maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. 

Simplify Consecutive Merge Store Candidate Search

  Now that address aliasing is much less conservative, push through
  simplified store merging search which only checks for parallel stores
  through the chain subgraph. This is cleaner as the separation of
  non-interfering loads/stores from the store-merging logic.

  Whem merging stores, search up the chain through a single load, and
  finds all possible stores by looking down from through a load and a
  TokenFactor to all stores visited. This improves the quality of the
  output SelectionDAG and generally the output CodeGen (with some
  exceptions).

  Additional Minor Changes:

    1. Finishes removing unused AliasLoad code
    2. Unifies the the chain aggregation in the merged stores across
       code paths
    3. Re-add the Store node to the worklist after calling
       SimplifyDemandedBits.
    4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
       arbitrary, but seemed sufficient to not cause regressions in
       tests.

  This finishes the change Matt Arsenault started in r246307 and
  jyknight's original patch.

  Many tests required some changes as memory operations are now
  reorderable. Some tests relying on the order were changed to use
  volatile memory operations

  Noteworthy tests:

    CodeGen/AArch64/argument-blocks.ll -
      It's not entirely clear what the test_varargs_stackalign test is
      supposed to be asserting, but the new code looks right.

    CodeGen/AArch64/arm64-memset-inline.lli -
    CodeGen/AArch64/arm64-stur.ll -
    CodeGen/ARM/memset-inline.ll -
      The backend now generates *worse* code due to store merging
      succeeding, as we do do a 16-byte constant-zero store efficiently.

    CodeGen/AArch64/merge-store.ll -
      Improved, but there still seems to be an extraneous vector insert
      from an element to itself?

    CodeGen/PowerPC/ppc64-align-long-double.ll -
      Worse code emitted in this case, due to the improved store->load
      forwarding.

    CodeGen/X86/dag-merge-fast-accesses.ll -
    CodeGen/X86/MergeConsecutiveStores.ll -
    CodeGen/X86/stores-merging.ll -
    CodeGen/Mips/load-store-left-right.ll -
      Restored correct merging of non-aligned stores

    CodeGen/AMDGPU/promote-alloca-stored-pointer-value.ll -
      Improved. Correctly merges buffer_store_dword calls

    CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll -
      Improved. Sidesteps loading a stored value and merges two stores

    CodeGen/X86/pr18023.ll -
      This test has been removed, as it was asserting incorrect
      behavior. Non-volatile stores *CAN* be moved past volatile loads,
      and now are.

    CodeGen/X86/vector-idiv.ll -
    CodeGen/X86/vector-lzcnt-128.ll -
      It's basically impossible to tell what these tests are actually
      testing. But, looks like the code got better due to the memory
      operations being recognized as non-aliasing.

    CodeGen/X86/win32-eh.ll -
      Both loads of the securitycookie are now merged.

    CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll -
      This test appears to work but no longer exhibits the spill
      behavior.

Reviewers: arsenm, hfinkel, tstellarAMD, nhaehnle, jyknight

Subscribers: wdng, nhaehnle, nemanjai, arsenm, weimingz, niravd, RKSimon, aemerson, qcolombet, resistor, tstellarAMD, t.p.northover, spatel

Differential Revision: https://reviews.llvm.org/D14834

llvm-svn: 282600
This commit is contained in:
Nirav Dave 2016-09-28 15:50:43 +00:00
parent a2ebee6f50
commit e17e055b75
70 changed files with 2331 additions and 2684 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

389
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -51,10 +51,6 @@ STATISTIC(LdStFP2Int , "Number of fp load/store pairs transformed to int");
STATISTIC(SlicedLoads, "Number of load sliced");
namespace {
static cl::opt<bool>
CombinerAA("combiner-alias-analysis", cl::Hidden,
cl::desc("Enable DAG combiner alias-analysis heuristics"));
static cl::opt<bool>
CombinerGlobalAA("combiner-global-alias-analysis", cl::Hidden,
cl::desc("Enable DAG combiner's use of IR alias analysis"));
@ -408,15 +404,12 @@ namespace {
/// Holds a pointer to an LSBaseSDNode as well as information on where it
/// is located in a sequence of memory operations connected by a chain.
struct MemOpLink {
MemOpLink (LSBaseSDNode *N, int64_t Offset, unsigned Seq):
MemNode(N), OffsetFromBase(Offset), SequenceNum(Seq) { }
MemOpLink(LSBaseSDNode *N, int64_t Offset)
: MemNode(N), OffsetFromBase(Offset) {}
// Ptr to the mem node.
LSBaseSDNode *MemNode;
// Offset from the base ptr.
int64_t OffsetFromBase;
// What is the sequence number of this mem node.
// Lowest mem operand in the DAG starts at zero.
unsigned SequenceNum;
};
/// This is a helper function for visitMUL to check the profitability
@ -431,7 +424,6 @@ namespace {
/// constant build_vector of the stored constant values in Stores.
SDValue getMergedConstantVectorStore(SelectionDAG &DAG, const SDLoc &SL,
ArrayRef<MemOpLink> Stores,
SmallVectorImpl<SDValue> &Chains,
EVT Ty) const;
/// This is a helper function for visitAND and visitZERO_EXTEND. Returns
@ -453,10 +445,8 @@ namespace {
/// This is a helper function for MergeConsecutiveStores.
/// Stores that may be merged are placed in StoreNodes.
/// Loads that may alias with those stores are placed in AliasLoadNodes.
void getStoreMergeAndAliasCandidates(
StoreSDNode* St, SmallVectorImpl<MemOpLink> &StoreNodes,
SmallVectorImpl<LSBaseSDNode*> &AliasLoadNodes);
void getStoreMergeCandidates(StoreSDNode *St,
SmallVectorImpl<MemOpLink> &StoreNodes);
/// Helper function for MergeConsecutiveStores. Checks if
/// Candidate stores have indirect dependency through their
@ -1606,11 +1596,9 @@ SDValue DAGCombiner::visitTokenFactor(SDNode *N) {
Result = DAG.getNode(ISD::TokenFactor, SDLoc(N), MVT::Other, Ops);
}
// Add users to worklist if AA is enabled, since it may introduce
// a lot of new chained token factors while removing memory deps.
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
return CombineTo(N, Result, UseAA /*add to worklist*/);
// Add users to worklist, since we may introduce a lot of new
// chained token factors while removing memory deps.
return CombineTo(N, Result, true /*add to worklist*/);
}
return Result;
@ -10169,11 +10157,22 @@ SDValue DAGCombiner::visitLOAD(SDNode *N) {
// TODO: Handle store large -> read small portion.
// TODO: Handle TRUNCSTORE/LOADEXT
if (ISD::isNormalLoad(N) && !LD->isVolatile()) {
if (ISD::isNON_TRUNCStore(Chain.getNode())) {
// Either a direct store, or a store off of a TokenFactor can be
// forwarded.
if (Chain->getOpcode() == ISD::TokenFactor) {
for (const SDValue &ChainOp : Chain->op_values()) {
if (ISD::isNON_TRUNCStore(ChainOp.getNode())) {
StoreSDNode *PrevST = cast<StoreSDNode>(ChainOp);
if (PrevST->getBasePtr() == Ptr &&
PrevST->getValue().getValueType() == N->getValueType(0))
return CombineTo(N, PrevST->getOperand(1), Chain);
}
}
} else if (ISD::isNON_TRUNCStore(Chain.getNode())) {
StoreSDNode *PrevST = cast<StoreSDNode>(Chain);
if (PrevST->getBasePtr() == Ptr &&
PrevST->getValue().getValueType() == N->getValueType(0))
return CombineTo(N, Chain.getOperand(1), Chain);
return CombineTo(N, PrevST->getOperand(1), Chain);
}
}
@ -10191,14 +10190,7 @@ SDValue DAGCombiner::visitLOAD(SDNode *N) {
}
}
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
#ifndef NDEBUG
if (CombinerAAOnlyFunc.getNumOccurrences() &&
CombinerAAOnlyFunc != DAG.getMachineFunction().getName())
UseAA = false;
#endif
if (UseAA && LD->isUnindexed()) {
if (LD->isUnindexed()) {
// Walk up chain skipping non-aliasing memory nodes.
SDValue BetterChain = FindBetterChain(N, Chain);
@ -11277,14 +11269,14 @@ bool DAGCombiner::isMulAddWithConstProfitable(SDNode *MulNode,
return false;
}
SDValue DAGCombiner::getMergedConstantVectorStore(
SelectionDAG &DAG, const SDLoc &SL, ArrayRef<MemOpLink> Stores,
SmallVectorImpl<SDValue> &Chains, EVT Ty) const {
SDValue DAGCombiner::getMergedConstantVectorStore(SelectionDAG &DAG,
const SDLoc &SL,
ArrayRef<MemOpLink> Stores,
EVT Ty) const {
SmallVector<SDValue, 8> BuildVector;
for (unsigned I = 0, E = Ty.getVectorNumElements(); I != E; ++I) {
StoreSDNode *St = cast<StoreSDNode>(Stores[I].MemNode);
Chains.push_back(St->getChain());
BuildVector.push_back(St->getValue());
}
@ -11300,21 +11292,8 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
int64_t ElementSizeBytes = MemVT.getSizeInBits() / 8;
LSBaseSDNode *FirstInChain = StoreNodes[0].MemNode;
unsigned LatestNodeUsed = 0;
for (unsigned i=0; i < NumStores; ++i) {
// Find a chain for the new wide-store operand. Notice that some
// of the store nodes that we found may not be selected for inclusion
// in the wide store. The chain we use needs to be the chain of the
// latest store node which is *used* and replaced by the wide store.
if (StoreNodes[i].SequenceNum < StoreNodes[LatestNodeUsed].SequenceNum)
LatestNodeUsed = i;
}
SmallVector<SDValue, 8> Chains;
// The latest Node in the DAG.
LSBaseSDNode *LatestOp = StoreNodes[LatestNodeUsed].MemNode;
SDLoc DL(StoreNodes[0].MemNode);
SDValue StoredVal;
@ -11330,7 +11309,7 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
assert(TLI.isTypeLegal(Ty) && "Illegal vector store");
if (IsConstantSrc) {
StoredVal = getMergedConstantVectorStore(DAG, DL, StoreNodes, Chains, Ty);
StoredVal = getMergedConstantVectorStore(DAG, DL, StoreNodes, Ty);
} else {
SmallVector<SDValue, 8> Ops;
for (unsigned i = 0; i < NumStores; ++i) {
@ -11340,7 +11319,6 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
if (Val.getValueType() != MemVT)
return false;
Ops.push_back(Val);
Chains.push_back(St->getChain());
}
// Build the extracted vector elements back into a vector.
@ -11360,7 +11338,6 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
for (unsigned i = 0; i < NumStores; ++i) {
unsigned Idx = IsLE ? (NumStores - 1 - i) : i;
StoreSDNode *St = cast<StoreSDNode>(StoreNodes[Idx].MemNode);
Chains.push_back(St->getChain());
SDValue Val = St->getValue();
StoreInt <<= ElementSizeBytes * 8;
@ -11378,7 +11355,11 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
StoredVal = DAG.getConstant(StoreInt, DL, StoreTy);
}
assert(!Chains.empty());
SmallVector<SDValue, 8> Chains;
// Gather all Chains we're inheriting
for (unsigned i = 0; i < NumStores; ++i)
Chains.push_back(StoreNodes[i].MemNode->getChain());
SDValue NewChain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chains);
SDValue NewStore = DAG.getStore(NewChain, DL, StoredVal,
@ -11386,45 +11367,19 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
FirstInChain->getPointerInfo(),
FirstInChain->getAlignment());
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
if (UseAA) {
// Replace all merged stores with the new store.
for (unsigned i = 0; i < NumStores; ++i)
CombineTo(StoreNodes[i].MemNode, NewStore);
} else {
// Replace the last store with the new store.
CombineTo(LatestOp, NewStore);
// Erase all other stores.
for (unsigned i = 0; i < NumStores; ++i) {
if (StoreNodes[i].MemNode == LatestOp)
continue;
StoreSDNode *St = cast<StoreSDNode>(StoreNodes[i].MemNode);
// ReplaceAllUsesWith will replace all uses that existed when it was
// called, but graph optimizations may cause new ones to appear. For
// example, the case in pr14333 looks like
//
// St's chain -> St -> another store -> X
//
// And the only difference from St to the other store is the chain.
// When we change it's chain to be St's chain they become identical,
// get CSEed and the net result is that X is now a use of St.
// Since we know that St is redundant, just iterate.
while (!St->use_empty())
DAG.ReplaceAllUsesWith(SDValue(St, 0), St->getChain());
deleteAndRecombine(St);
}
}
// Replace all merged stores with the new store
for (unsigned i = 0; i < NumStores; ++i)
CombineTo(StoreNodes[i].MemNode, NewStore);
return true;
}
void DAGCombiner::getStoreMergeAndAliasCandidates(
StoreSDNode* St, SmallVectorImpl<MemOpLink> &StoreNodes,
SmallVectorImpl<LSBaseSDNode*> &AliasLoadNodes) {
void DAGCombiner::getStoreMergeCandidates(
StoreSDNode *St, SmallVectorImpl<MemOpLink> &StoreNodes) {
// This holds the base pointer, index, and the offset in bytes from the base
// pointer.
BaseIndexOffset BasePtr = BaseIndexOffset::match(St->getBasePtr(), DAG);
EVT MemVT = St->getMemoryVT();
// We must have a base and an offset.
if (!BasePtr.Base.getNode())
@ -11434,104 +11389,49 @@ void DAGCombiner::getStoreMergeAndAliasCandidates(
if (BasePtr.Base.isUndef())
return;
// Walk up the chain and look for nodes with offsets from the same
// base pointer. Stop when reaching an instruction with a different kind
// or instruction which has a different base pointer.
EVT MemVT = St->getMemoryVT();
unsigned Seq = 0;
StoreSDNode *Index = St;
// We looking for a root node which is an ancestor to all mergable
// stores. We search up through a load, to our root and then down
// through all children. For instance we will find Store{1,2,3} if
// St is Store1, Store2. or Store3 where the root is not a load
// which always true for nonvolatile ops. TODO: Expand
// the search to find all valid candidates through multiple layers of loads.
//
// Root
// |-------|-------|
// Load Load Store3
// | |
// Store1 Store2
//
// FIXME: We should be able to climb and
// descend TokenFactors to find candidates as well.
SDNode *RootNode = (St->getChain()).getNode();
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
// Set of Parents of Candidates
std::set<SDNode *> CandidateParents;
if (UseAA) {
// Look at other users of the same chain. Stores on the same chain do not
// alias. If combiner-aa is enabled, non-aliasing stores are canonicalized
// to be on the same chain, so don't bother looking at adjacent chains.
if (LoadSDNode *Ldn = dyn_cast<LoadSDNode>(RootNode)) {
RootNode = Ldn->getChain().getNode();
for (auto I = RootNode->use_begin(), E = RootNode->use_end(); I != E; ++I)
if (I.getOperandNo() == 0 && isa<LoadSDNode>(*I)) // walk down chain
CandidateParents.insert(*I);
} else
CandidateParents.insert(RootNode);
SDValue Chain = St->getChain();
for (auto I = Chain->use_begin(), E = Chain->use_end(); I != E; ++I) {
if (StoreSDNode *OtherST = dyn_cast<StoreSDNode>(*I)) {
if (I.getOperandNo() != 0)
continue;
if (OtherST->isVolatile() || OtherST->isIndexed())
continue;
if (OtherST->getMemoryVT() != MemVT)
continue;
BaseIndexOffset Ptr = BaseIndexOffset::match(OtherST->getBasePtr(), DAG);
if (Ptr.equalBaseIndex(BasePtr))
StoreNodes.push_back(MemOpLink(OtherST, Ptr.Offset, Seq++));
}
}
return;
}
while (Index) {
// If the chain has more than one use, then we can't reorder the mem ops.
if (Index != St && !SDValue(Index, 0)->hasOneUse())
break;
// Find the base pointer and offset for this memory node.
BaseIndexOffset Ptr = BaseIndexOffset::match(Index->getBasePtr(), DAG);
// Check that the base pointer is the same as the original one.
if (!Ptr.equalBaseIndex(BasePtr))
break;
// The memory operands must not be volatile.
if (Index->isVolatile() || Index->isIndexed())
break;
// No truncation.
if (Index->isTruncatingStore())
break;
// The stored memory type must be the same.
if (Index->getMemoryVT() != MemVT)
break;
// We do not allow under-aligned stores in order to prevent
// overriding stores. NOTE: this is a bad hack. Alignment SHOULD
// be irrelevant here; what MATTERS is that we not move memory
// operations that potentially overlap past each-other.
if (Index->getAlignment() < MemVT.getStoreSize())
break;
// We found a potential memory operand to merge.
StoreNodes.push_back(MemOpLink(Index, Ptr.Offset, Seq++));
// Find the next memory operand in the chain. If the next operand in the
// chain is a store then move up and continue the scan with the next
// memory operand. If the next operand is a load save it and use alias
// information to check if it interferes with anything.
SDNode *NextInChain = Index->getChain().getNode();
while (1) {
if (StoreSDNode *STn = dyn_cast<StoreSDNode>(NextInChain)) {
// We found a store node. Use it for the next iteration.
Index = STn;
break;
} else if (LoadSDNode *Ldn = dyn_cast<LoadSDNode>(NextInChain)) {
if (Ldn->isVolatile()) {
Index = nullptr;
break;
// check all parents of mergable children
for (auto P = CandidateParents.begin(); P != CandidateParents.end(); ++P)
for (auto I = (*P)->use_begin(), E = (*P)->use_end(); I != E; ++I)
if (I.getOperandNo() == 0)
if (StoreSDNode *OtherST = dyn_cast<StoreSDNode>(*I)) {
if (OtherST->isVolatile() || OtherST->isIndexed())
continue;
if (OtherST->getMemoryVT() != MemVT)
continue;
BaseIndexOffset Ptr =
BaseIndexOffset::match(OtherST->getBasePtr(), DAG);
if (Ptr.equalBaseIndex(BasePtr))
StoreNodes.push_back(MemOpLink(OtherST, Ptr.Offset));
}
// Save the load node for later. Continue the scan.
AliasLoadNodes.push_back(Ldn);
NextInChain = Ldn->getChain().getNode();
continue;
} else {
Index = nullptr;
break;
}
}
}
}
// We need to check that merging these stores does not cause a loop
@ -11592,67 +11492,36 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
if (MemVT.isVector() && IsLoadSrc)
return false;
// Only look at ends of store sequences.
SDValue Chain = SDValue(St, 0);
if (Chain->hasOneUse() && Chain->use_begin()->getOpcode() == ISD::STORE)
return false;
// Save the LoadSDNodes that we find in the chain.
// We need to make sure that these nodes do not interfere with
// any of the store nodes.
SmallVector<LSBaseSDNode*, 8> AliasLoadNodes;
// Save the StoreSDNodes that we find in the chain.
// Find potential store merge candidates by searching through chain sub-DAG
SmallVector<MemOpLink, 8> StoreNodes;
getStoreMergeAndAliasCandidates(St, StoreNodes, AliasLoadNodes);
getStoreMergeCandidates(St, StoreNodes);
// Check if there is anything to merge.
if (StoreNodes.size() < 2)
return false;
// only do dependence check in AA case
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
if (UseAA && !checkMergeStoreCandidatesForDependencies(StoreNodes))
// Check that we can merge these candidates without causing a cycle
if (!checkMergeStoreCandidatesForDependencies(StoreNodes))
return false;
// Sort the memory operands according to their distance from the
// base pointer. As a secondary criteria: make sure stores coming
// later in the code come first in the list. This is important for
// the non-UseAA case, because we're merging stores into the FINAL
// store along a chain which potentially contains aliasing stores.
// Thus, if there are multiple stores to the same address, the last
// one can be considered for merging but not the others.
// base pointer.
std::sort(StoreNodes.begin(), StoreNodes.end(),
[](MemOpLink LHS, MemOpLink RHS) {
return LHS.OffsetFromBase < RHS.OffsetFromBase ||
(LHS.OffsetFromBase == RHS.OffsetFromBase &&
LHS.SequenceNum < RHS.SequenceNum);
});
return LHS.OffsetFromBase < RHS.OffsetFromBase;
});
// Scan the memory operations on the chain and find the first non-consecutive
// store memory address.
unsigned LastConsecutiveStore = 0;
int64_t StartAddress = StoreNodes[0].OffsetFromBase;
for (unsigned i = 0, e = StoreNodes.size(); i < e; ++i) {
// Check that the addresses are consecutive starting from the second
// element in the list of stores.
if (i > 0) {
int64_t CurrAddress = StoreNodes[i].OffsetFromBase;
if (CurrAddress - StartAddress != (ElementSizeBytes * i))
break;
}
// Check if this store interferes with any of the loads that we found.
// If we find a load that alias with this store. Stop the sequence.
if (any_of(AliasLoadNodes, [&](LSBaseSDNode *Ldn) {
return isAlias(Ldn, StoreNodes[i].MemNode);
}))
// Check that the addresses are consecutive starting from the second
// element in the list of stores.
for (unsigned i = 1, e = StoreNodes.size(); i < e; ++i) {
int64_t CurrAddress = StoreNodes[i].OffsetFromBase;
if (CurrAddress - StartAddress != (ElementSizeBytes * i))
break;
// Mark this node as useful.
LastConsecutiveStore = i;
}
@ -11806,7 +11675,7 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
}
// We found a potential memory operand to merge.
LoadNodes.push_back(MemOpLink(Ld, LdPtr.Offset, 0));
LoadNodes.push_back(MemOpLink(Ld, LdPtr.Offset));
}
if (LoadNodes.size() < 2)
@ -11895,22 +11764,8 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
// Collect the chains from all merged stores.
SmallVector<SDValue, 8> MergeStoreChains;
MergeStoreChains.push_back(StoreNodes[0].MemNode->getChain());
// The latest Node in the DAG.
unsigned LatestNodeUsed = 0;
for (unsigned i=1; i<NumElem; ++i) {
// Find a chain for the new wide-store operand. Notice that some
// of the store nodes that we found may not be selected for inclusion
// in the wide store. The chain we use needs to be the chain of the
// latest store node which is *used* and replaced by the wide store.
if (StoreNodes[i].SequenceNum < StoreNodes[LatestNodeUsed].SequenceNum)
LatestNodeUsed = i;
for (unsigned i = 0; i < NumElem; ++i)
MergeStoreChains.push_back(StoreNodes[i].MemNode->getChain());
}
LSBaseSDNode *LatestOp = StoreNodes[LatestNodeUsed].MemNode;
// Find if it is better to use vectors or integers to load and store
// to memory.
@ -11945,23 +11800,9 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
SDValue(NewLoad.getNode(), 1));
}
if (UseAA) {
// Replace the all stores with the new store.
for (unsigned i = 0; i < NumElem; ++i)
CombineTo(StoreNodes[i].MemNode, NewStore);
} else {
// Replace the last store with the new store.
CombineTo(LatestOp, NewStore);
// Erase all other stores.
for (unsigned i = 0; i < NumElem; ++i) {
// Remove all Store nodes.
if (StoreNodes[i].MemNode == LatestOp)
continue;
StoreSDNode *St = cast<StoreSDNode>(StoreNodes[i].MemNode);
DAG.ReplaceAllUsesOfValueWith(SDValue(St, 0), St->getChain());
deleteAndRecombine(St);
}
}
// Replace the all stores with the new store.
for (unsigned i = 0; i < NumElem; ++i)
CombineTo(StoreNodes[i].MemNode, NewStore);
return true;
}
@ -12119,19 +11960,7 @@ SDValue DAGCombiner::visitSTORE(SDNode *N) {
if (SDValue NewST = TransformFPLoadStorePair(N))
return NewST;
bool UseAA = CombinerAA.getNumOccurrences() > 0 ? CombinerAA
: DAG.getSubtarget().useAA();
#ifndef NDEBUG
if (CombinerAAOnlyFunc.getNumOccurrences() &&
CombinerAAOnlyFunc != DAG.getMachineFunction().getName())
UseAA = false;
#endif
if (UseAA && ST->isUnindexed()) {
// FIXME: We should do this even without AA enabled. AA will just allow
// FindBetterChain to work in more situations. The problem with this is that
// any combine that expects memory operations to be on consecutive chains
// first needs to be updated to look for users of the same chain.
if (ST->isUnindexed()) {
// Walk up chain skipping non-aliasing memory nodes, on this store and any
// adjacent stores.
if (findBetterNeighborChains(ST)) {
@ -12165,8 +11994,13 @@ SDValue DAGCombiner::visitSTORE(SDNode *N) {
if (SimplifyDemandedBits(
Value,
APInt::getLowBitsSet(Value.getScalarValueSizeInBits(),
ST->getMemoryVT().getScalarSizeInBits())))
ST->getMemoryVT().getScalarSizeInBits()))) {
// Re-visit the store if anything changed; SimplifyDemandedBits
// will add Value's node back to the worklist if necessary, but
// we also need to re-visit the Store node itself.
AddToWorklist(N);
return SDValue(N, 0);
}
}
// If this is a load followed by a store to the same location, then the store
@ -15159,6 +14993,18 @@ SDValue DAGCombiner::FindBetterChain(SDNode *N, SDValue OldChain) {
return DAG.getNode(ISD::TokenFactor, SDLoc(N), MVT::Other, Aliases);
}
// This function tries to collect a bunch of potentially interesting
// nodes to improve the chains of, all at once. This might seem
// redundant, as this function gets called when visiting every store
// node, so why not let the work be done on each store as it's visited?
//
// I believe this is mainly important because MergeConsecutiveStores
// is unable to deal with merging stores of different sizes, so unless
// we improve the chains of all the potential candidates up-front
// before running MergeConsecutiveStores, it might only see some of
// the nodes that will eventually be candidates, and then not be able
// to go from a partially-merged state to the desired final
// fully-merged state.
bool DAGCombiner::findBetterNeighborChains(StoreSDNode *St) {
// This holds the base pointer, index, and the offset in bytes from the base
// pointer.
@ -15194,10 +15040,8 @@ bool DAGCombiner::findBetterNeighborChains(StoreSDNode *St) {
if (!Ptr.equalBaseIndex(BasePtr))
break;
// Find the next memory operand in the chain. If the next operand in the
// chain is a store then move up and continue the scan with the next
// memory operand. If the next operand is a load save it and use alias
// information to check if it interferes with anything.
// Walk up the chain to find the next store node, ignoring any
// intermediate loads. Any other kind of node will halt the loop.
SDNode *NextInChain = Index->getChain().getNode();
while (true) {
if (StoreSDNode *STn = dyn_cast<StoreSDNode>(NextInChain)) {
@ -15216,9 +15060,14 @@ bool DAGCombiner::findBetterNeighborChains(StoreSDNode *St) {
Index = nullptr;
break;
}
}
} // end while
}
// At this point, ChainedStores lists all of the Store nodes
// reachable by iterating up through chain nodes matching the above
// conditions. For each such store identified, try to find an
// earlier chain to attach the store to which won't violate the
// required ordering.
bool MadeChangeToSt = false;
SmallVector<std::pair<StoreSDNode *, SDValue>, 8> BetterChains;

2
llvm/lib/CodeGen/TargetLoweringBase.cpp
View File

@ -824,7 +824,7 @@ TargetLoweringBase::TargetLoweringBase(const TargetMachine &tm) : TM(tm) {
MinFunctionAlignment = 0;
PrefFunctionAlignment = 0;
PrefLoopAlignment = 0;
GatherAllAliasesMaxDepth = 6;
GatherAllAliasesMaxDepth = 18;
MinStackArgumentAlignment = 1;
MinimumJumpTableEntries = 4;
// TODO: the default will be switched to 0 in the next commit, along

10
llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
View File

@ -446,16 +446,6 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM,
setSelectIsExpensive(false);
PredictableSelectIsExpensive = false;
// We want to find all load dependencies for long chains of stores to enable
// merging into very wide vectors. The problem is with vectors with > 4
// elements. MergeConsecutiveStores will attempt to merge these because x8/x16
// vectors are a legal type, even though we have to split the loads
// usually. When we can more precisely specify load legality per address
// space, we should be able to make FindBetterChain/MergeConsecutiveStores
// smarter so that they can figure out what to do in 2 iterations without all
// N > 4 stores on the same chain.
GatherAllAliasesMaxDepth = 16;
// FIXME: Need to really handle these.
MaxStoresPerMemcpy = 4096;
MaxStoresPerMemmove = 4096;

2
llvm/test/CodeGen/AArch64/argument-blocks.ll
View File

@ -62,7 +62,7 @@ define i64 @test_hfa_ignores_gprs([7 x float], [2 x float] %in, i64, i64 %res) {
; but should go in an 8-byte aligned slot.
define void @test_varargs_stackalign() {
; CHECK-LABEL: test_varargs_stackalign:
; CHECK-DARWINPCS: stp {{w[0-9]+}}, {{w[0-9]+}}, [sp, #16]
; CHECK-DARWINPCS: str {{x[0-9]+}}, [sp, #16]
call void(...) @callee([3 x float] undef, [2 x float] [float 1.0, float 2.0])
ret void

12
llvm/test/CodeGen/AArch64/arm64-abi-varargs.ll
View File

@ -6,17 +6,13 @@
define void @fn9(i32 %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6, i32 %a7, i32 %a8, i32 %a9, ...) nounwind noinline ssp {
; CHECK-LABEL: fn9:
; 9th fixed argument
; CHECK: ldr {{w[0-9]+}}, [sp, #64]
; CHECK: add [[ARGS:x[0-9]+]], sp, #72
; CHECK: add {{x[0-9]+}}, [[ARGS]], #8
; CHECK: add x[[ADDR:[0-9]+]], sp, #72
; First vararg
; CHECK: ldr {{w[0-9]+}}, [sp, #72]
; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, #8
; CHECK-DAG: ldr {{w[0-9]+}}, [sp, #72]
; Second vararg
; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}]
; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, #8
; CHECK-DAG: ldr {{w[0-9]+}}, [x[[ADDR]]]
; Third vararg
; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}]
; CHECK-DAG: ldr {{w[0-9]+}}, [x[[ADDR]]], #8
%1 = alloca i32, align 4
%2 = alloca i32, align 4
%3 = alloca i32, align 4

5
llvm/test/CodeGen/AArch64/arm64-abi.ll
View File

@ -205,10 +205,7 @@ declare i32 @args_i32(i32, i32, i32, i32, i32, i32, i32, i32, i16 signext, i32,
define i32 @test8(i32 %argc, i8** nocapture %argv) nounwind {
entry:
; CHECK-LABEL: test8
; CHECK: strb {{w[0-9]+}}, [sp, #3]
; CHECK: strb wzr, [sp, #2]
; CHECK: strb {{w[0-9]+}}, [sp, #1]
; CHECK: strb wzr, [sp]
; CHECK: str w8, [sp]
; CHECK: bl
; FAST-LABEL: test8
; FAST: strb {{w[0-9]+}}, [sp]

6
llvm/test/CodeGen/AArch64/arm64-memset-inline.ll
View File

@ -9,11 +9,15 @@ entry:
ret void
}
; FIXME: This shouldn't need to load in a zero value to store
; (e.g. stp xzr,xzr [sp, #16])
define void @t2() nounwind ssp {
entry:
; CHECK-LABEL: t2:
; CHECK: movi v0.2d, #0000000000000000
; CHECK: stur q0, [sp, #16]
; CHECK: strh wzr, [sp, #32]
; CHECK: stp xzr, xzr, [sp, #16]
; CHECK: str xzr, [sp, #8]
%buf = alloca [26 x i8], align 1
%0 = getelementptr inbounds [26 x i8], [26 x i8]* %buf, i32 0, i32 0

7
llvm/test/CodeGen/AArch64/arm64-stur.ll
View File

@ -47,11 +47,14 @@ define void @foo5(i8* %p, i32 %val) nounwind {
ret void
}
;; FIXME: Again, with the writing of a quadword zero...
define void @foo(%struct.X* nocapture %p) nounwind optsize ssp {
; CHECK-LABEL: foo:
; CHECK-NOT: str
; CHECK: stur xzr, [x0, #12]
; CHECK-NEXT: stur xzr, [x0, #4]
; CHECK: stur q0, [x0, #4]
; CHECK-FIXME: stur xzr, [x0, #12]
; CHECK-FIXME-NEXT: stur xzr, [x0, #4]
; CHECK-NEXT: ret
%B = getelementptr inbounds %struct.X, %struct.X* %p, i64 0, i32 1
%val = bitcast i64* %B to i8*

5
llvm/test/CodeGen/AArch64/merge-store.ll
View File

@ -4,8 +4,9 @@
@g0 = external global <3 x float>, align 16
@g1 = external global <3 x float>, align 4
; CHECK: ldr s[[R0:[0-9]+]], {{\[}}[[R1:x[0-9]+]]{{\]}}, #4
; CHECK: ld1{{\.?s?}} { v[[R0]]{{\.?s?}} }[1], {{\[}}[[R1]]{{\]}}
; CHECK: ldr q[[R0:[0-9]+]], {{\[}}[[R1:x[0-9]+]], :lo12:g0
;; TODO: this next line seems like a redundant no-op move?
; CHECK: ins v0.s[1], v0.s[1]
; CHECK: str d[[R0]]
define void @blam() {

3
llvm/test/CodeGen/AArch64/vector_merge_dep_check.ll
View File

@ -1,5 +1,4 @@
; RUN: llc --combiner-alias-analysis=false < %s | FileCheck %s
; RUN: llc --combiner-alias-analysis=true < %s | FileCheck %s
; RUN: llc < %s | FileCheck %s
; This test checks that we do not merge stores together which have
; dependencies through their non-chain operands (e.g. one store is the

3
llvm/test/CodeGen/AMDGPU/cvt_f32_ubyte.ll
View File

@ -88,12 +88,9 @@ define void @load_v4i8_to_v4f32_unaligned(<4 x float> addrspace(1)* noalias %out
; SI-DAG: v_cvt_f32_ubyte2_e32
; SI-DAG: v_cvt_f32_ubyte3_e32
; SI-DAG: v_lshrrev_b32_e32 v{{[0-9]+}}, 24
; SI-DAG: v_lshrrev_b32_e32 v{{[0-9]+}}, 16
; SI-DAG: v_lshlrev_b32_e32 v{{[0-9]+}}, 16
; SI-DAG: v_lshlrev_b32_e32 v{{[0-9]+}}, 8
; SI-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xffff,
; SI-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xff00,
; SI-DAG: v_add_i32
; SI: buffer_store_dwordx4

24
llvm/test/CodeGen/AMDGPU/debugger-insert-nops.ll
View File

@ -1,13 +1,21 @@
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s --check-prefix=CHECK
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s --check-prefix=CHECKNOP
; CHECK: test01.cl:2:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; This test expects that we have one instance for each line in some order with "s_nop 0" instances after each.
; CHECK: test01.cl:3:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; Check that each line appears at least once
; CHECK-DAG: test01.cl:2:3
; CHECK-DAG: test01.cl:3:3
; CHECK-DAG: test01.cl:4:3
; CHECK: test01.cl:4:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; Check that each of each of the lines consists of the line output, followed by "s_nop 0"
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECK: test01.cl:5:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
@ -21,7 +29,7 @@ entry:
call void @llvm.dbg.declare(metadata i32 addrspace(1)** %A.addr, metadata !17, metadata !18), !dbg !19
%0 = load i32 addrspace(1)*, i32 addrspace(1)** %A.addr, align 4, !dbg !20
%arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %0, i32 0, !dbg !20
store i32 1, i32 addrspace(1)* %arrayidx, align 4, !dbg !21
store i32 1, i32 addrspace(1)* %arrayidx, align 4, !dbg !20
%1 = load i32 addrspace(1)*, i32 addrspace(1)** %A.addr, align 4, !dbg !22
%arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %1, i32 1, !dbg !22
store i32 2, i32 addrspace(1)* %arrayidx1, align 4, !dbg !23

30
llvm/test/CodeGen/AMDGPU/merge-stores.ll
View File

@ -1,8 +1,5 @@
; RUN: llc -march=amdgcn -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-NOAA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-NOAA %s
; RUN: llc -march=amdgcn -verify-machineinstrs -combiner-alias-analysis -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -combiner-alias-analysis -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; This test is mostly to test DAG store merging, so disable the vectorizer.
; Run with devices with different unaligned load restrictions.
@ -149,17 +146,10 @@ define void @merge_global_store_4_constants_f32(float addrspace(1)* %out) #0 {
ret void
}
; FIXME: Should be able to merge this
; GCN-LABEL: {{^}}merge_global_store_4_constants_mixed_i32_f32:
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-AA: buffer_store_dwordx2
; GCN-AA: buffer_store_dword v
; GCN-AA: buffer_store_dword v
; GCN: buffer_store_dwordx2
; GCN: buffer_store_dword v
; GCN: buffer_store_dword v
; GCN: s_endpgm
define void @merge_global_store_4_constants_mixed_i32_f32(float addrspace(1)* %out) #0 {
%out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
@ -478,17 +468,9 @@ define void @merge_global_store_4_adjacent_loads_i8_natural_align(i8 addrspace(1
ret void
}
; This works once AA is enabled on the subtarget
; GCN-LABEL: {{^}}merge_global_store_4_vector_elts_loads_v4i32:
; GCN: buffer_load_dwordx4 [[LOAD:v\[[0-9]+:[0-9]+\]]]
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-AA: buffer_store_dwordx4 [[LOAD]]
; GCN: buffer_store_dwordx4 [[LOAD]]
; GCN: s_endpgm
define void @merge_global_store_4_vector_elts_loads_v4i32(i32 addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
%out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1

8
llvm/test/CodeGen/AMDGPU/private-element-size.ll
View File

@ -32,10 +32,10 @@
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:28{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
define void @private_elt_size_v4i32(<4 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()

17
llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
View File

@ -156,9 +156,8 @@ define void @reorder_global_load_local_store_global_load(i32 addrspace(1)* %out,
; FUNC-LABEL: @reorder_local_offsets
; CI: ds_read2_b32 {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}} offset0:100 offset1:102
; CI: ds_write2_b32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}} offset0:3 offset1:100
; CI: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:12
; CI: ds_write_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:408
; CI-DAG: ds_write2_b32 {{v[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset0:3 offset1:100
; CI-DAG: ds_write_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:408
; CI: buffer_store_dword
; CI: s_endpgm
define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(3)* noalias nocapture %ptr0) #0 {
@ -180,12 +179,12 @@ define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspa
}
; FUNC-LABEL: @reorder_global_offsets
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI-DAG: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI-DAG: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_store_dword
; CI: s_endpgm
define void @reorder_global_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(1)* noalias nocapture %ptr0) #0 {
%ptr1 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i32 3

7
llvm/test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll
View File

@ -3,6 +3,13 @@
; RUN: llc -march=amdgcn -mcpu=hawaii -mtriple=amdgcn-unknown-amdhsa -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CIHSA -check-prefix=HSA %s
; RUN: llc -march=amdgcn -mcpu=fiji -mtriple=amdgcn-unknown-amdhsa -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VIHSA -check-prefix=HSA %s
; FIXME: this fails because the load generated from extractelement is
;; now properly recognized as forwardable to the value stored in
;; insertelement, and thus the loads/stores drop away entirely. This
;; makes the intended test, of running out of registers, not occur.
;; XFAIL: *
; This ends up using all 256 registers and requires register
; scavenging which will fail to find an unsued register.

6
llvm/test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot.ll
View File

@ -1,6 +1,12 @@
; RUN: llc -march=amdgcn -mcpu=tahiti -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=fiji -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
;; FIXME: this fails because the load generated from extractelement is
;; now properly recognized as forwardable to the value stored in
;; insertelement, and thus the loads/stores drop away entirely. This
;; makes the intended test, of running out of registers, not occur.
;; XFAIL: *
; This ends up using all 255 registers and requires register
; scavenging which will fail to find an unsued register.

3
llvm/test/CodeGen/ARM/2012-10-04-AAPCS-byval-align8.ll
View File

@ -12,7 +12,8 @@ define void @test_byval_8_bytes_alignment(i32 %i, ...) {
entry:
; CHECK: sub sp, sp, #12
; CHECK: sub sp, sp, #4
; CHECK: stmib sp, {r1, r2, r3}
; CHECK: add r0, sp, #4
; CHECK: stm sp, {r0, r1, r2, r3}
%g = alloca i8*
%g1 = bitcast i8** %g to i8*
call void @llvm.va_start(i8* %g1)

4
llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll
View File

@ -51,12 +51,12 @@ entry:
; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; REALIGN: orr r[[R2:[0-9]+]], r[[R1:[0-9]+]], #48
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: orr r[[R2:[0-9]+]], r[[R1]], #32
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: orr r[[R2:[0-9]+]], r[[R1]], #16
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: orr r[[R1:[0-9]+]], r[[R1]], #16
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; REALIGN: add r[[R1:[0-9]+]], r[[R0:0]], #48

2
llvm/test/CodeGen/ARM/ifcvt10.ll
View File

@ -9,8 +9,6 @@ entry:
; CHECK-LABEL: t:
; CHECK: vpop {d8}
; CHECK-NOT: vpopne
; CHECK: pop {r7, pc}
; CHECK: vpop {d8}
; CHECK: pop {r7, pc}
br i1 undef, label %if.else, label %if.then

10
llvm/test/CodeGen/ARM/memset-inline.ll
View File

@ -3,9 +3,15 @@
define void @t1(i8* nocapture %c) nounwind optsize {
entry:
; CHECK-LABEL: t1:
;; FIXME: like with arm64-memset-inline.ll, learning how to merge
;; stores made this code worse, since it now uses a vector move,
;; instead of just using an strd instruction taking two registers.
; CHECK: vmov.i32 d16, #0x0
; CHECK: vst1.32 {d16}, [r0:64]!
; CHECK: movs r1, #0
; CHECK: strd r1, r1, [r0]
; CHECK: str r1, [r0, #8]
; CHECK: str r1, [r0]
call void @llvm.memset.p0i8.i64(i8* %c, i8 0, i64 12, i32 8, i1 false)
ret void
}

6
llvm/test/CodeGen/ARM/static-addr-hoisting.ll
View File

@ -6,9 +6,9 @@ define void @multiple_store() {
; CHECK: movs [[VAL:r[0-9]+]], #42
; CHECK: movt r[[BASE1]], #15
; CHECK: str [[VAL]], [r[[BASE1]]]
; CHECK: str [[VAL]], [r[[BASE1]], #24]
; CHECK: str.w [[VAL]], [r[[BASE1]], #42]
; CHECK-DAG: str [[VAL]], [r[[BASE1]]]
; CHECK-DAG: str [[VAL]], [r[[BASE1]], #24]
; CHECK-DAG: str.w [[VAL]], [r[[BASE1]], #42]
; CHECK: movw r[[BASE2:[0-9]+]], #20394
; CHECK: movt r[[BASE2]], #18

60
llvm/test/CodeGen/BPF/undef.ll
View File

@ -12,51 +12,51 @@
@llvm.used = appending global [6 x i8*] [i8* getelementptr inbounds ([4 x i8], [4 x i8]* @_license, i32 0, i32 0), i8* bitcast (i32 (%struct.__sk_buff*)* @ebpf_filter to i8*), i8* bitcast (%struct.bpf_map_def* @routing to i8*), i8* bitcast (%struct.bpf_map_def* @routing_miss_0 to i8*), i8* bitcast (%struct.bpf_map_def* @test1 to i8*), i8* bitcast (%struct.bpf_map_def* @test1_miss_4 to i8*)], section "llvm.metadata"
; Function Attrs: nounwind uwtable
; CHECK: mov r2, r10
; CHECK: addi r2, -2
; CHECK: mov r1, 0
; CHECK: sth 6(r2), r1
; CHECK: sth 4(r2), r1
; CHECK: sth 2(r2), r1
; CHECK: mov r2, 6
; CHECK: stb -7(r10), r2
; CHECK: mov r2, 5
; CHECK: stb -8(r10), r2
; CHECK: mov r2, 7
; CHECK: stb -6(r10), r2
; CHECK: mov r2, 8
; CHECK: stb -5(r10), r2
; CHECK: mov r2, 9
; CHECK: stb -4(r10), r2
; CHECK: mov r2, 10
; CHECK: stb -3(r10), r2
; CHECK: sth 24(r10), r1
; CHECK: sth 22(r10), r1
; CHECK: sth 20(r10), r1
; CHECK: sth 18(r10), r1
; CHECK: sth 16(r10), r1
; CHECK: sth 14(r10), r1
; CHECK: sth 12(r10), r1
; CHECK: sth 10(r10), r1
; CHECK: sth 8(r10), r1
; CHECK: sth 6(r10), r1
; CHECK: sth -2(r10), r1
; CHECK: sth 26(r10), r1
define i32 @ebpf_filter(%struct.__sk_buff* nocapture readnone %ebpf_packet) #0 section "socket1" {
%key = alloca %struct.routing_key_2, align 1
%1 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 0
; CHECK: mov r1, 5
; CHECK: stb -8(r10), r1
store i8 5, i8* %1, align 1
%2 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 1
; CHECK: mov r1, 6
; CHECK: stb -7(r10), r1
store i8 6, i8* %2, align 1
%3 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 2
; CHECK: mov r1, 7
; CHECK: stb -6(r10), r1
store i8 7, i8* %3, align 1
%4 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 3
; CHECK: mov r1, 8
; CHECK: stb -5(r10), r1
store i8 8, i8* %4, align 1
%5 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 4
; CHECK: mov r1, 9
; CHECK: stb -4(r10), r1
store i8 9, i8* %5, align 1
%6 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 5
; CHECK: mov r1, 10
; CHECK: stb -3(r10), r1
store i8 10, i8* %6, align 1
%7 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 1, i32 0, i64 0
; CHECK: mov r1, r10
; CHECK: addi r1, -2
; CHECK: mov r2, 0
; CHECK: sth 6(r1), r2
; CHECK: sth 4(r1), r2
; CHECK: sth 2(r1), r2
; CHECK: sth 24(r10), r2
; CHECK: sth 22(r10), r2
; CHECK: sth 20(r10), r2
; CHECK: sth 18(r10), r2
; CHECK: sth 16(r10), r2
; CHECK: sth 14(r10), r2
; CHECK: sth 12(r10), r2
; CHECK: sth 10(r10), r2
; CHECK: sth 8(r10), r2
; CHECK: sth 6(r10), r2
; CHECK: sth -2(r10), r2
; CHECK: sth 26(r10), r2
call void @llvm.memset.p0i8.i64(i8* %7, i8 0, i64 30, i32 1, i1 false)
%8 = call i32 (%struct.bpf_map_def*, %struct.routing_key_2*, ...) bitcast (i32 (...)* @bpf_map_lookup_elem to i32 (%struct.bpf_map_def*, %struct.routing_key_2*, ...)*)(%struct.bpf_map_def* nonnull @routing, %struct.routing_key_2* nonnull %key) #3
ret i32 undef

2
llvm/test/CodeGen/MSP430/Inst16mm.ll
View File

@ -1,4 +1,4 @@
; RUN: llc -march=msp430 -combiner-alias-analysis < %s | FileCheck %s
; RUN: llc -march=msp430 < %s | FileCheck %s
target datalayout = "e-p:16:8:8-i8:8:8-i16:8:8-i32:8:8"
target triple = "msp430-generic-generic"
@foo = common global i16 0, align 2

24
llvm/test/CodeGen/Mips/cconv/arguments-float.ll
View File

@ -63,39 +63,39 @@ entry:
; NEW-DAG: sd $5, 16([[R2]])
; O32 has run out of argument registers and starts using the stack
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 24($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 28($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 16($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 20($sp)
; O32-DAG: sw [[R3]], 24([[R2]])
; O32-DAG: sw [[R4]], 28([[R2]])
; NEW-DAG: sd $6, 24([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 32($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 36($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 24($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 28($sp)
; O32-DAG: sw [[R3]], 32([[R2]])
; O32-DAG: sw [[R4]], 36([[R2]])
; NEW-DAG: sd $7, 32([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 40($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 44($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 32($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 36($sp)
; O32-DAG: sw [[R3]], 40([[R2]])
; O32-DAG: sw [[R4]], 44([[R2]])
; NEW-DAG: sd $8, 40([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 48($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 52($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 40($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 44($sp)
; O32-DAG: sw [[R3]], 48([[R2]])
; O32-DAG: sw [[R4]], 52([[R2]])
; NEW-DAG: sd $9, 48([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 56($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 60($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 48($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 52($sp)
; O32-DAG: sw [[R3]], 56([[R2]])
; O32-DAG: sw [[R4]], 60([[R2]])
; NEW-DAG: sd $10, 56([[R2]])
; N32/N64 have run out of registers and starts using the stack too
; O32-DAG: lw [[R3:\$[0-9]+]], 64($sp)
; O32-DAG: lw [[R4:\$[0-9]+]], 68($sp)
; O32-DAG: lw [[R3:\$[0-9]+]], 56($sp)
; O32-DAG: lw [[R4:\$[0-9]+]], 60($sp)
; O32-DAG: sw [[R3]], 64([[R2]])
; O32-DAG: sw [[R4]], 68([[R2]])
; NEW-DAG: ld [[R3:\$[0-9]+]], 0($sp)

44
llvm/test/CodeGen/Mips/cconv/arguments-varargs.ll
View File

@ -315,12 +315,11 @@ entry:
; Big-endian mode for N32/N64 must add an additional 4 to the offset due to byte
; order.
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA_TMP2]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -349,10 +348,9 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])
@ -678,12 +676,11 @@ entry:
; Big-endian mode for N32/N64 must add an additional 4 to the offset due to byte
; order.
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA_TMP2]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -712,10 +709,9 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])
@ -1040,10 +1036,9 @@ entry:
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -1072,10 +1067,9 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])

77
llvm/test/CodeGen/Mips/fastcc.ll
View File

@ -132,20 +132,19 @@ entry:
define internal fastcc void @callee0(i32 %a0, i32 %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6, i32 %a7, i32 %a8, i32 %a9, i32 %a10, i32 %a11, i32 %a12, i32 %a13, i32 %a14, i32 %a15, i32 %a16) nounwind noinline {
entry:
; CHECK: callee0
; CHECK: sw $4
; CHECK: sw $5
; CHECK: sw $6
; CHECK: sw $7
; CHECK: sw $8
; CHECK: sw $9
; CHECK: sw $10
; CHECK: sw $11
; CHECK: sw $12
; CHECK: sw $13
; CHECK: sw $14
; CHECK: sw $15
; CHECK: sw $24
; CHECK: sw $3
; CHECK-DAG: sw $4
; CHECK-DAG: sw $5
; CHECK-DAG: sw $7
; CHECK-DAG: sw $8
; CHECK-DAG: sw $9
; CHECK-DAG: sw $10
; CHECK-DAG: sw $11
; CHECK-DAG: sw $12
; CHECK-DAG: sw $13
; CHECK-DAG: sw $14
; CHECK-DAG: sw $15
; CHECK-DAG: sw $24
; CHECK-DAG: sw $3
; t6, t7 and t8 are reserved in NaCl and cannot be used for fastcc.
; CHECK-NACL-NOT: sw $14
@ -223,27 +222,27 @@ entry:
define internal fastcc void @callee1(float %a0, float %a1, float %a2, float %a3, float %a4, float %a5, float %a6, float %a7, float %a8, float %a9, float %a10, float %a11, float %a12, float %a13, float %a14, float %a15, float %a16, float %a17, float %a18, float %a19, float %a20) nounwind noinline {
entry:
; CHECK: callee1
; CHECK: swc1 $f0
; CHECK: swc1 $f1
; CHECK: swc1 $f2
; CHECK: swc1 $f3
; CHECK: swc1 $f4
; CHECK: swc1 $f5
; CHECK: swc1 $f6
; CHECK: swc1 $f7
; CHECK: swc1 $f8
; CHECK: swc1 $f9
; CHECK: swc1 $f10
; CHECK: swc1 $f11
; CHECK: swc1 $f12
; CHECK: swc1 $f13
; CHECK: swc1 $f14
; CHECK: swc1 $f15
; CHECK: swc1 $f16
; CHECK: swc1 $f17
; CHECK: swc1 $f18
; CHECK: swc1 $f19
; CHECK-LABEL: callee1:
; CHECK-DAG: swc1 $f0
; CHECK-DAG: swc1 $f1
; CHECK-DAG: swc1 $f2
; CHECK-DAG: swc1 $f3
; CHECK-DAG: swc1 $f4
; CHECK-DAG: swc1 $f5
; CHECK-DAG: swc1 $f6
; CHECK-DAG: swc1 $f7
; CHECK-DAG: swc1 $f8
; CHECK-DAG: swc1 $f9
; CHECK-DAG: swc1 $f10
; CHECK-DAG: swc1 $f11
; CHECK-DAG: swc1 $f12
; CHECK-DAG: swc1 $f13
; CHECK-DAG: swc1 $f14
; CHECK-DAG: swc1 $f15
; CHECK-DAG: swc1 $f16
; CHECK-DAG: swc1 $f17
; CHECK-DAG: swc1 $f18
; CHECK-DAG: swc1 $f19
store float %a0, float* @gf0, align 4
store float %a1, float* @gf1, align 4
@ -290,7 +289,6 @@ entry:
; NOODDSPREG-DAG: lwc1 $f18, 36($[[R0]])
; NOODDSPREG-DAG: lwc1 $[[F0:f[0-9]*[02468]]], 40($[[R0]])
; NOODDSPREG-DAG: swc1 $[[F0]], 8($sp)
%0 = load float, float* getelementptr ([11 x float], [11 x float]* @fa, i32 0, i32 0), align 4
%1 = load float, float* getelementptr ([11 x float], [11 x float]* @fa, i32 0, i32 1), align 4
@ -316,8 +314,6 @@ entry:
; NOODDSPREG-LABEL: callee2:
; NOODDSPREG: addiu $sp, $sp, -[[OFFSET:[0-9]+]]
; Check that first 10 arguments are received in even float registers
; f0, f2, ... , f18. Check that 11th argument is received on stack.
@ -333,7 +329,7 @@ entry:
; NOODDSPREG-DAG: swc1 $f16, 32($[[R0]])
; NOODDSPREG-DAG: swc1 $f18, 36($[[R0]])
; NOODDSPREG-DAG: lwc1 $[[F0:f[0-9]*[02468]]], [[OFFSET]]($sp)
; NOODDSPREG-DAG: lwc1 $[[F0:f[0-9]*[02468]]], 0($sp)
; NOODDSPREG-DAG: swc1 $[[F0]], 40($[[R0]])
store float %a0, float* getelementptr ([11 x float], [11 x float]* @fa, i32 0, i32 0), align 4
@ -397,7 +393,6 @@ entry:
; FP64-NOODDSPREG-LABEL: callee3:
; FP64-NOODDSPREG: addiu $sp, $sp, -[[OFFSET:[0-9]+]]
; Check that first 10 arguments are received in even float registers
; f0, f2, ... , f18. Check that 11th argument is received on stack.
@ -414,7 +409,7 @@ entry:
; FP64-NOODDSPREG-DAG: sdc1 $f16, 64($[[R0]])
; FP64-NOODDSPREG-DAG: sdc1 $f18, 72($[[R0]])
; FP64-NOODDSPREG-DAG: ldc1 $[[F0:f[0-9]*[02468]]], [[OFFSET]]($sp)
; FP64-NOODDSPREG-DAG: ldc1 $[[F0:f[0-9]*[02468]]], 0($sp)
; FP64-NOODDSPREG-DAG: sdc1 $[[F0]], 80($[[R0]])
store double %a0, double* getelementptr ([11 x double], [11 x double]* @da, i32 0, i32 0), align 8

126
llvm/test/CodeGen/Mips/load-store-left-right.ll
View File

@ -250,12 +250,18 @@ entry:
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s0)(
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s0)(
; FIXME: We should be able to do better than this on MIPS32r6/MIPS64r6 since
; we have unaligned halfword load/store available
; ALL-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; ALL-DAG: sb $[[R1]], 2($[[PTR]])
; ALL-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; ALL-DAG: sb $[[R1]], 3($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 2($[[PTR]])
; MIPS32-DAG: lbu $[[R2:[0-9]+]], 1($[[PTR]])
; MIPS32-DAG: sb $[[R2]], 3($[[PTR]])
; MIPS32R6: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6: sh $[[R1]], 2($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 2($[[PTR]])
; MIPS64-DAG: lbu $[[R2:[0-9]+]], 1($[[PTR]])
; MIPS64-DAG: sb $[[R2]], 3($[[PTR]])
%0 = load %struct.S0, %struct.S0* getelementptr inbounds (%struct.S0, %struct.S0* @struct_s0, i32 0), align 1
store %struct.S0 %0, %struct.S0* getelementptr inbounds (%struct.S0, %struct.S0* @struct_s0, i32 1), align 1
@ -268,37 +274,54 @@ entry:
; MIPS32-EL: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32-EB: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS32-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS32-EL-DAG: swl $[[R1]], 7($[[PTR]])
; MIPS32-EL-DAG: swr $[[R1]], 4($[[PTR]])
; MIPS32-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS32-EB-DAG: swl $[[R1]], 4($[[PTR]])
; MIPS32-EB-DAG: swr $[[R1]], 7($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS32R6: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32R6-DAG: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6-DAG: sh $[[R1]], 4($[[PTR]])
; MIPS32R6-DAG: lhu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32R6-DAG: sh $[[R1]], 6($[[PTR]])
; MIPS32R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6-DAG: sw $[[R1]], 4($[[PTR]])
; MIPS64-EL: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 7($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 4($[[PTR]])
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 4($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 7($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64R6-DAG: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sh $[[R1]], 4($[[PTR]])
; MIPS64R6-DAG: lhu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64R6-DAG: sh $[[R1]], 6($[[PTR]])
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 4($[[PTR]])
%0 = load %struct.S1, %struct.S1* getelementptr inbounds (%struct.S1, %struct.S1* @struct_s1, i32 0), align 1
store %struct.S1 %0, %struct.S1* getelementptr inbounds (%struct.S1, %struct.S1* @struct_s1, i32 1), align 1
@ -336,30 +359,21 @@ entry:
; MIPS32R6-DAG: sw $[[R1]], 12($[[PTR]])
; MIPS64-EL: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 11($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 8($[[PTR]])
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 7($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 4($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 15($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 12($[[PTR]])
; MIPS64-EL-DAG: ldl $[[R1:[0-9]+]], 7($[[PTR]])
; MIPS64-EL-DAG: ldr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: sdl $[[R1]], 15($[[PTR]])
; MIPS64-EL-DAG: sdr $[[R1]], 8($[[PTR]])
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 8($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 11($[[PTR]])
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 4($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 7($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 12($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 15($[[PTR]])
; MIPS64-EB-DAG: ldl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: ldr $[[R1]], 7($[[PTR]])
; MIPS64-EB-DAG: sdl $[[R1]], 8($[[PTR]])
; MIPS64-EB-DAG: sdr $[[R1]], 15($[[PTR]])
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 8($[[PTR]])
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 4($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 12($[[PTR]])
; MIPS64R6-DAG: ld $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sd $[[R1]], 8($[[PTR]])
%0 = load %struct.S2, %struct.S2* getelementptr inbounds (%struct.S2, %struct.S2* @struct_s2, i32 0), align 1
store %struct.S2 %0, %struct.S2* getelementptr inbounds (%struct.S2, %struct.S2* @struct_s2, i32 1), align 1
@ -416,17 +430,17 @@ entry:
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EB: ld $[[SPTR:[0-9]+]], %got_disp(arr)(
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: dsll $[[R1]], $[[R1]], 32
; MIPS64-EB: ld $[[SPTR:[0-9]+]], %got_disp(arr)(
; MIPS64-EB-DAG: lbu $[[R2:[0-9]+]], 5($[[PTR]])
; MIPS64-EB-DAG: lbu $[[R3:[0-9]+]], 4($[[PTR]])
; MIPS64-EB-DAG: dsll $[[T0:[0-9]+]], $[[R3]], 8
; MIPS64-EB-DAG: or $[[T1:[0-9]+]], $[[T0]], $[[R2]]
; MIPS64-EB-DAG: dsll $[[T1]], $[[T1]], 16
; MIPS64-EB-DAG: or $[[T3:[0-9]+]], $[[R1]], $[[T1]]
; MIPS64-EB-DAG: lbu $[[R4:[0-9]+]], 6($[[PTR]])
; MIPS64-EB-DAG: dsll $[[T1]], $[[T1]], 16
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: dsll $[[R5:[0-9]+]], $[[R1]], 32
; MIPS64-EB-DAG: or $[[T3:[0-9]+]], $[[R5]], $[[T1]]
; MIPS64-EB-DAG: dsll $[[T4:[0-9]+]], $[[R4]], 8
; MIPS64-EB-DAG: or $4, $[[T3]], $[[T4]]

2
llvm/test/CodeGen/Mips/micromips-li.ll
View File

@ -13,6 +13,6 @@ entry:
ret i32 0
}
; CHECK: li16 ${{[2-7]|16|17}}, 1
; CHECK: addiu ${{[0-9]+}}, $zero, 2148
; CHECK: li16 ${{[2-7]|16|17}}, 1
; CHECK: ori ${{[0-9]+}}, $zero, 33332

2
llvm/test/CodeGen/Mips/mips64-f128.ll
View File

@ -573,10 +573,10 @@ entry:
; ALL-LABEL: store_LD_LD:
; ALL: ld $[[R0:[0-9]+]], %got_disp(gld1)
; ALL: ld $[[R1:[0-9]+]], 0($[[R0]])
; ALL: ld $[[R2:[0-9]+]], 8($[[R0]])
; ALL: ld $[[R3:[0-9]+]], %got_disp(gld0)
; ALL: sd $[[R2]], 8($[[R3]])
; ALL: ld $[[R1:[0-9]+]], 0($[[R0]])
; ALL: sd $[[R1]], 0($[[R3]])
define void @store_LD_LD() {

46
llvm/test/CodeGen/Mips/mno-ldc1-sdc1.ll
View File

@ -130,12 +130,12 @@
; MM-MNO-PIC: addiu $[[R1:[0-9]+]], $[[R0]], %lo(_gp_disp)
; MM-MNO-PIC: addu $[[R2:[0-9]+]], $[[R1]], $25
; MM-MNO-PIC: lw $[[R3:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC: lw16 $[[R4:[0-9]+]], 0($[[R3]])
; MM-MNO-PIC: lw16 $[[R5:[0-9]+]], 4($[[R3]])
; MM-MNO-LE-PIC: mtc1 $[[R4]], $f0
; MM-MNO-LE-PIC: mthc1 $[[R5]], $f0
; MM-MNO-BE-PIC: mtc1 $[[R5]], $f0
; MM-MNO-BE-PIC: mthc1 $[[R4]], $f0
; MM-MNO-PIC-DAG: lw16 $[[R4:[0-9]+]], 0($[[R3]])
; MM-MNO-PIC-DAG: lw16 $[[R5:[0-9]+]], 4($[[R3]])
; MM-MNO-LE-PIC-DAG: mtc1 $[[R4]], $f0
; MM-MNO-LE-PIC-DAG: mthc1 $[[R5]], $f0
; MM-MNO-BE-PIC-DAG: mtc1 $[[R5]], $f0
; MM-MNO-BE-PIC-DAG: mthc1 $[[R4]], $f0
; MM-STATIC-PIC: lui $[[R0:[0-9]+]], %hi(g0)
; MM-STATIC-PIC: ldc1 $f0, %lo(g0)($[[R0]])
@ -214,13 +214,13 @@ entry:
; MM-MNO-PIC: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; MM-MNO-PIC: addiu $[[R1:[0-9]+]], $[[R0]], %lo(_gp_disp)
; MM-MNO-PIC: addu $[[R2:[0-9]+]], $[[R1]], $25
; MM-MNO-LE-PIC: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC: lw $[[R4:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC: sw16 $[[R3]], 0($[[R4]])
; MM-MNO-LE-PIC: mfhc1 $[[R5:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfc1 $[[R5:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R5]], 4($[[R4]])
; MM-MNO-LE-PIC-DAG: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC-DAG: lw $[[R4:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC-DAG: sw16 $[[R3]], 0($[[R4]])
; MM-MNO-LE-PIC-DAG: mfhc1 $[[R5:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfc1 $[[R5:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R5]], 4($[[R4]])
; MM-STATIC-PIC: lui $[[R0:[0-9]+]], %hi(g0)
; MM-STATIC-PIC: sdc1 $f12, %lo(g0)($[[R0]])
@ -267,8 +267,8 @@ entry:
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $5, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $4, $[[R0]]
; MM-MNO-PIC: lw16 $[[R2:[0-9]+]], 0($[[R1]])
; MM-MNO-PIC: lw16 $[[R3:[0-9]+]], 4($[[R1]])
; MM-MNO-PIC-DAG: lw16 $[[R2:[0-9]+]], 0($[[R1]])
; MM-MNO-PIC-DAG: lw16 $[[R3:[0-9]+]], 4($[[R1]])
; MM-MNO-LE-PIC: mtc1 $[[R2]], $f0
; MM-MNO-LE-PIC: mthc1 $[[R3]], $f0
; MM-MNO-BE-PIC: mtc1 $[[R3]], $f0
@ -313,14 +313,14 @@ entry:
; MM: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM: sdc1 $f12, 0($[[R1]])
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM-MNO-LE-PIC: mfc1 $[[R2:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfhc1 $[[R2:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R2]], 0($[[R1]])
; MM-MNO-LE-PIC: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R3]], 4($[[R1]])
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM-MNO-LE-PIC-DAG: mfc1 $[[R2:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfhc1 $[[R2:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R2]], 0($[[R1]])
; MM-MNO-LE-PIC-DAG: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R3]], 4($[[R1]])
; MM-STATIC-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-STATIC-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]

32
llvm/test/CodeGen/Mips/msa/i5_ld_st.ll
View File

@ -336,8 +336,8 @@ entry:
; CHECK: llvm_mips_st_b_valid_range_tests:
; CHECK: ld.b
; CHECK: st.b [[R1:\$w[0-9]+]], -512(
; CHECK: st.b [[R1:\$w[0-9]+]], 511(
; CHECK-DAG: st.b [[R1:\$w[0-9]+]], -512(
; CHECK-DAG: st.b [[R1:\$w[0-9]+]], 511(
; CHECK: .size llvm_mips_st_b_valid_range_tests
;
@ -351,10 +351,10 @@ entry:
}
; CHECK: llvm_mips_st_b_invalid_range_tests:
; CHECK: addiu $2, $1, -513
; CHECK: addiu $2, $1, 512
; CHECK: ld.b
; CHECK: st.b [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, 512
; CHECK: addiu $1, $1, -513
; CHECK: st.b [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_b_invalid_range_tests
;
@ -404,8 +404,8 @@ entry:
; CHECK: llvm_mips_st_h_valid_range_tests:
; CHECK: ld.h
; CHECK: st.h [[R1:\$w[0-9]+]], -1024(
; CHECK: st.h [[R1:\$w[0-9]+]], 1022(
; CHECK-DAG: st.h [[R1:\$w[0-9]+]], -1024(
; CHECK-DAG: st.h [[R1:\$w[0-9]+]], 1022(
; CHECK: .size llvm_mips_st_h_valid_range_tests
;
@ -419,10 +419,10 @@ entry:
}
; CHECK: llvm_mips_st_h_invalid_range_tests:
; CHECK: addiu $2, $1, -1026
; CHECK: addiu $2, $1, 1024
; CHECK: ld.h
; CHECK: st.h [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, 1024
; CHECK: addiu $1, $1, -1026
; CHECK: st.h [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_h_invalid_range_tests
;
@ -472,8 +472,8 @@ entry:
; CHECK: llvm_mips_st_w_valid_range_tests:
; CHECK: ld.w
; CHECK: st.w [[R1:\$w[0-9]+]], -2048(
; CHECK: st.w [[R1:\$w[0-9]+]], 2044(
; CHECK-DAG: st.w [[R1:\$w[0-9]+]], -2048(
; CHECK-DAG: st.w [[R1:\$w[0-9]+]], 2044(
; CHECK: .size llvm_mips_st_w_valid_range_tests
;
@ -487,10 +487,10 @@ entry:
}
; CHECK: llvm_mips_st_w_invalid_range_tests:
; CHECK: addiu $2, $1, -2052
; CHECK: addiu $2, $1, 2048
; CHECK: ld.w
; CHECK: st.w [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, 2048
; CHECK: addiu $1, $1, -2052
; CHECK: st.w [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_w_invalid_range_tests
;
@ -540,8 +540,8 @@ entry:
; CHECK: llvm_mips_st_d_valid_range_tests:
; CHECK: ld.d
; CHECK: st.d [[R1:\$w[0-9]+]], -4096(
; CHECK: st.d [[R1:\$w[0-9]+]], 4088(
; CHECK-DAG: st.d [[R1:\$w[0-9]+]], -4096(
; CHECK-DAG: st.d [[R1:\$w[0-9]+]], 4088(
; CHECK: .size llvm_mips_st_d_valid_range_tests
;
@ -555,10 +555,10 @@ entry:
}
; CHECK: llvm_mips_st_d_invalid_range_tests:
; CHECK: addiu $2, $1, -4104
; CHECK: addiu $2, $1, 4096
; CHECK: ld.d
; CHECK: st.d [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, 4096
; CHECK: addiu $1, $1, -4104
; CHECK: st.d [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_d_invalid_range_tests
;

46
llvm/test/CodeGen/Mips/o32_cc_byval.ll
View File

@ -45,20 +45,18 @@ declare void @callee3(float, %struct.S3* byval, %struct.S1* byval)
define void @f2(float %f, %struct.S1* nocapture byval %s1) nounwind {
entry:
; CHECK: addiu $sp, $sp, -48
; CHECK: sw $7, 60($sp)
; CHECK: sw $6, 56($sp)
; CHECK: lw $4, 80($sp)
; CHECK: ldc1 $f[[F0:[0-9]+]], 72($sp)
; CHECK: lw $[[R3:[0-9]+]], 64($sp)
; CHECK: lw $[[R4:[0-9]+]], 68($sp)
; CHECK: lw $[[R2:[0-9]+]], 60($sp)
; CHECK: lh $[[R1:[0-9]+]], 58($sp)
; CHECK: lb $[[R0:[0-9]+]], 56($sp)
; CHECK: sw $[[R0]], 32($sp)
; CHECK: sw $[[R1]], 28($sp)
; CHECK: sw $[[R2]], 24($sp)
; CHECK: sw $[[R4]], 20($sp)
; CHECK: sw $[[R3]], 16($sp)
; CHECK-DAG: sw $7, 60($sp)
; CHECK-DAG: sw $6, 56($sp)
; CHECK-DAG: ldc1 $f[[F0:[0-9]+]], 72($sp)
; CHECK-DAG: lw $[[R3:[0-9]+]], 64($sp)
; CHECK-DAG: lw $[[R4:[0-9]+]], 68($sp)
; CHECK-DAG: lh $[[R1:[0-9]+]], 58($sp)
; CHECK-DAG: lb $[[R0:[0-9]+]], 56($sp)
; CHECK-DAG: sw $[[R0]], 32($sp)
; CHECK-DAG: sw $[[R1]], 28($sp)
; CHECK-DAG: sw $[[R4]], 20($sp)
; CHECK-DAG: sw $[[R3]], 16($sp)
; CHECK-DAG: sw $7, 24($sp)
; CHECK: mfc1 $6, $f[[F0]]
%i2 = getelementptr inbounds %struct.S1, %struct.S1* %s1, i32 0, i32 5
@ -86,9 +84,7 @@ entry:
; CHECK: sw $6, 56($sp)
; CHECK: sw $5, 52($sp)
; CHECK: sw $4, 48($sp)
; CHECK: lw $4, 48($sp)
; CHECK: lw $[[R0:[0-9]+]], 60($sp)
; CHECK: sw $[[R0]], 24($sp)
; CHECK: sw $7, 24($sp)
%arrayidx = getelementptr inbounds %struct.S2, %struct.S2* %s2, i32 0, i32 0, i32 0
%tmp = load i32, i32* %arrayidx, align 4
@ -101,14 +97,14 @@ entry:
define void @f4(float %f, %struct.S3* nocapture byval %s3, %struct.S1* nocapture byval %s1) nounwind {
entry:
; CHECK: addiu $sp, $sp, -48
; CHECK: sw $7, 60($sp)
; CHECK: sw $6, 56($sp)
; CHECK: sw $5, 52($sp)
; CHECK: lw $4, 60($sp)
; CHECK: lw $[[R1:[0-9]+]], 80($sp)
; CHECK: lb $[[R0:[0-9]+]], 52($sp)
; CHECK: sw $[[R0]], 32($sp)
; CHECK: sw $[[R1]], 24($sp)
; CHECK-DAG: sw $7, 60($sp)
; CHECK-DAG: sw $6, 56($sp)
; CHECK-DAG: sw $5, 52($sp)
; CHECK-DAG: lw $[[R1:[0-9]+]], 80($sp)
; CHECK-DAG: lb $[[R0:[0-9]+]], 52($sp)
; CHECK-DAG: sw $[[R0]], 32($sp)
; CHECK-DAG: sw $[[R1]], 24($sp)
; CHECK: move $4, $7
%i = getelementptr inbounds %struct.S1, %struct.S1* %s1, i32 0, i32 2
%tmp = load i32, i32* %i, align 4

4
llvm/test/CodeGen/Mips/o32_cc_vararg.ll
View File

@ -29,9 +29,9 @@ entry:
; CHECK-LABEL: va1:
; CHECK: addiu $sp, $sp, -16
; CHECK: sw $5, 20($sp)
; CHECK: sw $7, 28($sp)
; CHECK: sw $6, 24($sp)
; CHECK: sw $5, 20($sp)
; CHECK: lw $2, 20($sp)
}
@ -83,8 +83,8 @@ entry:
; CHECK-LABEL: va3:
; CHECK: addiu $sp, $sp, -16
; CHECK: sw $7, 28($sp)
; CHECK: sw $6, 24($sp)
; CHECK: sw $7, 28($sp)
; CHECK: lw $2, 24($sp)
}

31
llvm/test/CodeGen/PowerPC/anon_aggr.ll
View File

@ -60,10 +60,9 @@ equal:
unequal:
ret i8* %array2_ptr
}
; CHECK-LABEL: func2:
; CHECK: ld [[REG2:[0-9]+]], 72(1)
; CHECK: cmpld {{([0-9]+,)?}}4, [[REG2]]
; CHECK: cmpld {{([0-9]+,)?}}4, 6
; CHECK: mr [[REG2:[0-9]+]], 6
; CHECK-DAG: std [[REG2]], -[[OFFSET1:[0-9]+]]
; CHECK-DAG: std 4, -[[OFFSET2:[0-9]+]]
; CHECK: ld 3, -[[OFFSET2]](1)
@ -85,8 +84,8 @@ unequal:
; DARWIN64: mr
; DARWIN64: mr r[[REG3:[0-9]+]], r[[REGA:[0-9]+]]
; DARWIN64: cmpld {{(cr[0-9]+,)?}}r[[REGA]], r[[REG2]]
; DARWIN64: std r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN64: std r[[REG2]], -[[OFFSET2:[0-9]+]]
; DARWIN64: std r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN64: ld r3, -[[OFFSET1]]
; DARWIN64: ld r3, -[[OFFSET2]]
@ -106,24 +105,24 @@ unequal:
}
; CHECK-LABEL: func3:
; CHECK: ld [[REG3:[0-9]+]], 72(1)
; CHECK: ld [[REG4:[0-9]+]], 56(1)
; CHECK: cmpld {{([0-9]+,)?}}[[REG4]], [[REG3]]
; CHECK: std [[REG3]], -[[OFFSET1:[0-9]+]](1)
; CHECK: cmpld {{([0-9]+,)?}}4, 6
; CHECK: mr [[REG3:[0-9]+]], 6
; CHECK: mr [[REG4:[0-9]+]], 4
; CHECK: std [[REG4]], -[[OFFSET2:[0-9]+]](1)
; CHECK: std [[REG3]], -[[OFFSET1:[0-9]+]](1)
; CHECK: ld 3, -[[OFFSET2]](1)
; CHECK: ld 3, -[[OFFSET1]](1)
; DARWIN32: _func3:
; DARWIN32: addi r[[REG1:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32: addi r[[REG2:[0-9]+]], r[[REGSP]], 24
; DARWIN32: lwz r[[REG3:[0-9]+]], 44(r[[REGSP]])
; DARWIN32: lwz r[[REG4:[0-9]+]], 32(r[[REGSP]])
; DARWIN32-DAG: addi r[[REG1:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32-DAG: addi r[[REG2:[0-9]+]], r[[REGSP]], 24
; DARWIN32-DAG: lwz r[[REG3:[0-9]+]], 44(r[[REGSP]])
; DARWIN32-DAG: lwz r[[REG4:[0-9]+]], 32(r[[REGSP]])
; DARWIN32: cmplw {{(cr[0-9]+,)?}}r[[REG4]], r[[REG3]]
; DARWIN32: stw r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN32: stw r[[REG4]], -[[OFFSET2:[0-9]+]]
; DARWIN32: lwz r3, -[[OFFSET2]]
; DARWIN32: lwz r3, -[[OFFSET1]]
; DARWIN32-DAG: stw r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN32-DAG: stw r[[REG4]], -[[OFFSET2:[0-9]+]]
; DARWIN32-DAG: lwz r3, -[[OFFSET1:[0-9]+]]
; DARWIN32-DAG: lwz r3, -[[OFFSET2:[0-9]+]]
; DARWIN64: _func3:
; DARWIN64: ld r[[REG3:[0-9]+]], 72(r1)

12
llvm/test/CodeGen/PowerPC/complex-return.ll
View File

@ -24,10 +24,10 @@ entry:
}
; CHECK-LABEL: foo:
; CHECK: lfd 1
; CHECK: lfd 2
; CHECK: lfd 3
; CHECK: lfd 4
; CHECK-DAG: lfd 1
; CHECK-DAG: fmr 2
; CHECK-DAG: lfd 3
; CHECK-DAG: lfd 4
define { float, float } @oof() nounwind {
entry:
@ -50,6 +50,6 @@ entry:
}
; CHECK-LABEL: oof:
; CHECK: lfs 2
; CHECK: lfs 1
; CHECK-DAG: lfs 2
; CHECK-DAG: lfs 1

16
llvm/test/CodeGen/PowerPC/jaggedstructs.ll
View File

@ -18,14 +18,14 @@ entry:
ret void
}
; CHECK: std 6, 184(1)
; CHECK: std 5, 176(1)
; CHECK: std 4, 168(1)
; CHECK: std 3, 160(1)
; CHECK: lbz {{[0-9]+}}, 167(1)
; CHECK: lhz {{[0-9]+}}, 165(1)
; CHECK: stb {{[0-9]+}}, 55(1)
; CHECK: sth {{[0-9]+}}, 53(1)
; CHECK-DAG: std 3, 160(1)
; CHECK-DAG: std 6, 184(1)
; CHECK-DAG: std 5, 176(1)
; CHECK-DAG: std 4, 168(1)
; CHECK-DAG: lbz {{[0-9]+}}, 167(1)
; CHECK-DAG: lhz {{[0-9]+}}, 165(1)
; CHECK-DAG: stb {{[0-9]+}}, 55(1)
; CHECK-DAG: sth {{[0-9]+}}, 53(1)
; CHECK: lbz {{[0-9]+}}, 175(1)
; CHECK: lwz {{[0-9]+}}, 171(1)
; CHECK: stb {{[0-9]+}}, 63(1)

46
llvm/test/CodeGen/PowerPC/ppc64-align-long-double.ll
View File

@ -18,19 +18,35 @@ entry:
ret ppc_fp128 %0
}
; CHECK-DAG: std 6, 72(1)
; CHECK-DAG: std 5, 64(1)
; CHECK-DAG: std 4, 56(1)
; CHECK-DAG: std 3, 48(1)
; CHECK: lfd 1, 64(1)
; CHECK: lfd 2, 72(1)
;; FIXME: Sadly, we now have an extra store to a temp variable here,
;; which comes from (roughly):
;; store i64 <val> to i64* <frame>
;; bitcast (load i64* <frame>) to f64
;; The code now can elide the load, making:
;; store i64 <val> -> <frame>
;; bitcast i64 <val> to f64
;; Finally, the bitcast itself turns into a store/load pair.
;;
;; This behavior is new, because previously, llvm was accidentally
;; unable to detect that the load came directly from the store, and
;; elide it.
; CHECK-VSX-DAG: std 6, 72(1)
; CHECK-VSX-DAG: std 5, 64(1)
; CHECK-VSX-DAG: std 4, 56(1)
; CHECK-VSX-DAG: std 3, 48(1)
; CHECK-VSX: li 3, 16
; CHECK-VSX: addi 4, 1, 48
; CHECK-VSX: lxsdx 1, 4, 3
; CHECK-VSX: li 3, 24
; CHECK-VSX: lxsdx 2, 4, 3
; CHECK: std 6, 72(1)
; CHECK: std 5, 64(1)
; CHECK: std 4, 56(1)
; CHECK: std 3, 48(1)
; CHECK: std 5, -16(1)
; CHECK: std 6, -8(1)
; CHECK: lfd 1, -16(1)
; CHECK: lfd 2, -8(1)
; CHECK-VSX: std 6, 72(1)
; CHECK-VSX: std 5, 64(1)
; CHECK-VSX: std 4, 56(1)
; CHECK-VSX: std 3, 48(1)
; CHECK-VSX: std 5, -16(1)
; CHECK-VSX: std 6, -8(1)
; CHECK-VSX: addi 3, 1, -16
; CHECK-VSX: lxsdx 1, 0, 3
; CHECK-VSX: addi 3, 1, -8
; CHECK-VSX: lxsdx 2, 0, 3

28
llvm/test/CodeGen/PowerPC/structsinmem.ll
View File

@ -113,13 +113,13 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK: lha {{[0-9]+}}, 126(1)
; CHECK: lha {{[0-9]+}}, 132(1)
; CHECK: lbz {{[0-9]+}}, 119(1)
; CHECK: lwz {{[0-9]+}}, 140(1)
; CHECK: lwz {{[0-9]+}}, 144(1)
; CHECK: lwz {{[0-9]+}}, 152(1)
; CHECK: lwz {{[0-9]+}}, 160(1)
; CHECK-DAG: lha {{[0-9]+}}, 126(1)
; CHECK-DAG: lha {{[0-9]+}}, 132(1)
; CHECK-DAG: lbz {{[0-9]+}}, 119(1)
; CHECK-DAG: lwz {{[0-9]+}}, 140(1)
; CHECK-DAG: lwz {{[0-9]+}}, 144(1)
; CHECK-DAG: lwz {{[0-9]+}}, 152(1)
; CHECK-DAG: lwz {{[0-9]+}}, 160(1)
}
define i32 @caller2() nounwind {
@ -205,11 +205,11 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK: lha {{[0-9]+}}, 126(1)
; CHECK: lha {{[0-9]+}}, 133(1)
; CHECK: lbz {{[0-9]+}}, 119(1)
; CHECK: lwz {{[0-9]+}}, 140(1)
; CHECK: lwz {{[0-9]+}}, 147(1)
; CHECK: lwz {{[0-9]+}}, 154(1)
; CHECK: lwz {{[0-9]+}}, 161(1)
; CHECK-DAG: lha {{[0-9]+}}, 126(1)
; CHECK-DAG: lha {{[0-9]+}}, 133(1)
; CHECK-DAG: lbz {{[0-9]+}}, 119(1)
; CHECK-DAG: lwz {{[0-9]+}}, 140(1)
; CHECK-DAG: lwz {{[0-9]+}}, 147(1)
; CHECK-DAG: lwz {{[0-9]+}}, 154(1)
; CHECK-DAG: lwz {{[0-9]+}}, 161(1)
}

60
llvm/test/CodeGen/PowerPC/structsinregs.ll
View File

@ -59,6 +59,7 @@ entry:
%call = call i32 @callee1(%struct.s1* byval %p1, %struct.s2* byval %p2, %struct.s3* byval %p3, %struct.s4* byval %p4, %struct.s5* byval %p5, %struct.s6* byval %p6, %struct.s7* byval %p7)
ret i32 %call
; CHECK-LABEL: caller1
; CHECK: ld 9, 112(31)
; CHECK: ld 8, 120(31)
; CHECK: ld 7, 128(31)
@ -97,20 +98,21 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK: std 9, 96(1)
; CHECK: std 8, 88(1)
; CHECK: std 7, 80(1)
; CHECK: stw 6, 76(1)
; CHECK: stw 5, 68(1)
; CHECK: sth 4, 62(1)
; CHECK: stb 3, 55(1)
; CHECK: lha {{[0-9]+}}, 62(1)
; CHECK: lha {{[0-9]+}}, 68(1)
; CHECK: lbz {{[0-9]+}}, 55(1)
; CHECK: lwz {{[0-9]+}}, 76(1)
; CHECK: lwz {{[0-9]+}}, 80(1)
; CHECK: lwz {{[0-9]+}}, 88(1)
; CHECK: lwz {{[0-9]+}}, 96(1)
; CHECK-LABEL: callee1
; CHECK-DAG: std 9, 96(1)
; CHECK-DAG: std 8, 88(1)
; CHECK-DAG: std 7, 80(1)
; CHECK-DAG: stw 6, 76(1)
; CHECK-DAG: stw 5, 68(1)
; CHECK-DAG: sth 4, 62(1)
; CHECK-DAG: stb 3, 55(1)
; CHECK-DAG: lha {{[0-9]+}}, 62(1)
; CHECK-DAG: lha {{[0-9]+}}, 68(1)
; CHECK-DAG: lbz {{[0-9]+}}, 55(1)
; CHECK-DAG: lwz {{[0-9]+}}, 76(1)
; CHECK-DAG: lwz {{[0-9]+}}, 80(1)
; CHECK-DAG: lwz {{[0-9]+}}, 88(1)
; CHECK-DAG: lwz {{[0-9]+}}, 96(1)
}
define i32 @caller2() nounwind {
@ -139,6 +141,7 @@ entry:
%call = call i32 @callee2(%struct.t1* byval %p1, %struct.t2* byval %p2, %struct.t3* byval %p3, %struct.t4* byval %p4, %struct.t5* byval %p5, %struct.t6* byval %p6, %struct.t7* byval %p7)
ret i32 %call
; CHECK-LABEL: caller2
; CHECK: stb {{[0-9]+}}, 71(1)
; CHECK: sth {{[0-9]+}}, 69(1)
; CHECK: stb {{[0-9]+}}, 87(1)
@ -184,18 +187,19 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK: std 9, 96(1)
; CHECK: std 8, 88(1)
; CHECK: std 7, 80(1)
; CHECK: stw 6, 76(1)
; CHECK: std 5, 64(1)
; CHECK: sth 4, 62(1)
; CHECK: stb 3, 55(1)
; CHECK: lha {{[0-9]+}}, 62(1)
; CHECK: lha {{[0-9]+}}, 69(1)
; CHECK: lbz {{[0-9]+}}, 55(1)
; CHECK: lwz {{[0-9]+}}, 76(1)
; CHECK: lwz {{[0-9]+}}, 83(1)
; CHECK: lwz {{[0-9]+}}, 90(1)
; CHECK: lwz {{[0-9]+}}, 97(1)
; CHECK-LABEL: callee2
; CHECK-DAG: std 9, 96(1)
; CHECK-DAG: std 8, 88(1)
; CHECK-DAG: std 7, 80(1)
; CHECK-DAG: stw 6, 76(1)
; CHECK-DAG: std 5, 64(1)
; CHECK-DAG: sth 4, 62(1)
; CHECK-DAG: stb 3, 55(1)
; CHECK-DAG: lha {{[0-9]+}}, 62(1)
; CHECK-DAG: lha {{[0-9]+}}, 69(1)
; CHECK-DAG: lbz {{[0-9]+}}, 55(1)
; CHECK-DAG: lwz {{[0-9]+}}, 76(1)
; CHECK-DAG: lwz {{[0-9]+}}, 83(1)
; CHECK-DAG: lwz {{[0-9]+}}, 90(1)
; CHECK-DAG: lwz {{[0-9]+}}, 97(1)
}

5
llvm/test/CodeGen/SystemZ/unaligned-01.ll
View File

@ -1,10 +1,7 @@
; Check that unaligned accesses are allowed in general. We check the
; few exceptions (like CRL) in their respective test files.
;
; FIXME: -combiner-alias-analysis (the default for SystemZ) stops
; f1 from being optimized.
; RUN: llc < %s -mtriple=s390x-linux-gnu -combiner-alias-analysis=false \
; RUN: | FileCheck %s
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
; Check that these four byte stores become a single word store.
define void @f1(i8 *%ptr) {

2
llvm/test/CodeGen/Thumb/2010-07-15-debugOrdering.ll
View File

@ -9,9 +9,9 @@
define void @_Z19getClosestDiagonal3ii(%0* noalias sret, i32, i32) nounwind {
; CHECK: bl ___muldf3
; CHECK: bl ___muldf3
; CHECK: beq LBB0
; CHECK: bl ___muldf3
; CHECK: bl ___muldf3
; <label>:3
switch i32 %1, label %4 [
i32 0, label %5

8
llvm/test/CodeGen/Thumb/stack-access.ll
View File

@ -74,15 +74,17 @@ define zeroext i16 @test6() {
}
; Accessing the bottom of a large array shouldn't require materializing a base
;
; CHECK: movs [[REG:r[0-9]+]], #1
; CHECK: str [[REG]], [sp, #16]
; CHECK: str [[REG]], [sp, #4]
define void @test7() {
%arr = alloca [200 x i32], align 4
; CHECK: movs [[REG:r[0-9]+]], #1
; CHECK: str [[REG]], [sp, #4]
%arrayidx = getelementptr inbounds [200 x i32], [200 x i32]* %arr, i32 0, i32 1
store i32 1, i32* %arrayidx, align 4
; CHECK: str [[REG]], [sp, #16]
%arrayidx1 = getelementptr inbounds [200 x i32], [200 x i32]* %arr, i32 0, i32 4
store i32 1, i32* %arrayidx1, align 4

2
llvm/test/CodeGen/X86/2010-09-17-SideEffectsInChain.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -combiner-alias-analysis -march=x86-64 -mcpu=core2 | FileCheck %s
; RUN: llc < %s -march=x86-64 -mcpu=core2 | 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"
target triple = "x86_64-apple-darwin10.4"

2
llvm/test/CodeGen/X86/2012-11-28-merge-store-alias.ll
View File

@ -3,8 +3,8 @@
; CHECK: merge_stores_can
; CHECK: callq foo
; CHECK: xorps %xmm0, %xmm0
; CHECK-NEXT: movl 36(%rsp), %ebp
; CHECK-NEXT: movups %xmm0
; CHECK-NEXT: movl 36(%rsp), %ebp
; CHECK: callq foo
; CHECK: ret
declare i32 @foo([10 x i32]* )

14
llvm/test/CodeGen/X86/MergeConsecutiveStores.ll
View File

@ -292,16 +292,12 @@ block4: ; preds = %4, %.lr.ph
ret void
}
;; On x86, even unaligned copies should be merged to vector ops.
;; TODO: however, this cannot happen at the moment, due to brokenness
;; in MergeConsecutiveStores. See UseAA FIXME in DAGCombiner.cpp
;; visitSTORE.
;; On x86, even unaligned copies can be merged to vector ops.
; CHECK-LABEL: merge_loads_no_align:
; load:
; CHECK-NOT: vmovups ;; TODO
; CHECK: vmovups
; store:
; CHECK-NOT: vmovups ;; TODO
; CHECK: vmovups
; CHECK: ret
define void @merge_loads_no_align(i32 %count, %struct.B* noalias nocapture %q, %struct.B* noalias nocapture %p) nounwind uwtable noinline ssp {
%a1 = icmp sgt i32 %count, 0
@ -549,8 +545,8 @@ define void @merge_vec_element_and_scalar_load([6 x i64]* %array) {
; CHECK-LABEL: merge_vec_element_and_scalar_load
; CHECK: movq (%rdi), %rax
; CHECK-NEXT: movq 8(%rdi), %rcx
; CHECK-NEXT: movq %rax, 32(%rdi)
; CHECK-NEXT: movq 8(%rdi), %rax
; CHECK-NEXT: movq %rax, 40(%rdi)
; CHECK-NEXT: movq %rcx, 40(%rdi)
; CHECK-NEXT: retq
}

4
llvm/test/CodeGen/X86/avx512-mask-op.ll
View File

@ -1177,10 +1177,6 @@ define void @ktest_2(<32 x float> %in, float * %base) {
; KNL-NEXT: kmovw %k0, %eax
; KNL-NEXT: vpinsrb $15, %eax, %xmm2, %xmm2
; KNL-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; KNL-NEXT: vpsllw $7, %ymm2, %ymm2
; KNL-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
; KNL-NEXT: vpxor %ymm3, %ymm3, %ymm3
; KNL-NEXT: vpcmpgtb %ymm2, %ymm3, %ymm2
; KNL-NEXT: vmovups 4(%rdi), %zmm3 {%k2} {z}
; KNL-NEXT: vmovups 68(%rdi), %zmm4 {%k1} {z}
; KNL-NEXT: vcmpltps %zmm4, %zmm1, %k0

4
llvm/test/CodeGen/X86/chain_order.ll
View File

@ -11,9 +11,9 @@ define void @cftx020(double* nocapture %a) {
; CHECK-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vmovupd (%rdi), %xmm1
; CHECK-NEXT: vsubpd 16(%rdi), %xmm1, %xmm1
; CHECK-NEXT: vmovupd %xmm0, (%rdi)
; CHECK-NEXT: vmovupd %xmm1, 16(%rdi)
; CHECK-NEXT: vsubpd 16(%rdi), %xmm1, %xmm0
; CHECK-NEXT: vmovupd %xmm0, 16(%rdi)
; CHECK-NEXT: retq
entry:
%0 = load double, double* %a, align 8

56
llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
View File

@ -149,47 +149,47 @@ define <16 x i8> @_clearupper16xi8a(<16 x i8>) nounwind {
; SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE-NEXT: movd %esi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movd %edx, %xmm0
; SSE-NEXT: movd %esi, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE-NEXT: movd %edi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movd %edx, %xmm3
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movd %r9d, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE-NEXT: movd %r8d, %xmm0
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3],xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;

20
llvm/test/CodeGen/X86/combiner-aa-0.ll
View File

@ -1,20 +0,0 @@
; RUN: llc < %s -march=x86-64 -combiner-global-alias-analysis -combiner-alias-analysis
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"
%struct.Hash_Key = type { [4 x i32], i32 }
@g_flipV_hashkey = external global %struct.Hash_Key, align 16 ; <%struct.Hash_Key*> [#uses=1]
define void @foo() nounwind {
%t0 = load i32, i32* undef, align 16 ; <i32> [#uses=1]
%t1 = load i32, i32* null, align 4 ; <i32> [#uses=1]
%t2 = srem i32 %t0, 32 ; <i32> [#uses=1]
%t3 = shl i32 1, %t2 ; <i32> [#uses=1]
%t4 = xor i32 %t3, %t1 ; <i32> [#uses=1]
store i32 %t4, i32* null, align 4
%t5 = getelementptr %struct.Hash_Key, %struct.Hash_Key* @g_flipV_hashkey, i64 0, i32 0, i64 0 ; <i32*> [#uses=2]
%t6 = load i32, i32* %t5, align 4 ; <i32> [#uses=1]
%t7 = shl i32 1, undef ; <i32> [#uses=1]
%t8 = xor i32 %t7, %t6 ; <i32> [#uses=1]
store i32 %t8, i32* %t5, align 4
unreachable
}

23
llvm/test/CodeGen/X86/combiner-aa-1.ll
View File

@ -1,23 +0,0 @@
; RUN: llc < %s --combiner-alias-analysis --combiner-global-alias-analysis
; PR4880
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-f80:32:32"
target triple = "i386-pc-linux-gnu"
%struct.alst_node = type { %struct.node }
%struct.arg_node = type { %struct.node, i8*, %struct.alst_node* }
%struct.arglst_node = type { %struct.alst_node, %struct.arg_node*, %struct.arglst_node* }
%struct.lam_node = type { %struct.alst_node, %struct.arg_node*, %struct.alst_node* }
%struct.node = type { i32 (...)**, %struct.node* }
define i32 @._ZN8lam_node18resolve_name_clashEP8arg_nodeP9alst_node._ZNK8lam_nodeeqERK8exp_node._ZN11arglst_nodeD0Ev(%struct.lam_node* %this.this, %struct.arg_node* %outer_arg, %struct.alst_node* %env.cmp, %struct.arglst_node* %this, i32 %functionID) {
comb_entry:
%.SV59 = alloca %struct.node* ; <%struct.node**> [#uses=1]
%0 = load i32 (...)**, i32 (...)*** null, align 4 ; <i32 (...)**> [#uses=1]
%1 = getelementptr inbounds i32 (...)*, i32 (...)** %0, i32 3 ; <i32 (...)**> [#uses=1]
%2 = load i32 (...)*, i32 (...)** %1, align 4 ; <i32 (...)*> [#uses=1]
store %struct.node* undef, %struct.node** %.SV59
%3 = bitcast i32 (...)* %2 to i32 (%struct.node*)* ; <i32 (%struct.node*)*> [#uses=1]
%4 = tail call i32 %3(%struct.node* undef) ; <i32> [#uses=0]
unreachable
}

17
llvm/test/CodeGen/X86/copy-eflags.ll
View File

@ -9,19 +9,22 @@ target triple = "i686-unknown-linux-gnu"
@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
; CHECK-LABEL: func:
; This tests whether eax is properly saved/restored around the lahf/sahf
; instruction sequences.
; This tests whether eax is properly saved/restored around the
; lahf/sahf instruction sequences. We make mem op volatile to prevent
; their reordering to avoid spills.
define i32 @func() {
entry:
%bval = load i8, i8* @b
%inc = add i8 %bval, 1
store i8 %inc, i8* @b
%cval = load i32, i32* @c
store volatile i8 %inc, i8* @b
%cval = load volatile i32, i32* @c
%inc1 = add nsw i32 %cval, 1
store i32 %inc1, i32* @c
%aval = load i8, i8* @a
store volatile i32 %inc1, i32* @c
%aval = load volatile i8, i8* @a
%inc2 = add i8 %aval, 1
store i8 %inc2, i8* @a
store volatile i8 %inc2, i8* @a
; Copy flags produced by the incb of %inc1 to a register, need to save+restore
; eax around it. The flags will be reused by %tobool.
; CHECK: pushl %eax

12
llvm/test/CodeGen/X86/dag-merge-fast-accesses.ll
View File

@ -51,19 +51,11 @@ define void @merge_vec_element_store(<4 x double> %v, double* %ptr) {
}
;; TODO: FAST *should* be:
;; movups (%rdi), %xmm0
;; movups %xmm0, 40(%rdi)
;; ..but is not currently. See the UseAA FIXME in DAGCombiner.cpp
;; visitSTORE.
define void @merge_vec_load_and_stores(i64 *%ptr) {
; FAST-LABEL: merge_vec_load_and_stores:
; FAST: # BB#0:
; FAST-NEXT: movq (%rdi), %rax
; FAST-NEXT: movq 8(%rdi), %rcx
; FAST-NEXT: movq %rax, 40(%rdi)
; FAST-NEXT: movq %rcx, 48(%rdi)
; FAST-NEXT: movups (%rdi), %xmm0
; FAST-NEXT: movups %xmm0, 40(%rdi)
; FAST-NEXT: retq
;
; SLOW-LABEL: merge_vec_load_and_stores:

6
llvm/test/CodeGen/X86/dont-trunc-store-double-to-float.ll
View File

@ -1,9 +1,9 @@
; RUN: llc -march=x86 < %s | FileCheck %s
; CHECK-LABEL: @bar
; CHECK: movl $1074339512,
; CHECK: movl $1374389535,
; CHECK: movl $1078523331,
; CHECK-DAG: movl $1074339512,
; CHECK-DAG: movl $1374389535,
; CHECK-DAG: movl $1078523331,
define void @bar() unnamed_addr {
entry-block:
%a = alloca double

8
llvm/test/CodeGen/X86/extractelement-legalization-store-ordering.ll
View File

@ -18,13 +18,13 @@ target datalayout = "e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128"
; CHECK-NEXT: movdqa %xmm0, (%edx)
; CHECK-NEXT: shll $4, %ecx
; CHECK-NEXT: movl (%ecx,%edx), %esi
; CHECK-NEXT: movl 12(%ecx,%edx), %edi
; CHECK-NEXT: movl 4(%ecx,%edx), %edi
; CHECK-NEXT: movl 8(%ecx,%edx), %ebx
; CHECK-NEXT: movl 4(%ecx,%edx), %edx
; CHECK-NEXT: movl 12(%ecx,%edx), %edx
; CHECK-NEXT: movl %esi, 12(%eax,%ecx)
; CHECK-NEXT: movl %edx, (%eax,%ecx)
; CHECK-NEXT: movl %edi, (%eax,%ecx)
; CHECK-NEXT: movl %ebx, 8(%eax,%ecx)
; CHECK-NEXT: movl %edi, 4(%eax,%ecx)
; CHECK-NEXT: movl %edx, 4(%eax,%ecx)
; CHECK-NEXT: popl %esi
; CHECK-NEXT: popl %edi
; CHECK-NEXT: popl %ebx

8
llvm/test/CodeGen/X86/i256-add.ll
View File

@ -2,17 +2,17 @@
; RUN: grep adcl %t | count 7
; RUN: grep sbbl %t | count 7
define void @add(i256* %p, i256* %q) nounwind {
define void @add(i256* %p, i256* %q, i256* %r) nounwind {
%a = load i256, i256* %p
%b = load i256, i256* %q
%c = add i256 %a, %b
store i256 %c, i256* %p
store i256 %c, i256* %r
ret void
}
define void @sub(i256* %p, i256* %q) nounwind {
define void @sub(i256* %p, i256* %q, i256* %r) nounwind {
%a = load i256, i256* %p
%b = load i256, i256* %q
%c = sub i256 %a, %b
store i256 %c, i256* %p
store i256 %c, i256* %r
ret void
}

5
llvm/test/CodeGen/X86/i386-shrink-wrapping.ll
View File

@ -55,8 +55,7 @@ target triple = "i386-apple-macosx10.5"
;
; CHECK-NEXT: L_e$non_lazy_ptr, [[E:%[a-z]+]]
; CHECK-NEXT: movb [[D]], ([[E]])
; CHECK-NEXT: L_f$non_lazy_ptr, [[F:%[a-z]+]]
; CHECK-NEXT: movsbl ([[F]]), [[CONV:%[a-z]+]]
; CHECK-NEXT: movsbl ([[E]]), [[CONV:%[a-z]+]]
; CHECK-NEXT: movl $6, [[CONV:%[a-z]+]]
; The eflags is used in the next instruction.
; If that instruction disappear, we are not exercising the bug
@ -96,7 +95,7 @@ for.end: ; preds = %for.cond.preheader
%.b3 = load i1, i1* @d, align 1
%tmp2 = select i1 %.b3, i8 0, i8 6
store i8 %tmp2, i8* @e, align 1
%tmp3 = load i8, i8* @f, align 1
%tmp3 = load i8, i8* @e, align 1
%conv = sext i8 %tmp3 to i32
%add = add nsw i32 %conv, 1
%rem = srem i32 %tmp1, %add

5
llvm/test/CodeGen/X86/live-range-nosubreg.ll
View File

@ -1,7 +1,6 @@
; RUN: llc -march=x86-64 < %s | FileCheck %s
; RUN: llc -march=x86-64 < %s
; Check for a sane output. This testcase used to crash. See PR29132.
; CHECK: leal -1
; This testcase used to crash. See PR29132.
target triple = "x86_64-unknown-linux-gnu"

20
llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
View File

@ -1049,12 +1049,12 @@ define <2 x i64> @merge_2i64_i64_12_volatile(i64* %ptr) nounwind uwtable noinlin
define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable noinline ssp {
; SSE2-LABEL: merge_4f32_f32_2345_volatile:
; SSE2: # BB#0:
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: retq
;
@ -1077,13 +1077,13 @@ define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable n
; X32-SSE1-LABEL: merge_4f32_f32_2345_volatile:
; X32-SSE1: # BB#0:
; X32-SSE1-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-SSE1-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X32-SSE1-DAG: movss 8(%eax), %[[R0:xmm[0-3]]] # [[R0]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 12(%eax), %[[R1:xmm[0-3]]] # [[R1]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 16(%eax), %[[R2:xmm[0-3]]] # [[R2]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 20(%eax), %[[R3:xmm[0-3]]] # [[R3]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: unpcklps %[[R2]], %[[R0]] # [[R0]] = [[R0]][0],[[R2]][0],[[R0]][1],[[R2]][1]
; X32-SSE1-DAG: unpcklps %[[R3]], %[[R1]] # [[R1]] = [[R1]][0],[[R3]][0],[[R1]][1],[[R3]][1]
; X32-SSE1-DAG: unpcklps %[[R1]], %[[R0]] # [[R0]] = [[R0]][0],[[R1]][0],[[R0]][1],[[R1]][1]
; X32-SSE1-NEXT: retl
;
; X32-SSE41-LABEL: merge_4f32_f32_2345_volatile:

8
llvm/test/CodeGen/X86/merge-consecutive-loads-256.ll
View File

@ -682,10 +682,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX1: # BB#0:
; AVX1-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX1-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@ -693,10 +693,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX2: # BB#0:
; AVX2-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX2-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
;
@ -704,10 +704,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX512F: # BB#0:
; AVX512F-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX512F-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX512F-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512F-NEXT: retq
;
@ -716,10 +716,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; X32-AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-AVX-NEXT: vpxor %xmm0, %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $0, (%eax), %xmm0, %xmm1
; X32-AVX-NEXT: vpinsrw $3, 6(%eax), %xmm1, %xmm1
; X32-AVX-NEXT: vpinsrw $4, 24(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $6, 28(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $7, 30(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $3, 6(%eax), %xmm1, %xmm1
; X32-AVX-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; X32-AVX-NEXT: retl
%ptr0 = getelementptr inbounds i16, i16* %ptr, i64 0

8
llvm/test/CodeGen/X86/merge-store-partially-alias-loads.ll
View File

@ -21,11 +21,11 @@
; DBGDAG-DAG: [[LD2:t[0-9]+]]: i16,ch = load<LD2[%tmp81](align=1)> [[ENTRYTOKEN]], [[BASEPTR]], undef:i64
; DBGDAG-DAG: [[LD1:t[0-9]+]]: i8,ch = load<LD1[%tmp12]> [[ENTRYTOKEN]], [[ADDPTR]], undef:i64
; DBGDAG: [[LOADTOKEN:t[0-9]+]]: ch = TokenFactor [[LD2]]:1, [[LD1]]:1
; DBGDAG-DAG: [[ST1:t[0-9]+]]: ch = store<ST1[%tmp14]> [[ENTRYTOKEN]], [[LD1]], t{{[0-9]+}}, undef:i64
; DBGDAG-DAG: [[LOADTOKEN:t[0-9]+]]: ch = TokenFactor [[LD2]]:1, [[LD1]]:1
; DBGDAG: [[ST2:t[0-9]+]]: ch = store<ST2[%tmp10](align=1)> [[LOADTOKEN]], [[LD2]], t{{[0-9]+}}, undef:i64
; DBGDAG-DAG: [[ST2:t[0-9]+]]: ch = store<ST2[%tmp10](align=1)> [[LOADTOKEN]], [[LD2]], t{{[0-9]+}}, undef:i64
; DBGDAG-DAG: [[ST1:t[0-9]+]]: ch = store<ST1[%tmp14]> [[ST2]], [[LD1]], t{{[0-9]+}}, undef:i64
; DBGDAG: X86ISD::RET_FLAG [[ST1]],
; DBGDAG: X86ISD::RET_FLAG t{{[0-9]+}},
; DBGDAG: Type-legalized selection DAG: BB#0 'merge_store_partial_overlap_load:'
define void @merge_store_partial_overlap_load([4 x i8]* %tmp) {

31
llvm/test/CodeGen/X86/pr18023.ll
View File

@ -1,31 +0,0 @@
; RUN: llc < %s -mtriple x86_64-apple-macosx10.9.0 | FileCheck %s
; PR18023
; CHECK: movabsq $4294967296, %rcx
; CHECK: movq %rcx, (%rax)
; CHECK: movl $1, 4(%rax)
; CHECK: movl $0, 4(%rax)
; CHECK: movq $1, 4(%rax)
@c = common global i32 0, align 4
@a = common global [3 x i32] zeroinitializer, align 4
@b = common global i32 0, align 4
@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
define void @func() {
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 0), align 4
%1 = load volatile i32, i32* @b, align 4
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
%2 = load volatile i32, i32* @b, align 4
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
%3 = load volatile i32, i32* @b, align 4
store i32 3, i32* @c, align 4
%4 = load i32, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
%call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i32 %4)
ret void
}
declare i32 @printf(i8*, ...)

20
llvm/test/CodeGen/X86/split-store.ll
View File

@ -1,8 +1,8 @@
; RUN: llc -mtriple=x86_64-unknown-unknown < %s | FileCheck %s
; CHECK-LABEL: int32_float_pair
; CHECK: movl %edi, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
; CHECK-DAG: movl %edi, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
define void @int32_float_pair(i32 %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32
@ -15,8 +15,8 @@ entry:
}
; CHECK-LABEL: float_int32_pair
; CHECK: movss %xmm0, (%rsi)
; CHECK: movl %edi, 4(%rsi)
; CHECK-DAG: movss %xmm0, (%rsi)
; CHECK-DAG: movl %edi, 4(%rsi)
define void @float_int32_pair(float %tmp1, i32 %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp1 to i32
@ -29,9 +29,9 @@ entry:
}
; CHECK-LABEL: int16_float_pair
; CHECK: movzwl %di, %eax
; CHECK: movl %eax, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
; CHECK-DAG: movzwl %di, %eax
; CHECK-DAG: movl %eax, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
define void @int16_float_pair(i16 signext %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32
@ -44,9 +44,9 @@ entry:
}
; CHECK-LABEL: int8_float_pair
; CHECK: movzbl %dil, %eax
; CHECK: movl %eax, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
; CHECK-DAG: movzbl %dil, %eax
; CHECK-DAG: movl %eax, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
define void @int8_float_pair(i8 signext %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32

11
llvm/test/CodeGen/X86/stores-merging.ll
View File

@ -13,9 +13,9 @@ target triple = "x86_64-unknown-linux-gnu"
;; the same result in memory in the end.
; CHECK-LABEL: redundant_stores_merging:
; CHECK: movl $123, e+8(%rip)
; CHECK: movabsq $1958505086977, %rax
; CHECK: movabsq $528280977409, %rax
; CHECK: movq %rax, e+4(%rip)
; CHECK: movl $456, e+8(%rip)
define void @redundant_stores_merging() {
entry:
store i32 1, i32* getelementptr inbounds (%structTy, %structTy* @e, i64 0, i32 1), align 4
@ -26,9 +26,9 @@ entry:
;; This variant tests PR25154.
; CHECK-LABEL: redundant_stores_merging_reverse:
; CHECK: movl $123, e+8(%rip)
; CHECK: movabsq $1958505086977, %rax
; CHECK: movabsq $528280977409, %rax
; CHECK: movq %rax, e+4(%rip)
; CHECK: movl $456, e+8(%rip)
define void @redundant_stores_merging_reverse() {
entry:
store i32 123, i32* getelementptr inbounds (%structTy, %structTy* @e, i64 0, i32 2), align 4
@ -45,9 +45,8 @@ entry:
;; a movl, after the store to 3).
;; CHECK-LABEL: overlapping_stores_merging:
;; CHECK: movw $0, b+2(%rip)
;; CHECK: movl $1, b(%rip)
;; CHECK: movw $2, b+3(%rip)
;; CHECK: movw $1, b(%rip)
define void @overlapping_stores_merging() {
entry:
store i16 0, i16* bitcast (i8* getelementptr inbounds ([8 x i8], [8 x i8]* @b, i64 0, i64 2) to i16*), align 2

1872
llvm/test/CodeGen/X86/vector-compare-results.ll
View File

File diff suppressed because it is too large Load Diff

300
llvm/test/CodeGen/X86/vector-lzcnt-128.ll
View File

@ -1186,8 +1186,6 @@ define <8 x i16> @testv8i16u(<8 x i16> %in) nounwind {
define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE2-LABEL: testv16i8:
; SSE2: # BB#0:
; SSE2-NEXT: pushq %rbp
; SSE2-NEXT: pushq %rbx
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %ecx
@ -1195,47 +1193,40 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r11d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: bsrl %edx, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm2
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r10d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
; SSE2-NEXT: bsrl %ebp, %ebp
; SSE2-NEXT: cmovel %eax, %ebp
; SSE2-NEXT: xorl $7, %ebp
; SSE2-NEXT: movd %ebp, %xmm0
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT: bsrl %edi, %edi
; SSE2-NEXT: cmovel %eax, %edi
; SSE2-NEXT: xorl $7, %edi
; SSE2-NEXT: movd %edi, %xmm1
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm1
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT: bsrl %esi, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm3
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
@ -1244,35 +1235,42 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: bsrl %ebx, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: bsrl %edx, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm3
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: bsrl %r11d, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: bsrl %esi, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
; SSE2-NEXT: bsrl %r9d, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: bsrl %r10d, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm3
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: bsrl %r8d, %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: cmovel %eax, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm4
@ -1285,14 +1283,10 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT: popq %rbx
; SSE2-NEXT: popq %rbp
; SSE2-NEXT: retq
;
; SSE3-LABEL: testv16i8:
; SSE3: # BB#0:
; SSE3-NEXT: pushq %rbp
; SSE3-NEXT: pushq %rbx
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %ecx
@ -1300,47 +1294,40 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r11d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm1
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE3-NEXT: bsrl %edx, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm2
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r10d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
; SSE3-NEXT: bsrl %ebp, %ebp
; SSE3-NEXT: cmovel %eax, %ebp
; SSE3-NEXT: xorl $7, %ebp
; SSE3-NEXT: movd %ebp, %xmm0
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE3-NEXT: bsrl %edi, %edi
; SSE3-NEXT: cmovel %eax, %edi
; SSE3-NEXT: xorl $7, %edi
; SSE3-NEXT: movd %edi, %xmm1
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm1
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE3-NEXT: bsrl %esi, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm3
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
@ -1349,35 +1336,42 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE3-NEXT: bsrl %ebx, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: bsrl %edx, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm3
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE3-NEXT: bsrl %r11d, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: bsrl %esi, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
; SSE3-NEXT: bsrl %r9d, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: bsrl %r10d, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm3
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE3-NEXT: bsrl %r8d, %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: cmovel %eax, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm4
@ -1390,8 +1384,6 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE3-NEXT: popq %rbx
; SSE3-NEXT: popq %rbp
; SSE3-NEXT: retq
;
; SSSE3-LABEL: testv16i8:
@ -1477,77 +1469,76 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
define <16 x i8> @testv16i8u(<16 x i8> %in) nounwind {
; SSE2-LABEL: testv16i8u:
; SSE2: # BB#0:
; SSE2-NEXT: pushq %rbx
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r10d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE2-NEXT: bsrl %esi, %esi
; SSE2-NEXT: xorl $7, %esi
; SSE2-NEXT: movd %esi, %xmm1
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r11d
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebx
; SSE2-NEXT: bsrl %ebx, %ebx
; SSE2-NEXT: xorl $7, %ebx
; SSE2-NEXT: movd %ebx, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT: bsrl %edx, %edx
; SSE2-NEXT: xorl $7, %edx
; SSE2-NEXT: movd %edx, %xmm0
; SSE2-NEXT: bsrl %esi, %edx
; SSE2-NEXT: xorl $7, %edx
; SSE2-NEXT: movd %edx, %xmm3
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: bsrl %ecx, %ecx
; SSE2-NEXT: xorl $7, %ecx
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE2-NEXT: bsrl %edx, %edx
; SSE2-NEXT: xorl $7, %edx
; SSE2-NEXT: movd %edx, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: bsrl %edi, %edx
; SSE2-NEXT: xorl $7, %edx
; SSE2-NEXT: movd %edx, %xmm0
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: bsrl %r10d, %eax
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: bsrl %ecx, %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm3
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm3
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE2-NEXT: bsrl %r9d, %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm0
; SSE2-NEXT: bsrl %r11d, %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: bsrl %r8d, %eax
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: bsrl %eax, %eax
; SSE2-NEXT: xorl $7, %eax
; SSE2-NEXT: movd %eax, %xmm4
; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
@ -1558,82 +1549,80 @@ define <16 x i8> @testv16i8u(<16 x i8> %in) nounwind {
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT: popq %rbx
; SSE2-NEXT: retq
;
; SSE3-LABEL: testv16i8u:
; SSE3: # BB#0:
; SSE3-NEXT: pushq %rbx
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r10d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE3-NEXT: bsrl %esi, %esi
; SSE3-NEXT: xorl $7, %esi
; SSE3-NEXT: movd %esi, %xmm1
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %r11d
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebx
; SSE3-NEXT: bsrl %ebx, %ebx
; SSE3-NEXT: xorl $7, %ebx
; SSE3-NEXT: movd %ebx, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE3-NEXT: bsrl %edx, %edx
; SSE3-NEXT: xorl $7, %edx
; SSE3-NEXT: movd %edx, %xmm0
; SSE3-NEXT: bsrl %esi, %edx
; SSE3-NEXT: xorl $7, %edx
; SSE3-NEXT: movd %edx, %xmm3
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE3-NEXT: bsrl %ecx, %ecx
; SSE3-NEXT: xorl $7, %ecx
; SSE3-NEXT: movd %ecx, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE3-NEXT: bsrl %edx, %edx
; SSE3-NEXT: xorl $7, %edx
; SSE3-NEXT: movd %edx, %xmm1
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE3-NEXT: bsrl %edi, %edx
; SSE3-NEXT: xorl $7, %edx
; SSE3-NEXT: movd %edx, %xmm0
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE3-NEXT: bsrl %r10d, %eax
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: bsrl %ecx, %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE3-NEXT: bsrl %r9d, %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: bsrl %r11d, %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE3-NEXT: bsrl %r8d, %eax
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: bsrl %eax, %eax
; SSE3-NEXT: xorl $7, %eax
; SSE3-NEXT: movd %eax, %xmm4
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
@ -1644,7 +1633,6 @@ define <16 x i8> @testv16i8u(<16 x i8> %in) nounwind {
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE3-NEXT: popq %rbx
; SSE3-NEXT: retq
;
; SSSE3-LABEL: testv16i8u:

934
llvm/test/CodeGen/X86/vector-shuffle-variable-128.ll
View File

File diff suppressed because it is too large Load Diff

232
llvm/test/CodeGen/X86/vector-shuffle-variable-256.ll
View File

@ -1,4 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
@ -18,7 +18,7 @@ define <4 x double> @var_shuffle_v4f64_v4f64_xxxx_i64(<4 x double> %x, i64 %i0,
; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: movq %rbp, %rsp
; ALL-NEXT: popq %rbp
; ALL-NEXT: retq
@ -67,7 +67,7 @@ define <4 x double> @var_shuffle_v4f64_v2f64_xxxx_i64(<2 x double> %x, i64 %i0,
; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: retq
%x0 = extractelement <2 x double> %x, i64 %i0
%x1 = extractelement <2 x double> %x, i64 %i1
@ -90,11 +90,11 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
@ -108,11 +108,11 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
; AVX2-NEXT: retq
@ -137,7 +137,7 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xx00_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
@ -153,7 +153,7 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xx00_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
@ -176,11 +176,11 @@ define <4 x i64> @var_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64 %i0, i64 %i
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4i64_v2i64_xxxx_i64:
@ -188,11 +188,11 @@ define <4 x i64> @var_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64 %i0, i64 %i
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%x0 = extractelement <2 x i64> %x, i64 %i0
%x1 = extractelement <2 x i64> %x, i64 %i1
@ -210,29 +210,29 @@ define <8 x float> @var_shuffle_v8f32_v8f32_xxxxxxxx_i32(<8 x float> %x, i32 %i0
; AVX1: # BB#0:
; AVX1-NEXT: pushq %rbp
; AVX1-NEXT: movq %rsp, %rbp
; AVX1-NEXT: pushq %rbx
; AVX1-NEXT: andq $-32, %rsp
; AVX1-NEXT: subq $64, %rsp
; AVX1-NEXT: movslq %edi, %rax
; AVX1-NEXT: movslq %esi, %rsi
; AVX1-NEXT: movslq %edx, %rdx
; AVX1-NEXT: movslq %ecx, %r11
; AVX1-NEXT: movslq %r8d, %r10
; AVX1-NEXT: movslq %esi, %rbx
; AVX1-NEXT: movslq %edx, %r11
; AVX1-NEXT: movslq %ecx, %r10
; AVX1-NEXT: movslq %r8d, %rdi
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: movslq %r9d, %r8
; AVX1-NEXT: movslq 16(%rbp), %rdi
; AVX1-NEXT: movslq 24(%rbp), %rcx
; AVX1-NEXT: movslq %r9d, %rcx
; AVX1-NEXT: movslq 16(%rbp), %rdx
; AVX1-NEXT: movslq 24(%rbp), %rsi
; AVX1-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; AVX1-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX1-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX1-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
; AVX1-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; AVX1-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1],xmm0[0],xmm3[3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1,2],mem[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: leaq -8(%rbp), %rsp
; AVX1-NEXT: popq %rbx
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
;
@ -284,26 +284,26 @@ define <8 x float> @var_shuffle_v8f32_v8f32_xxxxxxxx_i32(<8 x float> %x, i32 %i0
define <8 x float> @var_shuffle_v8f32_v4f32_xxxxxxxx_i32(<4 x float> %x, i32 %i0, i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7) nounwind {
; ALL-LABEL: var_shuffle_v8f32_v4f32_xxxxxxxx_i32:
; ALL: # BB#0:
; ALL-NEXT: pushq %rbx
; ALL-NEXT: movslq %edi, %rax
; ALL-NEXT: movslq %esi, %rsi
; ALL-NEXT: movslq %edx, %rdx
; ALL-NEXT: movslq %ecx, %r11
; ALL-NEXT: movslq %r8d, %r10
; ALL-NEXT: movslq %esi, %rbx
; ALL-NEXT: movslq %edx, %r11
; ALL-NEXT: movslq %ecx, %r10
; ALL-NEXT: movslq %r8d, %rdi
; ALL-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; ALL-NEXT: movslq %r9d, %r8
; ALL-NEXT: movslq {{[0-9]+}}(%rsp), %rdi
; ALL-NEXT: movslq {{[0-9]+}}(%rsp), %rcx
; ALL-NEXT: movslq %r9d, %rcx
; ALL-NEXT: movslq {{[0-9]+}}(%rsp), %rdx
; ALL-NEXT: movslq {{[0-9]+}}(%rsp), %rsi
; ALL-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; ALL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1],xmm0[0],xmm3[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1,2],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: popq %rbx
; ALL-NEXT: retq
%x0 = extractelement <4 x float> %x, i32 %i0
%x1 = extractelement <4 x float> %x, i32 %i1
@ -336,26 +336,19 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm0
; AVX1-NEXT: movslq 40(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $1, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 48(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $2, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 56(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $3, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 64(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $4, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 72(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 80(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq 88(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq %edi, %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm1
@ -370,11 +363,9 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX1-NEXT: movslq %r9d, %rax
; AVX1-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movslq 16(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movslq 24(%rbp), %rax
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
@ -391,26 +382,19 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm0
; AVX2-NEXT: movslq 40(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $1, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 48(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $2, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 56(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $3, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 64(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $4, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 72(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 80(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq 88(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq %edi, %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm1
@ -425,11 +409,9 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX2-NEXT: movslq %r9d, %rax
; AVX2-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movslq 16(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movslq 24(%rbp), %rax
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
@ -477,26 +459,19 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $1, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $2, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $3, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $4, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movslq %edi, %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm1
@ -511,11 +486,9 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX1-NEXT: movslq %r9d, %rax
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@ -526,26 +499,19 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $1, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $2, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $3, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $4, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movslq %edi, %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm1
@ -560,11 +526,9 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX2-NEXT: movslq %r9d, %rax
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movslq {{[0-9]+}}(%rsp), %rax
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%x0 = extractelement <8 x i16> %x, i32 %i0
@ -620,11 +584,11 @@ define <4 x i64> @mem_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64* %i) nounwi
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
@ -642,11 +606,11 @@ define <4 x i64> @mem_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64* %i) nounwi
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
; AVX2-NEXT: retq
@ -679,11 +643,11 @@ define <4 x i64> @mem_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64* %i) nounwi
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: mem_shuffle_v4i64_v2i64_xxxx_i64:
@ -695,11 +659,11 @@ define <4 x i64> @mem_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64* %i) nounwi
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%p0 = getelementptr inbounds i64, i64* %i, i32 0
%p1 = getelementptr inbounds i64, i64* %i, i32 1

157
llvm/test/CodeGen/X86/win32-eh.ll
View File

@ -27,23 +27,26 @@ catch:
; CHECK-LABEL: _use_except_handler3:
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: pushl %ebx
; CHECK: pushl %edi
; CHECK: pushl %esi
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl $-1, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler3, -20(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler3, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-1, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler3, -20(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler3, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK: movl %[[next]], %fs:0
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: LBB1_2: # %catch{{$}}
; CHECK-NEXT: LBB1_2: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler3:
@ -66,23 +69,37 @@ catch:
; CHECK-LABEL: _use_except_handler4:
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %esp, -36(%ebp)
; CHECK: movl $-2, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler4, %[[lsda:[^ ,]*]]
; CHECK: xorl ___security_cookie, %[[lsda]]
; CHECK: movl %[[lsda]], -20(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler4, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %ebp, %eax
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-2, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler4, %[[lsda:[^ ,]*]]
; CHECK-NEXT: movl ___security_cookie, %[[seccookie:[^ ,]*]]
; CHECK-NEXT: xorl %[[seccookie]], %[[lsda]]
; CHECK-NEXT: movl %[[lsda]], -20(%ebp)
; CHECK-NEXT: xorl %[[seccookie]], %[[tmp1:[^ ,]*]]
; CHECK-NEXT: movl %[[tmp1]], -40(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler4, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: LBB2_2: # %catch{{$}}
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK-NEXT: addl $28, %esp
; CHECK-NEXT: popl %esi
; CHECK-NEXT: popl %edi
; CHECK-NEXT: popl %ebx
; CHECK-NEXT: popl %ebp
; CHECK-NEXT: retl
; CHECK-NEXT: LBB2_2: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler4:
@ -109,26 +126,33 @@ catch:
; CHECK-LABEL: _use_except_handler4_ssp:
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %ebp, %[[ehguard:[^ ,]*]]
; CHECK: movl %esp, -36(%ebp)
; CHECK: movl $-2, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler4_ssp, %[[lsda:[^ ,]*]]
; CHECK: xorl ___security_cookie, %[[lsda]]
; CHECK: movl %[[lsda]], -20(%ebp)
; CHECK: xorl ___security_cookie, %[[ehguard]]
; CHECK: movl %[[ehguard]], -40(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler4, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %ebp, %[[ehguard:[^ ,]*]]
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-2, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler4_ssp, %[[lsda:[^ ,]*]]
; CHECK-NEXT: movl ___security_cookie, %[[seccookie:[^ ,]*]]
; CHECK-NEXT: xorl %[[seccookie]], %[[lsda]]
; CHECK-NEXT: movl %[[lsda]], -20(%ebp)
; CHECK-NEXT: xorl %[[seccookie]], %[[ehguard]]
; CHECK-NEXT: movl %[[ehguard]], -40(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler4, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK: movl %[[next]], %fs:0
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: [[catch:[^ ,]*]]: # %catch{{$}}
; CHECK-NEXT: [[catch:[^ ,]*]]: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler4_ssp:
@ -155,23 +179,26 @@ catch:
; CHECK-LABEL: _use_CxxFrameHandler3:
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %esp, -28(%ebp)
; CHECK: movl $-1, -16(%ebp)
; CHECK: leal -24(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $___ehhandler$use_CxxFrameHandler3, -20(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -24(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: movl $0, -16(%ebp)
; CHECK: calll _may_throw_or_crash
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %esp, -28(%ebp)
; CHECK-NEXT: movl $-1, -16(%ebp)
; CHECK-NEXT: leal -24(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $___ehhandler$use_CxxFrameHandler3, -20(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -24(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl -24(%ebp), %[[next:[^ ,]*]]
; CHECK: movl %[[next]], %fs:0
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: .section .xdata,"dr"
; CHECK: .p2align 2
; CHECK-NEXT: .p2align 2
; CHECK-LABEL: L__ehtable$use_CxxFrameHandler3:
; CHECK-NEXT: .long 429065506
; CHECK-NEXT: .long 2
@ -185,8 +212,8 @@ catch:
; CHECK-LABEL: ___ehhandler$use_CxxFrameHandler3:
; CHECK: movl $L__ehtable$use_CxxFrameHandler3, %eax
; CHECK: jmp ___CxxFrameHandler3 # TAILCALL
; CHECK-NEXT: jmp ___CxxFrameHandler3 # TAILCALL
; CHECK: .safeseh __except_handler3
; CHECK: .safeseh __except_handler4
; CHECK: .safeseh ___ehhandler$use_CxxFrameHandler3
; CHECK-NEXT: .safeseh __except_handler4
; CHECK-NEXT: .safeseh ___ehhandler$use_CxxFrameHandler3

2
llvm/test/CodeGen/XCore/varargs.ll
View File

@ -26,10 +26,10 @@ entry:
; CHECK-LABEL: test_vararg
; CHECK: extsp 6
; CHECK: stw lr, sp[1]
; CHECK: stw r3, sp[6]
; CHECK: stw r0, sp[3]
; CHECK: stw r1, sp[4]
; CHECK: stw r2, sp[5]
; CHECK: stw r3, sp[6]
; CHECK: ldaw r0, sp[3]
; CHECK: stw r0, sp[2]
%list = alloca i8*, align 4