ROCTx Library Tracing (#390)

* Update include/rocprofiler-sdk/marker/*

- Update rocprofiler_marker_api_args_t for all API functions
- Add ROCPROFILER_MARKER_API_ID_roctxGetThreadId to rocprofiler_marker_api_id_t

* Update include/rocprofiler-sdk/marker/api_args.h

- fix include

* Update lib/common/mpl.hpp

- is_pair
- is_type_complete_v

* Update include/rocprofiler-sdk/marker/*

- fix rocprofiler_marker_api_retval_t
- add roctxGetThreadId to rocprofiler_marker_api_args_t
- fix type in enum: HsaDevice -> HsaAgent
- add table_api_id.h

* Update include/rocprofiler-sdk/marker.h

- include marker/table_api_id.h

* Update include/rocprofiler-sdk/buffer_tracing.h

- Buffer marker tracer records have begin and end timestamp

* Add lib/rocprofiler-sdk/marker

- tracing implementation for marker (roctx) library

* Update include/rocprofiler-sdk/{buffer_tracing,marker/table_api_id}.h

- rocprofiler_buffer_tracing_marker_record_t -> rocprofiler_buffer_tracing_marker_api_record_t

* Update lib/rocprofiler-sdk/buffer_tracing.cpp

- support for ROCPROFILER_BUFFER_TRACING_MARKER_API

* Update lib/rocprofiler-sdk/callback_tracing.cpp

- support for ROCPROFILER_CALLBACK_TRACING_MARKER_API

* Update lib/rocprofiler-sdk/intercept_table.cpp

- template instantiation for notify_runtime_api_registration

* Update lib/rocprofiler-sdk/registration.cpp

- enable roctx in rocprofiler_set_api_table

* Update lib/rocprofiler-sdk/marker/marker.cpp

- rocprofiler_buffer_tracing_marker_record_t -> rocprofiler_buffer_tracing_marker_api_record_t

* Update lib/rocprofiler/tests for roctx testing

- add roctx.cpp
  - unit tests for roctx callback and buffer tracing
- support marker API in get_{buffer,callback}_tracing_names()

* Update lib/common/logging.cpp

- logging initialized message mentions env variable

* Update lib/common/mpl.hpp

- NOLINT for misc-definitions-in-headers

* Update lib/rocprofiler-sdk/tests/CMakeLists.txt

- include LD_LIBRARY_PATH in rocprofiler-lib-tests-shared tests

* Update lib/rocprofiler-sdk/registration.cpp

- client_library_vec_t is now vector of option<client_library>
  - enables resetting the client_library after finalization
- removed acquiring registration lock when invoke_client_finalizers called via atexit
  - this was causing some lock-order-inversion warnings (potential deadlock)

* Update lib/rocprofiler-sdk/agent.cpp

- model name for agent supports spaces

* Update tests/common/serialization.hpp

- add serialization support for marker tracing data structures

* Update tests/apps

- Add ROCTx markers into reproducible-runtime and transpose

* Update tests/tools/json-tools.cpp

- add marker tracing support
- remove strdup (no longer necessary)

* Update tests/kernel-tracing/validate.py

- validate marker API tracing data

* Update tests/async-copy-tracing/validate.py

- validate marker API tracing data

* Update cmake for load path resolution during testing

* Update tests/async-copy-tracing/CMakeLists.txt

- fix test LD_LIBRARY_PATH

* Update cmake/Templates/rocprofiler-sdk-roctx/config.cmake.in

- fix constructing rocprofiler-sdk-roctx::rocprofiler-sdk-roctx

tests/apps/CMakeLists.txt

@@ -5,6 +5,10 @@ cmake_minimum_required(VERSION 3.21.0 FATAL_ERROR)
 
 project(rocprofiler-test-apps LANGUAGES C CXX)
 
+set(CMAKE_BUILD_RPATH
+    "\$ORIGIN:\$ORIGIN/../lib:$<TARGET_FILE_DIR:rocprofiler-sdk-roctx::rocprofiler-sdk-roctx-shared-library>"
+    )
+
 # applications used by integration tests
 add_subdirectory(reproducible-runtime)
 add_subdirectory(transpose)

tests/apps/reproducible-runtime/CMakeLists.txt

@@ -43,6 +43,10 @@ target_compile_options(reproducible-runtime PRIVATE -W -Wall -Wextra -Wpedantic
 find_package(Threads REQUIRED)
 target_link_libraries(reproducible-runtime PRIVATE Threads::Threads)
 
+find_package(rocprofiler-sdk-roctx REQUIRED)
+target_link_libraries(reproducible-runtime
+                      PRIVATE rocprofiler-sdk-roctx::rocprofiler-sdk-roctx)
+
 if(REPRODUCIBLE_RUNTIME_USE_MPI)
     find_package(MPI REQUIRED)
     target_compile_definitions(reproducible-runtime PRIVATE USE_MPI)

tests/apps/reproducible-runtime/reproducible-runtime.cpp

@@ -21,6 +21,7 @@
 // THE SOFTWARE.
 
 #include "hip/hip_runtime.h"
+#include "rocprofiler-sdk-roctx/roctx.h"
 
 #include <unistd.h>
 #include <chrono>
@@ -124,6 +125,8 @@ reproducible_runtime(uint32_t nspin_v)
 void
 run(int tid, int devid)
 {
+    auto roctx_range_id = roctxRangeStart("run");
+
     constexpr int min_sa         = 8;
     constexpr int min_avail_simd = 24;
     dim3          grid(min_sa * min_avail_simd);
@@ -140,6 +143,7 @@ run(int tid, int devid)
 
     do
     {
+        roctxMark("iteration");
         uint32_t cyclesleft = 2000 * 1000 * (nruntime - static_cast<double>(time));
         HIP_API_CALL(hipEventRecord(start, stream));
         reproducible_runtime<<<grid, block, 0, stream>>>(std::min<uint32_t>(nspin, cyclesleft));
@@ -166,6 +170,8 @@ run(int tid, int devid)
 
     HIP_API_CALL(hipStreamSynchronize(stream));
     HIP_API_CALL(hipStreamDestroy(stream));
+
+    roctxRangeStop(roctx_range_id);
 }
 
 namespace

tests/apps/transpose/CMakeLists.txt

@@ -42,6 +42,9 @@ target_compile_options(transpose PRIVATE -W -Wall -Wextra -Wpedantic -Wshadow -W
 find_package(Threads REQUIRED)
 target_link_libraries(transpose PRIVATE Threads::Threads)
 
+find_package(rocprofiler-sdk-roctx REQUIRED)
+target_link_libraries(transpose PRIVATE rocprofiler-sdk-roctx::rocprofiler-sdk-roctx)
+
 if(TRANSPOSE_USE_MPI)
     find_package(MPI REQUIRED)
     target_compile_definitions(transpose PRIVATE USE_MPI)

tests/apps/transpose/transpose.cpp

@@ -21,6 +21,7 @@
 // THE SOFTWARE.
 
 #include "hip/hip_runtime.h"
+#include "rocprofiler-sdk-roctx/roctx.h"
 
 #include <chrono>
 #include <cstdio>
@@ -173,6 +174,8 @@ transpose(const int* in, int* out, int M, int N)
 void
 run(int rank, int tid, int devid, int argc, char** argv)
 {
+    roctxRangePush("run");
+
     constexpr unsigned int M = 4960 * 2;
     constexpr unsigned int N = 4960 * 2;
 
@@ -243,6 +246,8 @@ run(int rank, int tid, int devid, int argc, char** argv)
 
     delete[] inp_matrix;
     delete[] out_matrix;
+
+    roctxRangePop();
 }
 
 namespace