Re-apply r245635, "[InstCombine] Transform A & (L - 1) u< L --> L != 0"

The original checkin was buggy, this change has a fix.

Original commit message:

[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@245753 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineCompares.cpp b/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 9ce1c3fc41b302126f33943cd0d1610a0c3b8749..905f66a380f9457afb1627679eee6aacb893aadd 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -3490,6 +3490,18 @@ Instruction *InstCombiner::visitICmpInst(ICmpInst &I) {
       }
       }
     }
+
+    if (BO0) {
+      // Transform  A & (L - 1) `ult` L --> L != 0
+      auto LSubOne = m_Add(m_Specific(Op1), 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, Op1, Zero);
+      }
+    }
   }
 
   { Value *A, *B;

diff --git a/test/Transforms/InstCombine/icmp.ll b/test/Transforms/InstCombine/icmp.ll
index edcf76d5a7d2cbf451f23281d8cd2facc3b03614..5d97411625ebf6a8d587ac5e58d9780ef53fa01a 100644 (file)
--- a/test/Transforms/InstCombine/icmp.ll
+++ b/test/Transforms/InstCombine/icmp.ll
@@ -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
+}