[RISCV] Add RISCV-specific TargetTransformInfo

[lenary]

Summary

LLVM Allows Targets to provide information that guides optimisations
made to LLVM IR. This is done with callbacks on a TargetTransformInfo object.

This patch adds a TargetTransformInfo class for RISC-V. This will allow us to
implement RISC-V specific callbacks as they become necessary.

This commit also adds the getIntImmCost callbacks, and tests them with a simple
constant hoisting test.

[asb]

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

18

Don't you want to implement this in terms of getIntMatCost, as you introduced in D62857?

[lenary]

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

18

I felt that was:

• less clear;
• less easy to customise, for other LLVM IR instructions with constant arguments that might mean other things; and
• obscured the fact that getIntImmCost is an estimate, where the code that uses the result has fairly specific "thresholds" that trigger optimisation behaviour.

I felt these three points outweighed the abstraction benefits of calling getIntMatCost.

[MaskRay]

llvm/test/Transforms/ConstantHoisting/RISCV/lit.local.cfg

4

Delete the empty line... No need to copy it from X86 :)

[lenary]

• Address review feedback

[lenary]

I attempted to update this diff, but with a rebased branch arc didn't cope. Starting again.

llvm/lib/Target/RISCV/CMakeLists.txt

add_llvm_target(RISCVCodeGen
   RISCVISelDAGToDAG.cpp
   RISCVISelLowering.cpp
   RISCVMCInstLower.cpp
   RISCVMergeBaseOffset.cpp
   RISCVRegisterInfo.cpp
   RISCVSubtarget.cpp
   RISCVTargetMachine.cpp
   RISCVTargetObjectFile.cpp
+  RISCVTargetTransformInfo.cpp
   )
 
 add_subdirectory(AsmParser)
 add_subdirectory(Disassembler)
 add_subdirectory(MCTargetDesc)
 add_subdirectory(TargetInfo)
 add_subdirectory(Utils)

llvm/lib/Target/RISCV/LLVMBuild.txt

 has_asmparser = 1
 has_asmprinter = 1
 has_disassembler = 1
 
 [component_1]
 type = Library
 name = RISCVCodeGen
 parent = RISCV
-required_libraries = AsmPrinter Core CodeGen MC RISCVDesc
+required_libraries = Analysis AsmPrinter Core CodeGen MC RISCVDesc
   RISCVInfo RISCVUtils SelectionDAG Support Target
 add_to_library_groups = RISCV

llvm/lib/Target/RISCV/RISCVISelLowering.h

ISD::NodeType getExtendForAtomicOps() const override {
     return ISD::SIGN_EXTEND;
   }
 
   bool shouldExpandShift(SelectionDAG &DAG, SDNode *N) const override {
     if (DAG.getMachineFunction().getFunction().hasMinSize())
       return false;
     return true;
   }
+  bool isDesirableToCommuteWithShift(const SDNode *N,
+                                     CombineLevel Level) const override;
 
 private:
   void analyzeInputArgs(MachineFunction &MF, CCState &CCInfo,
                         const SmallVectorImpl<ISD::InputArg> &Ins,
                         bool IsRet) const;
   void analyzeOutputArgs(MachineFunction &MF, CCState &CCInfo,
                          const SmallVectorImpl<ISD::OutputArg> &Outs,
                          bool IsRet, CallLoweringInfo *CLI) const;

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

 //===----------------------------------------------------------------------===//
 
 #include "RISCVISelLowering.h"
 #include "RISCV.h"
 #include "RISCVMachineFunctionInfo.h"
 #include "RISCVRegisterInfo.h"
 #include "RISCVSubtarget.h"
 #include "RISCVTargetMachine.h"
+#include "Utils/RISCVMatInt.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/SelectionDAGISel.h"
return DCI.CombineTo(N,
                          DAG.getNode(ISD::AND, DL, MVT::i64, NewFMV,
                                      DAG.getConstant(~SignBit, DL, MVT::i64)));
   }
   }
 
   return SDValue();
 }
 
+bool RISCVTargetLowering::isDesirableToCommuteWithShift(
+    const SDNode *N, CombineLevel Level) const {
+  // The following folds are only desirable if `(OP _, c1 << c2)` can be
+  // materialised in fewer instructions than `(OP _, c1)`:
+  //
+  //   (shl (add x, c1), c2) -> (add (shl x, c2), c1 << c2)
+  //   (shl (or x, c1), c2) -> (or (shl x, c2), c1 << c2)
+  SDValue N0 = N->getOperand(0);
+  if (N0.getOpcode() == ISD::ADD || N0.getOpcode() == ISD::OR) {
+    auto *C1 = dyn_cast<ConstantSDNode>(N0->getOperand(1));
+    auto *C2 = dyn_cast<ConstantSDNode>(N->getOperand(1));
+    if (C1 && C2) {
+      APInt C1Int = C1->getAPIntValue();
+      APInt ShiftedC1Int = C1Int << C2->getAPIntValue();
+
+      // We can materialise `c1 << c2` into an add immediate, so it's "free",
+      // and the combine should happen, to potentially allow further combines
+      // later.
+      if (isLegalAddImmediate(ShiftedC1Int.getSExtValue()))
+        return true;
+
+      // We can materialise `c1` in an add immediate, so it's "free", and the
+      // combine should be prevented.
+      if (isLegalAddImmediate(C1Int.getSExtValue()))
+        return false;
+
+      // Neither constant will fit into an immediate, so find materialisation
+      // costs.
+      int C1Cost = RISCVMatInt::getIntMatCost(C1Int, Subtarget.is64Bit());
+      int ShiftedC1Cost =
+          RISCVMatInt::getIntMatCost(ShiftedC1Int, Subtarget.is64Bit());
+
+      // Materialising `c1` is cheaper than materialising `c1 << c2`, so the
+      // combine should be prevented.
+      if (C1Cost < ShiftedC1Cost)
+        return false;
+    }
+  }
+  return true;
+}
+
 unsigned RISCVTargetLowering::ComputeNumSignBitsForTargetNode(
     SDValue Op, const APInt &DemandedElts, const SelectionDAG &DAG,
     unsigned Depth) const {
   switch (Op.getOpcode()) {
   default:
     break;
   case RISCVISD::SLLW:
   case RISCVISD::SRAW:

llvm/lib/Target/RISCV/RISCVTargetMachine.h

const RISCVSubtarget *getSubtargetImpl(const Function &) const override {
     return &Subtarget;
   }
 
   TargetPassConfig *createPassConfig(PassManagerBase &PM) override;
 
   TargetLoweringObjectFile *getObjFileLowering() const override {
     return TLOF.get();
   }
+
+  TargetTransformInfo getTargetTransformInfo(const Function &F) override;
 };
 }
 
 #endif

llvm/lib/Target/RISCV/RISCVTargetMachine.cpp

 //===-- RISCVTargetMachine.cpp - Define TargetMachine for RISCV -----------===//
 //
 // 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
 //
 //===----------------------------------------------------------------------===//
 //
 // Implements the info about RISCV target spec.
 //
 //===----------------------------------------------------------------------===//
 
-#include "RISCV.h"
 #include "RISCVTargetMachine.h"
+#include "RISCV.h"
 #include "RISCVTargetObjectFile.h"
+#include "RISCVTargetTransformInfo.h"
 #include "TargetInfo/RISCVTargetInfo.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/LegacyPassManager.h"
 #include "llvm/Support/FormattedStream.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Target/TargetOptions.h"
 using namespace llvm;
RISCVTargetMachine::RISCVTargetMachine(const Target &T, const Triple &TT,
     : LLVMTargetMachine(T, computeDataLayout(TT), TT, CPU, FS, Options,
                         getEffectiveRelocModel(TT, RM),
                         getEffectiveCodeModel(CM, CodeModel::Small), OL),
       TLOF(make_unique<RISCVELFTargetObjectFile>()),
       Subtarget(TT, CPU, FS, Options.MCOptions.getABIName(), *this) {
   initAsmInfo();
 }
 
+TargetTransformInfo
+RISCVTargetMachine::getTargetTransformInfo(const Function &F) {
+  return TargetTransformInfo(RISCVTTIImpl(this, F));
+}
+
 namespace {
 class RISCVPassConfig : public TargetPassConfig {
 public:
   RISCVPassConfig(RISCVTargetMachine &TM, PassManagerBase &PM)
       : TargetPassConfig(TM, PM) {}
 
   RISCVTargetMachine &getRISCVTargetMachine() const {
     return getTM<RISCVTargetMachine>();

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h

+//===- RISCVTargetTransformInfo.h - RISC-V specific TTI ---------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This file a TargetTransformInfo::Concept conforming object specific to the
+/// RISC-V target machine. It uses the target's detailed information to
+/// provide more precise answers to certain TTI queries, while letting the
+/// target independent and default TTI implementations handle the rest.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_RISCV_RISCVTARGETTRANSFORMINFO_H
+#define LLVM_LIB_TARGET_RISCV_RISCVTARGETTRANSFORMINFO_H
+
+#include "RISCVSubtarget.h"
+#include "RISCVTargetMachine.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/CodeGen/BasicTTIImpl.h"
+#include "llvm/IR/Function.h"
+
+namespace llvm {
+
+class RISCVTTIImpl : public BasicTTIImplBase<RISCVTTIImpl> {
+  using BaseT = BasicTTIImplBase<RISCVTTIImpl>;
+  using TTI = TargetTransformInfo;
+
+  friend BaseT;
+
+  const RISCVSubtarget *ST;
+  const RISCVTargetLowering *TLI;
+
+  const RISCVSubtarget *getST() const { return ST; }
+  const RISCVTargetLowering *getTLI() const { return TLI; }
+
+public:
+  explicit RISCVTTIImpl(const RISCVTargetMachine *TM, const Function &F)
+      : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
+        TLI(ST->getTargetLowering()) {}
+
+  using BaseT::getIntImmCost;
+  int getIntImmCost(const APInt &Imm);
+  int getIntImmCost(const APInt &Imm, Type *Ty);
+  int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
+  int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
+                    Type *Ty);
+};
+
+} // end namespace llvm
+
+#endif // LLVM_LIB_TARGET_RISCV_RISCVTARGETTRANSFORMINFO_H
 No newline at end of file

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

+//===-- RISCVTargetTransformInfo.cpp - RISC-V specific TTI ----------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "RISCVTargetTransformInfo.h"
+#include "Utils/RISCVMatInt.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/CodeGen/BasicTTIImpl.h"
+#include "llvm/CodeGen/TargetLowering.h"
+using namespace llvm;
+
+#define DEBUG_TYPE "riscvtti"
+
+int RISCVTTIImpl::getIntImmCost(const APInt &Imm) {
+  if (Imm == 0)
+    return TTI::TCC_Free;
+
+  if (getTLI()->isLegalAddImmediate(Imm.getSExtValue()))
+    return TTI::TCC_Free;
+
+  return RISCVMatInt::getIntMatCost(Imm, getST()->is64Bit());
+}
+
+int RISCVTTIImpl::getIntImmCost(const APInt &Imm, Type *Ty) {
+  assert(Ty->isIntegerTy());
+
+  return getIntImmCost(Imm);
+}
+
+int RISCVTTIImpl::getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
+                                Type *Ty) {
+  return getIntImmCost(Imm, Ty);
+}
+
+int RISCVTTIImpl::getIntImmCost(Intrinsic::ID IID, unsigned Idx,
+                                const APInt &Imm, Type *Ty) {
+  return getIntImmCost(Imm, Ty);
+}

llvm/lib/Target/RISCV/Utils/RISCVMatInt.h

 //===- RISCVMatInt.h - Immediate materialisation ---------------*- C++ -*--===//
 //
 // 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
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_LIB_TARGET_RISCV_MATINT_H
 #define LLVM_LIB_TARGET_RISCV_MATINT_H
 
+#include "llvm/ADT/APInt.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Support/MachineValueType.h"
 #include <cstdint>
 
 namespace llvm {
 
 namespace RISCVMatInt {
 struct Inst {
   unsigned Opc;
   int64_t Imm;
 
   Inst(unsigned Opc, int64_t Imm) : Opc(Opc), Imm(Imm) {}
 };
 using InstSeq = SmallVector<Inst, 8>;
 
 // Helper to generate an instruction sequence that will materialise the given
 // immediate value into a register. A sequence of instructions represented by
 // a simple struct produced rather than directly emitting the instructions in
 // order to allow this helper to be used from both the MC layer and during
 // instruction selection.
 void generateInstSeq(int64_t Val, bool IsRV64, InstSeq &Res);
+
+// Helper to estimate the number of instructions required to materialise the
+// given immediate value into a register. This estimate does not account for
+// `Val` possibly fitting into an immediate, and so may over-estimate.
+//
+// This will attempt to produce instructions to materialise `Val`. `IsRV64`
+// should match the target architecture.
+int getIntMatCost(const APInt &Val, bool IsRV64);
 } // namespace RISCVMatInt
 } // namespace llvm
 #endif

llvm/lib/Target/RISCV/Utils/RISCVMatInt.cpp

void generateInstSeq(int64_t Val, bool Is64Bit, InstSeq &Res) {
   Hi52 = SignExtend64(Hi52 >> (ShiftAmount - 12), 64 - ShiftAmount);
 
   generateInstSeq(Hi52, Is64Bit, Res);
 
   Res.push_back(Inst(RISCV::SLLI, ShiftAmount));
   if (Lo12)
     Res.push_back(Inst(RISCV::ADDI, Lo12));
 }
+
+// This will attempt to produce instructions to materialise `Val`. `Is64Bit`
+// should match the target architecture.
+int getIntMatCost(const APInt &Val, bool Is64Bit) {
+  unsigned BitSize = Val.getMinSignedBits();
+  int PlatRegSize = Is64Bit ? 64 : 32;
+
+  // Split the constant into platform register size chunks, and calculate cost
+  // of each chunk.
+  int Cost = 0;
+  for (unsigned ShiftVal = 0; ShiftVal < BitSize; ShiftVal += PlatRegSize) {
+    APInt Chunk = Val.ashr(ShiftVal).sextOrTrunc(PlatRegSize);
+    InstSeq MatSeq;
+    generateInstSeq(Chunk.getSExtValue(), Is64Bit, MatSeq);
+    Cost += MatSeq.size();
+  }
+  return std::max(1, Cost);
+}
 } // namespace RISCVMatInt
 } // namespace llvm

llvm/test/CodeGen/RISCV/add-before-shl.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV32I %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+
+; These test that constant adds are not moved after shifts by DAGCombine,
+; if the constant can fit into an immediate.
+;
+; Materialising the large (shifted) constant produced for the new add
+; uses an extra register, and takes several instructions. It is more
+; efficient to perform the add before the shift if the constant to be
+; added fits into an immediate.
+
+define signext i32 @add_small_const(i32 signext %a) nounwind {
+; RV32I-LABEL: add_small_const:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi a0, a0, 1
+; RV32I-NEXT:    slli a0, a0, 24
+; RV32I-NEXT:    srai a0, a0, 24
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: add_small_const:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, a0, 1
+; RV64I-NEXT:    slli a0, a0, 56
+; RV64I-NEXT:    srai a0, a0, 56
+; RV64I-NEXT:    ret
+  %1 = add i32 %a, 1
+  %2 = shl i32 %1, 24
+  %3 = ashr i32 %2, 24
+  ret i32 %3
+}
+
+define signext i32 @add_large_const(i32 signext %a) nounwind {
+; RV32I-LABEL: add_large_const:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    slli a0, a0, 16
+; RV32I-NEXT:    lui a1, 65520
+; RV32I-NEXT:    add a0, a0, a1
+; RV32I-NEXT:    srai a0, a0, 16
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: add_large_const:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a1, 1
+; RV64I-NEXT:    addiw a1, a1, -1
+; RV64I-NEXT:    add a0, a0, a1
+; RV64I-NEXT:    slli a0, a0, 48
+; RV64I-NEXT:    srai a0, a0, 48
+; RV64I-NEXT:    ret
+  %1 = add i32 %a, 4095
+  %2 = shl i32 %1, 16
+  %3 = ashr i32 %2, 16
+  ret i32 %3
+}
+
+define signext i32 @add_huge_const(i32 signext %a) nounwind {
+; RV32I-LABEL: add_huge_const:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    slli a0, a0, 16
+; RV32I-NEXT:    lui a1, 524272
+; RV32I-NEXT:    add a0, a0, a1
+; RV32I-NEXT:    srai a0, a0, 16
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: add_huge_const:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a1, 8
+; RV64I-NEXT:    addiw a1, a1, -1
+; RV64I-NEXT:    add a0, a0, a1
+; RV64I-NEXT:    slli a0, a0, 48
+; RV64I-NEXT:    srai a0, a0, 48
+; RV64I-NEXT:    ret
+  %1 = add i32 %a, 32767
+  %2 = shl i32 %1, 16
+  %3 = ashr i32 %2, 16
+  ret i32 %3
+}

llvm/test/Transforms/ConstantHoisting/RISCV/immediates.ll

+; RUN: opt -mtriple=riscv32-unknown-elf -S -consthoist < %s | FileCheck %s
+; RUN: opt -mtriple=riscv64-unknown-elf -S -consthoist < %s | FileCheck %s
+
+; Check that we don't hoist immediates with small values.
+define i64 @test1(i64 %a) nounwind {
+; CHECK-LABEL: test1
+; CHECK-NOT: %const = bitcast i64 2 to i64
+  %1 = mul i64 %a, 2
+  %2 = add i64 %1, 2
+  ret i64 %2
+}
+
+; Check that we don't hoist immediates with small values.
+define i64 @test2(i64 %a) nounwind {
+; CHECK-LABEL: test2
+; CHECK-NOT: %const = bitcast i64 2047 to i64
+  %1 = mul i64 %a, 2047
+  %2 = add i64 %1, 2047
+  ret i64 %2
+}
+
+; Check that we hoist immediates with large values.
+define i64 @test3(i64 %a) nounwind {
+; CHECK-LABEL: test3
+; CHECK: %const = bitcast i64 32767 to i64
+  %1 = mul i64 %a, 32767
+  %2 = add i64 %1, 32767
+  ret i64 %2
+}
 No newline at end of file

llvm/test/Transforms/ConstantHoisting/RISCV/lit.local.cfg

+if not 'RISCV' in config.root.targets:
+    config.unsupported = True