diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp index 3b46156c1ab0..f62941fbf642 100644 --- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp +++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp @@ -1467,6 +1467,11 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) { // normalized. if (SO1->getType() != GO1->getType()) return nullptr; + // Only do the combine when GO1 and SO1 are both constants. Only in + // this case, we are sure the cost after the merge is never more than + // that before the merge. + if (!isa(GO1) || !isa(SO1)) + return nullptr; Sum = Builder->CreateAdd(SO1, GO1, PtrOp->getName()+".sum"); } diff --git a/llvm/test/Transforms/InstCombine/descale-zero.ll b/llvm/test/Transforms/InstCombine/descale-zero.ll deleted file mode 100644 index 4347be48e618..000000000000 --- a/llvm/test/Transforms/InstCombine/descale-zero.ll +++ /dev/null @@ -1,20 +0,0 @@ -; RUN: opt < %s -instcombine -S | FileCheck %s - -target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" -target triple = "x86_64-apple-macosx10.10.0" - -define internal i8* @descale_zero() { -entry: -; CHECK: load i8*, i8** inttoptr (i64 48 to i8**), align 16 -; CHECK-NEXT: ret i8* - %i16_ptr = load i16*, i16** inttoptr (i64 48 to i16**), align 16 - %num = load i64, i64* inttoptr (i64 64 to i64*), align 64 - %num_times_2 = shl i64 %num, 1 - %num_times_2_plus_4 = add i64 %num_times_2, 4 - %i8_ptr = bitcast i16* %i16_ptr to i8* - %i8_ptr_num_times_2_plus_4 = getelementptr i8, i8* %i8_ptr, i64 %num_times_2_plus_4 - %num_times_neg2 = mul i64 %num, -2 - %num_times_neg2_minus_4 = add i64 %num_times_neg2, -4 - %addr = getelementptr i8, i8* %i8_ptr_num_times_2_plus_4, i64 %num_times_neg2_minus_4 - ret i8* %addr -} diff --git a/llvm/test/Transforms/InstCombine/gep-merge.ll b/llvm/test/Transforms/InstCombine/gep-merge.ll new file mode 100644 index 000000000000..3cfe781ac8b7 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/gep-merge.ll @@ -0,0 +1,48 @@ +; This test makes sure that gep(gep ...) merge doesn't come into effect. +; RUN: opt < %s -instcombine -S | FileCheck %s + +; Make sure there are no geps being merged. +; CHECK-LABEL: @fn3( +; CHECK: getelementptr +; CHECK: getelementptr +; CHECK: getelementptr + +@_ZN2cv1aE = global i8* zeroinitializer, align 8 +declare i32 @fn1() #2 +declare i32 @fn2() #2 + +; Function Attrs: uwtable +define linkonce_odr i32 @fn3() { +entry: + %call = call i32 @fn1() + %call1 = call i32 @fn2() + %0 = load i8*, i8** @_ZN2cv1aE, align 8 + %idx.ext2 = sext i32 %call1 to i64 + %add.ptr3 = getelementptr inbounds i8, i8* %0, i64 %idx.ext2 + br label %for.cond5 + +for.cond5: + %total1 = phi i32 [ 0, %entry ], [ %total2, %for.body7 ] + %x.1 = phi i32 [ 0, %entry ], [ %inc, %for.body7 ] + %cmp6 = icmp slt i32 %x.1, %call + br i1 %cmp6, label %for.body7, label %for.cond34 + +for.body7: ; preds = %for.cond5 + %mul = mul nsw i32 %x.1, 2 + %idxprom = sext i32 %mul to i64 + %arrayidx = getelementptr inbounds i8, i8* %add.ptr3, i64 %idxprom + %1 = load i8, i8* %arrayidx, align 1 + %conv = zext i8 %1 to i32 + %sub = sub nsw i32 %mul, 1 + %idxprom10 = sext i32 %sub to i64 + %arrayidx11 = getelementptr inbounds i8, i8* %add.ptr3, i64 %idxprom10 + %2 = load i8, i8* %arrayidx11, align 1 + %conv2 = zext i8 %2 to i32 + %add1 = add nsw i32 %conv, %conv2 + %total2 = add nsw i32 %total1, %add1 + %inc = add nsw i32 %x.1, 1 + br label %for.cond5 + +for.cond34: + ret i32 %total1 +} diff --git a/llvm/test/Transforms/InstCombine/getelementptr.ll b/llvm/test/Transforms/InstCombine/getelementptr.ll index 9bb1b12a6972..276ada91f3c6 100644 --- a/llvm/test/Transforms/InstCombine/getelementptr.ll +++ b/llvm/test/Transforms/InstCombine/getelementptr.ll @@ -104,8 +104,8 @@ define i32* @test7(i32* %I, i64 %C, i64 %D) { %B = getelementptr i32, i32* %A, i64 %D ret i32* %B ; CHECK-LABEL: @test7( -; CHECK: %A.sum = add i64 %C, %D -; CHECK: getelementptr i32, i32* %I, i64 %A.sum +; CHECK: %A = getelementptr i32, i32* %I, i64 %C +; CHECK: %B = getelementptr i32, i32* %A, i64 %D } define i8* @test8([10 x i32]* %X) {