34028294e4
This patch adds `olGetEventElapsedTime` to the new LLVM Offload API, as requested in [#185728](https://github.com/llvm/llvm-project/issues/185728), and adds the corresponding support in `plugins-nextgen`. A main motivation for this change is to make it possible to measure the elapsed time of work submitted to a queue, especially kernel launches. This is relevant to the intended use of the new Offload API for microbenchmarking GPU libc math functions. ### Summary The new API returns the elapsed time, in milliseconds, between two events on the same device. To support the common pattern `create start event → enqueue kernel → create end event → sync end event → get elapsed time`, `olCreateEvent` now always creates and records a backend event through the device interface. For backends that materialize real event state, this gives the event concrete backend state that can be used for elapsed-time measurement. For backends that do not materialize backend event state, `EventInfo` may still remain null and existing event operations continue to treat such events as trivially complete. Previously, an event created on an empty queue could be represented only as a logical event. That representation was sufficient for sync and completion queries, but it was not suitable for elapsed-time measurement because there was no backend event state to timestamp. The new behavior preserves the meaning of completion of prior work while also allowing backends with timing support to attach real event state. ### Changes in `plugins-nextgen` #### Common interface Add elapsed-time support to the common device and plugin interfaces: * `GenericPluginTy::get_event_elapsed_time` * `GenericDeviceTy::getEventElapsedTime` * `GenericDeviceTy::getEventElapsedTimeImpl` #### AMDGPU * Add the required ROCr declarations and wrappers. * Enable queue profiling at queue creation time. * Record events by enqueuing a real barrier marker packet on the stream. * Retain the timing signal needed to query the recorded marker later. * Implement `getEventElapsedTimeImpl` using `hsa_amd_profiling_get_dispatch_time`, converting the result to milliseconds with `HSA_SYSTEM_INFO_TIMESTAMP_FREQUENCY`. This follows the ROCm/HIP approach of enabling queue profiling at HSA queue creation time, while keeping the AMDGPU queue path simpler than the lazy-enable alternative discussed during review. #### CUDA * Add the required CUDA driver declarations and wrappers. * Implement `getEventElapsedTimeImpl` with `cuEventElapsedTime`. #### Host * Add `getEventElapsedTimeImpl` that stores `0.0f` in the output pointer, when present, and returns success. Reason: the host plugin does not materialize backend event state and already treats event operations as trivially successful. Returning `0.0f` preserves that model without introducing a new failure mode. #### Level Zero * Add `getEventElapsedTimeImpl`, but leave it unimplemented. Reason: the Level Zero plugin currently does not provide standalone backend event support for this event model. For example, `waitEventImpl` / `syncEventImpl` are still unimplemented there. --------- Signed-off-by: Leandro Augusto Lacerda Campos <leandrolcampos@yahoo.com.br> Signed-off-by: Leandro A. Lacerda Campos <leandrolcampos@yahoo.com.br>
147 lines
4.3 KiB
C++
147 lines
4.3 KiB
C++
//===------- Offload API tests - olGetEventElapsedTime --------------------===//
|
|
//
|
|
// 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 "../common/Fixtures.hpp"
|
|
#include "llvm/Support/MemoryBuffer.h"
|
|
#include <OffloadAPI.h>
|
|
#include <gtest/gtest.h>
|
|
|
|
namespace {
|
|
|
|
struct olGetEventElapsedTimeTest : OffloadQueueTest {
|
|
void SetUp() override {
|
|
RETURN_ON_FATAL_FAILURE(OffloadQueueTest::SetUp());
|
|
|
|
ASSERT_TRUE(TestEnvironment::loadDeviceBinary("foo", Device, DeviceBin));
|
|
ASSERT_SUCCESS(olCreateProgram(Device, DeviceBin->getBufferStart(),
|
|
DeviceBin->getBufferSize(), &Program));
|
|
ASSERT_SUCCESS(olGetSymbol(Program, "foo", OL_SYMBOL_KIND_KERNEL, &Kernel));
|
|
|
|
LaunchArgs.Dimensions = 1;
|
|
LaunchArgs.GroupSize = {64, 1, 1};
|
|
LaunchArgs.NumGroups = {1, 1, 1};
|
|
LaunchArgs.DynSharedMemory = 0;
|
|
|
|
ASSERT_SUCCESS(olMemAlloc(Device, OL_ALLOC_TYPE_MANAGED,
|
|
LaunchArgs.GroupSize.x * sizeof(uint32_t), &Mem));
|
|
}
|
|
|
|
void TearDown() override {
|
|
if (Mem)
|
|
ASSERT_SUCCESS(olMemFree(Mem));
|
|
if (Program)
|
|
ASSERT_SUCCESS(olDestroyProgram(Program));
|
|
RETURN_ON_FATAL_FAILURE(OffloadQueueTest::TearDown());
|
|
}
|
|
|
|
void launchFoo() {
|
|
struct {
|
|
void *Mem;
|
|
} Args{Mem};
|
|
|
|
ASSERT_SUCCESS(olLaunchKernel(Queue, Device, Kernel, &Args, sizeof(Args),
|
|
&LaunchArgs));
|
|
}
|
|
|
|
std::unique_ptr<llvm::MemoryBuffer> DeviceBin;
|
|
ol_program_handle_t Program = nullptr;
|
|
ol_symbol_handle_t Kernel = nullptr;
|
|
ol_kernel_launch_size_args_t LaunchArgs{};
|
|
void *Mem = nullptr;
|
|
};
|
|
|
|
OFFLOAD_TESTS_INSTANTIATE_DEVICE_FIXTURE(olGetEventElapsedTimeTest);
|
|
|
|
TEST_P(olGetEventElapsedTimeTest, Success) {
|
|
ol_event_handle_t StartEvent = nullptr;
|
|
ol_event_handle_t EndEvent = nullptr;
|
|
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &StartEvent));
|
|
ASSERT_NE(StartEvent, nullptr);
|
|
|
|
launchFoo();
|
|
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &EndEvent));
|
|
ASSERT_NE(EndEvent, nullptr);
|
|
|
|
ASSERT_SUCCESS(olSyncEvent(EndEvent));
|
|
|
|
float ElapsedTime = -1.0f;
|
|
|
|
ASSERT_SUCCESS(olGetEventElapsedTime(StartEvent, EndEvent, &ElapsedTime));
|
|
ASSERT_GE(ElapsedTime, 0.0f);
|
|
|
|
ASSERT_SUCCESS(olDestroyEvent(StartEvent));
|
|
ASSERT_SUCCESS(olDestroyEvent(EndEvent));
|
|
}
|
|
|
|
TEST_P(olGetEventElapsedTimeTest, SuccessMultipleCalls) {
|
|
ol_event_handle_t StartEvent = nullptr;
|
|
ol_event_handle_t EndEvent = nullptr;
|
|
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &StartEvent));
|
|
ASSERT_NE(StartEvent, nullptr);
|
|
|
|
launchFoo();
|
|
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &EndEvent));
|
|
ASSERT_NE(EndEvent, nullptr);
|
|
|
|
ASSERT_SUCCESS(olSyncEvent(EndEvent));
|
|
|
|
float ElapsedTimeA = -1.0f;
|
|
float ElapsedTimeB = -1.0f;
|
|
|
|
ASSERT_SUCCESS(olGetEventElapsedTime(StartEvent, EndEvent, &ElapsedTimeA));
|
|
ASSERT_SUCCESS(olGetEventElapsedTime(StartEvent, EndEvent, &ElapsedTimeB));
|
|
|
|
ASSERT_GE(ElapsedTimeA, 0.0f);
|
|
ASSERT_GE(ElapsedTimeB, 0.0f);
|
|
|
|
ASSERT_SUCCESS(olDestroyEvent(StartEvent));
|
|
ASSERT_SUCCESS(olDestroyEvent(EndEvent));
|
|
}
|
|
|
|
TEST_P(olGetEventElapsedTimeTest, InvalidNullStartEvent) {
|
|
ol_event_handle_t EndEvent = nullptr;
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &EndEvent));
|
|
|
|
float ElapsedTime = 0.0f;
|
|
ASSERT_ERROR(OL_ERRC_INVALID_NULL_HANDLE,
|
|
olGetEventElapsedTime(nullptr, EndEvent, &ElapsedTime));
|
|
|
|
ASSERT_SUCCESS(olDestroyEvent(EndEvent));
|
|
}
|
|
|
|
TEST_P(olGetEventElapsedTimeTest, InvalidNullEndEvent) {
|
|
ol_event_handle_t StartEvent = nullptr;
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &StartEvent));
|
|
|
|
float ElapsedTime = 0.0f;
|
|
ASSERT_ERROR(OL_ERRC_INVALID_NULL_HANDLE,
|
|
olGetEventElapsedTime(StartEvent, nullptr, &ElapsedTime));
|
|
|
|
ASSERT_SUCCESS(olDestroyEvent(StartEvent));
|
|
}
|
|
|
|
TEST_P(olGetEventElapsedTimeTest, InvalidNullElapsedTime) {
|
|
ol_event_handle_t StartEvent = nullptr;
|
|
ol_event_handle_t EndEvent = nullptr;
|
|
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &StartEvent));
|
|
ASSERT_SUCCESS(olCreateEvent(Queue, &EndEvent));
|
|
|
|
ASSERT_ERROR(OL_ERRC_INVALID_NULL_POINTER,
|
|
olGetEventElapsedTime(StartEvent, EndEvent, nullptr));
|
|
|
|
ASSERT_SUCCESS(olDestroyEvent(StartEvent));
|
|
ASSERT_SUCCESS(olDestroyEvent(EndEvent));
|
|
}
|
|
|
|
} // namespace
|