R600/SI: Adjsut SGPR live ranges before register allocation

SGPRs are written by instructions that sometimes will ignore control flow,
which means if you have code like:

if (VGPR0) {
  SGPR0 = S_MOV_B32 0
} else {
  SGPR0 = S_MOV_B32 1
}

The value of SGPR0 will 1 no matter what the condition is.

In order to deal with this situation correctly, we need to view the
program as if it were a single basic block when we calculate the
live ranges for the SGPRs.  They way we actually update the live
range is by iterating over all of the segments in each LiveRange
object and setting the end of each segment equal to the start of
the next segment.  So a live range like:

[3888r,9312r:0)[10032B,10384B:0)  0@3888r

will become:

[3888r,10032B:0)[10032B,10384B:0)  0@3888r

This change will allow us to use SALU instructions within branches.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212215 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/AMDGPU.h b/lib/Target/R600/AMDGPU.h
index f92bde853770f8360f21403e7988242ed2ffe13f..713fc4b8f3295abf693aba91cc7fffa7f7169db2 100644 (file)
--- a/lib/Target/R600/AMDGPU.h
+++ b/lib/Target/R600/AMDGPU.h
@@ -41,6 +41,7 @@ FunctionPass *createSIAnnotateControlFlowPass();
 FunctionPass *createSILowerI1CopiesPass();
 FunctionPass *createSILowerControlFlowPass(TargetMachine &tm);
 FunctionPass *createSIFixSGPRCopiesPass(TargetMachine &tm);
 FunctionPass *createSILowerI1CopiesPass();
 FunctionPass *createSILowerControlFlowPass(TargetMachine &tm);
 FunctionPass *createSIFixSGPRCopiesPass(TargetMachine &tm);

+FunctionPass *createSIFixSGPRLiveRangesPass();

 FunctionPass *createSICodeEmitterPass(formatted_raw_ostream &OS);
 FunctionPass *createSIInsertWaits(TargetMachine &tm);
 
 FunctionPass *createSICodeEmitterPass(formatted_raw_ostream &OS);
 FunctionPass *createSIInsertWaits(TargetMachine &tm);
 


@@ -56,6 +57,10 @@ FunctionPass *createAMDGPUISelDag(TargetMachine &tm);
 ImmutablePass *
 createAMDGPUTargetTransformInfoPass(const AMDGPUTargetMachine *TM);
 
 ImmutablePass *
 createAMDGPUTargetTransformInfoPass(const AMDGPUTargetMachine *TM);
 

+void initializeSIFixSGPRLiveRangesPass(PassRegistry&);
+extern char &SIFixSGPRLiveRangesID;
+
+

 extern Target TheAMDGPUTarget;
 
 } // End namespace llvm
 extern Target TheAMDGPUTarget;
 
 } // End namespace llvm

diff --git a/lib/Target/R600/AMDGPUTargetMachine.cpp b/lib/Target/R600/AMDGPUTargetMachine.cpp
index be1eceaaa00de1ff1f94b82598e95708f5cec417..8aab94446b5d4bb04d7266e6fb09eadb768a13e7 100644 (file)
--- a/lib/Target/R600/AMDGPUTargetMachine.cpp
+++ b/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);
     // 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;
 }
   }
   return false;
 }

diff --git a/lib/Target/R600/CMakeLists.txt b/lib/Target/R600/CMakeLists.txt
index dc1fa9f55795250364ece267f9c0fccb7d4a232c..4d160826004827979cd4a77e3764562ad91fb032 100644 (file)
--- a/lib/Target/R600/CMakeLists.txt
+++ b/lib/Target/R600/CMakeLists.txt
@@ -40,6 +40,7 @@ add_llvm_target(R600CodeGen
   R600TextureIntrinsicsReplacer.cpp
   SIAnnotateControlFlow.cpp
   SIFixSGPRCopies.cpp
   R600TextureIntrinsicsReplacer.cpp
   SIAnnotateControlFlow.cpp
   SIFixSGPRCopies.cpp

+  SIFixSGPRLiveRanges.cpp

   SIInsertWaits.cpp
   SIInstrInfo.cpp
   SIISelLowering.cpp
   SIInsertWaits.cpp
   SIInstrInfo.cpp
   SIISelLowering.cpp

diff --git a/lib/Target/R600/SIFixSGPRLiveRanges.cpp b/lib/Target/R600/SIFixSGPRLiveRanges.cpp
new file mode 100644 (file)
index 0000000..7d116ee
--- /dev/null
+++ b/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;
+}