16a385ba21
We already created a versioned `__tgt_kernel_arguments` struct but it
was only briefly used and its content was passed in isolation anyway.
This makes it hard to add more information in the future. With this
patch we fully embrace the struct as means to pass information from the
compiler to the plugin as part of a kernel launch.
The patch also extends and renames the struct, bumping the version
number to 2. Version 1 entries are auto-upgraded. This is in preparation
for "bare" kernel launches, per kernel dynamic shared memory, CUDA/HIP
lowering, etc.
The `__tgt_target_kernel_nowait` interface was deprecated as it was
unused. Once we actually implement support for something like that, we
can add an appropriate API.
Note: Only plugins with the `launch_kernel` interface are now supported.
That means that a new clang won't be able to use an old runtime.
An old clang can still use the new runtime since the libomptarget
interface did not change.
Differential Revision: https://reviews.llvm.org/D141232
199 lines
7.7 KiB
C++
199 lines
7.7 KiB
C++
//===------------ rtl.h - Target independent OpenMP target RTL ------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Declarations for handling RTL plugins.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _OMPTARGET_RTL_H
|
|
#define _OMPTARGET_RTL_H
|
|
|
|
#include "omptarget.h"
|
|
#include "llvm/ADT/DenseSet.h"
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/Support/DynamicLibrary.h"
|
|
|
|
#include "omptarget.h"
|
|
|
|
#include <list>
|
|
#include <map>
|
|
#include <mutex>
|
|
#include <string>
|
|
|
|
// Forward declarations.
|
|
struct DeviceTy;
|
|
struct __tgt_bin_desc;
|
|
|
|
struct RTLInfoTy {
|
|
typedef int32_t(init_plugin_ty)();
|
|
typedef int32_t(deinit_plugin_ty)();
|
|
typedef int32_t(is_valid_binary_ty)(void *);
|
|
typedef int32_t(is_valid_binary_info_ty)(void *, void *);
|
|
typedef int32_t(is_data_exchangable_ty)(int32_t, int32_t);
|
|
typedef int32_t(number_of_devices_ty)();
|
|
typedef int32_t(init_device_ty)(int32_t);
|
|
typedef int32_t(deinit_device_ty)(int32_t);
|
|
typedef __tgt_target_table *(load_binary_ty)(int32_t, void *);
|
|
typedef void *(data_alloc_ty)(int32_t, int64_t, void *, int32_t);
|
|
typedef int32_t(data_submit_ty)(int32_t, void *, void *, int64_t);
|
|
typedef int32_t(data_submit_async_ty)(int32_t, void *, void *, int64_t,
|
|
__tgt_async_info *);
|
|
typedef int32_t(data_retrieve_ty)(int32_t, void *, void *, int64_t);
|
|
typedef int32_t(data_retrieve_async_ty)(int32_t, void *, void *, int64_t,
|
|
__tgt_async_info *);
|
|
typedef int32_t(data_exchange_ty)(int32_t, void *, int32_t, void *, int64_t);
|
|
typedef int32_t(data_exchange_async_ty)(int32_t, void *, int32_t, void *,
|
|
int64_t, __tgt_async_info *);
|
|
typedef int32_t(data_delete_ty)(int32_t, void *, int32_t);
|
|
typedef int32_t(launch_kernel_ty)(int32_t, void *, void **, ptrdiff_t *,
|
|
const KernelArgsTy *, __tgt_async_info *);
|
|
typedef int64_t(init_requires_ty)(int64_t);
|
|
typedef int32_t(synchronize_ty)(int32_t, __tgt_async_info *);
|
|
typedef int32_t(query_async_ty)(int32_t, __tgt_async_info *);
|
|
typedef int32_t (*register_lib_ty)(__tgt_bin_desc *);
|
|
typedef int32_t(supports_empty_images_ty)();
|
|
typedef void(print_device_info_ty)(int32_t);
|
|
typedef void(set_info_flag_ty)(uint32_t);
|
|
typedef int32_t(create_event_ty)(int32_t, void **);
|
|
typedef int32_t(record_event_ty)(int32_t, void *, __tgt_async_info *);
|
|
typedef int32_t(wait_event_ty)(int32_t, void *, __tgt_async_info *);
|
|
typedef int32_t(sync_event_ty)(int32_t, void *);
|
|
typedef int32_t(destroy_event_ty)(int32_t, void *);
|
|
typedef int32_t(release_async_info_ty)(int32_t, __tgt_async_info *);
|
|
typedef int32_t(init_async_info_ty)(int32_t, __tgt_async_info **);
|
|
typedef int64_t(init_device_into_ty)(int64_t, __tgt_device_info *,
|
|
const char **);
|
|
typedef int32_t(data_lock_ty)(int32_t, void *, int64_t, void **);
|
|
typedef int32_t(data_unlock_ty)(int32_t, void *);
|
|
|
|
int32_t Idx = -1; // RTL index, index is the number of devices
|
|
// of other RTLs that were registered before,
|
|
// i.e. the OpenMP index of the first device
|
|
// to be registered with this RTL.
|
|
int32_t NumberOfDevices = -1; // Number of devices this RTL deals with.
|
|
|
|
std::unique_ptr<llvm::sys::DynamicLibrary> LibraryHandler;
|
|
|
|
#ifdef OMPTARGET_DEBUG
|
|
std::string RTLName;
|
|
#endif
|
|
|
|
// Functions implemented in the RTL.
|
|
init_plugin_ty *init_plugin = nullptr;
|
|
deinit_plugin_ty *deinit_plugin = nullptr;
|
|
is_valid_binary_ty *is_valid_binary = nullptr;
|
|
is_valid_binary_info_ty *is_valid_binary_info = nullptr;
|
|
is_data_exchangable_ty *is_data_exchangable = nullptr;
|
|
number_of_devices_ty *number_of_devices = nullptr;
|
|
init_device_ty *init_device = nullptr;
|
|
deinit_device_ty *deinit_device = nullptr;
|
|
load_binary_ty *load_binary = nullptr;
|
|
data_alloc_ty *data_alloc = nullptr;
|
|
data_submit_ty *data_submit = nullptr;
|
|
data_submit_async_ty *data_submit_async = nullptr;
|
|
data_retrieve_ty *data_retrieve = nullptr;
|
|
data_retrieve_async_ty *data_retrieve_async = nullptr;
|
|
data_exchange_ty *data_exchange = nullptr;
|
|
data_exchange_async_ty *data_exchange_async = nullptr;
|
|
data_delete_ty *data_delete = nullptr;
|
|
launch_kernel_ty *launch_kernel = nullptr;
|
|
init_requires_ty *init_requires = nullptr;
|
|
synchronize_ty *synchronize = nullptr;
|
|
query_async_ty *query_async = nullptr;
|
|
register_lib_ty register_lib = nullptr;
|
|
register_lib_ty unregister_lib = nullptr;
|
|
supports_empty_images_ty *supports_empty_images = nullptr;
|
|
set_info_flag_ty *set_info_flag = nullptr;
|
|
print_device_info_ty *print_device_info = nullptr;
|
|
create_event_ty *create_event = nullptr;
|
|
record_event_ty *record_event = nullptr;
|
|
wait_event_ty *wait_event = nullptr;
|
|
sync_event_ty *sync_event = nullptr;
|
|
destroy_event_ty *destroy_event = nullptr;
|
|
init_async_info_ty *init_async_info = nullptr;
|
|
init_device_into_ty *init_device_info = nullptr;
|
|
release_async_info_ty *release_async_info = nullptr;
|
|
data_lock_ty *data_lock = nullptr;
|
|
data_unlock_ty *data_unlock = nullptr;
|
|
|
|
// Are there images associated with this RTL.
|
|
bool IsUsed = false;
|
|
|
|
llvm::DenseSet<const __tgt_device_image *> UsedImages;
|
|
|
|
// Mutex for thread-safety when calling RTL interface functions.
|
|
// It is easier to enforce thread-safety at the libomptarget level,
|
|
// so that developers of new RTLs do not have to worry about it.
|
|
std::mutex Mtx;
|
|
};
|
|
|
|
/// RTLs identified in the system.
|
|
struct RTLsTy {
|
|
// List of the detected runtime libraries.
|
|
std::list<RTLInfoTy> AllRTLs;
|
|
|
|
// Array of pointers to the detected runtime libraries that have compatible
|
|
// binaries.
|
|
llvm::SmallVector<RTLInfoTy *> UsedRTLs;
|
|
|
|
int64_t RequiresFlags = OMP_REQ_UNDEFINED;
|
|
|
|
explicit RTLsTy() = default;
|
|
|
|
// Register the clauses of the requires directive.
|
|
void registerRequires(int64_t Flags);
|
|
|
|
// Initialize RTL if it has not been initialized
|
|
void initRTLonce(RTLInfoTy &RTL);
|
|
|
|
// Initialize all RTLs
|
|
void initAllRTLs();
|
|
|
|
// Register a shared library with all (compatible) RTLs.
|
|
void registerLib(__tgt_bin_desc *Desc);
|
|
|
|
// Unregister a shared library from all RTLs.
|
|
void unregisterLib(__tgt_bin_desc *Desc);
|
|
|
|
// not thread-safe, called from global constructor (i.e. once)
|
|
void loadRTLs();
|
|
|
|
private:
|
|
static bool attemptLoadRTL(const std::string &RTLName, RTLInfoTy &RTL);
|
|
};
|
|
|
|
/// Map between the host entry begin and the translation table. Each
|
|
/// registered library gets one TranslationTable. Use the map from
|
|
/// __tgt_offload_entry so that we may quickly determine whether we
|
|
/// are trying to (re)register an existing lib or really have a new one.
|
|
struct TranslationTable {
|
|
__tgt_target_table HostTable;
|
|
|
|
// Image assigned to a given device.
|
|
llvm::SmallVector<__tgt_device_image *>
|
|
TargetsImages; // One image per device ID.
|
|
|
|
// Table of entry points or NULL if it was not already computed.
|
|
llvm::SmallVector<__tgt_target_table *>
|
|
TargetsTable; // One table per device ID.
|
|
};
|
|
typedef std::map<__tgt_offload_entry *, TranslationTable>
|
|
HostEntriesBeginToTransTableTy;
|
|
|
|
/// Map between the host ptr and a table index
|
|
struct TableMap {
|
|
TranslationTable *Table = nullptr; // table associated with the host ptr.
|
|
uint32_t Index = 0; // index in which the host ptr translated entry is found.
|
|
TableMap() = default;
|
|
TableMap(TranslationTable *Table, uint32_t Index)
|
|
: Table(Table), Index(Index) {}
|
|
};
|
|
typedef std::map<void *, TableMap> HostPtrToTableMapTy;
|
|
|
|
#endif
|