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

105 lines
3.4 KiB
C++

//===-- ARMOptimizeBarriersPass - two DMBs without a memory access in between,
//removed one -===//
//
// 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 "ARM.h"
#include "ARMInstrInfo.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
using namespace llvm;
#define DEBUG_TYPE "double barriers"
STATISTIC(NumDMBsRemoved, "Number of DMBs removed");
namespace {
class ARMOptimizeBarriersPass : public MachineFunctionPass {
public:
static char ID;
ARMOptimizeBarriersPass() : MachineFunctionPass(ID) {}
bool runOnMachineFunction(MachineFunction &Fn) override;
MachineFunctionProperties getRequiredProperties() const override {
return MachineFunctionProperties().setNoVRegs();
}
StringRef getPassName() const override { return "optimise barriers pass"; }
};
char ARMOptimizeBarriersPass::ID = 0;
}
// Returns whether the instruction can safely move past a DMB instruction
// The current implementation allows this iif MI does not have any possible
// memory access
static bool CanMovePastDMB(const MachineInstr *MI) {
return !(MI->mayLoad() ||
MI->mayStore() ||
MI->hasUnmodeledSideEffects() ||
MI->isCall() ||
MI->isReturn());
}
bool ARMOptimizeBarriersPass::runOnMachineFunction(MachineFunction &MF) {
if (skipFunction(MF.getFunction()))
return false;
// Vector to store the DMBs we will remove after the first iteration
std::vector<MachineInstr *> ToRemove;
// DMBType is the Imm value of the first operand. It determines whether it's a
// DMB ish, dmb sy, dmb osh, etc
int64_t DMBType = -1;
// Find a dmb. If we can move it until the next dmb, tag the second one for
// removal
for (auto &MBB : MF) {
// Will be true when we have seen a DMB, and not seen any instruction since
// that cannot move past a DMB
bool IsRemovableNextDMB = false;
for (auto &MI : MBB) {
if (MI.getOpcode() == ARM::DMB) {
if (IsRemovableNextDMB) {
// If the Imm of this DMB is the same as that of the last DMB, we can
// tag this second DMB for removal
if (MI.getOperand(0).getImm() == DMBType) {
ToRemove.push_back(&MI);
} else {
// If it has a different DMBType, we cannot remove it, but will scan
// for the next DMB, recording this DMB's type as last seen DMB type
DMBType = MI.getOperand(0).getImm();
}
} else {
// After we see a DMB, a next one is removable
IsRemovableNextDMB = true;
DMBType = MI.getOperand(0).getImm();
}
} else if (!CanMovePastDMB(&MI)) {
// If we find an instruction unable to pass past a DMB, a next DMB is
// not removable
IsRemovableNextDMB = false;
}
}
}
bool Changed = false;
// Remove the tagged DMB
for (auto *MI : ToRemove) {
MI->eraseFromParent();
++NumDMBsRemoved;
Changed = true;
}
return Changed;
}
/// createARMOptimizeBarriersPass - Returns an instance of the remove double
/// barriers
/// pass.
FunctionPass *llvm::createARMOptimizeBarriersPass() {
return new ARMOptimizeBarriersPass();
}