Handle hsa_queue_destroy after finalization (#679)
* Handle hsa_queue_destroy after finalization
- fixes issue where hsa_queue_destroy(...) is invoked after rocprofiler-sdk has finalized
- hsa::get_queue_controller() returns pointer
- if queue controller is a null pointer, skip invoking QueueController::destroy_queue
* Update HIP/HSA/marker update_table logging
* Update rocprofv3 tests
- remove HSA_TOOLS_LIB env variable
- remove setting ROCPROFILER_LOG_LEVEL env variable
- add timeouts to tests which are missing them
* Disable thread sanitizer deadlock detection
* Update CI workflow
- rename vega20-ubuntu job to core-ci
- enable navi32 in core-ci and sanitizers
* Update run-ci.py
- set gcovr html medium and high threshold
* Update lib/rocprofiler-sdk/hsa/queue_controller.cpp
- remove this capture from enable/disable serialization
* Update lib/rocprofiler-sdk/hsa/{hsa_barrier,profile_serializer}.*
- hsa_barrier::set_barrier accepts const-ref to queue map
- profile_serializer::enable and profile_serializer::disable accept const-ref to queue map
* Logging for HIP/HSA/marker/profile_serializer
* Logging for HIP/HSA/marker/queue_controller
* Improve test_retired_correlation_ids asserts
* Fix tests/counter-collection/validate.py
- scale expected SQ_WAVES counter value based on warp size of GPU
* Tweak github comment for code coverage
* Remove gcovr html high/medium threshold args
* Fix tests/counter-collection/validate.py
- round before casting to int in test_counter_values
* operator bool for profile_serializer
- only wait on CV if profile_serializer is used
* Logging updates (profile_serializer + code_object)
* Update counter-collection validate.py
* QueueController does not wait on CV if finalizing/finalized
* Update CI workflow
- remove navi32 from core job
* Improve HIP/HSA/marker tracing get_functor/functor
- remove lambda wrapper around functor
* Update lib/rocprofiler-sdk/hsa/queue_controller.cpp
- do not acquire cvmutex lock during finalization
* Update lib/rocprofiler-sdk/hsa/hsa_barrier.*
- move ctor and dtor to implementation
- skip signal store screlease and destroy if already finalized
* Update CI workflow
- remove navi32 runners
* bwelton fixes for hangs
* CMake improvements + simplified demangle
- remove amd-comgr from common target (and thus removed from roctx DT_NEEDED)
---------
Co-authored-by: Benjamin Welton <bewelton@amd.com>
This commit is contained in:
committed by
GitHub
parent
78939e705a
commit
2f9b1767e9
@@ -170,11 +170,12 @@ CoreApiTable&
|
||||
get_api_table()
|
||||
{
|
||||
static auto _v = []() {
|
||||
auto val = CoreApiTable{};
|
||||
val.hsa_iterate_agents_fn = hsa_iterate_agents;
|
||||
val.hsa_agent_get_info_fn = hsa_agent_get_info;
|
||||
val.hsa_queue_create_fn = hsa_queue_create;
|
||||
val.hsa_queue_destroy_fn = hsa_queue_destroy;
|
||||
auto val = CoreApiTable{};
|
||||
val.hsa_iterate_agents_fn = hsa_iterate_agents;
|
||||
val.hsa_agent_get_info_fn = hsa_agent_get_info;
|
||||
val.hsa_queue_create_fn = hsa_queue_create;
|
||||
val.hsa_queue_destroy_fn = hsa_queue_destroy;
|
||||
val.hsa_signal_wait_relaxed_fn = hsa_signal_wait_relaxed;
|
||||
return val;
|
||||
}();
|
||||
return _v;
|
||||
@@ -211,7 +212,8 @@ test_init()
|
||||
table.amd_ext_ = &get_ext_table();
|
||||
table.core_ = &get_api_table();
|
||||
agent::construct_agent_cache(&table);
|
||||
hsa::get_queue_controller().init(get_api_table(), get_ext_table());
|
||||
ASSERT_TRUE(hsa::get_queue_controller() != nullptr);
|
||||
hsa::get_queue_controller()->init(get_api_table(), get_ext_table());
|
||||
}
|
||||
|
||||
} // namespace
|
||||
@@ -221,7 +223,7 @@ TEST(dimension, block_dim_test)
|
||||
ASSERT_EQ(hsa_init(), HSA_STATUS_SUCCESS);
|
||||
test_init();
|
||||
|
||||
auto agents = hsa::get_queue_controller().get_supported_agents();
|
||||
auto agents = hsa::get_queue_controller()->get_supported_agents();
|
||||
ASSERT_GT(agents.size(), 0);
|
||||
for(const auto& [_, agent] : agents)
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user