e7101dac9c
Summary: Currently we have this `__tgt_device_image` indirection which just takes a reference to some pointers. This was all find and good when the only usage of this was from a section of GPU code that came from an ELF constant section. However, we have expanded beyond that and now need to worry about managing lifetimes. We have code that references the image even after it was loaded internally. This patch changes the implementation to instaed copy the memory buffer and manage it locally. This PR reworks the JIT and other image handling to directly manage its own memory. We now don't need to duplicate this behavior externally at the Offload API level. Also we actually free these if the user unloads them. Upside, less likely to crash and burn. Downside, more latency when loading an image.
115 lines
4.0 KiB
C++
115 lines
4.0 KiB
C++
//===- JIT.h - Target independent JIT infrastructure ----------------------===//
|
|
//
|
|
// 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 OPENMP_LIBOMPTARGET_PLUGINS_NEXTGEN_COMMON_JIT_H
|
|
#define OPENMP_LIBOMPTARGET_PLUGINS_NEXTGEN_COMMON_JIT_H
|
|
|
|
#include "Shared/EnvironmentVar.h"
|
|
#include "Shared/Utils.h"
|
|
|
|
#include "llvm/ADT/StringMap.h"
|
|
#include "llvm/ADT/StringRef.h"
|
|
#include "llvm/Analysis/TargetLibraryInfo.h"
|
|
#include "llvm/IR/LLVMContext.h"
|
|
#include "llvm/IR/Module.h"
|
|
#include "llvm/Support/Error.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
#include "llvm/TargetParser/Triple.h"
|
|
|
|
#include <functional>
|
|
#include <memory>
|
|
#include <string>
|
|
|
|
struct __tgt_device_image;
|
|
|
|
namespace llvm {
|
|
class MemoryBuffer;
|
|
|
|
namespace omp {
|
|
namespace target {
|
|
namespace plugin {
|
|
struct GenericDeviceTy;
|
|
} // namespace plugin
|
|
|
|
/// The JIT infrastructure and caching mechanism.
|
|
struct JITEngine {
|
|
/// Function type for a callback that will be called after the backend is
|
|
/// called.
|
|
using PostProcessingFn =
|
|
std::function<Expected<std::unique_ptr<MemoryBuffer>>(
|
|
std::unique_ptr<MemoryBuffer>)>;
|
|
|
|
JITEngine(Triple::ArchType TA);
|
|
|
|
/// Run jit compilation if \p Image is a bitcode image, otherwise simply
|
|
/// return \p Image. It is expected to return a memory buffer containing the
|
|
/// generated device image that could be loaded to the device directly.
|
|
Expected<std::unique_ptr<MemoryBuffer>>
|
|
process(StringRef Image, target::plugin::GenericDeviceTy &Device);
|
|
|
|
private:
|
|
/// Compile the bitcode image \p Image and generate the binary image that can
|
|
/// be loaded to the target device of the triple \p Triple architecture \p
|
|
/// MCpu. \p PostProcessing will be called after codegen to handle cases such
|
|
/// as assembler as an external tool.
|
|
Expected<std::unique_ptr<MemoryBuffer>>
|
|
compile(StringRef Image, const std::string &ComputeUnitKind,
|
|
PostProcessingFn PostProcessing);
|
|
|
|
/// Create or retrieve the object image file from the file system or via
|
|
/// compilation of the \p Image.
|
|
Expected<std::unique_ptr<MemoryBuffer>>
|
|
getOrCreateObjFile(StringRef Image, LLVMContext &Ctx,
|
|
const std::string &ComputeUnitKind);
|
|
|
|
/// Run backend, which contains optimization and code generation.
|
|
Expected<std::unique_ptr<MemoryBuffer>>
|
|
backend(Module &M, const std::string &ComputeUnitKind, unsigned OptLevel);
|
|
|
|
/// Run optimization pipeline.
|
|
void opt(TargetMachine *TM, TargetLibraryInfoImpl *TLII, Module &M,
|
|
unsigned OptLevel);
|
|
|
|
/// Run code generation.
|
|
void codegen(TargetMachine *TM, TargetLibraryInfoImpl *TLII, Module &M,
|
|
raw_pwrite_stream &OS);
|
|
|
|
/// The target triple used by the JIT.
|
|
const Triple TT;
|
|
|
|
struct ComputeUnitInfo {
|
|
/// LLVM Context in which the modules will be constructed.
|
|
LLVMContext Context;
|
|
};
|
|
|
|
/// Map from (march) "CPUs" (e.g., sm_80, or gfx90a), which we call compute
|
|
/// units as they are not CPUs, to the image information we cached for them.
|
|
StringMap<ComputeUnitInfo> ComputeUnitMap;
|
|
std::mutex ComputeUnitMapMutex;
|
|
|
|
/// Control environment variables.
|
|
StringEnvar ReplacementObjectFileName =
|
|
StringEnvar("LIBOMPTARGET_JIT_REPLACEMENT_OBJECT");
|
|
StringEnvar ReplacementModuleFileName =
|
|
StringEnvar("LIBOMPTARGET_JIT_REPLACEMENT_MODULE");
|
|
StringEnvar PreOptIRModuleFileName =
|
|
StringEnvar("LIBOMPTARGET_JIT_PRE_OPT_IR_MODULE");
|
|
StringEnvar PostOptIRModuleFileName =
|
|
StringEnvar("LIBOMPTARGET_JIT_POST_OPT_IR_MODULE");
|
|
UInt32Envar JITOptLevel = UInt32Envar("LIBOMPTARGET_JIT_OPT_LEVEL", 3);
|
|
BoolEnvar JITSkipOpt = BoolEnvar("LIBOMPTARGET_JIT_SKIP_OPT", false);
|
|
};
|
|
|
|
} // namespace target
|
|
} // namespace omp
|
|
} // namespace llvm
|
|
|
|
#endif // OPENMP_LIBOMPTARGET_PLUGINS_NEXTGEN_COMMON_JIT_H
|