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]
This commit is contained in:
Trowbridge, Ian
GitHub
@@ -1,9 +1,9 @@
|
||||
"Kind","Agent_Id","Queue_Id","Thread_Id","Dispatch_Id","Kernel_Id","Kernel_Name","Correlation_Id","Start_Timestamp","End_Timestamp","Private_Segment_Size","Group_Segment_Size","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH",1,1,69,1,16,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1451,8819330200067564,8819330200116308,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,2,69,5,16,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1484,8819330200118678,8819330200219573,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,1,69,2,19,"subtract_kernel(float*, float const*, float const*, int, int)",1459,8819330200120456,8819330200223721,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,3,69,9,16,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1517,8819330200152902,8819330200283428,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,4,69,13,16,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1550,8819330200187127,8819330200320468,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,2,69,6,19,"subtract_kernel(float*, float const*, float const*, int, int)",1492,8819330200225499,8819330200364618,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",1,1,69,3,18,"multiply_kernel(float*, float const*, float const*, int, int)",1467,8819330200229796,8819330200369359,0,0,64,1,1,1024,1024,1
|
||||
|
||||
"Kind","Agent_Id","Queue_Id","Stream_Id","Thread_Id","Dispatch_Id","Kernel_Id","Kernel_Name","Correlation_Id","Start_Timestamp","End_Timestamp","Private_Segment_Size","Group_Segment_Size","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH",2,1,1,21228,1,11,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1937,2414192765353337,2414192765369494,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,2,14,"subtract_kernel(float*, float const*, float const*, int, int)",1945,2414192765424862,2414192765435326,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,3,13,"multiply_kernel(float*, float const*, float const*, int, int)",1953,2414192765487486,2414192765497669,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,4,12,"divide_kernel(float*, float const*, float const*, int, int)",1961,2414192765545619,2414192765555722,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,5,11,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1969,2414192765608844,2414192765621674,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,6,14,"subtract_kernel(float*, float const*, float const*, int, int)",1977,2414192765658519,2414192765669424,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,7,13,"multiply_kernel(float*, float const*, float const*, int, int)",1985,2414192765715650,2414192765726795,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,8,12,"divide_kernel(float*, float const*, float const*, int, int)",1993,2414192765773422,2414192765784969,0,0,64,1,1,1024,1024,1
|
||||
|
||||
|
@@ -1,3 +1,5 @@
|
||||
"Kind","Direction","Source_Agent_Id","Destination_Agent_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",0,1,0,14955949675563,14955950239443
|
||||
"MEMORY_COPY","MEMORY_COPY_DEVICE_TO_HOST",1,0,0,14955952733485,14955953315285
|
||||
"Kind","Direction","Stream_Id","Source_Agent_Id","Destination_Agent_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",1,0,2,952,2414192684609085,2414192684710679
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",1,0,2,960,2414192684873841,2414192684973470
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",2,0,2,1066,2414192706436949,2414192706538622
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",2,0,2,1074,2414192706592442,2414192706692312
|
||||
|
||||
|
@@ -354,7 +354,7 @@ Here are the contents of ``kernel_trace.csv`` file:
|
||||
|
||||
.. csv-table:: Kernel trace
|
||||
:file: /data/kernel_trace.csv
|
||||
:widths: 10,10,10,10,10,10,10,10,20,20,10,10,10,10,10,10,10,10
|
||||
:widths: 10,10,10,10,10,10,10,10,10,20,20,10,10,10,10,10,10,10,10
|
||||
:header-rows: 1
|
||||
|
||||
For the description of the fields in the output file, see :ref:`output-file-fields`.
|
||||
@@ -378,7 +378,7 @@ Here are the contents of ``memory_copy_trace.csv`` file:
|
||||
|
||||
.. csv-table:: Memory copy trace
|
||||
:file: /data/memory_copy_trace.csv
|
||||
:widths: 10,10,10,10,10,20,20
|
||||
:widths: 10,10,10,10,10,10,20,20
|
||||
:header-rows: 1
|
||||
|
||||
For the description of the fields in the output file, see :ref:`output-file-fields`.
|
||||
@@ -1086,6 +1086,9 @@ The following table lists the various fields or the columns in the output CSV fi
|
||||
* - Queue_Id
|
||||
- ROCm queue unique identifier to which the kernel was submitted.
|
||||
|
||||
* - Stream_Id
|
||||
- Identifies HIP stream ID to which kernel or memory copy operation was submitted. Defaults to 0 if the hip-stream-display option is not enabled
|
||||
|
||||
* - Private_Segment_Size
|
||||
- The amount of memory required in bytes for the combined private, spill, and arg segments for a work item.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user