Files
TheRock/compiler/amd-llvm/llvm/lib/Target/AMDGPU/SILowerI1Copies.h
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

99 lines
3.5 KiB
C++

//===-- SILowerI1Copies.h --------------------------------------*- 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
/// Interface definition of the PhiLoweringHelper class that implements lane
/// mask merging algorithm for divergent i1 phis.
//
//===----------------------------------------------------------------------===//
#include "AMDGPULaneMaskUtils.h"
#include "GCNSubtarget.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachinePostDominators.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/MachineSSAUpdater.h"
namespace llvm {
namespace AMDGPU {
/// Incoming for lane mask phi as machine instruction, incoming register \p Reg
/// and incoming block \p Block are taken from machine instruction.
/// \p UpdatedReg (if valid) is \p Reg lane mask merged with another lane mask.
struct Incoming {
Register Reg;
MachineBasicBlock *Block;
Register UpdatedReg;
Incoming(Register Reg, MachineBasicBlock *Block, Register UpdatedReg)
: Reg(Reg), Block(Block), UpdatedReg(UpdatedReg) {}
};
Register createLaneMaskReg(MachineRegisterInfo *MRI,
MachineRegisterInfo::VRegAttrs LaneMaskRegAttrs);
class PhiLoweringHelper {
public:
PhiLoweringHelper(MachineFunction *MF, MachineDominatorTree *DT,
MachinePostDominatorTree *PDT);
virtual ~PhiLoweringHelper() = default;
protected:
bool IsWave32 = false;
MachineFunction *MF = nullptr;
MachineDominatorTree *DT = nullptr;
MachinePostDominatorTree *PDT = nullptr;
MachineRegisterInfo *MRI = nullptr;
const GCNSubtarget *ST = nullptr;
const SIInstrInfo *TII = nullptr;
MachineRegisterInfo::VRegAttrs LaneMaskRegAttrs;
const AMDGPU::LaneMaskConstants *LMC = nullptr;
#ifndef NDEBUG
DenseSet<Register> PhiRegisters;
#endif
public:
bool lowerPhis();
bool isConstantLaneMask(Register Reg, bool &Val) const;
MachineBasicBlock::iterator
getSaluInsertionAtEnd(MachineBasicBlock &MBB) const;
void initializeLaneMaskRegisterAttributes(Register LaneMask) {
LaneMaskRegAttrs = MRI->getVRegAttrs(LaneMask);
}
void
initializeLaneMaskRegisterAttributes(MachineRegisterInfo::VRegAttrs Attrs) {
LaneMaskRegAttrs = Attrs;
}
bool isLaneMaskReg(Register Reg) const {
return TII->getRegisterInfo().isSGPRReg(*MRI, Reg) &&
TII->getRegisterInfo().getRegSizeInBits(Reg, *MRI) ==
ST->getWavefrontSize();
}
// Helpers from lowerPhis that are different between sdag and global-isel.
virtual void markAsLaneMask(Register DstReg) const = 0;
virtual void getCandidatesForLowering(
SmallVectorImpl<MachineInstr *> &Vreg1Phis) const = 0;
virtual void
collectIncomingValuesFromPhi(const MachineInstr *MI,
SmallVectorImpl<Incoming> &Incomings) const = 0;
virtual void replaceDstReg(Register NewReg, Register OldReg,
MachineBasicBlock *MBB) = 0;
virtual void buildMergeLaneMasks(MachineBasicBlock &MBB,
MachineBasicBlock::iterator I,
const DebugLoc &DL, Register DstReg,
Register PrevReg, Register CurReg) = 0;
virtual void constrainAsLaneMask(Incoming &In) = 0;
};
} // namespace AMDGPU
} // end namespace llvm