Commit Graph

37726 Commits

Author SHA1 Message Date
Marko Arandjelovic 3ec1d2d2f1 SWDEV-512344 - Unmap all subbuffers
Since hipMemMap can be called for multiple device handles on the same virtual memory, the same is true for hipMemUnmap, meaning that virtual memory can be "partially unmapped".

This means that the unmap function can be called for a specific part of the reserved address, meaning that only the designated subbuffer should be released. If unmap is called on the entire reserved memory, then all subbuffers should be released.

The main point is that for every hsa_amd_vmem_map, there should be a corresponding hsa_amd_vmem_unmap. Otherwise, if entire memory is unmapped by a single unmap call, then HSA will report the memory as "in use" if an attempt is made to delete it.

Change-Id: I039308eafb820decfb1c09f60347f26cdad1a362
2025-03-02 13:41:48 -05:00
dependabot[bot] 254592953c Bump rocm-docs-core from 1.15.0 to 1.17.0 in /docs/sphinx (#572)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.15.0 to 1.17.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.15.0...v1.17.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

[ROCm/rocprofiler-compute commit: 3b78dc9177]
2025-02-28 16:34:11 -07:00
dependabot[bot] 3b78dc9177 Bump rocm-docs-core from 1.15.0 to 1.17.0 in /docs/sphinx (#572)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.15.0 to 1.17.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.15.0...v1.17.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-02-28 16:34:11 -07:00
Todd tiantuo Li 0558a8cd8a SWDEV-1 - skip OCLMemoryInfo test for APUs
Change-Id: I5afc244f68115a538eb3d989c3aa119e0f279deb
2025-02-28 13:10:40 -05:00
Saleel Kudchadker 37d606d193 SWDEV-513197 - Unify getBuffer implementation
- Use getBuffer/releaseBuffer in BlitManager
- Cleanup XferBuffer as we use ManagedBuffer for both reads/writes

Change-Id: I2661b85dd012763b17a38a743fec1b1d79125f67
2025-02-28 12:47:51 -05:00
Rawat, Swati f7d1f14c60 Documentation updates (#236)
* Documentation updates

* formatting

* Update using-rocprofv3.rst

* Update counter_collection_services.md

---------

Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 31b8f61c8e]
2025-02-28 10:10:26 +05:30
Rawat, Swati 31b8f61c8e Documentation updates (#236)
* Documentation updates

* formatting

* Update using-rocprofv3.rst

* Update counter_collection_services.md

---------

Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com>
2025-02-28 10:10:26 +05:30
David Galiffi 009ffbb3b0 Add doc formatting to workflow (#123)
- Add document formatting workflow from ROCm/rocm-docs-core/.github/workflows/linting.yml
- Updated runners to use ubuntu-22.04, since 20.04 is being deprecated.

[ROCm/rocprofiler-systems commit: a18d00d784]
2025-02-27 23:25:03 -05:00
David Galiffi a18d00d784 Add doc formatting to workflow (#123)
- Add document formatting workflow from ROCm/rocm-docs-core/.github/workflows/linting.yml
- Updated runners to use ubuntu-22.04, since 20.04 is being deprecated.
2025-02-27 23:25:03 -05:00
David Belanger 3ceb131df5 kfdtest: Fix ExtendedCuMasking test case
Modify test case to support XL cards.

Change-Id: I6ad45a290d50a5238804ce7417bcdb33a3912872
Signed-off-by: David Belanger <david.belanger@amd.com>
2025-02-27 21:25:19 -05:00
Saleel Kudchadker ca530c660b SWDEV-513197 - Improve launch perf for Device Heap kernels
- If any kernel uses device heap, the launch needs to be preceeded by an
  init kernel, Save on the extra barrier packet launch/flush between the
init heap kernel and user kernel

Change-Id: I8ebc6246188200e5f673dc464bc76a53bcb8b7c6
2025-02-27 19:17:51 -05:00
Ioannis Assiouras e9b33af45a SWDEV-509788 - Code cleanups in Event class
Change-Id: I4163ce6c1dabeaab92de13b51b6a46b7be83e2bd
2025-02-27 17:16:50 -05:00
Fei Zheng a8ade68e64 Change normal_unit default to per_kernel
[ROCm/rocprofiler-compute commit: 6ece52fbe8]
2025-02-27 12:46:47 -07:00
Fei Zheng 6ece52fbe8 Change normal_unit default to per_kernel 2025-02-27 12:46:47 -07:00
Sohaib Nadeem 2304111f79 Fix an application crash when collecting performance counters with rocprofiler (#117)
* Add check to skip counter_storage::write() if internal storage field is destroyed.
* Output warning message if counter data is not available when trying to write out to Timemory

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 43f900d01e]
2025-02-27 14:34:52 -05:00
Sohaib Nadeem 43f900d01e Fix an application crash when collecting performance counters with rocprofiler (#117)
* Add check to skip counter_storage::write() if internal storage field is destroyed.
* Output warning message if counter data is not available when trying to write out to Timemory

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-02-27 14:34:52 -05:00
Alex Xie 375a147e51 SWDEV-514060 - Use newer OpenCL API in test using AMD extension API
Change-Id: Ifdbb3c45628116e48f68ae29324e4cc554c9f2d5
2025-02-27 11:20:37 -05:00
vedithal-amd 4b1979912b clear yum metadata before yum install (#582)
[ROCm/rocprofiler-compute commit: bec537e2a1]
2025-02-27 09:39:26 -05:00
vedithal-amd bec537e2a1 clear yum metadata before yum install (#582) 2025-02-27 09:39:26 -05:00
Fei Zheng a9f021e17c Add FP8 metrics for MI300
[ROCm/rocprofiler-compute commit: 58217f2c6a]
2025-02-26 18:45:19 -07:00
Fei Zheng 58217f2c6a Add FP8 metrics for MI300 2025-02-26 18:45:19 -07:00
vedithal-amd 2fc811bbbd Do not fail if VERSION.sha not found (#579)
* Create VERSION.sha file while creating standalone binary

* Do not fail on VERSION.sha not found

* Add git to docker container for testing

[ROCm/rocprofiler-compute commit: 19a9365bb9]
2025-02-26 11:39:37 -05:00
vedithal-amd 19a9365bb9 Do not fail if VERSION.sha not found (#579)
* Create VERSION.sha file while creating standalone binary

* Do not fail on VERSION.sha not found

* Add git to docker container for testing
2025-02-26 11:39:37 -05:00
Saleel Kudchadker d8f5c2560f SWDEV-515407 - Fix incorrect test behavior
- For H2D transfer cases, we cannot enfore ErrorNotReady behavior if the
  source is unpinned. In that case the driver can sync depending on if
it pins or stages the source buffer.

Change-Id: I436a4b667bff172cfbadc58631a46a215c40fcb1
2025-02-26 11:39:34 -05:00
Rahul Manocha 4bf634dfca SWDEV-510849 - Restore pinned memory copy path
1) Create getBuffer method to return pinned host memory or staging buffer
2) for D2H path use managed buffer instead of static buffer
3) use staging buffer copy for 16KB < size < 1MB
4) use pinned memory copy for size > 1MB

Change-Id: I13d4d6ab60691bc6c7724239db1e11e23f0f3dc2
2025-02-26 11:25:02 -05:00
Jacob Lambert 187648429b SWDEV-360440 - Prepare CLR dynamic Comgr load for V3
Change-Id: Iffd835056740ff10711468cc752b7b55078b9f8f
2025-02-26 11:22:18 -05:00
Pengda Xie ade704dd2f SWDEV-512044 - Fix logic error in texture size validation
Change-Id: I6aefcfed25b099c17bf0856d621081c0a5ce46c5
2025-02-26 11:20:58 -05:00
Julia Jiang f327d4f809 SWDEV - 508961 - Update requestedHandleType in hipother repos
Change-Id: I50b91dfb42bd2a4daae80a3353b642e9df03fe46
2025-02-26 11:14:58 -05:00
Khatri, Shweta 0984a1f0fd rocr: GFX9, GFX10, GFX11: Use view3dAs2dArray flag, for thick/3D swizzle modes. (#58)
A HSA_IMAGE_ENABLE_3D_SWIZZLE_DEBUG environment flag exists already to
enable/disable this. Default value is false (view3dAs2dArray = 1)
Enabling this flag will enable support for swizzles that do 3D
interleaving on GFX9, GF10 and GFX11. By default support for swizzles that
do 3D interleaving is disabled.
2025-02-26 09:38:17 -05:00
Ioannis Assiouras a8f309049d SWDEV-516994 - Fix race condition in the implementation of graph AutoFreeOnLaunch on Windows
Change-Id: I3c98d0d4bffe2a9e0aa5cfa24b6c8e9a8087da29
2025-02-26 02:36:31 -05:00
Tony Gutierrez d3a4dc9687 rocr: Remove KMT usage from AMD ext
Use the core Driver in AMD's HSA extension API to make it
agnostic to the underlying OS and kernel-mode driver.
2025-02-25 21:51:52 -05:00
Sajina PK 1db0539c30 Add support for rocJPEG API tracing (#116)
- Add rocDecode API Tracing support using domain `rocjpeg_api` in ROCPROFSYS_ROCM_DOMAINS.
- Modify existing `videodecode` and `jpegdecode` ctests to verify API tracing
- Print Perfetto values for easy debugging in verbose mode
- Convert CMake error to a warning and skip building the "decode" examples if requirements are not found

[ROCm/rocprofiler-systems commit: 3bea1d8eac]
2025-02-25 21:14:14 -05:00
Sajina PK 3bea1d8eac Add support for rocJPEG API tracing (#116)
- Add rocDecode API Tracing support using domain `rocjpeg_api` in ROCPROFSYS_ROCM_DOMAINS.
- Modify existing `videodecode` and `jpegdecode` ctests to verify API tracing
- Print Perfetto values for easy debugging in verbose mode
- Convert CMake error to a warning and skip building the "decode" examples if requirements are not found
2025-02-25 21:14:14 -05:00
Kuricheti, Mythreya c4ccaa4f5c [fix] typo in name rocprofiler_rocjpef_api_id_t -> rocprofiler_rocjpeg_api_id_t (#237)
[fix] rocjpeg fix

[ROCm/rocprofiler-sdk commit: b9eaf88fa3]
2025-02-25 11:23:31 -06:00
Kuricheti, Mythreya b9eaf88fa3 [fix] typo in name rocprofiler_rocjpef_api_id_t -> rocprofiler_rocjpeg_api_id_t (#237)
[fix] rocjpeg fix
2025-02-25 11:23:31 -06:00
taosang2 ff516573f2 SWDEV-1 Disable a test
Disable Performance_hipExtLaunchKernelGGL_QueryGPUFrequency
as it should be a local perf test.

Change-Id: I7e94743d6958ffaadae9cff297e3f2d93f9ff817
2025-02-25 09:37:38 -05:00
Branislav Brzak 8f12e1dcd9 SWDEV-516564 - SWDEV-512817 - Remove mentions of gfx940 and gfx941
Change-Id: Ie9cd254ed31ce9af23c8a3106dd961f276be1c4d
2025-02-25 05:35:25 -05:00
James Zhu f8d8b8011f kfdtest: fix resource leakage
Resource allocated in SetUp/HsaNodeInfo::Init,
needs be delete in TearDown/HsaNodeInfo::Delete.

Signed-off-by: James Zhu <James.Zhu@amd.com>
2025-02-24 19:38:59 -05:00
vedithal-amd 4a890ce8d0 Check PATH to verify executable in remaining args (#578)
[ROCm/rocprofiler-compute commit: 649660d54e]
2025-02-24 13:33:55 -05:00
vedithal-amd 649660d54e Check PATH to verify executable in remaining args (#578) 2025-02-24 13:33:55 -05:00
Rambabu Swargam c54034fe59 SWDEV-517063 - [catch2][dtest] Disable failing hipGraphInstantiateWithFlags tests
Change-Id: I8b999c7b6de66dccde5bc00dd7a2a87d2c562a96
2025-02-24 09:35:19 -05:00
Indic, Vladimir 08e81f5972 PCS vs CC test: initializing buffer_id to zero (#229)
[ROCm/rocprofiler-sdk commit: f7b5759a20]
2025-02-24 04:41:07 -08:00
Indic, Vladimir f7b5759a20 PCS vs CC test: initializing buffer_id to zero (#229) 2025-02-24 04:41:07 -08:00
xuchen-amd 69f0312b7b Improve kokkos trace handling. (#573)
* Improve kokkos trace is handling.

* Fix formatting.

* Syntax fix and adding comments.

[ROCm/rocprofiler-compute commit: 10e1d57bfb]
2025-02-22 14:07:14 -05:00
xuchen-amd 10e1d57bfb Improve kokkos trace handling. (#573)
* Improve kokkos trace is handling.

* Fix formatting.

* Syntax fix and adding comments.
2025-02-22 14:07:14 -05:00
Rahul Manocha 5930f047bb SWDEV-489106 - Linker API addition to runtime
1) Add Linker APIs to runtime to support SPIRV linking
2) Migrate Internal implementations to runtime and share with rtc
3) Add Support to bundled and unbundled SPIRV Code object linking.

Change-Id: Ic1fd4431f842a208a2468e8aec54a65b5fa6b0e3
2025-02-22 13:39:23 -05:00
Li, Todd tiantuo 9faaf20aae SWDEV-508980 - [6.4 Preview] fix hipDeviceSetCacheConfig during stream capture
Change-Id: I8e89774a8163fdc120155f742606ee2c0aa7103b
2025-02-22 01:05:28 -05:00
Li, Todd tiantuo c07468e53c SWDEV-510271 - [6.4 Preview] fix hipCreateSurfaceObject & hipDestroySurfaceObject during stream capture
Change-Id: I19e149549c271d847f52b72e04cb2427ca194b24
2025-02-22 01:04:35 -05:00
Khatri, Shweta 322a794cf6 rocr: Adding support for Stochastic PC Sampling for gfx94x (#47)
Change-Id: Ide4c2e25b88f1f25ea4ce35a619b93963c0355ee
2025-02-22 00:13:08 -05:00
Trowbridge, Ian 74efdad1aa rocJPEG API Tracing (#73)
* 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>

[ROCm/rocprofiler-sdk commit: 31fe8858d1]
2025-02-21 13:43:49 -08:00