[llvm] r343973 - [AMDGPU] Add an AMDGPU specific atomic optimizer.
Neil Henning via llvm-commits
llvm-commits at lists.llvm.org
Mon Oct 8 08:49:19 PDT 2018
Author: sheredom
Date: Mon Oct 8 08:49:19 2018
New Revision: 343973
URL: http://llvm.org/viewvc/llvm-project?rev=343973&view=rev
Log:
[AMDGPU] Add an AMDGPU specific atomic optimizer.
This commit adds a new IR level pass to the AMDGPU backend to perform
atomic optimizations. It works by:
- Running through a function and finding atomicrmw add/sub or uses of
the atomic buffer intrinsics for add/sub.
- If all arguments except the value to be added/subtracted are uniform,
record the value to be optimized.
- Run through the atomic operations we can optimize and, depending on
whether the value is uniform/divergent use wavefront wide operations
(DPP in the divergent case) to calculate the total amount to be
atomically added/subtracted.
- Then let only a single lane of each wavefront perform the atomic
operation, reducing the total number of atomic operations in flight.
- Lastly we recombine the result from the single lane to each lane of
the wavefront, and calculate our individual lanes offset into the
final result.
Differential Revision: https://reviews.llvm.org/D51969
Added:
llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
Modified:
llvm/trunk/lib/Target/AMDGPU/AMDGPU.h
llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
llvm/trunk/lib/Target/AMDGPU/CMakeLists.txt
llvm/trunk/test/CodeGen/AMDGPU/atomic_load_add.ll
llvm/trunk/test/CodeGen/AMDGPU/atomic_load_sub.ll
llvm/trunk/test/CodeGen/AMDGPU/global_atomics.ll
llvm/trunk/test/CodeGen/AMDGPU/global_atomics_i64.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
llvm/trunk/test/CodeGen/AMDGPU/local-atomics.ll
llvm/trunk/test/CodeGen/AMDGPU/local-atomics64.ll
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPU.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPU.h?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPU.h (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPU.h Mon Oct 8 08:49:19 2018
@@ -69,6 +69,10 @@ Pass *createAMDGPUAnnotateKernelFeatures
void initializeAMDGPUAnnotateKernelFeaturesPass(PassRegistry &);
extern char &AMDGPUAnnotateKernelFeaturesID;
+FunctionPass *createAMDGPUAtomicOptimizerPass();
+void initializeAMDGPUAtomicOptimizerPass(PassRegistry &);
+extern char &AMDGPUAtomicOptimizerID;
+
ModulePass *createAMDGPULowerIntrinsicsPass();
void initializeAMDGPULowerIntrinsicsPass(PassRegistry &);
extern char &AMDGPULowerIntrinsicsID;
Added: llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp?rev=343973&view=auto
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp (added)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp Mon Oct 8 08:49:19 2018
@@ -0,0 +1,421 @@
+//===-- AMDGPUAtomicOptimizer.cpp -----------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// This pass optimizes atomic operations by using a single lane of a wavefront
+/// to perform the atomic operation, thus reducing contention on that memory
+/// location.
+//
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPU.h"
+#include "AMDGPUSubtarget.h"
+#include "llvm/Analysis/LegacyDivergenceAnalysis.h"
+#include "llvm/CodeGen/TargetPassConfig.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstVisitor.h"
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
+
+#define DEBUG_TYPE "amdgpu-atomic-optimizer"
+
+using namespace llvm;
+
+namespace {
+
+enum DPP_CTRL {
+ DPP_ROW_SR1 = 0x111,
+ DPP_ROW_SR2 = 0x112,
+ DPP_ROW_SR4 = 0x114,
+ DPP_ROW_SR8 = 0x118,
+ DPP_WF_SR1 = 0x138,
+ DPP_ROW_BCAST15 = 0x142,
+ DPP_ROW_BCAST31 = 0x143
+};
+
+struct ReplacementInfo {
+ Instruction *I;
+ Instruction::BinaryOps Op;
+ unsigned ValIdx;
+ bool ValDivergent;
+};
+
+class AMDGPUAtomicOptimizer : public FunctionPass,
+ public InstVisitor<AMDGPUAtomicOptimizer> {
+private:
+ SmallVector<ReplacementInfo, 8> ToReplace;
+ const LegacyDivergenceAnalysis *DA;
+ const DataLayout *DL;
+ DominatorTree *DT;
+ bool HasDPP;
+
+ void optimizeAtomic(Instruction &I, Instruction::BinaryOps Op,
+ unsigned ValIdx, bool ValDivergent) const;
+
+ void setConvergent(CallInst *const CI) const;
+
+public:
+ static char ID;
+
+ AMDGPUAtomicOptimizer() : FunctionPass(ID) {}
+
+ bool runOnFunction(Function &F) override;
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.addPreserved<DominatorTreeWrapperPass>();
+ AU.addRequired<LegacyDivergenceAnalysis>();
+ AU.addRequired<TargetPassConfig>();
+ }
+
+ void visitAtomicRMWInst(AtomicRMWInst &I);
+ void visitIntrinsicInst(IntrinsicInst &I);
+};
+
+} // namespace
+
+char AMDGPUAtomicOptimizer::ID = 0;
+
+char &llvm::AMDGPUAtomicOptimizerID = AMDGPUAtomicOptimizer::ID;
+
+bool AMDGPUAtomicOptimizer::runOnFunction(Function &F) {
+ if (skipFunction(F)) {
+ return false;
+ }
+
+ DA = &getAnalysis<LegacyDivergenceAnalysis>();
+ DL = &F.getParent()->getDataLayout();
+ DominatorTreeWrapperPass *const DTW =
+ getAnalysisIfAvailable<DominatorTreeWrapperPass>();
+ DT = DTW ? &DTW->getDomTree() : nullptr;
+ const TargetPassConfig &TPC = getAnalysis<TargetPassConfig>();
+ const TargetMachine &TM = TPC.getTM<TargetMachine>();
+ const GCNSubtarget &ST = TM.getSubtarget<GCNSubtarget>(F);
+ HasDPP = ST.hasDPP();
+
+ visit(F);
+
+ const bool Changed = !ToReplace.empty();
+
+ for (ReplacementInfo &Info : ToReplace) {
+ optimizeAtomic(*Info.I, Info.Op, Info.ValIdx, Info.ValDivergent);
+ }
+
+ ToReplace.clear();
+
+ return Changed;
+}
+
+void AMDGPUAtomicOptimizer::visitAtomicRMWInst(AtomicRMWInst &I) {
+ // Early exit for unhandled address space atomic instructions.
+ switch (I.getPointerAddressSpace()) {
+ default:
+ return;
+ case AMDGPUAS::GLOBAL_ADDRESS:
+ case AMDGPUAS::LOCAL_ADDRESS:
+ break;
+ }
+
+ Instruction::BinaryOps Op;
+
+ switch (I.getOperation()) {
+ default:
+ return;
+ case AtomicRMWInst::Add:
+ Op = Instruction::Add;
+ break;
+ case AtomicRMWInst::Sub:
+ Op = Instruction::Sub;
+ break;
+ }
+
+ const unsigned PtrIdx = 0;
+ const unsigned ValIdx = 1;
+
+ // If the pointer operand is divergent, then each lane is doing an atomic
+ // operation on a different address, and we cannot optimize that.
+ if (DA->isDivergent(I.getOperand(PtrIdx))) {
+ return;
+ }
+
+ const bool ValDivergent = DA->isDivergent(I.getOperand(ValIdx));
+
+ // If the value operand is divergent, each lane is contributing a different
+ // value to the atomic calculation. We can only optimize divergent values if
+ // we have DPP available on our subtarget, and the atomic operation is 32
+ // bits.
+ if (ValDivergent && (!HasDPP || (DL->getTypeSizeInBits(I.getType()) != 32))) {
+ return;
+ }
+
+ // If we get here, we can optimize the atomic using a single wavefront-wide
+ // atomic operation to do the calculation for the entire wavefront, so
+ // remember the instruction so we can come back to it.
+ const ReplacementInfo Info = {&I, Op, ValIdx, ValDivergent};
+
+ ToReplace.push_back(Info);
+}
+
+void AMDGPUAtomicOptimizer::visitIntrinsicInst(IntrinsicInst &I) {
+ Instruction::BinaryOps Op;
+
+ switch (I.getIntrinsicID()) {
+ default:
+ return;
+ case Intrinsic::amdgcn_buffer_atomic_add:
+ case Intrinsic::amdgcn_struct_buffer_atomic_add:
+ case Intrinsic::amdgcn_raw_buffer_atomic_add:
+ Op = Instruction::Add;
+ break;
+ case Intrinsic::amdgcn_buffer_atomic_sub:
+ case Intrinsic::amdgcn_struct_buffer_atomic_sub:
+ case Intrinsic::amdgcn_raw_buffer_atomic_sub:
+ Op = Instruction::Sub;
+ break;
+ }
+
+ const unsigned ValIdx = 0;
+
+ const bool ValDivergent = DA->isDivergent(I.getOperand(ValIdx));
+
+ // If the value operand is divergent, each lane is contributing a different
+ // value to the atomic calculation. We can only optimize divergent values if
+ // we have DPP available on our subtarget, and the atomic operation is 32
+ // bits.
+ if (ValDivergent && (!HasDPP || (DL->getTypeSizeInBits(I.getType()) != 32))) {
+ return;
+ }
+
+ // If any of the other arguments to the intrinsic are divergent, we can't
+ // optimize the operation.
+ for (unsigned Idx = 1; Idx < I.getNumOperands(); Idx++) {
+ if (DA->isDivergent(I.getOperand(Idx))) {
+ return;
+ }
+ }
+
+ // If we get here, we can optimize the atomic using a single wavefront-wide
+ // atomic operation to do the calculation for the entire wavefront, so
+ // remember the instruction so we can come back to it.
+ const ReplacementInfo Info = {&I, Op, ValIdx, ValDivergent};
+
+ ToReplace.push_back(Info);
+}
+
+void AMDGPUAtomicOptimizer::optimizeAtomic(Instruction &I,
+ Instruction::BinaryOps Op,
+ unsigned ValIdx,
+ bool ValDivergent) const {
+ LLVMContext &Context = I.getContext();
+
+ // Start building just before the instruction.
+ IRBuilder<> B(&I);
+
+ Type *const Ty = I.getType();
+ const unsigned TyBitWidth = DL->getTypeSizeInBits(Ty);
+ Type *const VecTy = VectorType::get(B.getInt32Ty(), 2);
+
+ // This is the value in the atomic operation we need to combine in order to
+ // reduce the number of atomic operations.
+ Value *const V = I.getOperand(ValIdx);
+
+ // We need to know how many lanes are active within the wavefront, and we do
+ // this by getting the exec register, which tells us all the lanes that are
+ // active.
+ MDNode *const RegName =
+ llvm::MDNode::get(Context, llvm::MDString::get(Context, "exec"));
+ Value *const Metadata = llvm::MetadataAsValue::get(Context, RegName);
+ CallInst *const Exec =
+ B.CreateIntrinsic(Intrinsic::read_register, {B.getInt64Ty()}, {Metadata});
+ setConvergent(Exec);
+
+ // We need to know how many lanes are active within the wavefront that are
+ // below us. If we counted each lane linearly starting from 0, a lane is
+ // below us only if its associated index was less than ours. We do this by
+ // using the mbcnt intrinsic.
+ Value *const BitCast = B.CreateBitCast(Exec, VecTy);
+ Value *const ExtractLo = B.CreateExtractElement(BitCast, B.getInt32(0));
+ Value *const ExtractHi = B.CreateExtractElement(BitCast, B.getInt32(1));
+ CallInst *const PartialMbcnt = B.CreateIntrinsic(
+ Intrinsic::amdgcn_mbcnt_lo, {}, {ExtractLo, B.getInt32(0)});
+ CallInst *const Mbcnt = B.CreateIntrinsic(Intrinsic::amdgcn_mbcnt_hi, {},
+ {ExtractHi, PartialMbcnt});
+
+ Value *const MbcntCast = B.CreateIntCast(Mbcnt, Ty, false);
+
+ Value *LaneOffset = nullptr;
+ Value *NewV = nullptr;
+
+ // If we have a divergent value in each lane, we need to combine the value
+ // using DPP.
+ if (ValDivergent) {
+ // First we need to set all inactive invocations to 0, so that they can
+ // correctly contribute to the final result.
+ CallInst *const SetInactive = B.CreateIntrinsic(
+ Intrinsic::amdgcn_set_inactive, Ty, {V, B.getIntN(TyBitWidth, 0)});
+ setConvergent(SetInactive);
+ NewV = SetInactive;
+
+ const unsigned Iters = 6;
+ const unsigned DPPCtrl[Iters] = {DPP_ROW_SR1, DPP_ROW_SR2,
+ DPP_ROW_SR4, DPP_ROW_SR8,
+ DPP_ROW_BCAST15, DPP_ROW_BCAST31};
+ const unsigned RowMask[Iters] = {0xf, 0xf, 0xf, 0xf, 0xa, 0xc};
+
+ // This loop performs an inclusive scan across the wavefront, with all lanes
+ // active (by using the WWM intrinsic).
+ for (unsigned Idx = 0; Idx < Iters; Idx++) {
+ CallInst *const DPP = B.CreateIntrinsic(Intrinsic::amdgcn_mov_dpp, Ty,
+ {NewV, B.getInt32(DPPCtrl[Idx]),
+ B.getInt32(RowMask[Idx]),
+ B.getInt32(0xf), B.getFalse()});
+ setConvergent(DPP);
+ Value *const WWM = B.CreateIntrinsic(Intrinsic::amdgcn_wwm, Ty, DPP);
+
+ NewV = B.CreateBinOp(Op, NewV, WWM);
+ NewV = B.CreateIntrinsic(Intrinsic::amdgcn_wwm, Ty, NewV);
+ }
+
+ // NewV has returned the inclusive scan of V, but for the lane offset we
+ // require an exclusive scan. We do this by shifting the values from the
+ // entire wavefront right by 1, and by setting the bound_ctrl (last argument
+ // to the intrinsic below) to true, we can guarantee that 0 will be shifted
+ // into the 0'th invocation.
+ CallInst *const DPP =
+ B.CreateIntrinsic(Intrinsic::amdgcn_mov_dpp, {Ty},
+ {NewV, B.getInt32(DPP_WF_SR1), B.getInt32(0xf),
+ B.getInt32(0xf), B.getTrue()});
+ setConvergent(DPP);
+ LaneOffset = B.CreateIntrinsic(Intrinsic::amdgcn_wwm, Ty, DPP);
+
+ // Read the value from the last lane, which has accumlated the values of
+ // each active lane in the wavefront. This will be our new value with which
+ // we will provide to the atomic operation.
+ if (TyBitWidth == 64) {
+ Value *const ExtractLo = B.CreateTrunc(NewV, B.getInt32Ty());
+ Value *const ExtractHi =
+ B.CreateTrunc(B.CreateLShr(NewV, B.getInt64(32)), B.getInt32Ty());
+ CallInst *const ReadLaneLo = B.CreateIntrinsic(
+ Intrinsic::amdgcn_readlane, {}, {ExtractLo, B.getInt32(63)});
+ setConvergent(ReadLaneLo);
+ CallInst *const ReadLaneHi = B.CreateIntrinsic(
+ Intrinsic::amdgcn_readlane, {}, {ExtractHi, B.getInt32(63)});
+ setConvergent(ReadLaneHi);
+ Value *const PartialInsert = B.CreateInsertElement(
+ UndefValue::get(VecTy), ReadLaneLo, B.getInt32(0));
+ Value *const Insert =
+ B.CreateInsertElement(PartialInsert, ReadLaneHi, B.getInt32(1));
+ NewV = B.CreateBitCast(Insert, Ty);
+ } else if (TyBitWidth == 32) {
+ CallInst *const ReadLane = B.CreateIntrinsic(Intrinsic::amdgcn_readlane,
+ {}, {NewV, B.getInt32(63)});
+ setConvergent(ReadLane);
+ NewV = ReadLane;
+ } else {
+ llvm_unreachable("Unhandled atomic bit width");
+ }
+ } else {
+ // Get the total number of active lanes we have by using popcount.
+ Instruction *const Ctpop = B.CreateUnaryIntrinsic(Intrinsic::ctpop, Exec);
+ Value *const CtpopCast = B.CreateIntCast(Ctpop, Ty, false);
+
+ // Calculate the new value we will be contributing to the atomic operation
+ // for the entire wavefront.
+ NewV = B.CreateMul(V, CtpopCast);
+ LaneOffset = B.CreateMul(V, MbcntCast);
+ }
+
+ // We only want a single lane to enter our new control flow, and we do this
+ // by checking if there are any active lanes below us. Only one lane will
+ // have 0 active lanes below us, so that will be the only one to progress.
+ Value *const Cond = B.CreateICmpEQ(MbcntCast, B.getIntN(TyBitWidth, 0));
+
+ // Store I's original basic block before we split the block.
+ BasicBlock *const EntryBB = I.getParent();
+
+ // We need to introduce some new control flow to force a single lane to be
+ // active. We do this by splitting I's basic block at I, and introducing the
+ // new block such that:
+ // entry --> single_lane -\
+ // \------------------> exit
+ Instruction *const SingleLaneTerminator =
+ SplitBlockAndInsertIfThen(Cond, &I, false, nullptr, DT, nullptr);
+
+ // Move the IR builder into single_lane next.
+ B.SetInsertPoint(SingleLaneTerminator);
+
+ // Clone the original atomic operation into single lane, replacing the
+ // original value with our newly created one.
+ Instruction *const NewI = I.clone();
+ B.Insert(NewI);
+ NewI->setOperand(ValIdx, NewV);
+
+ // Move the IR builder into exit next, and start inserting just before the
+ // original instruction.
+ B.SetInsertPoint(&I);
+
+ // Create a PHI node to get our new atomic result into the exit block.
+ PHINode *const PHI = B.CreatePHI(Ty, 2);
+ PHI->addIncoming(UndefValue::get(Ty), EntryBB);
+ PHI->addIncoming(NewI, SingleLaneTerminator->getParent());
+
+ // We need to broadcast the value who was the lowest active lane (the first
+ // lane) to all other lanes in the wavefront. We use an intrinsic for this,
+ // but have to handle 64-bit broadcasts with two calls to this intrinsic.
+ Value *BroadcastI = nullptr;
+
+ if (TyBitWidth == 64) {
+ Value *const ExtractLo = B.CreateTrunc(PHI, B.getInt32Ty());
+ Value *const ExtractHi =
+ B.CreateTrunc(B.CreateLShr(PHI, B.getInt64(32)), B.getInt32Ty());
+ CallInst *const ReadFirstLaneLo =
+ B.CreateIntrinsic(Intrinsic::amdgcn_readfirstlane, {}, ExtractLo);
+ setConvergent(ReadFirstLaneLo);
+ CallInst *const ReadFirstLaneHi =
+ B.CreateIntrinsic(Intrinsic::amdgcn_readfirstlane, {}, ExtractHi);
+ setConvergent(ReadFirstLaneHi);
+ Value *const PartialInsert = B.CreateInsertElement(
+ UndefValue::get(VecTy), ReadFirstLaneLo, B.getInt32(0));
+ Value *const Insert =
+ B.CreateInsertElement(PartialInsert, ReadFirstLaneHi, B.getInt32(1));
+ BroadcastI = B.CreateBitCast(Insert, Ty);
+ } else if (TyBitWidth == 32) {
+ CallInst *const ReadFirstLane =
+ B.CreateIntrinsic(Intrinsic::amdgcn_readfirstlane, {}, PHI);
+ setConvergent(ReadFirstLane);
+ BroadcastI = ReadFirstLane;
+ } else {
+ llvm_unreachable("Unhandled atomic bit width");
+ }
+
+ // Now that we have the result of our single atomic operation, we need to
+ // get our individual lane's slice into the result. We use the lane offset we
+ // previously calculated combined with the atomic result value we got from the
+ // first lane, to get our lane's index into the atomic result.
+ Value *const Result = B.CreateBinOp(Op, BroadcastI, LaneOffset);
+
+ // Replace the original atomic instruction with the new one.
+ I.replaceAllUsesWith(Result);
+
+ // And delete the original.
+ I.eraseFromParent();
+}
+
+void AMDGPUAtomicOptimizer::setConvergent(CallInst *const CI) const {
+ CI->addAttribute(AttributeList::FunctionIndex, Attribute::Convergent);
+}
+
+INITIALIZE_PASS_BEGIN(AMDGPUAtomicOptimizer, DEBUG_TYPE,
+ "AMDGPU atomic optimizations", false, false)
+INITIALIZE_PASS_DEPENDENCY(LegacyDivergenceAnalysis)
+INITIALIZE_PASS_DEPENDENCY(TargetPassConfig)
+INITIALIZE_PASS_END(AMDGPUAtomicOptimizer, DEBUG_TYPE,
+ "AMDGPU atomic optimizations", false, false)
+
+FunctionPass *llvm::createAMDGPUAtomicOptimizerPass() {
+ return new AMDGPUAtomicOptimizer();
+}
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp Mon Oct 8 08:49:19 2018
@@ -138,6 +138,13 @@ static cl::opt<bool> EnableLowerKernelAr
cl::init(true),
cl::Hidden);
+// Enable atomic optimization
+static cl::opt<bool> EnableAtomicOptimizations(
+ "amdgpu-atomic-optimizations",
+ cl::desc("Enable atomic optimizations"),
+ cl::init(false),
+ cl::Hidden);
+
extern "C" void LLVMInitializeAMDGPUTarget() {
// Register the target
RegisterTargetMachine<R600TargetMachine> X(getTheAMDGPUTarget());
@@ -163,6 +170,7 @@ extern "C" void LLVMInitializeAMDGPUTarg
initializeAMDGPUAnnotateKernelFeaturesPass(*PR);
initializeAMDGPUAnnotateUniformValuesPass(*PR);
initializeAMDGPUArgumentUsageInfoPass(*PR);
+ initializeAMDGPUAtomicOptimizerPass(*PR);
initializeAMDGPULowerKernelArgumentsPass(*PR);
initializeAMDGPULowerKernelAttributesPass(*PR);
initializeAMDGPULowerIntrinsicsPass(*PR);
@@ -747,6 +755,10 @@ ScheduleDAGInstrs *GCNPassConfig::create
bool GCNPassConfig::addPreISel() {
AMDGPUPassConfig::addPreISel();
+ if (EnableAtomicOptimizations) {
+ addPass(createAMDGPUAtomicOptimizerPass());
+ }
+
// FIXME: We need to run a pass to propagate the attributes when calls are
// supported.
addPass(createAMDGPUAnnotateKernelFeaturesPass());
Modified: llvm/trunk/lib/Target/AMDGPU/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/CMakeLists.txt?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/CMakeLists.txt (original)
+++ llvm/trunk/lib/Target/AMDGPU/CMakeLists.txt Mon Oct 8 08:49:19 2018
@@ -37,6 +37,7 @@ add_llvm_target(AMDGPUCodeGen
AMDGPUAnnotateUniformValues.cpp
AMDGPUArgumentUsageInfo.cpp
AMDGPUAsmPrinter.cpp
+ AMDGPUAtomicOptimizer.cpp
AMDGPUCallLowering.cpp
AMDGPUCodeGenPrepare.cpp
AMDGPUFrameLowering.cpp
Modified: llvm/trunk/test/CodeGen/AMDGPU/atomic_load_add.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_load_add.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_load_add.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_load_add.ll Mon Oct 8 08:49:19 2018
@@ -1,7 +1,7 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=R600,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false < %s | FileCheck -check-prefixes=R600,FUNC %s
; FUNC-LABEL: {{^}}atomic_add_local:
; SICIVI: s_mov_b32 m0
Modified: llvm/trunk/test/CodeGen/AMDGPU/atomic_load_sub.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_load_sub.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_load_sub.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_load_sub.ll Mon Oct 8 08:49:19 2018
@@ -1,7 +1,7 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -enable-var-scope -check-prefixes=R600,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false < %s | FileCheck -enable-var-scope -check-prefixes=R600,FUNC %s
; FUNC-LABEL: {{^}}atomic_sub_local:
; SICIVI: s_mov_b32 m0
Added: llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll?rev=343973&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll Mon Oct 8 08:49:19 2018
@@ -0,0 +1,129 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.buffer.atomic.add(i32, <4 x i32>, i32, i32, i1)
+declare i32 @llvm.amdgcn.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i1)
+
+; Show that what the atomic optimization pass will do for raw buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+ %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+ %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
Added: llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll?rev=343973&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll Mon Oct 8 08:49:19 2018
@@ -0,0 +1,189 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+
+; Show that what the atomic optimization pass will do for global pointers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+ %old = atomicrmw add i32 addrspace(1)* %inout, i32 5 acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %additive) {
+entry:
+ %old = atomicrmw add i32 addrspace(1)* %inout, i32 %additive acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw add i32 addrspace(1)* %inout, i32 %lane acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+ %old = atomicrmw add i64 addrspace(1)* %inout, i64 5 acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %additive) {
+entry:
+ %old = atomicrmw add i64 addrspace(1)* %inout, i64 %additive acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %zext = zext i32 %lane to i64
+ %old = atomicrmw add i64 addrspace(1)* %inout, i64 %zext acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+ %old = atomicrmw sub i32 addrspace(1)* %inout, i32 5 acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %subitive) {
+entry:
+ %old = atomicrmw sub i32 addrspace(1)* %inout, i32 %subitive acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw sub i32 addrspace(1)* %inout, i32 %lane acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+ %old = atomicrmw sub i64 addrspace(1)* %inout, i64 5 acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %subitive) {
+entry:
+ %old = atomicrmw sub i64 addrspace(1)* %inout, i64 %subitive acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %zext = zext i32 %lane to i64
+ %old = atomicrmw sub i64 addrspace(1)* %inout, i64 %zext acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
Added: llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll?rev=343973&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll Mon Oct 8 08:49:19 2018
@@ -0,0 +1,192 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+
+ at local_var32 = addrspace(3) global i32 undef, align 4
+ at local_var64 = addrspace(3) global i64 undef, align 8
+
+; Show that what the atomic optimization pass will do for local pointers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out) {
+entry:
+ %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 5 acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 %additive) {
+entry:
+ %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %additive acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
+entry:
+ %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 5 acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 %additive) {
+entry:
+ %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %additive acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %zext = zext i32 %lane to i64
+ %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %zext acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out) {
+entry:
+ %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 5 acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 %subitive) {
+entry:
+ %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %subitive acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
+entry:
+ %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 5 acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 %subitive) {
+entry:
+ %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %subitive acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %zext = zext i32 %lane to i64
+ %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %zext acq_rel
+ store i64 %old, i64 addrspace(1)* %out
+ ret void
+}
Added: llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll?rev=343973&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll Mon Oct 8 08:49:19 2018
@@ -0,0 +1,129 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32)
+
+; Show that what the atomic optimization pass will do for raw buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
Added: llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll?rev=343973&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll Mon Oct 8 08:49:19 2018
@@ -0,0 +1,155 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.struct.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32, i32)
+declare i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32, i32)
+
+; Show that what the atomic optimization pass will do for struct buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_vindex:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vindex:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
+ store i32 %old, i32 addrspace(1)* %out
+ ret void
+}
Modified: llvm/trunk/test/CodeGen/AMDGPU/global_atomics.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/global_atomics.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/global_atomics.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/global_atomics.ll Mon Oct 8 08:49:19 2018
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
; GCN-LABEL: {{^}}atomic_add_i32_offset:
; SIVI: buffer_atomic_add v{{[0-9]+}}, off, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:16{{$}}
Modified: llvm/trunk/test/CodeGen/AMDGPU/global_atomics_i64.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/global_atomics_i64.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/global_atomics_i64.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/global_atomics_i64.ll Mon Oct 8 08:49:19 2018
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
; GCN-LABEL: {{^}}atomic_add_i64_offset:
; CIVI: buffer_atomic_add_x2 v{{\[[0-9]+:[0-9]+\]}}, off, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:32{{$}}
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll Mon Oct 8 08:49:19 2018
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
;CHECK-LABEL: {{^}}test1:
;CHECK-NOT: s_waitcnt
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll Mon Oct 8 08:49:19 2018
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
;CHECK-LABEL: {{^}}test1:
;CHECK-NOT: s_waitcnt
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll Mon Oct 8 08:49:19 2018
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
;CHECK-LABEL: {{^}}test1:
;CHECK-NOT: s_waitcnt
Modified: llvm/trunk/test/CodeGen/AMDGPU/local-atomics.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/local-atomics.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/local-atomics.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/local-atomics.ll Mon Oct 8 08:49:19 2018
@@ -1,8 +1,8 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=EG,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=EG,FUNC %s
; FUNC-LABEL: {{^}}lds_atomic_xchg_ret_i32:
; EG: LDS_WRXCHG_RET *
Modified: llvm/trunk/test/CodeGen/AMDGPU/local-atomics64.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/local-atomics64.ll?rev=343973&r1=343972&r2=343973&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/local-atomics64.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/local-atomics64.ll Mon Oct 8 08:49:19 2018
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,VI,SICIVI,GFX89 %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,VI,SICIVI,GFX89 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s
; GCN-LABEL: {{^}}lds_atomic_xchg_ret_i64:
; SICIVI: s_mov_b32 m0
More information about the llvm-commits
mailing list