From: Anna Thomas Date: Tue, 9 Aug 2016 17:18:05 +0000 (+0000) Subject: [AliasAnalysis] Treat invariant.start as read-memory X-Git-Tag: llvmorg-4.0.0-rc1~12947 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=037e540f0842c33e72cbcb1ba7bf1659b170e852;p=platform%2Fupstream%2Fllvm.git [AliasAnalysis] Treat invariant.start as read-memory Summary: We teach alias analysis that invariant.start is readonly. This helps with GVN and memcopy optimizations that currently treat. invariant.start as a clobber. We need to treat this as readonly, so that DSE does not incorrectly remove stores prior to the invariant.start Reviewers: sanjoy, reames, majnemer, dberlin Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D23214 llvm-svn: 278138 --- diff --git a/llvm/lib/Analysis/BasicAliasAnalysis.cpp b/llvm/lib/Analysis/BasicAliasAnalysis.cpp index 89ae3d0..84affa1 100644 --- a/llvm/lib/Analysis/BasicAliasAnalysis.cpp +++ b/llvm/lib/Analysis/BasicAliasAnalysis.cpp @@ -781,6 +781,32 @@ ModRefInfo BasicAAResult::getModRefInfo(ImmutableCallSite CS, if (isIntrinsicCall(CS, Intrinsic::experimental_guard)) return MRI_Ref; + // Like assumes, invariant.start intrinsics were also marked as arbitrarily + // writing so that proper control dependencies are maintained but they never + // mod any particular memory location visible to the IR. + // *Unlike* assumes (which are now modeled as NoModRef), invariant.start + // intrinsic is now modeled as reading memory. This prevents hoisting the + // invariant.start intrinsic over stores. Consider: + // *ptr = 40; + // *ptr = 50; + // invariant_start(ptr) + // int val = *ptr; + // print(val); + // + // This cannot be transformed to: + // + // *ptr = 40; + // invariant_start(ptr) + // *ptr = 50; + // int val = *ptr; + // print(val); + // + // The transformation will cause the second store to be ignored (based on + // rules of invariant.start) and print 40, while the first program always + // prints 50. + if (isIntrinsicCall(CS, Intrinsic::invariant_start)) + return MRI_Ref; + // The AAResultBase base class has some smarts, lets use them. return AAResultBase::getModRefInfo(CS, Loc); } diff --git a/llvm/test/Transforms/DeadStoreElimination/invariant.start.ll b/llvm/test/Transforms/DeadStoreElimination/invariant.start.ll new file mode 100644 index 0000000..cac3713 --- /dev/null +++ b/llvm/test/Transforms/DeadStoreElimination/invariant.start.ll @@ -0,0 +1,34 @@ +; Test to make sure llvm.invariant.start calls are not treated as clobbers. +; RUN: opt < %s -basicaa -dse -S | FileCheck %s + +declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly + +; We cannot remove the store 1 to %p. +; FIXME: By the semantics of invariant.start, the store 3 to p is unreachable. +define void @test(i8 *%p) { + store i8 1, i8* %p, align 4 + %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %p) + store i8 3, i8* %p, align 4 + ret void +; CHECK-LABEL: @test( +; CHECK-NEXT: store i8 1, i8* %p, align 4 +; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %p) +; CHECK-NEXT: store i8 3, i8* %p, align 4 +; CHECK-NEXT: ret void +} + +; FIXME: We should be able to remove the first store to p, even though p and q +; may alias. +define void @test2(i8* %p, i8* %q) { + store i8 1, i8* %p, align 4 + store i8 2, i8* %q, align 4 + %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %q) + store i8 3, i8* %p, align 4 + ret void +; CHECK-LABEL: @test2( +; CHECK-NEXT: store i8 1, i8* %p, align 4 +; CHECK-NEXT: store i8 2, i8* %q, align 4 +; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %q) +; CHECK-NEXT: store i8 3, i8* %p, align 4 +; CHECK-NEXT: ret void +} diff --git a/llvm/test/Transforms/GVN/invariant.start.ll b/llvm/test/Transforms/GVN/invariant.start.ll new file mode 100644 index 0000000..25f7798 --- /dev/null +++ b/llvm/test/Transforms/GVN/invariant.start.ll @@ -0,0 +1,59 @@ +; Test to make sure llvm.invariant.start calls are not treated as clobbers. +; RUN: opt < %s -gvn -S | FileCheck %s + + +declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly +declare void @llvm.invariant.end.p0i8({}*, i64, i8* nocapture) nounwind + +; We forward store to the load across the invariant.start intrinsic +define i8 @forward_store() { +; CHECK-LABEL: @forward_store +; CHECK: call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) +; CHECK-NOT: load +; CHECK: ret i8 0 + %a = alloca i8 + store i8 0, i8* %a + %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) + %r = load i8, i8* %a + ret i8 %r +} + +declare i8 @dummy(i8* nocapture) nounwind readonly + +; We forward store to the load in the non-local analysis case, +; i.e. invariant.start is in another basic block. +define i8 @forward_store_nonlocal(i1 %cond) { +; CHECK-LABEL: forward_store_nonlocal +; CHECK: call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) +; CHECK: ret i8 0 +; CHECK: ret i8 %val + %a = alloca i8 + store i8 0, i8* %a + %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) + br i1 %cond, label %loadblock, label %exit + +loadblock: + %r = load i8, i8* %a + ret i8 %r + +exit: + %val = call i8 @dummy(i8* %a) + ret i8 %val +} + +; We should not value forward %foo to the invariant.end corresponding to %bar. +define i8 @forward_store1() { +; CHECK-LABEL: forward_store1 +; CHECK: %foo = call {}* @llvm.invariant.start.p0i8 +; CHECK-NOT: load +; CHECK: %bar = call {}* @llvm.invariant.start.p0i8 +; CHECK: call void @llvm.invariant.end.p0i8({}* %bar, i64 1, i8* %a) +; CHECK: ret i8 0 + %a = alloca i8 + store i8 0, i8* %a + %foo = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) + %r = load i8, i8* %a + %bar = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %a) + call void @llvm.invariant.end.p0i8({}* %bar, i64 1, i8* %a) + ret i8 %r +} diff --git a/llvm/test/Transforms/MemCpyOpt/invariant.start.ll b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll new file mode 100644 index 0000000..ed8d7ed --- /dev/null +++ b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll @@ -0,0 +1,49 @@ +; MemCpy optimizations should take place even in presence of invariant.start +; RUN: opt < %s -basicaa -memcpyopt -dse -S | FileCheck %s + +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" + +target triple = "i686-apple-darwin9" + +%0 = type { x86_fp80, x86_fp80 } +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, +i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, +i64, i32, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) + +declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly + +; FIXME: The invariant.start does not modify %P. +; The intermediate alloca and one of the memcpy's should be eliminated, the +; other should be transformed to a memmove. +define void @test1(i8* %P, i8* %Q) nounwind { + %memtmp = alloca %0, align 16 + %R = bitcast %0* %memtmp to i8* + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false) + %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false) + ret void +; CHECK-LABEL: @test1( +; CHECK-NEXT: %memtmp = alloca %0, align 16 +; CHECK-NEXT: %R = bitcast %0* %memtmp to i8* +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false) +; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false) +; CHECK-NEXT: ret void +} + + +; The invariant.start intrinsic does not inhibit tranforming the memcpy to a +; memset. +define void @test2(i8* %dst1, i8* %dst2, i8 %c) { +; CHECK-LABEL: define void @test2( +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) +; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 8, i1 false) +; CHECK-NEXT: ret void + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) + %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 8, i1 false) + ret void +}