summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--llvm/lib/Target/R600/AMDGPU.h5
-rw-r--r--llvm/lib/Target/R600/AMDGPUTargetMachine.cpp2
-rw-r--r--llvm/lib/Target/R600/CMakeLists.txt1
-rw-r--r--llvm/lib/Target/R600/SIFixSGPRLiveRanges.cpp110
4 files changed, 118 insertions, 0 deletions
diff --git a/llvm/lib/Target/R600/AMDGPU.h b/llvm/lib/Target/R600/AMDGPU.h
index f92bde85377..713fc4b8f32 100644
--- a/llvm/lib/Target/R600/AMDGPU.h
+++ b/llvm/lib/Target/R600/AMDGPU.h
@@ -41,6 +41,7 @@ FunctionPass *createSIAnnotateControlFlowPass();
FunctionPass *createSILowerI1CopiesPass();
FunctionPass *createSILowerControlFlowPass(TargetMachine &tm);
FunctionPass *createSIFixSGPRCopiesPass(TargetMachine &tm);
+FunctionPass *createSIFixSGPRLiveRangesPass();
FunctionPass *createSICodeEmitterPass(formatted_raw_ostream &OS);
FunctionPass *createSIInsertWaits(TargetMachine &tm);
@@ -56,6 +57,10 @@ FunctionPass *createAMDGPUISelDag(TargetMachine &tm);
ImmutablePass *
createAMDGPUTargetTransformInfoPass(const AMDGPUTargetMachine *TM);
+void initializeSIFixSGPRLiveRangesPass(PassRegistry&);
+extern char &SIFixSGPRLiveRangesID;
+
+
extern Target TheAMDGPUTarget;
} // End namespace llvm
diff --git a/llvm/lib/Target/R600/AMDGPUTargetMachine.cpp b/llvm/lib/Target/R600/AMDGPUTargetMachine.cpp
index be1eceaaa00..8aab94446b5 100644
--- a/llvm/lib/Target/R600/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/R600/AMDGPUTargetMachine.cpp
@@ -174,6 +174,8 @@ bool AMDGPUPassConfig::addPreRegAlloc() {
// SIFixSGPRCopies can generate a lot of duplicate instructions,
// so we need to run MachineCSE afterwards.
addPass(&MachineCSEID);
+ initializeSIFixSGPRLiveRangesPass(*PassRegistry::getPassRegistry());
+ insertPass(&RegisterCoalescerID, &SIFixSGPRLiveRangesID);
}
return false;
}
diff --git a/llvm/lib/Target/R600/CMakeLists.txt b/llvm/lib/Target/R600/CMakeLists.txt
index dc1fa9f5579..4d160826004 100644
--- a/llvm/lib/Target/R600/CMakeLists.txt
+++ b/llvm/lib/Target/R600/CMakeLists.txt
@@ -40,6 +40,7 @@ add_llvm_target(R600CodeGen
R600TextureIntrinsicsReplacer.cpp
SIAnnotateControlFlow.cpp
SIFixSGPRCopies.cpp
+ SIFixSGPRLiveRanges.cpp
SIInsertWaits.cpp
SIInstrInfo.cpp
SIISelLowering.cpp
diff --git a/llvm/lib/Target/R600/SIFixSGPRLiveRanges.cpp b/llvm/lib/Target/R600/SIFixSGPRLiveRanges.cpp
new file mode 100644
index 00000000000..7d116eef396
--- /dev/null
+++ b/llvm/lib/Target/R600/SIFixSGPRLiveRanges.cpp
@@ -0,0 +1,110 @@
+//===-- SIFixSGPRLiveRanges.cpp - Fix SGPR live ranges ----------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// SALU instructions ignore control flow, so we need to modify the live ranges
+/// of the registers they define.
+///
+/// The strategy is to view the entire program as if it were a single basic
+/// block and calculate the intervals accordingly. We implement this
+/// by walking this list of segments for each LiveRange and setting the
+/// end of each segment equal to the start of the segment that immediately
+/// follows it.
+
+#include "AMDGPU.h"
+#include "SIRegisterInfo.h"
+#include "llvm/CodeGen/LiveIntervalAnalysis.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Target/TargetMachine.h"
+
+using namespace llvm;
+
+#define DEBUG_TYPE "si-fix-sgpr-live-ranges"
+
+namespace {
+
+class SIFixSGPRLiveRanges : public MachineFunctionPass {
+public:
+ static char ID;
+
+public:
+ SIFixSGPRLiveRanges() : MachineFunctionPass(ID) {
+ initializeSIFixSGPRLiveRangesPass(*PassRegistry::getPassRegistry());
+ }
+
+ virtual bool runOnMachineFunction(MachineFunction &MF) override;
+
+ virtual const char *getPassName() const override {
+ return "SI Fix SGPR live ranges";
+ }
+
+ virtual void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.addRequired<LiveIntervals>();
+ AU.addPreserved<LiveIntervals>();
+ AU.addPreserved<SlotIndexes>();
+ AU.setPreservesCFG();
+ MachineFunctionPass::getAnalysisUsage(AU);
+ }
+};
+
+} // End anonymous namespace.
+
+INITIALIZE_PASS_BEGIN(SIFixSGPRLiveRanges, DEBUG_TYPE,
+ "SI Fix SGPR Live Ranges", false, false)
+INITIALIZE_PASS_DEPENDENCY(LiveIntervals)
+INITIALIZE_PASS_END(SIFixSGPRLiveRanges, DEBUG_TYPE,
+ "SI Fix SGPR Live Ranges", false, false)
+
+char SIFixSGPRLiveRanges::ID = 0;
+
+char &llvm::SIFixSGPRLiveRangesID = SIFixSGPRLiveRanges::ID;
+
+FunctionPass *llvm::createSIFixSGPRLiveRangesPass() {
+ return new SIFixSGPRLiveRanges();
+}
+
+bool SIFixSGPRLiveRanges::runOnMachineFunction(MachineFunction &MF) {
+ MachineRegisterInfo &MRI = MF.getRegInfo();
+ const SIRegisterInfo *TRI = static_cast<const SIRegisterInfo *>(
+ MF.getTarget().getRegisterInfo());
+ LiveIntervals *LIS = &getAnalysis<LiveIntervals>();
+
+ for (MachineFunction::iterator BI = MF.begin(), BE = MF.end();
+ BI != BE; ++BI) {
+
+ MachineBasicBlock &MBB = *BI;
+ for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
+ I != E; ++I) {
+ MachineInstr &MI = *I;
+ MachineOperand *ExecUse = MI.findRegisterUseOperand(AMDGPU::EXEC);
+ if (ExecUse)
+ continue;
+
+ for (const MachineOperand &Def : MI.operands()) {
+ if (!Def.isReg() || !Def.isDef() ||!TargetRegisterInfo::isVirtualRegister(Def.getReg()))
+ continue;
+
+ const TargetRegisterClass *RC = MRI.getRegClass(Def.getReg());
+
+ if (!TRI->isSGPRClass(RC))
+ continue;
+ LiveInterval &LI = LIS->getInterval(Def.getReg());
+ for (unsigned i = 0, e = LI.size() - 1; i != e; ++i) {
+ LiveRange::Segment &Seg = LI.segments[i];
+ LiveRange::Segment &Next = LI.segments[i + 1];
+ Seg.end = Next.start;
+ }
+ }
+ }
+ }
+
+ return false;
+}
OpenPOWER on IntegriCloud