[LICM] Report failing to hoist a load with an invariant address

These are interesting because lack of precision in alias information
could be standing in the way of this optimization.

An example is the case in the test suite that I showed in the DevMeeting
talk:

http://lab.llvm.org:8080/artifacts/opt-view_test-suite/build/MultiSource/Benchmarks/FreeBench/distray/CMakeFiles/distray.dir/html/_org_test-suite_MultiSource_Benchmarks_FreeBench_distray_distray.c.html#L236

canSinkOrHoistInst is also used from LoopSink, which does not use
opt-remarks so we need to take ORE as an optional argument.

Differential Revision: https://reviews.llvm.org/D27939

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291648 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Transforms/Utils/LoopUtils.h b/include/llvm/Transforms/Utils/LoopUtils.h
index b786e4a..27b45c4 100644 (file)
--- a/include/llvm/Transforms/Utils/LoopUtils.h
+++ b/include/llvm/Transforms/Utils/LoopUtils.h
@@ -483,10 +483,11 @@ void getLoopAnalysisUsage(AnalysisUsage &AU);
 /// If SafetyInfo is not null, we are checking for hoisting/sinking
 /// instructions from loop body to preheader/exit. Check if the instruction
 /// can execute speculatively.
-///
+/// If \p ORE is set use it to emit optimization remarks.
 bool canSinkOrHoistInst(Instruction &I, AAResults *AA, DominatorTree *DT,
                         Loop *CurLoop, AliasSetTracker *CurAST,
-                        LoopSafetyInfo *SafetyInfo);
+                        LoopSafetyInfo *SafetyInfo,
+                        OptimizationRemarkEmitter *ORE = nullptr);
 }
 
 #endif

diff --git a/lib/Transforms/Scalar/LICM.cpp b/lib/Transforms/Scalar/LICM.cpp
index bd719ec..225cfe2 100644 (file)
--- a/lib/Transforms/Scalar/LICM.cpp
+++ b/lib/Transforms/Scalar/LICM.cpp
@@ -377,7 +377,7 @@ bool llvm::sinkRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
     // operands of the instruction are loop invariant.
     //
     if (isNotUsedInLoop(I, CurLoop, SafetyInfo) &&
-        canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, SafetyInfo)) {
+        canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, SafetyInfo, ORE)) {
       ++II;
       Changed |= sink(I, LI, DT, CurLoop, CurAST, SafetyInfo, ORE);
     }
@@ -432,7 +432,7 @@ bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
       // is safe to hoist the instruction.
       //
       if (CurLoop->hasLoopInvariantOperands(&I) &&
-          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, SafetyInfo) &&
+          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, SafetyInfo, ORE) &&
           isSafeToExecuteUnconditionally(
               I, DT, CurLoop, SafetyInfo,
               CurLoop->getLoopPreheader()->getTerminator()))
@@ -481,7 +481,8 @@ void llvm::computeLoopSafetyInfo(LoopSafetyInfo *SafetyInfo, Loop *CurLoop) {
 
 bool llvm::canSinkOrHoistInst(Instruction &I, AAResults *AA, DominatorTree *DT,
                               Loop *CurLoop, AliasSetTracker *CurAST,
-                              LoopSafetyInfo *SafetyInfo) {
+                              LoopSafetyInfo *SafetyInfo,
+                              OptimizationRemarkEmitter *ORE) {
   // Loads have extra constraints we have to verify before we can hoist them.
   if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
     if (!LI->isUnordered())
@@ -502,7 +503,17 @@ bool llvm::canSinkOrHoistInst(Instruction &I, AAResults *AA, DominatorTree *DT,
     AAMDNodes AAInfo;
     LI->getAAMetadata(AAInfo);
 
-    return !pointerInvalidatedByLoop(LI->getOperand(0), Size, AAInfo, CurAST);
+    bool Invalidated =
+        pointerInvalidatedByLoop(LI->getOperand(0), Size, AAInfo, CurAST);
+    // Check loop-invariant address because this may also be a sinkable load
+    // whose address is not necessarily loop-invariant.
+    if (ORE && Invalidated && CurLoop->isLoopInvariant(LI->getPointerOperand()))
+      ORE->emit(OptimizationRemarkMissed(
+                    DEBUG_TYPE, "LoadWithLoopInvariantAddressInvalidated", LI)
+                << "failed to move load with loop-invariant address "
+                   "because the loop may invalidate its value");
+
+    return !Invalidated;
   } else if (CallInst *CI = dyn_cast<CallInst>(&I)) {
     // Don't sink or hoist dbg info; it's legal, but not useful.
     if (isa<DbgInfoIntrinsic>(I))

diff --git a/test/Transforms/LICM/opt-remarks-intervening-store.ll b/test/Transforms/LICM/opt-remarks-intervening-store.ll
new file mode 100644 (file)
index 0000000..95389ce
--- /dev/null
+++ b/test/Transforms/LICM/opt-remarks-intervening-store.ll
@@ -0,0 +1,67 @@
+; RUN: opt < %s -licm -pass-remarks-missed=licm -o /dev/null 2>&1 | FileCheck %s
+; RUN: opt -aa-pipeline=basic-aa -passes='require<aa>,require<targetir>,require<scalar-evolution>,require<opt-remark-emit>,loop(licm)' %s -o /dev/null -pass-remarks-missed=licm 2>&1 | FileCheck %s
+target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
+
+; Without the noalias on %p, we can't optmize this and the remark should tell
+; us about it.
+
+define void @test(i32* %array, i32* %p) {
+Entry:
+  br label %Loop
+
+Loop:
+  %j = phi i32 [ 0, %Entry ], [ %Next, %Loop ]
+  %addr = getelementptr i32, i32* %array, i32 %j
+  %a = load i32, i32* %addr
+; CHECK: remark: /tmp/kk.c:2:20: failed to move load with loop-invariant address because the loop may invalidate its value
+  %b = load i32, i32* %p, !dbg !8
+  %a2 = add i32 %a, %b
+  store i32 %a2, i32* %addr
+  %Next = add i32 %j, 1
+  %cond = icmp eq i32 %Next, 0
+  br i1 %cond, label %Out, label %Loop
+
+Out:
+  ret void
+}
+
+; This illustrates why we need to check loop-invariance before issuing this
+; remark.
+
+define i32 @invalidated_load_with_non_loop_invariant_address(i32* %array, i32* %array2) {
+Entry:
+  br label %Loop
+
+Loop:
+  %j = phi i32 [ 0, %Entry ], [ %Next, %Loop ]
+
+; CHECK-NOT: /tmp/kk.c:3:20: {{.*}} loop-invariant
+  %addr = getelementptr i32, i32* %array, i32 %j
+  %a = load i32, i32* %addr, !dbg !9
+
+  %addr2 = getelementptr i32, i32* %array2, i32 %j
+  store i32 %j, i32* %addr2
+
+  %Next = add i32 %j, 1
+  %cond = icmp eq i32 %Next, 0
+  br i1 %cond, label %Out, label %Loop
+
+Out:
+  %a2 = phi i32 [ %a, %Loop ]
+  ret i32 %a2
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4}
+!llvm.ident = !{!5}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 3.9.0 ", isOptimized: true, runtimeVersion: 0, emissionKind: NoDebug, enums: !2)
+!1 = !DIFile(filename: "/tmp/kk.c", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = !{i32 1, !"PIC Level", i32 2}
+!5 = !{!"clang version 3.9.0 "}
+!6 = distinct !DISubprogram(name: "success", scope: !1, file: !1, line: 1, type: !7, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, unit: !0, variables: !2)
+!7 = !DISubroutineType(types: !2)
+!8 = !DILocation(line: 2, column: 20, scope: !6)
+!9 = !DILocation(line: 3, column: 20, scope: !6)