llvm/llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp

//===- AMDGPUOpenCLEnqueuedBlockLowering.cpp - Lower enqueued block -------===//
//
// 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 post-linking pass replaces the function pointer of enqueued
// block kernel with a global variable (runtime handle) and adds
// "runtime-handle" attribute to the enqueued block kernel.
//
// In LLVM CodeGen the runtime-handle metadata will be translated to
// RuntimeHandle metadata in code object. Runtime allocates a global buffer
// for each kernel with RuntimeHandle metadata and saves the kernel address
// required for the AQL packet into the buffer. __enqueue_kernel function
// in device library knows that the invoke function pointer in the block
// literal is actually runtime handle and loads the kernel address from it
// and put it into AQL packet for dispatching.
//
// This cannot be done in FE since FE cannot create a unique global variable
// with external linkage across LLVM modules. The global variable with internal
// linkage does not work since optimization passes will try to replace loads
// of the global variable with its initialization value.
//
// It also identifies the kernels directly or indirectly enqueues kernels
// and adds "calls-enqueue-kernel" function attribute to them, which will
// be used to determine whether to emit runtime metadata for the kernel
// enqueue related hidden kernel arguments.
//
//===----------------------------------------------------------------------===//

#include "AMDGPU.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Module.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"

#define DEBUG_TYPE …

usingnamespacellvm;

namespace {

/// Lower enqueued blocks.
class AMDGPUOpenCLEnqueuedBlockLowering : public ModulePass { … };

} // end anonymous namespace

char AMDGPUOpenCLEnqueuedBlockLowering::ID = …;

char &llvm::AMDGPUOpenCLEnqueuedBlockLoweringID = …;

INITIALIZE_PASS(…)

ModulePass* llvm::createAMDGPUOpenCLEnqueuedBlockLoweringPass() { … }

bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) { … }