Shared Library Constructor (rocprofv3 deadlock fix) (#599)
* Moved tests/apps to tests/bin
* Renamed cmake project in tests/bin
* Update samples
- Use ROCPROFILER_DEFAULT_FAIL_REGEX
- tweaks to stdout messages
* Update tests
- Use ROCPROFILER_DEFAULT_FAIL_REGEX
* Add tests/lib
- libraries with HIP code
* Update PTL submodule
- remove atexit delete of thread_id_map
* Update cmake/rocprofiler_options.cmake
- Set ROCPROFILER_DEFAULT_FAIL_REGEX
* Update common lib: env + logging
- improved customization of logging settings
- default to disabling logging to files
- install failure handler for rocprofv3
- set_env support in environment.*
* Add lib/rocprofiler-sdk/shared_library.cpp
- shared library constructor
* Update lib/rocprofiler-sdk-tool/tool.cpp
- destructor thread safety
- convert callback_name_info and buffered_name_info to pointers
- install failure handler for logging
* Add tests/bin/hip-in-libraries
- hip-in-libraries is an exe which uses two shared libraries where each shared library contains HIP kernels
- used for testing deadlocking within __hipRegisterFatBinary
* Update bin/rocprofv3
- reorganized the env variables
- use exec to launch command
- set ROCPROFILER_LIBRARY_CTOR=1
* Add tests/rocprofv3/tracing-hip-in-libraries
- uses hip-in-libraries exe for exe which uses shared libraries to launch HIP kernels
* Update bin/rocprofv3
- fix counter collection (no exec)
* Update lib/rocprofiler-sdk-tool/tool.cpp
- replace "Kernel-Name" with "Kernel_Name"
* Update lib/rocprofiler-sdk/registration.cpp
Use RTLD_LOCAL instead of RTLD_GLOBAL for env libraries
* Update tests/rocprofv3
- replace "Kernel-Name" with "Kernel_Name"
* Update tests
- vector-ops (bin) stream syncs + runs with 4 queues per device
- improve counter-collection/input1 validation
- rocprofv3/tracing-hip-in-libraries does not do sys-trace
- improved validation script for tracing-hip-in-libraries
- updated dispatch_callback in json-tool.cpp following reworking of prototypes for counter collection
* Update samples/counter_collection
- updated dispatch_callback(s) and record_callback(s) following reworking of prototypes
* Update bin/rocprofv3
- reorganized help menu
- added options for sub-HSA tables
- added --hip-runtime-trace
- changed --hip-trace to include --hip-compiler-trace
* Update lib/rocprofiler-sdk-tool
- improved kernel filtering
- removed arch_vgpr, accum_vgpr, sgpr code (in rocprofiler-sdk)
- fixed issue with counter-collection w/o tracing
- added support for fine grained HSA API tracing
- removed directly linking to HSA-runtime
* Update lib/rocprofiler-sdk/agent.cpp
- rocp_agents != hsa_agents is non-fatal when ROCPROFILER_BUILD_CI=OFF (CMake option)
* GPR (vector and scalar) info in kernel symbol data
- rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t contains general purpose register info
* Header include order fix
- Include repo headers first
- Third party library headers next
- standard library headers last
* Update dispatch profiling public API
- introduce rocprofiler_profile_counting_dispatch_data_t
- change signature of rocprofiler_profile_counting_dispatch_callback_t and rocprofiler_profile_counting_record_callback_t
- provide rocprofiler_user_data_t pointer in dispatch callback
- provide rocprofiler_user_data_t value (from dispatch cb) in record callback
* Update tests/bin/CMakeLists.txt
- fix add_subdirectory(hip-in-libraries) order
* Update VERSION
- bump to 0.2.0 in prep for AFAR
[ROCm/rocprofiler-sdk commit: 7b6d3c70bd]
Tento commit je obsažen v:
Jonathan R. Madsen
GitHub
@@ -526,19 +526,16 @@ counter_collection_buffered(rocprofiler_context_id_t, /*context*/
|
||||
}
|
||||
|
||||
void
|
||||
dispatch_callback(rocprofiler_queue_id_t, /*queue_id*/
|
||||
const rocprofiler_agent_t* agent,
|
||||
rocprofiler_correlation_id_t, /*correlation_id*/
|
||||
const hsa_kernel_dispatch_packet_t*, /*dispatch_packet*/
|
||||
uint64_t, /*kernel_id*/
|
||||
void* /*callback_data_args*/,
|
||||
rocprofiler_profile_config_id_t* config)
|
||||
dispatch_callback(rocprofiler_profile_counting_dispatch_data_t dispatch_data,
|
||||
rocprofiler_profile_config_id_t* config,
|
||||
rocprofiler_user_data_t* /*user_data*/,
|
||||
void* /*callback_data_args*/)
|
||||
{
|
||||
static std::shared_mutex m_mutex = {};
|
||||
static std::unordered_map<uint64_t, rocprofiler_profile_config_id_t> profile_cache = {};
|
||||
|
||||
auto search_cache = [&]() {
|
||||
if(auto pos = profile_cache.find(agent->id.handle); pos != profile_cache.end())
|
||||
if(auto pos = profile_cache.find(dispatch_data.agent_id.handle); pos != profile_cache.end())
|
||||
{
|
||||
*config = pos->second;
|
||||
return true;
|
||||
@@ -565,7 +562,7 @@ dispatch_callback(rocprofiler_queue_id_t, /*queue_id*/
|
||||
|
||||
// Iterate through the agents and get the counters available on that agent
|
||||
ROCPROFILER_CALL(rocprofiler_iterate_agent_supported_counters(
|
||||
agent->id,
|
||||
dispatch_data.agent_id,
|
||||
[]([[maybe_unused]] rocprofiler_agent_id_t id,
|
||||
rocprofiler_counter_id_t* counters,
|
||||
size_t num_counters,
|
||||
@@ -600,11 +597,12 @@ dispatch_callback(rocprofiler_queue_id_t, /*queue_id*/
|
||||
|
||||
// Create a colleciton profile for the counters
|
||||
rocprofiler_profile_config_id_t profile;
|
||||
ROCPROFILER_CALL(rocprofiler_create_profile_config(
|
||||
agent->id, collect_counters.data(), collect_counters.size(), &profile),
|
||||
"Could not construct profile cfg");
|
||||
ROCPROFILER_CALL(
|
||||
rocprofiler_create_profile_config(
|
||||
dispatch_data.agent_id, collect_counters.data(), collect_counters.size(), &profile),
|
||||
"Could not construct profile cfg");
|
||||
|
||||
profile_cache.emplace(agent->id.handle, profile);
|
||||
profile_cache.emplace(dispatch_data.agent_id.handle, profile);
|
||||
// Return the profile to collect those counters for this dispatch
|
||||
*config = profile;
|
||||
}
|
||||
|
||||
Odkázat v novém úkolu
Zablokovat Uživatele