Files
rocm-systems/projects/rocprofiler-sdk/samples/counter_collection/client.cpp
T
Jonathan R. Madsen 6108ea7efd Code object, kernel dispatch, and memory copy tracing (#177)
* Update samples/api_buffered_tracing

- external correlation id
- support ROCPROFILER_BUFFER_TRACING_KERNEL_DISPATCH

* Update lib/rocprofiler/context.cpp

- update alternative get_active_contexts paradigm

* Update lib/rocprofiler/external_correlation.cpp

- inherit correlation id from main thread

* Update lib/rocprofiler/hsa/queue.*

- typedef changes
- rocprofiler_packet union
- modify Queue::queue_info_session_t
  - use rocprofiler_packet
  - add thread id
  - add kernel id
  - add correlation id
- out of line definitions
- AsyncSignalHandler function update
  - handle kernel dispatch tracing
- Move CreateBarrierPacket and AddVendorSpecificPacket to lambdas
- handle contexts

* Update lib/rocprofiler/hsa/hsa.cpp

- remove unnecessary log function
- use new get_active_contexts paradigm
- use new correlation id updates

* Update AgentCache and kernel dispatch record

- include const rocprofiler_agent_t* in rocprofiler_buffer_tracing_kernel_dispatch_record_t
- AgentCache::get_rocp_agent returns const pointer

* Replace ROCPROFILER_SERVICE_ with ROCPROFILER_

* source formatting

* Code Object Tracing

- include/rocprofiler/callback_tracing.h
  - remove rocprofiler_callback_tracing_code_object_unload_data_t
  - remove rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t
- include/rocprofiler/fwd.h
  - remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_UNLOAD
  - remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_DEVICE_KERNEL_SYMBOL_UNREGISTER
- lib/common/utility.hpp
  - assert_public_api_struct_properties()
  - init_public_api_struct(...)
- lib/rocprofiler/registration.cpp
  - invoke hsa::code_object_init
- lib/rocprofiler/hsa/CMakeLists.txt
  - compile code_object code
- lib/rocprofiler/hsa/code_object.{hpp,cpp}
  - tracing code object load/unload
- lib/rocprofiler/hsa/queue.cpp
  - get_kernel_id

* Update lib/rocprofiler/hsa/hsa.cpp

- fix should_wrap_functor logic (which was not handling callback_tracer + buffered_tracer properly)

* Update lib/rocprofiler/hsa/queue.cpp

- fix rocprofiler_buffer_tracing_kernel_dispatch_record_t construction

* Update samples/api_buffered_tracing/client.cpp

- print kernel names

* Move samples/apps to tests/apps

* Update lib/rocprofiler/hsa/code_object.cpp

- ensure unload callbacks when application is exiting
- support user data in between load/unload callbacks

* Update lib/rocprofiler/hsa/queue.{hpp,cpp}

- store contexts and external correlation ids in queue_info_session
- reduce signal_limiter to 96 to fix hangs
- fix support for kernel tracing and async memory copies

* Add lib/common/scope_destructor.hpp

- similar to static_cleanup_wrapper but different

* Update include/rocprofiler/buffer_tracing.h

- update rocprofiler_buffer_tracing_memory_copy_record_t
- remove operation: user can figure that out from correlation id
- add kernel id
- add rocprofiler agent id

* Update include/rocprofiler/callback_tracing.h

- fix data type of load_delta field in code object
- remove rocp_agent from kernel_symbol_register_data_t (known via code_object_id)

* Add samples/code_object_tracing

- sample demonstrating code object tracing

* Update samples

- minor tweak to print_call_stack

* Update lib/rocprofiler/hsa/code_object.cpp

- flip ordering of unload callbacks for code object unloading and kernel symbol deregistering

* clang-tidy fixes

* Update lib/rocprofiler/hsa/code_object.cpp

- fix heap-use-after-free issue with code object

* Update include/rocprofiler/external_correlation.h

- update documentation to include info about default value of external correlation value

* Use common::container::small_vector for contexts

- small_vector<const context*> is an ideal data structure for array of active contexts

* Update context handling for code object unload

- code object unload is only called for contexts which received the load callback

* Update samples

- improve ROCPROFILER_CALL macro to include status string
- api_buffered_tracing handles ROCPROFILER_STATUS_ERROR_BUFFER_BUSY

* Code object shutdown

- ensure code object callbacks are invoked prior to finalizing

* Update lib/common (memory allocators)

- added lib/common/memory folder with allocators

* Add lib/rocprofiler/allocator.*

- rocprofiler::allocator::static_data_allocator
  - special allocator for static data which finalizes before any data gets destroyed
- rocprofiler::allocator::unique_static_ptr_t
  - unique_ptr that uses static data deleter (ensure finalize is called)

* Update lib/rocprofiler/buffer.cpp

- flush checks fini status
- use unique_static_ptr_t

* Update lib/rocprofiler/internal_threading.*

- change meaning of thread_pool_t and task_group_t
- improve finalization to prevent data races and heap-use-after-free

* Update lib/rocprofiler/registration.cpp

- use static_data_allocator for client_library vector

* Update lib/rocprofiler/context/context.*

- use allocator::unique_static_ptr_t

* Update lib/rocprofiler/allocator.cpp

- avoid deadlock in deleter<static_data>::operator()

* Update lib/rocprofiler/registration.cpp

- avoid deadlock in rocprofiler::registration::finalize()

* Update lib/rocprofiler/hsa/code_object.cpp

- suppress duplicate reporting of code-object/kernel-symbol load/unload

* Update leak sanitizer suppressions

- __new_exitfn (via stdlib/cxa_atexit.c leaks

[ROCm/rocprofiler-sdk commit: 3082288a25]
2023-11-13 22:30:15 -06:00

182 lines
6.9 KiB
C++

#include "client.hpp"
#include <set>
#include <sstream> // std::stringstream
#include <vector>
#include <rocprofiler/registration.h>
#include <rocprofiler/rocprofiler.h>
#define ROCPROFILER_CALL(result, msg) \
{ \
rocprofiler_status_t CHECKSTATUS = result; \
if(CHECKSTATUS != ROCPROFILER_STATUS_SUCCESS) \
{ \
std::string status_msg = rocprofiler_get_status_string(CHECKSTATUS); \
std::cerr << "[" #result "][" << __FILE__ << ":" << __LINE__ << "] " << msg \
<< " failed with error code " << CHECKSTATUS << ": " << status_msg \
<< std::endl; \
std::stringstream errmsg{}; \
errmsg << "[" #result "][" << __FILE__ << ":" << __LINE__ << "] " << msg " failure (" \
<< status_msg << ")"; \
throw std::runtime_error(errmsg.str()); \
} \
}
int
start()
{
return 1;
}
namespace
{
rocprofiler_context_id_t&
get_client_ctx()
{
static rocprofiler_context_id_t ctx;
return ctx;
}
void
test_callback(rocprofiler_queue_id_t queue_id,
rocprofiler_agent_t agent_id,
rocprofiler_correlation_id_t corr_id,
const hsa_kernel_dispatch_packet_t*,
void*,
rocprofiler_record_counter_t* out_counters,
size_t out_size,
rocprofiler_profile_config_id_t)
{
static int enter_count = 0;
enter_count++;
// Limit output to avoid massive log size
if(enter_count % 100 != 0) return;
std::stringstream ss;
for(size_t i = 0; i < out_size; i++)
{
ss << "(Id: " << out_counters[i].id << " Value [D]: " << out_counters[i].derived_counter
<< ", Value [I]: " << out_counters[i].hw_counter << "),";
}
// Callback containing counter data.
std::clog << "[" << __FUNCTION__ << "] " << queue_id.handle << " | " << agent_id.id.handle
<< " | " << corr_id.internal << "|" << ss.str() << "\n";
}
int
tool_init(rocprofiler_client_finalize_t, void*)
{
std::set<std::string> counters_to_collect = {"SQ_WAVES"};
std::vector<rocprofiler_agent_t> gpu_agents;
auto agent_query = [](const rocprofiler_agent_t** agents, size_t num_agents, void* user_data) {
std::vector<rocprofiler_agent_t>* vec =
static_cast<std::vector<rocprofiler_agent_t>*>(user_data);
for(size_t i = 0; i < num_agents; i++)
{
const rocprofiler_agent_t* agent = agents[i];
if(agent->type == ROCPROFILER_AGENT_TYPE_GPU)
{
vec->push_back(*agent);
}
}
return ROCPROFILER_STATUS_SUCCESS;
};
ROCPROFILER_CALL(rocprofiler_query_available_agents(
agent_query, sizeof(rocprofiler_agent_t), static_cast<void*>(&gpu_agents)),
"Could not query agents");
ROCPROFILER_CALL(rocprofiler_create_context(&get_client_ctx()), "context creation failed");
std::vector<rocprofiler_profile_config_id_t> profile_configs;
for(auto& agent : gpu_agents)
{
std::vector<rocprofiler_counter_id_t> collect_counters;
std::vector<rocprofiler_counter_id_t> gpu_counters;
std::clog << agent.name << "\n";
ROCPROFILER_CALL(
rocprofiler_iterate_agent_supported_counters(
agent,
[](rocprofiler_counter_id_t* counters, size_t num_counters, void* user_data) {
std::vector<rocprofiler_counter_id_t>* vec =
static_cast<std::vector<rocprofiler_counter_id_t>*>(user_data);
for(size_t i = 0; i < num_counters; i++)
{
vec->push_back(counters[i]);
}
return ROCPROFILER_STATUS_SUCCESS;
},
static_cast<void*>(&gpu_counters)),
"Could not fetch supported counters");
for(auto& counter : gpu_counters)
{
const char* name;
size_t size;
ROCPROFILER_CALL(rocprofiler_query_counter_name(counter, &name, &size),
"Could not query name");
if(counters_to_collect.count(std::string(name)) > 0)
{
std::clog << "Counter: " << counter.handle << " " << name << "\n";
collect_counters.push_back(counter);
}
}
rocprofiler_profile_config_id_t profile;
ROCPROFILER_CALL(rocprofiler_create_profile_config(
agent, collect_counters.data(), collect_counters.size(), &profile),
"Could not construct profile cfg");
ROCPROFILER_CALL(rocprofiler_configure_dispatch_profile_counting_service(
get_client_ctx(), profile, test_callback, nullptr),
"Could not setup dispatch service");
profile_configs.push_back(profile);
}
rocprofiler_start_context(get_client_ctx());
// no errors
return 0;
}
void
tool_fini(void*)
{
rocprofiler_stop_context(get_client_ctx());
std::clog << "In tool fini\n";
}
} // namespace
extern "C" rocprofiler_tool_configure_result_t*
rocprofiler_configure(uint32_t version,
const char* runtime_version,
uint32_t,
rocprofiler_client_id_t* id)
{
// set the client name
id->name = "CounterClientSample";
// compute major/minor/patch version info
uint32_t major = version / 10000;
uint32_t minor = (version % 10000) / 100;
uint32_t patch = version % 100;
// generate info string
auto info = std::stringstream{};
info << id->name << " is using rocprofiler v" << major << "." << minor << "." << patch << " ("
<< runtime_version << ")";
std::clog << info.str() << std::endl;
// create configure data
static auto cfg =
rocprofiler_tool_configure_result_t{sizeof(rocprofiler_tool_configure_result_t),
&tool_init,
&tool_fini,
static_cast<void*>(nullptr)};
// return pointer to configure data
return &cfg;
}