Add NVPTXPeephole pass to reduce unnecessary address cast

Summary:
This patch first change the register that holds local address for stack
frame to %SPL. Then the new NVPTXPeephole pass will try to scan the
following pattern

   %vreg0<def> = LEA_ADDRi64 <fi#0>, 4
   %vreg1<def> = cvta_to_local %vreg0

and transform it into

   %vreg1<def> = LEA_ADDRi64 %VRFrameLocal, 4

Patched by Xuetian Weng

Test Plan: test/CodeGen/NVPTX/local-stack-frame.ll

Reviewers: jholewinski, jingyue

Reviewed By: jingyue

Subscribers: eliben, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D10549

llvm-svn: 240587

llvm/lib/Target/NVPTX/CMakeLists.txt

@@ -22,6 +22,7 @@ set(NVPTXCodeGen_sources
   NVPTXLowerAggrCopies.cpp
   NVPTXLowerKernelArgs.cpp
   NVPTXLowerAlloca.cpp
+  NVPTXPeephole.cpp
   NVPTXMCExpr.cpp
   NVPTXPrologEpilogPass.cpp
   NVPTXRegisterInfo.cpp

llvm/lib/Target/NVPTX/NVPTX.h

@@ -71,6 +71,7 @@ MachineFunctionPass *createNVPTXReplaceImageHandlesPass();
 FunctionPass *createNVPTXImageOptimizerPass();
 FunctionPass *createNVPTXLowerKernelArgsPass(const NVPTXTargetMachine *TM);
 BasicBlockPass *createNVPTXLowerAllocaPass();
+MachineFunctionPass *createNVPTXPeephole();
 
 bool isImageOrSamplerVal(const Value *, const Module *);
 

llvm/lib/Target/NVPTX/NVPTXFrameLowering.cpp

@@ -36,33 +36,40 @@ void NVPTXFrameLowering::emitPrologue(MachineFunction &MF,
   if (MF.getFrameInfo()->hasStackObjects()) {
     assert(&MF.front() == &MBB && "Shrink-wrapping not yet supported");
     // Insert "mov.u32 %SP, %Depot"
-    MachineBasicBlock::iterator MBBI = MBB.begin();
+    MachineInstr *MI = MBB.begin();
+    MachineRegisterInfo &MR = MF.getRegInfo();
+
     // This instruction really occurs before first instruction
     // in the BB, so giving it no debug location.
     DebugLoc dl = DebugLoc();
 
-    MachineRegisterInfo &MRI = MF.getRegInfo();
-
     // mov %SPL, %depot;
     // cvta.local %SP, %SPL;
     if (static_cast<const NVPTXTargetMachine &>(MF.getTarget()).is64Bit()) {
-      unsigned LocalReg = MRI.createVirtualRegister(&NVPTX::Int64RegsRegClass);
-      MachineInstr *MI =
-          BuildMI(MBB, MBBI, dl, MF.getSubtarget().getInstrInfo()->get(
-                                     NVPTX::cvta_local_yes_64),
-                  NVPTX::VRFrame).addReg(LocalReg);
+      // Check if %SP is actually used
+      if (MR.hasOneNonDBGUse(NVPTX::VRFrame)) {
+        MI = BuildMI(MBB, MI, dl, MF.getSubtarget().getInstrInfo()->get(
+                                      NVPTX::cvta_local_yes_64),
+                     NVPTX::VRFrame)
+                 .addReg(NVPTX::VRFrameLocal);
+      }
+
       BuildMI(MBB, MI, dl,
               MF.getSubtarget().getInstrInfo()->get(NVPTX::MOV_DEPOT_ADDR_64),
-              LocalReg).addImm(MF.getFunctionNumber());
+              NVPTX::VRFrameLocal)
+          .addImm(MF.getFunctionNumber());
     } else {
-      unsigned LocalReg = MRI.createVirtualRegister(&NVPTX::Int32RegsRegClass);
-      MachineInstr *MI =
-          BuildMI(MBB, MBBI, dl,
-                  MF.getSubtarget().getInstrInfo()->get(NVPTX::cvta_local_yes),
-                  NVPTX::VRFrame).addReg(LocalReg);
+      // Check if %SP is actually used
+      if (MR.hasOneNonDBGUse(NVPTX::VRFrame)) {
+        MI = BuildMI(MBB, MI, dl, MF.getSubtarget().getInstrInfo()->get(
+                                      NVPTX::cvta_local_yes),
+                     NVPTX::VRFrame)
+                 .addReg(NVPTX::VRFrameLocal);
+      }
       BuildMI(MBB, MI, dl,
               MF.getSubtarget().getInstrInfo()->get(NVPTX::MOV_DEPOT_ADDR),
-              LocalReg).addImm(MF.getFunctionNumber());
+              NVPTX::VRFrameLocal)
+          .addImm(MF.getFunctionNumber());
     }
   }
 }

llvm/lib/Target/NVPTX/NVPTXPeephole.cpp

@@ -0,0 +1,151 @@
+//===-- NVPTXPeephole.cpp - NVPTX Peephole Optimiztions -------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// In NVPTX, NVPTXFrameLowering will emit following instruction at the beginning
+// of a MachineFunction.
+//
+//   mov %SPL, %depot
+//   cvta.local %SP, %SPL
+//
+// Because Frame Index is a generic address and alloca can only return generic
+// pointer, without this pass the instructions producing alloca'ed address will
+// be based on %SP. NVPTXLowerAlloca tends to help replace store and load on
+// this address with their .local versions, but this may introduce a lot of
+// cvta.to.local instructions. Performance can be improved if we avoid casting
+// address back and forth and directly calculate local address based on %SPL.
+// This peephole pass optimizes these cases, for example
+//
+// It will transform the following pattern
+//    %vreg0<def> = LEA_ADDRi64 <fi#0>, 4
+//    %vreg1<def> = cvta_to_local_yes_64 %vreg0
+//
+// into
+//    %vreg1<def> = LEA_ADDRi64 %VRFrameLocal, 4
+//
+// %VRFrameLocal is the virtual register name of %SPL
+//
+//===----------------------------------------------------------------------===//
+
+#include "NVPTX.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineFrameInfo.h"
+#include "llvm/Target/TargetRegisterInfo.h"
+#include "llvm/Target/TargetInstrInfo.h"
+
+using namespace llvm;
+
+#define DEBUG_TYPE "nvptx-peephole"
+
+namespace llvm {
+void initializeNVPTXPeepholePass(PassRegistry &);
+}
+
+namespace {
+struct NVPTXPeephole : public MachineFunctionPass {
+ public:
+  static char ID;
+  NVPTXPeephole() : MachineFunctionPass(ID) {
+    initializeNVPTXPeepholePass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "NVPTX optimize redundant cvta.to.local instruction";
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+};
+}
+
+char NVPTXPeephole::ID = 0;
+
+INITIALIZE_PASS(NVPTXPeephole, "nvptx-peephole", "NVPTX Peephole", false, false)
+
+static bool isCVTAToLocalCombinationCandidate(MachineInstr &Root) {
+  auto &MBB = *Root.getParent();
+  auto &MF = *MBB.getParent();
+  // Check current instruction is cvta.to.local
+  if (Root.getOpcode() != NVPTX::cvta_to_local_yes_64 &&
+      Root.getOpcode() != NVPTX::cvta_to_local_yes)
+    return false;
+
+  auto &Op = Root.getOperand(1);
+  const auto &MRI = MF.getRegInfo();
+  MachineInstr *GenericAddrDef = nullptr;
+  if (Op.isReg() && TargetRegisterInfo::isVirtualRegister(Op.getReg())) {
+    GenericAddrDef = MRI.getUniqueVRegDef(Op.getReg());
+  }
+
+  // Check the register operand is uniquely defined by LEA_ADDRi instruction
+  if (!GenericAddrDef || GenericAddrDef->getParent() != &MBB ||
+      (GenericAddrDef->getOpcode() != NVPTX::LEA_ADDRi64 &&
+       GenericAddrDef->getOpcode() != NVPTX::LEA_ADDRi)) {
+    return false;
+  }
+
+  // Check the LEA_ADDRi operand is Frame index
+  auto &BaseAddrOp = GenericAddrDef->getOperand(1);
+  if (BaseAddrOp.getType() == MachineOperand::MO_FrameIndex) {
+    return true;
+  }
+
+  return false;
+}
+
+static void CombineCVTAToLocal(MachineInstr &Root) {
+  auto &MBB = *Root.getParent();
+  auto &MF = *MBB.getParent();
+  const auto &MRI = MF.getRegInfo();
+  const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
+  auto &Prev = *MRI.getUniqueVRegDef(Root.getOperand(1).getReg());
+
+  // Get the correct offset
+  int FrameIndex = Prev.getOperand(1).getIndex();
+  int Offset = MF.getFrameInfo()->getObjectOffset(FrameIndex) +
+               Prev.getOperand(2).getImm();
+
+  MachineInstrBuilder MIB =
+      BuildMI(MF, Root.getDebugLoc(), TII->get(Prev.getOpcode()),
+              Root.getOperand(0).getReg())
+          .addReg(NVPTX::VRFrameLocal)
+          .addOperand(MachineOperand::CreateImm(Offset));
+
+  MBB.insert((MachineBasicBlock::iterator)&Root, MIB);
+
+  // Check if MRI has only one non dbg use, which is Root
+  if (MRI.hasOneNonDBGUse(Prev.getOperand(0).getReg())) {
+    Prev.eraseFromParentAndMarkDBGValuesForRemoval();
+  }
+  Root.eraseFromParentAndMarkDBGValuesForRemoval();
+}
+
+bool NVPTXPeephole::runOnMachineFunction(MachineFunction &MF) {
+  bool Changed = false;
+  // Loop over all of the basic blocks.
+  for (auto &MBB : MF) {
+    // Traverse the basic block.
+    auto BlockIter = MBB.begin();
+
+    while (BlockIter != MBB.end()) {
+      auto &MI = *BlockIter++;
+      if (isCVTAToLocalCombinationCandidate(MI)) {
+        CombineCVTAToLocal(MI);
+        Changed = true;
+      }
+    }  // Instruction
+  }    // Basic Block
+  return Changed;
+}
+
+MachineFunctionPass *llvm::createNVPTXPeephole() { return new NVPTXPeephole(); }

llvm/lib/Target/NVPTX/NVPTXRegisterInfo.td

@@ -65,5 +65,5 @@ def Float32ArgRegs : NVPTXRegClass<[f32], 32, (add (sequence "fa%u", 0, 4))>;
 def Float64ArgRegs : NVPTXRegClass<[f64], 64, (add (sequence "da%u", 0, 4))>;
 
 // Read NVPTXRegisterInfo.cpp to see how VRFrame and VRDepot are used.
-def SpecialRegs : NVPTXRegClass<[i32], 32, (add VRFrame, VRDepot,
+def SpecialRegs : NVPTXRegClass<[i32], 32, (add VRFrame, VRFrameLocal, VRDepot,
                                             (sequence "ENVREG%u", 0, 31))>;

llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp

@@ -205,6 +205,8 @@ bool NVPTXPassConfig::addInstSelector() {
   if (!ST.hasImageHandles())
     addPass(createNVPTXReplaceImageHandlesPass());
 
+  addPass(createNVPTXPeephole());
+
   return false;
 }
 

llvm/test/CodeGen/NVPTX/call-with-alloca-buffer.ll

@@ -20,8 +20,7 @@ entry:
   %buf = alloca [16 x i8], align 4
 
 ; CHECK: .local .align 4 .b8 	__local_depot0[16]
-; CHECK: mov.u64 %rd[[BUF_REG:[0-9]+]]
-; CHECK: cvta.local.u64 %SP, %rd[[BUF_REG]]
+; CHECK: mov.u64 %SPL
 
 ; CHECK: ld.param.u64 %rd[[A_REG:[0-9]+]], [kernel_func_param_0]
 ; CHECK: cvta.to.global.u64 %rd[[A1_REG:[0-9]+]], %rd[[A_REG]]

llvm/test/CodeGen/NVPTX/local-stack-frame.ll

@@ -3,16 +3,56 @@
 
 ; Ensure we access the local stack properly
 
-; PTX32:        mov.u32          %r{{[0-9]+}}, __local_depot{{[0-9]+}};
-; PTX32:        cvta.local.u32   %SP, %r{{[0-9]+}};
+; PTX32:        mov.u32          %SPL, __local_depot{{[0-9]+}};
+; PTX32:        cvta.local.u32   %SP, %SPL;
 ; PTX32:        ld.param.u32     %r{{[0-9]+}}, [foo_param_0];
 ; PTX32:        st.volatile.u32  [%SP+0], %r{{[0-9]+}};
-; PTX64:        mov.u64          %rd{{[0-9]+}}, __local_depot{{[0-9]+}};
-; PTX64:        cvta.local.u64   %SP, %rd{{[0-9]+}};
+; PTX64:        mov.u64          %SPL, __local_depot{{[0-9]+}};
+; PTX64:        cvta.local.u64   %SP, %SPL;
 ; PTX64:        ld.param.u32     %r{{[0-9]+}}, [foo_param_0];
 ; PTX64:        st.volatile.u32  [%SP+0], %r{{[0-9]+}};
 define void @foo(i32 %a) {
   %local = alloca i32, align 4
   store volatile i32 %a, i32* %local
   ret void
 }
+
+; PTX32:        mov.u32          %SPL, __local_depot{{[0-9]+}};
+; PTX32:        cvta.local.u32   %SP, %SPL;
+; PTX32:        ld.param.u32     %r{{[0-9]+}}, [foo2_param_0];
+; PTX32:        add.u32          %r[[SP_REG:[0-9]+]], %SPL, 0;
+; PTX32:        st.local.u32  [%r[[SP_REG]]], %r{{[0-9]+}};
+; PTX64:        mov.u64          %SPL, __local_depot{{[0-9]+}};
+; PTX64:        cvta.local.u64   %SP, %SPL;
+; PTX64:        ld.param.u32     %r{{[0-9]+}}, [foo2_param_0];
+; PTX64:        add.u64          %rd[[SP_REG:[0-9]+]], %SPL, 0;
+; PTX64:        st.local.u32  [%rd[[SP_REG]]], %r{{[0-9]+}};
+define void @foo2(i32 %a) {
+  %local = alloca i32, align 4
+  store i32 %a, i32* %local
+  call void @bar(i32* %local)
+  ret void
+}
+
+declare void @bar(i32* %a)
+
+!nvvm.annotations = !{!0}
+!0 = !{void (i32)* @foo2, !"kernel", i32 1}
+
+; PTX32:        mov.u32          %SPL, __local_depot{{[0-9]+}};
+; PTX32-NOT:    cvta.local.u32   %SP, %SPL;
+; PTX32:        ld.param.u32     %r{{[0-9]+}}, [foo3_param_0];
+; PTX32:        add.u32          %r{{[0-9]+}}, %SPL, 0;
+; PTX32:        st.local.u32  [%r{{[0-9]+}}], %r{{[0-9]+}};
+; PTX64:        mov.u64          %SPL, __local_depot{{[0-9]+}};
+; PTX64-NOT:    cvta.local.u64   %SP, %SPL;
+; PTX64:        ld.param.u32     %r{{[0-9]+}}, [foo3_param_0];
+; PTX64:        add.u64          %rd{{[0-9]+}}, %SPL, 0;
+; PTX64:        st.local.u32  [%rd{{[0-9]+}}], %r{{[0-9]+}};
+define void @foo3(i32 %a) {
+  %local = alloca [3 x i32], align 4
+  %1 = bitcast [3 x i32]* %local to i32*
+  %2 = getelementptr inbounds i32, i32* %1, i32 %a
+  store i32 %a, i32* %2
+  ret void
+}