HIP Streams to Queues Translation (#235)
* rocprofiler_stream_id_t: opaque handle for a stream
- e.g. HIP stream
- the same HIP stream may map to different HSA queues at different points in the application
- added to:
- rocprofiler_buffer_tracing_hip_api_record_t
- rocprofiler_buffer_tracing_memory_copy_record_t
- rocprofiler_callback_tracing_hip_api_data_t
- rocprofiler_callback_tracing_memory_copy_data_t
---------
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Mark Meserve <mark.meserve@amd.com>
Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com>
Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
Co-authored-by: Jakaraddi, Manjunath <Manjunath.Jakaraddi@amd.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
Co-authored-by: Nagaraj, Sriraksha <Sriraksha.Nagaraj@amd.com>
Co-authored-by: U, Srihari <Srihari.U@amd.com>
Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
Co-authored-by: Welton, Benjamin <Benjamin.Welton@amd.com>
Co-authored-by: Benjamin Welton <ben@amd.com>
Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>
[ROCm/rocprofiler-sdk commit: ccd1e54293]
Tento commit je obsažen v:
@@ -63,8 +63,8 @@ get_stats(const stats_map_t& data_v)
|
||||
|
||||
stats_entry_t
|
||||
generate_stats(const output_config& /*cfg*/,
|
||||
const metadata& tool_metadata,
|
||||
const generator<rocprofiler_buffer_tracing_kernel_dispatch_record_t>& data)
|
||||
const metadata& tool_metadata,
|
||||
const generator<tool_buffer_tracing_kernel_dispatch_with_stream_record_t>& data)
|
||||
{
|
||||
auto kernel_stats = stats_map_t{};
|
||||
for(auto ditr : data)
|
||||
@@ -72,7 +72,7 @@ generate_stats(const output_config& /*cfg*/,
|
||||
for(auto record : data.get(ditr))
|
||||
{
|
||||
auto kernel_name = tool_metadata.get_kernel_name(record.dispatch_info.kernel_id,
|
||||
record.correlation_id.external.value);
|
||||
record.kernel_rename_val);
|
||||
|
||||
kernel_stats[kernel_name] += (record.end_timestamp - record.start_timestamp);
|
||||
}
|
||||
@@ -119,8 +119,8 @@ generate_stats(const output_config& /*cfg*/,
|
||||
|
||||
stats_entry_t
|
||||
generate_stats(const output_config& /*cfg*/,
|
||||
const metadata& tool_metadata,
|
||||
const generator<rocprofiler_buffer_tracing_memory_copy_record_t>& data)
|
||||
const metadata& tool_metadata,
|
||||
const generator<tool_buffer_tracing_memory_copy_with_stream_record_t>& data)
|
||||
{
|
||||
auto memory_copy_stats = stats_map_t{};
|
||||
for(auto ditr : data)
|
||||
|
||||
Odkázat v novém úkolu
Zablokovat Uživatele