diff options
| -rw-r--r-- | llvm/test/Transforms/InstCombine/assume_inevitable.ll | 74 |
1 files changed, 74 insertions, 0 deletions
diff --git a/llvm/test/Transforms/InstCombine/assume_inevitable.ll b/llvm/test/Transforms/InstCombine/assume_inevitable.ll new file mode 100644 index 00000000000..a063775b057 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/assume_inevitable.ll @@ -0,0 +1,74 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -instcombine -S | FileCheck %s + +; Check that assume is propagated backwards through all +; operations that are `isGuaranteedToTransferExecutionToSuccessor` +; (it should reach the load and mark it as `align 32`). +define i32 @assume_inevitable(i32* %a, i32* %b, i8* %c) { +; CHECK-LABEL: @assume_inevitable( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[M:%.*]] = alloca i64, align 8 +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[A:%.*]], align 4 +; CHECK-NEXT: [[LOADRES:%.*]] = load i32, i32* [[B:%.*]], align 4 +; CHECK-NEXT: [[LOADRES2:%.*]] = call i32 @llvm.annotation.i32(i32 [[LOADRES]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str1, i64 0, i64 0), i32 2) +; CHECK-NEXT: store i32 [[LOADRES2]], i32* [[A]], align 4 +; CHECK-NEXT: [[DUMMY_EQ:%.*]] = icmp ugt i32 [[LOADRES]], 42 +; CHECK-NEXT: tail call void @llvm.assume(i1 [[DUMMY_EQ]]) +; CHECK-NEXT: [[M_I8:%.*]] = bitcast i64* [[M]] to i8* +; CHECK-NEXT: [[M_A:%.*]] = call i8* @llvm.ptr.annotation.p0i8(i8* nonnull [[M_I8]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str1, i64 0, i64 0), i32 2) +; CHECK-NEXT: [[M_X:%.*]] = bitcast i8* [[M_A]] to i64* +; CHECK-NEXT: [[OBJSZ:%.*]] = call i64 @llvm.objectsize.i64.p0i8(i8* [[C:%.*]], i1 false, i1 false, i1 false) +; CHECK-NEXT: store i64 [[OBJSZ]], i64* [[M_X]], align 4 +; CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i32* [[A]] to i64 +; CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31 +; CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0 +; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND]]) +; CHECK-NEXT: ret i32 [[TMP0]] +; +entry: + %dummy = alloca i8, align 4 + %m = alloca i64 + %0 = load i32, i32* %a, align 4 + + ; START perform a bunch of inevitable operations + %loadres = load i32, i32* %b + %loadres2 = call i32 @llvm.annotation.i32(i32 %loadres, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str1, i32 0, i32 0), i32 2) + store i32 %loadres2, i32* %a + + %dummy_eq = icmp ugt i32 %loadres, 42 + tail call void @llvm.assume(i1 %dummy_eq) + + call void @llvm.lifetime.start.p0i8(i64 1, i8* %dummy) + %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %dummy) + call void @llvm.invariant.end.p0i8({}* %i, i64 1, i8* %dummy) + call void @llvm.lifetime.end.p0i8(i64 1, i8* %dummy) + + %m_i8 = bitcast i64* %m to i8* + %m_a = call i8* @llvm.ptr.annotation.p0i8(i8* %m_i8, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str1, i32 0, i32 0), i32 2) + %m_x = bitcast i8* %m_a to i64* + %objsz = call i64 @llvm.objectsize.i64.p0i8(i8* %c, i1 false) + store i64 %objsz, i64* %m_x + ; END perform a bunch of inevitable operations + + ; AND here's the assume: + %ptrint = ptrtoint i32* %a to i64 + %maskedptr = and i64 %ptrint, 31 + %maskcond = icmp eq i64 %maskedptr, 0 + tail call void @llvm.assume(i1 %maskcond) + + ret i32 %0 +} + +@.str = private unnamed_addr constant [4 x i8] c"sth\00", section "llvm.metadata" +@.str1 = private unnamed_addr constant [4 x i8] c"t.c\00", section "llvm.metadata" + +declare i64 @llvm.objectsize.i64.p0i8(i8*, i1) +declare i32 @llvm.annotation.i32(i32, i8*, i8*, i32) +declare i8* @llvm.ptr.annotation.p0i8(i8*, i8*, i8*, i32) + +declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) +declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) + +declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) +declare void @llvm.invariant.end.p0i8({}*, i64, i8* nocapture) +declare void @llvm.assume(i1) |
