SWDEV-492623: Hip Host Function to Device Symbols Mapping (#18)
* Adding changes to register and read symbols from the hip fat binary * adding json output for host_functions * added error handling * adding json tool support * Adding tests * formatting changes * Adding documentation * refactoring as per amd-staging * Adding intializers and changing macros * Fix page-migration background thread on fork (#31) * Fix page-migration background thread on fork After falling off main in the forked child, all the children try to join on on the parent's monitoring thread. This results in a deadlock. Parent is waiting for the child to exit, but the child is trying to join the parent's thread which is signaled from the parent's static destructors. Even with just one parent and child, due to copy-on-write semantics, a child signalling the background thread to join will still block (thread's updated state is not visible in the child). This fix creates background treads on fork per-child with a pthread_atfork handler, ensuring that each child has its own monitoring thread. * Formatting fixes * Detach page-migration background thread and update test timeout * Attach files with ctest * Update corr-id assert * Tweak on-fork, simplify background thread * Revert thread detach * Adding --collection-period feature in rocprofv3 to match v1/v2 parity (#9) * Adding Trace Period feature to rocprofv3 * Adding feature documentation * Update source/bin/rocprofv3.py Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Fixing format * Moving to Collection Period and changing the input params * Format Fixes * Fixing rebasing issues * Removing atomic include from the tool * Adding more options for units, optimizing the code * Fixing rocprofv3.py * Fixing time conv & adding time controlled app * Fixing format * Changing to shared memory testing methodology * use of shmem use * Fix include headers for transpose-time-controlled.cpp * Format upload-image-to-github.py * Removing shmem and using only env var to dump timestamps from the tool * Tool Fixes + Test Config * Adding Tests * Fixing Review comments * Update trace period implementation * Update trace period tests * check between start and stop timestamps * Merge Fix * Update validate.py * Improve safety of rocprofiler_stop_context after finalization * Pass context id to collection_period_cntrl by value * Adding 20 us error margin * Ensure log level for collection-period test is not more than warning --------- Co-authored-by: Ammar ELWazir <aelwazir@amd.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com> * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - move error code check macros to implementation - fix macros which check error code - use constexpr values instead of #define * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - debugging for error that cannot be locally reproduced * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - improve error handling and logging * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - tweak to non-fatal logging messages * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - cleanup of logging messages * Update host kernel symbol register data fields * Update source/lib/rocprofiler-sdk/code_object/hip/code_object.hpp --------- Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com> Co-authored-by: Kuricheti, Mythreya <Mythreya.Kuricheti@amd.com> Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com> Co-authored-by: Ammar ELWazir <aelwazir@amd.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
This commit is contained in:
Jakaraddi, Manjunath
committed by
GitHub
GitHub
parent
61ce79c84d
commit
78d8f4b8ea
@@ -202,7 +202,10 @@ make_array(Tp&& arg, Args&&... args)
|
||||
using call_stack_t = std::vector<source_location>;
|
||||
|
||||
using kernel_symbol_data_t = rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t;
|
||||
using host_function_data_t =
|
||||
rocprofiler_callback_tracing_code_object_host_kernel_symbol_register_data_t;
|
||||
using kernel_symbol_map_t = std::unordered_map<rocprofiler_kernel_id_t, kernel_symbol_data_t>;
|
||||
using host_functions_map_t = std::unordered_map<uint64_t, host_function_data_t>;
|
||||
|
||||
rocprofiler_client_id_t* client_id = nullptr;
|
||||
rocprofiler_client_finalize_t client_fini_func = nullptr;
|
||||
@@ -294,6 +297,21 @@ struct kernel_symbol_callback_record_t
|
||||
}
|
||||
};
|
||||
|
||||
struct host_function_callback_record_t
|
||||
{
|
||||
uint64_t timestamp = 0;
|
||||
rocprofiler_callback_tracing_record_t record = {};
|
||||
rocprofiler_callback_tracing_code_object_host_kernel_symbol_register_data_t payload = {};
|
||||
|
||||
template <typename ArchiveT>
|
||||
void save(ArchiveT& ar) const
|
||||
{
|
||||
ar(cereal::make_nvp("timestamp", timestamp));
|
||||
cereal::save(ar, record);
|
||||
ar(cereal::make_nvp("payload", payload));
|
||||
}
|
||||
};
|
||||
|
||||
struct runtime_init_callback_record_t
|
||||
{
|
||||
uint64_t timestamp = 0;
|
||||
@@ -527,6 +545,7 @@ auto counter_info = std::deque<rocprofiler_counter_info_v0_t>{}
|
||||
auto runtime_init_cb_records = std::deque<runtime_init_callback_record_t>{};
|
||||
auto code_object_records = std::deque<code_object_callback_record_t>{};
|
||||
auto kernel_symbol_records = std::deque<kernel_symbol_callback_record_t>{};
|
||||
auto host_function_records = std::deque<host_function_callback_record_t>{};
|
||||
auto hsa_api_cb_records = std::deque<hsa_api_callback_record_t>{};
|
||||
auto marker_api_cb_records = std::deque<marker_api_callback_record_t>{};
|
||||
auto counter_collection_bf_records = std::deque<profile_counting_record>{};
|
||||
@@ -676,6 +695,13 @@ tool_tracing_callback(rocprofiler_callback_tracing_record_t record,
|
||||
auto _lk = std::unique_lock<std::mutex>{_mutex};
|
||||
kernel_symbol_records.emplace_back(kernel_symbol_callback_record_t{ts, record, data_v});
|
||||
}
|
||||
else if(record.operation == ROCPROFILER_CODE_OBJECT_HOST_KERNEL_SYMBOL_REGISTER)
|
||||
{
|
||||
auto data_v = *static_cast<host_function_data_t*>(record.payload);
|
||||
static auto _mutex = std::mutex{};
|
||||
auto _lk = std::unique_lock<std::mutex>{_mutex};
|
||||
host_function_records.emplace_back(host_function_callback_record_t{ts, record, data_v});
|
||||
}
|
||||
}
|
||||
else if(record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_CORE_API ||
|
||||
record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_AMD_EXT_API ||
|
||||
@@ -1652,6 +1678,7 @@ tool_fini(void* tool_data)
|
||||
<< ", runtime_init_callback_records=" << runtime_init_cb_records.size()
|
||||
<< ", code_object_callback_records=" << code_object_records.size()
|
||||
<< ", kernel_symbol_callback_records=" << kernel_symbol_records.size()
|
||||
<< ", host_function_callback_records=" << host_function_records.size()
|
||||
<< ", hsa_api_callback_records=" << hsa_api_cb_records.size()
|
||||
<< ", hip_api_callback_records=" << hip_api_cb_records.size()
|
||||
<< ", marker_api_callback_records=" << marker_api_cb_records.size()
|
||||
@@ -1760,6 +1787,7 @@ write_json(call_stack_t* _call_stack)
|
||||
json_ar(cereal::make_nvp("runtime_init", runtime_init_cb_records));
|
||||
json_ar(cereal::make_nvp("code_objects", code_object_records));
|
||||
json_ar(cereal::make_nvp("kernel_symbols", kernel_symbol_records));
|
||||
json_ar(cereal::make_nvp("host_functions", host_function_records));
|
||||
json_ar(cereal::make_nvp("hsa_api_traces", hsa_api_cb_records));
|
||||
json_ar(cereal::make_nvp("hip_api_traces", hip_api_cb_records));
|
||||
json_ar(cereal::make_nvp("marker_api_traces", marker_api_cb_records));
|
||||
|
||||
Reference in New Issue
Block a user