Update run-ci.py (#641)

* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

* Update run-ci.py

* Update run-ci.py

* Update continuous_integration.yml

* Update continuous_integration.yml

running directly using the prepared runner container

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update run-ci.py

* Clean up

* Fixing install paths

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing GPU Agents Test Validation

* python formatting (black) (#712)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* python formatting (black) (#713)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* Fixing static number of async copies and using hsa_api instead for validation

* python formatting (black) (#714)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Increasing the time limit for waiting on active signals

* Update continuous_integration.yml

* Update async_copy.cpp

* Update CMakeLists.txt

* changing node id to logical node id in rocprofv3

* Update tool.cpp

* testing async mem copy signal decrement

* Update logging.cpp

* Update validate.py

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 2905fb5e95]
This commit is contained in:
Ammar ELWazir
2024-04-02 01:39:24 -05:00
committed by GitHub
parent c1c514f743
commit 521e2794e6
10 changed files with 144 additions and 93 deletions
@@ -660,10 +660,12 @@ buffered_tracing_callback(rocprofiler_context_id_t /*context*/,
record);
auto kernel_trace_ss = std::stringstream{};
// TODO(aelwazir): To be changed back to use node id once ROCR fixes
// the hsa_agents to use the real node id
tool::csv::kernel_trace_csv_encoder::write_row(
kernel_trace_ss,
CHECK_NOTNULL(buffered_name_info)->kind_names.at(record->kind),
agent_info->at(record->agent_id)->node_id,
agent_info->at(record->agent_id)->logical_node_id,
record->queue_id.handle,
record->kernel_id,
std::move(kernel_name),
@@ -710,14 +712,16 @@ buffered_tracing_callback(rocprofiler_context_id_t /*context*/,
static_cast<rocprofiler_buffer_tracing_memory_copy_record_t*>(header->payload);
auto memory_copy_trace_ss = std::stringstream{};
// TODO(aelwazir): To be changed back to use node id once ROCR fixes
// the hsa_agents to use the real node id
tool::csv::memory_copy_csv_encoder::write_row(
memory_copy_trace_ss,
CHECK_NOTNULL(buffered_name_info)->kind_names.at(record->kind),
CHECK_NOTNULL(buffered_name_info)
->operation_names.at(record->kind)
.at(record->operation),
agent_info->at(record->src_agent_id)->node_id,
agent_info->at(record->dst_agent_id)->node_id,
agent_info->at(record->src_agent_id)->logical_node_id,
agent_info->at(record->dst_agent_id)->logical_node_id,
record->correlation_id.internal,
record->start_timestamp,
record->end_timestamp);
@@ -930,10 +934,12 @@ counter_record_callback(rocprofiler_profile_counting_dispatch_data_t dispatch_da
using csv_encoder = tool::csv::counter_collection_csv_encoder;
auto counter_collection_ss = std::stringstream{};
// TODO(aelwazir): To be changed back to use node id once ROCR fixes
// the hsa_agents to use the real node id
csv_encoder::write_row(counter_collection_ss,
correlation_id.internal,
cnt_dispatch_data_v->dispatch_index,
agent_info->at(dispatch_data.agent_id)->node_id,
agent_info->at(dispatch_data.agent_id)->logical_node_id,
dispatch_data.queue_id.handle,
getpid(),
cnt_dispatch_data_v->thread_id,
@@ -963,7 +969,9 @@ list_metrics_iterate_agents(rocprofiler_agent_version_t,
{
const auto* agent = static_cast<const rocprofiler_agent_v0_t*>(agents[idx]);
auto counters_v = counter_vec_t{};
uint32_t node_id = agent->node_id;
// TODO(aelwazir): To be changed back to use node id once ROCR fixes
// the hsa_agents to use the real node id
uint32_t node_id = agent->logical_node_id;
ROCPROFILER_CALL(
rocprofiler_iterate_agent_supported_counters(
agent->id,