i32> %x, <i32 16, i32 16>