Files
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

102 lines
3.7 KiB
C++

//=======- NVPTXFrameLowering.cpp - NVPTX Frame Information ---*- 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
//
//===----------------------------------------------------------------------===//
//
// This file contains the NVPTX implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//
#include "NVPTXFrameLowering.h"
#include "NVPTX.h"
#include "NVPTXRegisterInfo.h"
#include "NVPTXSubtarget.h"
#include "NVPTXTargetMachine.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
using namespace llvm;
NVPTXFrameLowering::NVPTXFrameLowering()
: TargetFrameLowering(TargetFrameLowering::StackGrowsUp, Align(8), 0) {}
bool NVPTXFrameLowering::hasFPImpl(const MachineFunction &MF) const {
return true;
}
void NVPTXFrameLowering::emitPrologue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
if (MF.getFrameInfo().hasStackObjects()) {
assert(&MF.front() == &MBB && "Shrink-wrapping not yet supported");
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineRegisterInfo &MR = MF.getRegInfo();
const NVPTXRegisterInfo *NRI =
MF.getSubtarget<NVPTXSubtarget>().getRegisterInfo();
// This instruction really occurs before first instruction
// in the BB, so giving it no debug location.
DebugLoc dl = DebugLoc();
// Emits
// mov %SPL, %depot;
// cvta.local %SP, %SPL;
// for local address accesses in MF.
bool Is64Bit =
static_cast<const NVPTXTargetMachine &>(MF.getTarget()).is64Bit();
unsigned CvtaLocalOpcode =
(Is64Bit ? NVPTX::cvta_local_64 : NVPTX::cvta_local);
unsigned MovDepotOpcode =
(Is64Bit ? NVPTX::MOV_DEPOT_ADDR_64 : NVPTX::MOV_DEPOT_ADDR);
if (!MR.use_empty(NRI->getFrameRegister(MF))) {
// If %SP is not used, do not bother emitting "cvta.local %SP, %SPL".
MBBI = BuildMI(MBB, MBBI, dl,
MF.getSubtarget().getInstrInfo()->get(CvtaLocalOpcode),
NRI->getFrameRegister(MF))
.addReg(NRI->getFrameLocalRegister(MF));
}
if (!MR.use_empty(NRI->getFrameLocalRegister(MF))) {
BuildMI(MBB, MBBI, dl,
MF.getSubtarget().getInstrInfo()->get(MovDepotOpcode),
NRI->getFrameLocalRegister(MF))
.addImm(MF.getFunctionNumber());
}
}
}
StackOffset
NVPTXFrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
Register &FrameReg) const {
const MachineFrameInfo &MFI = MF.getFrameInfo();
FrameReg = NVPTX::VRDepot;
return StackOffset::getFixed(MFI.getObjectOffset(FI) -
getOffsetOfLocalArea());
}
void NVPTXFrameLowering::emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const {}
// This function eliminates ADJCALLSTACKDOWN,
// ADJCALLSTACKUP pseudo instructions
MachineBasicBlock::iterator NVPTXFrameLowering::eliminateCallFramePseudoInstr(
MachineFunction &MF, MachineBasicBlock &MBB,
MachineBasicBlock::iterator I) const {
// Simply discard ADJCALLSTACKDOWN,
// ADJCALLSTACKUP instructions.
return MBB.erase(I);
}
TargetFrameLowering::DwarfFrameBase
NVPTXFrameLowering::getDwarfFrameBase(const MachineFunction &MF) const {
DwarfFrameBase FrameBase;
FrameBase.Kind = DwarfFrameBase::CFA;
FrameBase.Location.Offset = 0;
return FrameBase;
}