* rocDecode API Tracing support
* Test bin file added to rocdecode. Need to add validate python methods
* Added option to not make rocDecode tests
* Added rocdecode and rocprofv3 tests
* Added csv test
* Address PR comments. Changed tests to use built-in rocstreambit decoder to remove ffmpeg dependancy. Changed cmake option to disbale tests rather than not build them. Tests work locally, but will fail until rocDecode is built with tracing enabled on CI
* Add option to avoid building rocdecode tests
* Added option to avoid building rocdecode bin file
* Support for rocJPEG API Trace
* Added newline to rocjpeg_version.h
* json-tool code added, initial test/bin commit
* Formatting
* Resolved rocjpeg bin test compilation errors
* Tests implemented. Perfetto module currently resulting in errors, so need to retest whenever it is fixed
* Formatting and compilation errors
* Minor fixes
* Copyright year update and minor fixes
* Doc update fix
* Added rocjpeg csv file in data
* Addresses review comments: Updated fixed Findroc.. and uses root directory as a hint, fixed documentation error, changed tables to use _CORE, minor style fixes
* Added rocdecode and rocjpeg to CI
* Removed rocdecode and rocjpeg from CI and added back build tests option
* Updated Cmake Files
* Added rocDecode and rocJPEG to CI
* Remove cmake line added in error
* Temporarily modified tests to pass if rocdecode or rocjpeg tracing are not supported for CI, cmake changes
* Added find_package for test
* Added back use of system rocDecode and rocJPEG, modifies system files to include prefix path
* Updated no-link to include INCLUDE_DIR/roc(decode|jpeg), added comments for tests
* Resolve merge conflicts and formatting
* Added regex find and replace instead of include for CI
* VAAPI package causing errors on Vega20
* Removed system rocjpeg and rocdecode use temporarily until cmake issues resolved
* Removed workflows regex
* Formatting and minor test modification
* Modified test for vega20
* Update rocDecode and rocJPEG cmake and tests
* Changelog
* Fix merge conflict
* Added back if-statements around add-tests since cmake-generator-expressions are resulting in errors when the packages are missing
* Removed if found statements, replaced with TARGET:EXISTS
* Skip json file for rocjpeg and rocdecode tests if not supported
* Add os import
---------
Co-authored-by: Kandula, Venkateshwar reddy <Venkateshwarreddy.Kandula@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
This change removes the stream callback from hipStreamWaitEvent and
uses a stream memory wait operation instead. This allows the
hipStreamWaitEvent to be non-blocking on the host.
Change-Id: Ie5530febda5a5bcb5daa0db8a01249d6b137fd43
- Add JPEG activity track in perfetto trace
- Add JPEG decode tests to the examples
- Change existing videodecode test to include JPEG testing
- Rename videodecode test file to decode to include jpeg tests too
- Fix a bug in the test which checks for total activity of 0
- Disable rocDecode and rocJPEG samples from the github image files
[ROCm/rocprofiler-systems commit: 59d3399901]
- Add JPEG activity track in perfetto trace
- Add JPEG decode tests to the examples
- Change existing videodecode test to include JPEG testing
- Rename videodecode test file to decode to include jpeg tests too
- Fix a bug in the test which checks for total activity of 0
- Disable rocDecode and rocJPEG samples from the github image files
Use the core Driver object in the CPU agent to make it OS/driver
agnostic.
Implement the GetMemoryProperties() and GetCacheProperties methods
for the KFD driver.
* Add cmake function to create standalone binary
* Mention licenses used by dependencies in the LICENSE file
* Add test cases for standalone binary by adding --call-binary option for pytest
* Docker compose file to create standalone binary in standardized RHEL 8 environment
* Add README instructions on how to create and test standalone binary
* Move docker files from utils to docker folder; Add standalone binary testing instructions
* Add CHANGELOG statement
* Use different service names in docker compose files
* Use volume mounting in docker files
[ROCm/rocprofiler-compute commit: 40f79c28b1]
* Add cmake function to create standalone binary
* Mention licenses used by dependencies in the LICENSE file
* Add test cases for standalone binary by adding --call-binary option for pytest
* Docker compose file to create standalone binary in standardized RHEL 8 environment
* Add README instructions on how to create and test standalone binary
* Move docker files from utils to docker folder; Add standalone binary testing instructions
* Add CHANGELOG statement
* Use different service names in docker compose files
* Use volume mounting in docker files
1) Map RTC linker API enums to Runtime Linker API enums
2) Add API declarations for Runtime linker APIs
Change-Id: Id5da355a77365f97868e462847f3906e87fd2af7
Add initial implementation of virtual memory heap with
dynamic virtual memory mapping support for memory pools.
DEBUG_HIP_MEM_POOL_VMHEAP controls the new method.
Change-Id: I8dc5be2e0f34ab472f1800f43bb6243639a5e500
Compute doesn't support IB chaining, but RGP may collect
perf counters, which require more space in CB.
Increase CB size if RGP is enabled.
Change-Id: Iaa0a620ead8541a679b0dfe5e5711af5afdba545
Add support for these 2 new queries:
- HSA_AMD_AGENT_INFO_SCRATCH_LIMIT_MAX
Maximum amount of scratch memory allowed on this agent
- HSA_AMD_AGENT_INFO_SCRATCH_LIMIT_CURRENT
Current limit for scratch memory on this agent
Updating ROCr code to match new handshake protocol with CP FW for
asynchronous scratch reclaim.
Increase previous limits when scratch reclaim feature is available.
* Fix a couple typos. Add note about limitations with AI / ML workloads.
* Updated note based on feedback.
[ROCm/rocprofiler-systems commit: b1d0c431c7]
Add dynamic arrays of devices to avoid array overflow.
Fixed the following tests:
Unit_hipDeviceGetByPCIBusId_WrongBusID)
Unit_hipSetDevice_ValidVisibleDeviceList
Unit_hipSetDevice_MinRvdMaxHvdDevicesList
Change-Id: I73d022321609d20ef2bd419f2cff287f6002a4d2
Changes: - Fixed Device Name (market name)
- Added new API rsmi_dev_market_name_get()
- Updated tests
- Updated amdgpu_drm.h to match latest mainline kernel
- Fixed subsystem ID to only show hex value (not subsystem name)
- rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
[ROCm/rocm_smi_lib commit: 6a5e94c451]
Changes: - Fixed Device Name (market name)
- Added new API rsmi_dev_market_name_get()
- Updated tests
- Updated amdgpu_drm.h to match latest mainline kernel
- Fixed subsystem ID to only show hex value (not subsystem name)
- rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
- Use correct header in device_library_decl
- use std:: instead of __hip_internal:: for host compilation
- hide device specific stuff behind __clang__ and __HIP__ check
Change-Id: I2f3647e00555ed0e79f9954a459c41394c3cd49b
- Also add a cache, which allows compiled code objects to be reused
instead of compiling again. This should improve performance on
multigpu systems.
Change-Id: Ib135d616c076b77f8aaf28de275d408b38021d89
Trowbridge, Ian
Galantsev, Dmitrii
Elwazir, Ammar
Ioannis Assiouras
Marko Arandjelovic
David Galiffi
Julia Jiang
Sajina PK
Tony Gutierrez
Pengda Xie
Rakesh Roy
vedithal-amd
kjayapra-amd
Rahul Manocha
German Andryeyev
Cheruvally, Aravindan
ywang103-amd
dependabot[bot]
David Yat Sin
Kandula, Venkateshwar reddy
Jimbo Xie
Dragoslav Sicarov
Charis Poag
Jatin Chaudhary