[InstCombine] Transform A & (L - 1) u< L --> L != 0

Summary:
This transform is never a pessimization at the IR level (since it
replaces an `icmp` with another), and has potentiall payoffs:

 1. It may make the `icmp` fold away or become loop invariant.
 2. It may make the `A & (L - 1)` computation dead.

This shows up in Java, in range checks generated by array accesses of
the form `a[i & (a.length - 1)]`.

Reviewers: reames, majnemer

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D12210

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245635 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjoy Das 2015-08-20 22:31:55 +00:00
parent 9cd73adba0
commit ba38902605
2 changed files with 33 additions and 0 deletions

View File

@ -3490,6 +3490,19 @@ Instruction *InstCombiner::visitICmpInst(ICmpInst &I) {
}
}
}
if (BO0) {
// Transform A & (L - 1) `ult` L --> L != 0
Value *L;
auto LSubOne = m_Add(m_Value(L), m_AllOnes());
auto BitwiseAnd =
m_CombineOr(m_And(m_Value(), LSubOne), m_And(LSubOne, m_Value()));
if (match(BO0, BitwiseAnd) && I.getPredicate() == ICmpInst::ICMP_ULT) {
auto *Zero = Constant::getNullValue(BO0->getType());
return new ICmpInst(ICmpInst::ICMP_NE, L, Zero);
}
}
}
{ Value *A, *B;

View File

@ -1603,3 +1603,23 @@ define i32 @f7(i32 %a, i32 %b) {
%s = select i1 %cmp, i32 10000, i32 0
ret i32 %s
}
; CHECK: @f8(
; CHECK-NEXT: [[RESULT:%[a-z0-9]+]] = icmp ne i32 %lim, 0
; CHECK-NEXT: ret i1 [[RESULT]]
define i1 @f8(i32 %val, i32 %lim) {
%lim.sub = add i32 %lim, -1
%val.and = and i32 %val, %lim.sub
%r = icmp ult i32 %val.and, %lim
ret i1 %r
}
; CHECK: @f9(
; CHECK-NEXT: [[RESULT:%[a-z0-9]+]] = icmp ne i32 %lim, 0
; CHECK-NEXT: ret i1 [[RESULT]]
define i1 @f9(i32 %val, i32 %lim) {
%lim.sub = sub i32 %lim, 1
%val.and = and i32 %val, %lim.sub
%r = icmp ult i32 %val.and, %lim
ret i1 %r
}