[HEXAGON] Utilize new mask instruction

Co-authored-by: Harsha Jagasia <[email protected]>
Co-authored-by: Krzysztof Parzyszek <[email protected]>

llvm/lib/Target/Hexagon/CMakeLists.txt

@@ -48,6 +48,7 @@ add_llvm_target(HexagonCodeGen
   HexagonLoopIdiomRecognition.cpp
   HexagonMachineFunctionInfo.cpp
   HexagonMachineScheduler.cpp
+  HexagonMask.cpp
   HexagonMCInstLower.cpp
   HexagonNewValueJump.cpp
   HexagonOptAddrMode.cpp

llvm/lib/Target/Hexagon/HexagonMask.cpp

@@ -0,0 +1,110 @@
+//===-- HexagonMask.cpp - replace const ext tfri with mask ------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+//===----------------------------------------------------------------------===//
+
+#define DEBUG_TYPE "mask"
+
+#include "HexagonMachineFunctionInfo.h"
+#include "HexagonSubtarget.h"
+#include "HexagonTargetMachine.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/ADT/Twine.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/MathExtras.h"
+#include "llvm/Target/TargetMachine.h"
+
+using namespace llvm;
+
+namespace llvm {
+FunctionPass *createHexagonMask();
+void initializeHexagonMaskPass(PassRegistry &);
+
+class HexagonMask : public MachineFunctionPass {
+public:
+  static char ID;
+  HexagonMask() : MachineFunctionPass(ID) {
+    PassRegistry &Registry = *PassRegistry::getPassRegistry();
+    initializeHexagonMaskPass(Registry);
+  }
+
+  StringRef getPassName() const override {
+    return "Hexagon replace const ext tfri with mask";
+  }
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+private:
+  const HexagonInstrInfo *HII;
+  void replaceConstExtTransferImmWithMask(MachineFunction &MF);
+};
+
+char HexagonMask::ID = 0;
+
+void HexagonMask::replaceConstExtTransferImmWithMask(MachineFunction &MF) {
+  for (auto &MBB : MF) {
+    for (auto &MI : llvm::make_early_inc_range(MBB)) {
+      if (MI.getOpcode() != Hexagon::A2_tfrsi)
+        continue;
+
+      const MachineOperand &Op0 = MI.getOperand(0);
+      const MachineOperand &Op1 = MI.getOperand(1);
+      if (!Op1.isImm())
+        continue;
+      int32_t V = Op1.getImm();
+      if (isInt<16>(V))
+        continue;
+
+      unsigned Idx, Len;
+      if (!isShiftedMask_32(V, Idx, Len))
+        continue;
+      if (!isUInt<5>(Idx) || !isUInt<5>(Len))
+        continue;
+
+      BuildMI(MBB, MI, MI.getDebugLoc(), HII->get(Hexagon::S2_mask),
+              Op0.getReg())
+          .addImm(Len)
+          .addImm(Idx);
+      MBB.erase(MI);
+    }
+  }
+}
+
+bool HexagonMask::runOnMachineFunction(MachineFunction &MF) {
+  auto &HST = MF.getSubtarget<HexagonSubtarget>();
+  HII = HST.getInstrInfo();
+  const Function &F = MF.getFunction();
+
+  if (!F.hasFnAttribute(Attribute::OptimizeForSize))
+    return false;
+  // The mask instruction available in v66 can be used to generate values in
+  // registers using 2 immediates Eg. to form 0x07fffffc in R0, you would write
+  // "R0 = mask(#25,#2)" Since it is a single-word instruction, it takes less
+  // code size than a constant-extended transfer at Os
+  replaceConstExtTransferImmWithMask(MF);
+
+  return true;
+}
+
+} // namespace llvm
+
+//===----------------------------------------------------------------------===//
+//                         Public Constructor Functions
+//===----------------------------------------------------------------------===//
+
+INITIALIZE_PASS(HexagonMask, "hexagon-mask", "Hexagon mask", false, false)
+
+FunctionPass *llvm::createHexagonMask() { return new HexagonMask(); }

llvm/lib/Target/Hexagon/HexagonTargetMachine.cpp

@@ -59,6 +59,10 @@ static cl::opt<bool>
     DisableHCP("disable-hcp", cl::Hidden,
                cl::desc("Disable Hexagon constant propagation"));
 
+static cl::opt<bool> DisableHexagonMask(
+    "disable-mask", cl::Hidden,
+    cl::desc("Disable Hexagon specific Mask generation pass"));
+
 static cl::opt<bool> DisableStoreWidening("disable-store-widen", cl::Hidden,
                                           cl::init(false),
                                           cl::desc("Disable store widening"));
@@ -180,6 +184,8 @@ void initializeHexagonGenMuxPass(PassRegistry &);
 void initializeHexagonHardwareLoopsPass(PassRegistry &);
 void initializeHexagonLoopIdiomRecognizeLegacyPassPass(PassRegistry &);
 void initializeHexagonLoopAlignPass(PassRegistry &);
+void initializeHexagonMaskPass(PassRegistry &);
+void initializeHexagonMergeActivateWeightPass(PassRegistry &);
 void initializeHexagonNewValueJumpPass(PassRegistry &);
 void initializeHexagonOptAddrModePass(PassRegistry &);
 void initializeHexagonPacketizerPass(PassRegistry &);
@@ -213,6 +219,8 @@ FunctionPass *createHexagonISelDag(HexagonTargetMachine &TM,
                                    CodeGenOptLevel OptLevel);
 FunctionPass *createHexagonLoopAlign();
 FunctionPass *createHexagonLoopRescheduling();
+FunctionPass *createHexagonMask();
+FunctionPass *createHexagonMergeActivateWeight();
 FunctionPass *createHexagonNewValueJump();
 FunctionPass *createHexagonOptAddrMode();
 FunctionPass *createHexagonOptimizeSZextends();
@@ -474,10 +482,13 @@ void HexagonPassConfig::addPostRegAlloc() {
 }
 
 void HexagonPassConfig::addPreSched2() {
+  bool NoOpt = (getOptLevel() == CodeGenOptLevel::None);
   addPass(createHexagonCopyToCombine());
   if (getOptLevel() != CodeGenOptLevel::None)
     addPass(&IfConverterID);
   addPass(createHexagonSplitConst32AndConst64());
+  if (!NoOpt && !DisableHexagonMask)
+    addPass(createHexagonMask());
 }
 
 void HexagonPassConfig::addPreEmitPass() {

llvm/test/CodeGen/Hexagon/mask.ll

@@ -0,0 +1,17 @@
+; RUN: llc -mtriple=hexagon -mcpu=hexagonv73 < %s | FileCheck %s
+
+target triple = "hexagon"
+
+; CHECK-LABEL: test1:
+; CHECK: r0 = mask(#25,#2)
+; Function Attrs: optsize
+define i32 @test1() #1 {
+entry:
+  %0 = call i32 @llvm.hexagon.A2.tfr(i32 134217724)
+  ret i32 %0
+}
+
+declare i32 @llvm.hexagon.A2.tfr(i32) #0
+
+attributes #0 = { nounwind readnone }
+attributes #1 = { optsize }