Index: include/llvm/IR/IRBuilder.h =================================================================== --- include/llvm/IR/IRBuilder.h +++ include/llvm/IR/IRBuilder.h @@ -435,6 +435,28 @@ MDNode *ScopeTag = nullptr, MDNode *NoAliasTag = nullptr); + /// \brief Create and insert an atomic memcpy between the specified + /// pointers. + /// + /// If the pointers aren't i8*, they will be converted. If a TBAA tag is + /// specified, it will be added to the instruction. Likewise with alias.scope + /// and noalias tags. + CallInst *CreateElementAtomicMemCpy( + Value *Dst, Value *Src, uint64_t NumElements, uint32_t ElementSize, + MDNode *TBAATag = nullptr, MDNode *TBAAStructTag = nullptr, + MDNode *ScopeTag = nullptr, MDNode *NoAliasTag = nullptr) { + return CreateElementAtomicMemCpy(Dst, Src, getInt64(NumElements), + ElementSize, TBAATag, TBAAStructTag, + ScopeTag, NoAliasTag); + } + + CallInst *CreateElementAtomicMemCpy(Value *Dst, Value *Src, + Value *NumElements, uint32_t ElementSize, + MDNode *TBAATag = nullptr, + MDNode *TBAAStructTag = nullptr, + MDNode *ScopeTag = nullptr, + MDNode *NoAliasTag = nullptr); + /// \brief Create and insert a memmove between the specified /// pointers. /// Index: lib/IR/IRBuilder.cpp =================================================================== --- lib/IR/IRBuilder.cpp +++ lib/IR/IRBuilder.cpp @@ -134,6 +134,38 @@ return CI; } +CallInst *IRBuilderBase::CreateElementAtomicMemCpy( + Value *Dst, Value *Src, Value *NumElements, uint32_t ElementSize, + MDNode *TBAATag, MDNode *TBAAStructTag, MDNode *ScopeTag, + MDNode *NoAliasTag) { + Dst = getCastedInt8PtrValue(Dst); + Src = getCastedInt8PtrValue(Src); + + Value *Ops[] = {Dst, Src, NumElements, getInt32(ElementSize)}; + Type *Tys[] = {Dst->getType(), Src->getType()}; + Module *M = BB->getParent()->getParent(); + Value *TheFn = + Intrinsic::getDeclaration(M, Intrinsic::memcpy_element_atomic, Tys); + + CallInst *CI = createCallHelper(TheFn, Ops, this); + + // Set the TBAA info if present. + if (TBAATag) + CI->setMetadata(LLVMContext::MD_tbaa, TBAATag); + + // Set the TBAA Struct info if present. + if (TBAAStructTag) + CI->setMetadata(LLVMContext::MD_tbaa_struct, TBAAStructTag); + + if (ScopeTag) + CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag); + + if (NoAliasTag) + CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag); + + return CI; +} + CallInst *IRBuilderBase:: CreateMemMove(Value *Dst, Value *Src, Value *Size, unsigned Align, bool isVolatile, MDNode *TBAATag, MDNode *ScopeTag, Index: lib/Transforms/Scalar/LoopIdiomRecognize.cpp =================================================================== --- lib/Transforms/Scalar/LoopIdiomRecognize.cpp +++ lib/Transforms/Scalar/LoopIdiomRecognize.cpp @@ -52,6 +52,7 @@ #include "llvm/Analysis/TargetLibraryInfo.h" #include "llvm/Analysis/TargetTransformInfo.h" #include "llvm/Analysis/ValueTracking.h" +#include "llvm/CodeGen/RuntimeLibcalls.h" #include "llvm/IR/DataLayout.h" #include "llvm/IR/Dominators.h" #include "llvm/IR/IRBuilder.h" @@ -116,6 +117,7 @@ Memset, MemsetPattern, Memcpy, + AtomicMemcpy, DontUse // Dummy retval never to be used. Allows catching errors in retval // handling. }; @@ -353,8 +355,10 @@ LoopIdiomRecognize::LegalStoreKind LoopIdiomRecognize::isLegalStore(StoreInst *SI) { + // Note: isUnordered == isSimple() || atomic-unordered + bool UnorderedAtomic = SI->isAtomic() && SI->isUnordered(); // Don't touch volatile stores. - if (!SI->isSimple()) + if (!UnorderedAtomic && !SI->isSimple()) return LegalStoreKind::None; // Don't convert stores of non-integral pointer types to memsets (which stores @@ -397,13 +401,14 @@ // If we're allowed to form a memset, and the stored value would be // acceptable for memset, use it. - if (HasMemset && SplatValue && + // Note: memset and memset_pattern on unordered-atomic is not supported + if (!UnorderedAtomic && HasMemset && SplatValue && // Verify that the stored value is loop invariant. If not, we can't // promote the memset. CurLoop->isLoopInvariant(SplatValue)) { // It looks like we can use SplatValue. return LegalStoreKind::Memset; - } else if (HasMemsetPattern && + } else if (!UnorderedAtomic && HasMemsetPattern && // Don't create memset_pattern16s with address spaces. StorePtr->getType()->getPointerAddressSpace() == 0 && (PatternValue = getMemSetPatternValue(StoredVal, DL))) { @@ -422,7 +427,9 @@ // The store must be feeding a non-volatile load. LoadInst *LI = dyn_cast(SI->getValueOperand()); - if (!LI || !LI->isSimple()) + + // Note: Unordered == isSimple() || unordered-atomic + if (!LI || !LI->isUnordered()) return LegalStoreKind::None; // See if the pointer expression is an AddRec like {base,+,1} on the current @@ -438,7 +445,9 @@ return LegalStoreKind::None; // Success. This store can be converted into a memcpy. - return LegalStoreKind::Memcpy; + UnorderedAtomic = UnorderedAtomic || LI->isAtomic(); + return UnorderedAtomic ? LegalStoreKind::AtomicMemcpy + : LegalStoreKind::Memcpy; } // This store can't be transformed into a memset/memcpy. return LegalStoreKind::None; @@ -469,6 +478,7 @@ StoreRefsForMemsetPattern[Ptr].push_back(SI); } break; case LegalStoreKind::Memcpy: + case LegalStoreKind::AtomicMemcpy: StoreRefsForMemcpy.push_back(SI); break; default: @@ -882,7 +892,7 @@ /// for (i) A[i] = B[i]; bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(StoreInst *SI, const SCEV *BECount) { - assert(SI->isSimple() && "Expected only non-volatile stores."); + assert(SI->isUnordered() && "Expected only non-volatile non-ordered stores."); Value *StorePtr = SI->getPointerOperand(); const SCEVAddRecExpr *StoreEv = cast(SE->getSCEV(StorePtr)); @@ -892,7 +902,7 @@ // The store must be feeding a non-volatile load. LoadInst *LI = cast(SI->getValueOperand()); - assert(LI->isSimple() && "Expected only non-volatile stores."); + assert(LI->isUnordered() && "Expected only non-volatile non-ordered loads."); // See if the pointer expression is an AddRec like {base,+,1} on the current // loop, which indicates a strided load. If we have something else, it's a @@ -966,16 +976,52 @@ const SCEV *NumBytesS = SE->getAddExpr(BECount, SE->getOne(IntPtrTy), SCEV::FlagNUW); - if (StoreSize != 1) - NumBytesS = SE->getMulExpr(NumBytesS, SE->getConstant(IntPtrTy, StoreSize), - SCEV::FlagNUW); - Value *NumBytes = - Expander.expandCodeFor(NumBytesS, IntPtrTy, Preheader->getTerminator()); + unsigned Align = std::min(SI->getAlignment(), LI->getAlignment()); + CallInst *NewCall = nullptr; + // Check whether to generate an unordered atomic memcpy: + // If the load or store are atomic, then they must neccessarily be unordered + // by previous checks. + if (!SI->isAtomic() && !LI->isAtomic()) { + if (StoreSize != 1) + NumBytesS = SE->getMulExpr( + NumBytesS, SE->getConstant(IntPtrTy, StoreSize), SCEV::FlagNUW); + + Value *NumBytes = + Expander.expandCodeFor(NumBytesS, IntPtrTy, Preheader->getTerminator()); - CallInst *NewCall = - Builder.CreateMemCpy(StoreBasePtr, LoadBasePtr, NumBytes, - std::min(SI->getAlignment(), LI->getAlignment())); + NewCall = Builder.CreateMemCpy(StoreBasePtr, LoadBasePtr, NumBytes, Align); + } else { + // If the element.atomic memcpy is not lowered into explicit + // loads/stores later, then it will be lowered into an element-size + // specific lib call. If the lib call doesn't exist for our store size, then + // we shouldn't generate the memcpy. + if (RTLIB::UNKNOWN_LIBCALL == RTLIB::getMEMCPY_ELEMENT_ATOMIC(StoreSize)) + return false; + + Value *NumElements = + Expander.expandCodeFor(NumBytesS, IntPtrTy, Preheader->getTerminator()); + + NewCall = Builder.CreateElementAtomicMemCpy(StoreBasePtr, LoadBasePtr, + NumElements, StoreSize); + // Propagate alignment info onto the pointer args. Note that unordered + // atomic loads/stores are *required* by the spec to have an alignment + // but non-atomic loads/stores may not. + auto setAlignment = [NewCall](unsigned argNo, unsigned alignment) { + // Note that it's possible that either the LI or the SI is simple; if that + // is the case, then it may not have an alignment but we require an + // alignment on the args of element.atomic.memcpy because it will treat + // both source and dest as requiring unordered atomic accesses. So, we + // conservatively set the alignment to 1 in this case. + if (!alignment) + alignment = 1; + NewCall->addAttribute( + argNo + AttributeList::FirstArgIndex, + Attribute::getWithAlignment(NewCall->getContext(), alignment)); + }; + setAlignment(0, SI->getAlignment()); + setAlignment(1, LI->getAlignment()); + } NewCall->setDebugLoc(SI->getDebugLoc()); DEBUG(dbgs() << " Formed memcpy: " << *NewCall << "\n" Index: test/Transforms/LoopIdiom/unordered-atomic-memcpy.ll =================================================================== --- /dev/null +++ test/Transforms/LoopIdiom/unordered-atomic-memcpy.ll @@ -0,0 +1,172 @@ +; RUN: opt -basicaa -loop-idiom < %s -S | FileCheck %s +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" + +;; memcpy.atomic formation (atomic load & store) +define void @test1(i64 %Size) nounwind ssp { +; CHECK-LABEL: @test1( +; CHECK: call void @llvm.memcpy.element.atomic.p0i8.p0i8(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1) +; CHECK-NOT: store +; CHECK: ret void +bb.nph: + %Base = alloca i8, i32 10000 + %Dest = alloca i8, i32 10000 + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + %DestI = getelementptr i8, i8* %Dest, i64 %indvar + %V = load atomic i8, i8* %I.0.014 unordered, align 1 + store atomic i8 %V, i8* %DestI unordered, align 1 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +;; memcpy.atomic formation (atomic store, normal load) +define void @test2(i64 %Size) nounwind ssp { +; CHECK-LABEL: @test2( +; CHECK: call void @llvm.memcpy.element.atomic.p0i8.p0i8(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1) +; CHECK-NOT: store +; CHECK: ret void +bb.nph: + %Base = alloca i8, i32 10000 + %Dest = alloca i8, i32 10000 + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + %DestI = getelementptr i8, i8* %Dest, i64 %indvar + %V = load i8, i8* %I.0.014, align 1 + store atomic i8 %V, i8* %DestI unordered, align 1 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +;; memcpy.atomic formation (atomic store, normal load w/ no align) +define void @test2b(i64 %Size) nounwind ssp { +; CHECK-LABEL: @test2b( +; CHECK: call void @llvm.memcpy.element.atomic.p0i8.p0i8(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1) +; CHECK-NOT: store +; CHECK: ret void +bb.nph: + %Base = alloca i8, i32 10000 + %Dest = alloca i8, i32 10000 + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + %DestI = getelementptr i8, i8* %Dest, i64 %indvar + %V = load i8, i8* %I.0.014 + store atomic i8 %V, i8* %DestI unordered, align 1 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +;; memcpy.atomic formation (normal store, atomic load) +define void @test3(i64 %Size) nounwind ssp { +; CHECK-LABEL: @test3( +; CHECK: call void @llvm.memcpy.element.atomic.p0i8.p0i8(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1) +; CHECK-NOT: store +; CHECK: ret void +bb.nph: + %Base = alloca i8, i32 10000 + %Dest = alloca i8, i32 10000 + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + %DestI = getelementptr i8, i8* %Dest, i64 %indvar + %V = load atomic i8, i8* %I.0.014 unordered, align 1 + store i8 %V, i8* %DestI, align 1 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +;; memcpy.atomic formation (normal store w/ no align, atomic load) +define void @test3b(i64 %Size) nounwind ssp { +; CHECK-LABEL: @test3b( +; CHECK: call void @llvm.memcpy.element.atomic.p0i8.p0i8(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1) +; CHECK-NOT: store +; CHECK: ret void +bb.nph: + %Base = alloca i8, i32 10000 + %Dest = alloca i8, i32 10000 + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + %DestI = getelementptr i8, i8* %Dest, i64 %indvar + %V = load atomic i8, i8* %I.0.014 unordered, align 1 + store i8 %V, i8* %DestI + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +; Make sure that atomic memset doesn't get recognized by mistake +define void @test_nomemset(i8* %Base, i64 %Size) nounwind ssp { +; CHECK-LABEL: @test_nomemset( +; CHECK-NOT: call void @llvm.memset +; CHECK: store +; CHECK: ret void +bb.nph: ; preds = %entry + br label %for.body + +for.body: ; preds = %bb.nph, %for.body + %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ] + %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar + store atomic i8 0, i8* %I.0.014 unordered, align 1 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, %Size + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +; Verify that unordered memset_pattern isn't recognized. +; This is a replica of test11_pattern from basic.ll +define void @test_nomemset_pattern(i32* nocapture %P) nounwind ssp { +; CHECK-LABEL: @test_nomemset_pattern( +; CHECK-NEXT: entry: +; CHECK-NOT: bitcast +; CHECK-NOT: memset_pattern +; CHECK: store atomic +; CHECK: ret void +entry: + br label %for.body + +for.body: ; preds = %entry, %for.body + %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %for.body ] + %arrayidx = getelementptr i32, i32* %P, i64 %indvar + store atomic i32 1, i32* %arrayidx unordered, align 4 + %indvar.next = add i64 %indvar, 1 + %exitcond = icmp eq i64 %indvar.next, 10000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +}