Revert "[Atomics][LoopIdiom] Recognize unordered atomic memcpy"
This reverts commit r304310.
It caused build failures in polly and mingw
due to undefined reference to
llvm::RTLIB::getMEMCPY_ELEMENT_ATOMIC.
llvm-svn: 304315
diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
index ebd6f1e..c6a05ec 100644
--- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -52,7 +52,6 @@
#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"
@@ -117,7 +116,6 @@
Memset,
MemsetPattern,
Memcpy,
- UnorderedAtomicMemcpy,
DontUse // Dummy retval never to be used. Allows catching errors in retval
// handling.
};
@@ -355,12 +353,8 @@
LoopIdiomRecognize::LegalStoreKind
LoopIdiomRecognize::isLegalStore(StoreInst *SI) {
-
// Don't touch volatile stores.
- if (SI->isVolatile())
- return LegalStoreKind::None;
- // We only want simple or unordered-atomic stores.
- if (!SI->isUnordered())
+ if (!SI->isSimple())
return LegalStoreKind::None;
// Don't convert stores of non-integral pointer types to memsets (which stores
@@ -401,18 +395,15 @@
Value *SplatValue = isBytewiseValue(StoredVal);
Constant *PatternValue = nullptr;
- // Note: memset and memset_pattern on unordered-atomic is yet not supported
- bool UnorderedAtomic = SI->isUnordered() && !SI->isSimple();
-
// If we're allowed to form a memset, and the stored value would be
// acceptable for memset, use it.
- if (!UnorderedAtomic && HasMemset && SplatValue &&
+ if (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 (!UnorderedAtomic && HasMemsetPattern &&
+ } else if (HasMemsetPattern &&
// Don't create memset_pattern16s with address spaces.
StorePtr->getType()->getPointerAddressSpace() == 0 &&
(PatternValue = getMemSetPatternValue(StoredVal, DL))) {
@@ -431,12 +422,7 @@
// The store must be feeding a non-volatile load.
LoadInst *LI = dyn_cast<LoadInst>(SI->getValueOperand());
-
- // Only allow non-volatile loads
- if (!LI || LI->isVolatile())
- return LegalStoreKind::None;
- // Only allow simple or unordered-atomic loads
- if (!LI->isUnordered())
+ if (!LI || !LI->isSimple())
return LegalStoreKind::None;
// See if the pointer expression is an AddRec like {base,+,1} on the current
@@ -452,9 +438,7 @@
return LegalStoreKind::None;
// Success. This store can be converted into a memcpy.
- UnorderedAtomic = UnorderedAtomic || LI->isAtomic();
- return UnorderedAtomic ? LegalStoreKind::UnorderedAtomicMemcpy
- : LegalStoreKind::Memcpy;
+ return LegalStoreKind::Memcpy;
}
// This store can't be transformed into a memset/memcpy.
return LegalStoreKind::None;
@@ -485,7 +469,6 @@
StoreRefsForMemsetPattern[Ptr].push_back(SI);
} break;
case LegalStoreKind::Memcpy:
- case LegalStoreKind::UnorderedAtomicMemcpy:
StoreRefsForMemcpy.push_back(SI);
break;
default:
@@ -899,7 +882,7 @@
/// for (i) A[i] = B[i];
bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(StoreInst *SI,
const SCEV *BECount) {
- assert(SI->isUnordered() && "Expected only non-volatile non-ordered stores.");
+ assert(SI->isSimple() && "Expected only non-volatile stores.");
Value *StorePtr = SI->getPointerOperand();
const SCEVAddRecExpr *StoreEv = cast<SCEVAddRecExpr>(SE->getSCEV(StorePtr));
@@ -909,7 +892,7 @@
// The store must be feeding a non-volatile load.
LoadInst *LI = cast<LoadInst>(SI->getValueOperand());
- assert(LI->isUnordered() && "Expected only non-volatile non-ordered loads.");
+ assert(LI->isSimple() && "Expected only non-volatile stores.");
// 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
@@ -983,49 +966,16 @@
const SCEV *NumBytesS =
SE->getAddExpr(BECount, SE->getOne(IntPtrTy), SCEV::FlagNUW);
+ if (StoreSize != 1)
+ NumBytesS = SE->getMulExpr(NumBytesS, SE->getConstant(IntPtrTy, StoreSize),
+ SCEV::FlagNUW);
- 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());
- Value *NumBytes =
- Expander.expandCodeFor(NumBytesS, IntPtrTy, Preheader->getTerminator());
-
- NewCall = Builder.CreateMemCpy(StoreBasePtr, LoadBasePtr, NumBytes, Align);
- } else {
- // We cannot allow unaligned ops for unordered load/store, so reject
- // anything where the alignment isn't at least the element size.
- if (Align < StoreSize)
- return false;
-
- // 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.
- NewCall->addAttribute(
- 0 + AttributeList::FirstArgIndex,
- Attribute::getWithAlignment(NewCall->getContext(), SI->getAlignment()));
- NewCall->addAttribute(
- 1 + AttributeList::FirstArgIndex,
- Attribute::getWithAlignment(NewCall->getContext(), LI->getAlignment()));
- }
+ CallInst *NewCall =
+ Builder.CreateMemCpy(StoreBasePtr, LoadBasePtr, NumBytes,
+ std::min(SI->getAlignment(), LI->getAlignment()));
NewCall->setDebugLoc(SI->getDebugLoc());
DEBUG(dbgs() << " Formed memcpy: " << *NewCall << "\n"