* CMakeLists/README/DOC - updates and fixes
* Fix few typos in the sample code in doc
* Add a sample code snippet for decoding a batch of jpeg images
[ROCm/rocjpeg commit: 7fafba6e70]
* Adding performance collection feature in rccl_replayer, and updating MSCCL logging and replayer parsing
* Performance collection feature in rccl_replayer, and updating MSCCL logging and replayer parsing
[ROCm/rccl commit: cf311b71ee]
* Adding performance collection feature in rccl_replayer, and updating MSCCL logging and replayer parsing
* Performance collection feature in rccl_replayer, and updating MSCCL logging and replayer parsing
* PCS: show chiplet; cover loading/unloading in integration test
* Use (code_object_id, pc_addr) pair as instruction id.
[ROCm/rocprofiler-sdk commit: 0f89f0449d]
Only check the lock if counter collection is being
attempted by the profiler. Not when it is loaded.
SWDEV-474455
Change-Id: Ie14de3c8db57e0cbd279ffca51c333a375ca8654
Signed-off-by: Benjamin Welton <bewelton@amd.com>
Only check the lock if counter collection is being
attempted by the profiler. Not when it is loaded.
SWDEV-474455
Change-Id: Ie14de3c8db57e0cbd279ffca51c333a375ca8654
Signed-off-by: Benjamin Welton <bewelton@amd.com>
[ROCm/rocprofiler commit: 0be3e07388]
Creation of ReferenceCountedObject will increase reference count by 1.
Clear the commands from Node after capture so that they wont be reference later.
Change-Id: I1cc4085939cf65218ec2aa2e25ab6d737f7cacd3
[ROCm/clr commit: 6ae5d6896c]
Creation of ReferenceCountedObject will increase reference count by 1.
Clear the commands from Node after capture so that they wont be reference later.
Change-Id: I1cc4085939cf65218ec2aa2e25ab6d737f7cacd3
Capture AQL packets during GraphInstantiation and enqueue AQL packets during graph launch.
Added support to capture single graph memset node.
Capture support for memset node is currently disabled.
Memset capture will be enabled when capture for multiple packets are supported..
Change-Id: I14dfbc41731025cc3a548a730558915def3fa384
[ROCm/clr commit: 346da4bb40]
Capture AQL packets during GraphInstantiation and enqueue AQL packets during graph launch.
Added support to capture single graph memset node.
Capture support for memset node is currently disabled.
Memset capture will be enabled when capture for multiple packets are supported..
Change-Id: I14dfbc41731025cc3a548a730558915def3fa384
Should have been checking environment variables for package name
overrides.
Disabled RPM Build's AUTOREQ and AUTOPROV
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-compute commit: 98e7d0cfb3]
Should have been checking environment variables for package name
overrides.
Disabled RPM Build's AUTOREQ and AUTOPROV
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
- Added film grain parameter saving and loading procedures.
- Added buffer management for film grain synthesis output.
- Fixed the corruption issue with 10-bit film grain streams. We need to see surface attibutes based on pixel format when creating VAAPI surfaces.
- Added missing global motion, loop filter and segmentation parameter loading in load reference frame procedure.
- Fixed an issue with one tile streams.
- Fixed an issue with un-initialized frame header structure after frame decode.
- Fixed a bug with decode buffer status update.
[ROCm/rocdecode commit: ac82d17e9f]
- Added film grain parameter saving and loading procedures.
- Added buffer management for film grain synthesis output.
- Fixed the corruption issue with 10-bit film grain streams. We need to see surface attibutes based on pixel format when creating VAAPI surfaces.
- Added missing global motion, loop filter and segmentation parameter loading in load reference frame procedure.
- Fixed an issue with one tile streams.
- Fixed an issue with un-initialized frame header structure after frame decode.
- Fixed a bug with decode buffer status update.
* Update the MemoryPool by defining the max pool size, and use it when adding a new entry to the pool
* Fix finding the gfx942_mi300x
[ROCm/rocjpeg commit: 6d7d72c6da]
- HIP path doesn't support resource tracking. Thus, double copy can't be enabled,
because it requires resource tracking.
Change-Id: I0f9c4e185b5b2d2b1abde041fca21bb099db9ccd
[ROCm/clr commit: 4c763e45a1]
- HIP path doesn't support resource tracking. Thus, double copy can't be enabled,
because it requires resource tracking.
Change-Id: I0f9c4e185b5b2d2b1abde041fca21bb099db9ccd
* adding rocprof parser script
* adding the support for multiple json files
* adding pytorch profiler script
* remove filtering from pytorch log
* adding the addressing the comments and add the feature to parse all kernels
* completing the report for torch profiler
---------
Co-authored-by: Marzieh Berenjkoub <mberenjk@amd.com>
[ROCm/rccl commit: 519843d2cf]
* adding rocprof parser script
* adding the support for multiple json files
* adding pytorch profiler script
* remove filtering from pytorch log
* adding the addressing the comments and add the feature to parse all kernels
* completing the report for torch profiler
---------
Co-authored-by: Marzieh Berenjkoub <mberenjk@amd.com>
Aryan Salmanpour
Manas Yendluri
saurabhAMD
Rajy Rawther
Vladimir Indic
Benjamin Welton
corey-derochie-amd
Anusha GodavarthySurya
Giovanni LB
Chris Freehill
David Galiffi
jeffqjiangNew
Maisam Arif
Galantsev, Dmitrii
German Andryeyev
Charis Poag
mberenjk
Nusrat Islam