InstCombine: When comparing two GEPs that were derived from the same base pointer but use different types, expand the offset calculation and to the compare on the offset if profitable.

This came up in SmallVector code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150962 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 40 insertions, 0 deletions

diff --git a/lib/Transforms/InstCombine/InstCombineCompares.cpp b/lib/Transforms/InstCombine/InstCombineCompares.cpp
index bb7763ddeb..5a91c7b970 100644
--- a/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -607,6 +607,20 @@ Instruction *InstCombiner::FoldGEPICmp(GEPOperator *GEPLHS, Value *RHS,
         return new ICmpInst(ICmpInst::getSignedPredicate(Cond),
                             GEPLHS->getOperand(0), GEPRHS->getOperand(0));
 
+      // If we're comparing GEPs with two base pointers that only differ in type
+      // and both GEPs have only constant indices or just one use, then fold
+      // the compare with the adjusted indices.
+      if (TD &&
+          (GEPLHS->hasAllConstantIndices() || GEPLHS->hasOneUse()) &&
+          (GEPRHS->hasAllConstantIndices() || GEPRHS->hasOneUse()) &&
+          PtrBase->stripPointerCasts() ==
+            GEPRHS->getOperand(0)->stripPointerCasts()) {
+        Value *Cmp = Builder->CreateICmp(ICmpInst::getSignedPredicate(Cond),
+                                         EmitGEPOffset(GEPLHS),
+                                         EmitGEPOffset(GEPRHS));
+        return ReplaceInstUsesWith(I, Cmp);
+      }
+
       // Otherwise, the base pointers are different and the indices are
       // different, bail out.
       return 0;
diff --git a/test/Transforms/InstCombine/icmp.ll b/test/Transforms/InstCombine/icmp.ll
index 1652e71401..09152f0986 100644
--- a/test/Transforms/InstCombine/icmp.ll
+++ b/test/Transforms/InstCombine/icmp.ll
@@ -589,3 +589,29 @@ define void @test58() nounwind {
   ret void
 }
 declare i32 @test58_d(i64)
+
+define i1 @test59(i8* %foo) {
+  %bit = bitcast i8* %foo to i32*
+  %gep1 = getelementptr inbounds i32* %bit, i64 2
+  %gep2 = getelementptr inbounds i8* %foo, i64 10
+  %cast1 = bitcast i32* %gep1 to i8*
+  %cmp = icmp ult i8* %cast1, %gep2
+  %use = ptrtoint i8* %cast1 to i64
+  %call = call i32 @test58_d(i64 %use) nounwind
+  ret i1 %cmp
+; CHECK: @test59
+; CHECK: ret i1 true
+}
+
+define i1 @test60(i8* %foo, i64 %i, i64 %j) {
+  %bit = bitcast i8* %foo to i32*
+  %gep1 = getelementptr inbounds i32* %bit, i64 %i
+  %gep2 = getelementptr inbounds i8* %foo, i64 %j
+  %cast1 = bitcast i32* %gep1 to i8*
+  %cmp = icmp ult i8* %cast1, %gep2
+  ret i1 %cmp
+; CHECK: @test60
+; CHECK-NEXT: %gep1.idx = shl nuw i64 %i, 2
+; CHECK-NEXT: icmp slt i64 %gep1.idx, %j
+; CHECK-NEXT: ret i1
+}