AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
37,726 Commits 3 Branches 0 Tags
6150a119a4ed018c85a17c1945540b6116a1bae6
Commit Graph

37726 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
gobhardw 1eae69c812 Disabling kernel names matching test 
Change-Id: I70d74c421599a38207943a59c424ae7681b9fdcb


[ROCm/rocprofiler commit: fe55de6bef]
 2024-12-03 15:59:24 +05:30
Satyanvesh Dittakavi db56cec3ab SWDEV-488922 - Document the usage of DEBUG_HIP_7_PREVIEW 
hipGetLastError API's behavior matches with its corresponding
CUDA API when this variable is set to 1

Change-Id: I661af7083e9c8dfc5e4f2003e39702ece4ccfa21
 2024-12-03 02:15:02 -05:00
Elwazir, Ammar a50f80aaed CI: Enabling Navi3 and Vega20 runners & PR Jira Addition (#32) 
* Enabling Navi3 and Vega20 runners

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing Github Actions issues

* Fixing docs workflow

* Fixing docs workflow miniconda3 location

* Fixing docs workflow env setup

* Fixing docs workflow env setup

* Fixing docs workflow miniconda3 env

* Fixing docs source build workflow

* Balancing between navi3, vega20, mi300, mi200

* git sync workflow update

* Adding Jira ticket place holder in PR Description

* Fixing RHEL & SLES Builds

* Fixing RHEL & SLES Builds

* Fixing RHEL & SLES Builds

* Fixing Re-run workflow

* Update pull_request_template.md

* Update continuous_integration.yml

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>

[ROCm/rocprofiler-sdk commit: f16c87f594]
 2024-12-02 22:48:37 -06:00
Elwazir, Ammar f16c87f594 CI: Enabling Navi3 and Vega20 runners & PR Jira Addition (#32) 
* Enabling Navi3 and Vega20 runners

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing Github Actions issues

* Fixing docs workflow

* Fixing docs workflow miniconda3 location

* Fixing docs workflow env setup

* Fixing docs workflow env setup

* Fixing docs workflow miniconda3 env

* Fixing docs source build workflow

* Balancing between navi3, vega20, mi300, mi200

* git sync workflow update

* Adding Jira ticket place holder in PR Description

* Fixing RHEL & SLES Builds

* Fixing RHEL & SLES Builds

* Fixing RHEL & SLES Builds

* Fixing Re-run workflow

* Update pull_request_template.md

* Update continuous_integration.yml

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
 2024-12-02 22:48:37 -06:00
gobhardw 9c68ae6ef8 Disabling kernel number, names checking tests 
Change-Id: I629d8e9029386bf6a23b2e866169044d63327241
 2024-12-03 10:12:52 +05:30
gobhardw f9a3bd2477 Disabling kernel number, names checking tests 
Change-Id: I629d8e9029386bf6a23b2e866169044d63327241


[ROCm/rocprofiler commit: 9c68ae6ef8]
 2024-12-03 10:12:52 +05:30
arvindcheru d11f5c20d5 Update ROCM-CORE contributing template and basics docs (#9) 
* Add Contributing documentation as per template, updated Readme documentation and Update codeowners
* Moving Readme.txt to Readme.md format 
* Update Review Comments - CMAKE commands Updated, removed library dump and added API usage
* Update Review Comments - Enhanced Text descriptions, prerequisites/install prefix descriptions
* Update Review Comments - Added RPM Package Samples also and Enhanced Descriptions
 2024-12-02 23:24:44 -05:00
Lang Yu 37135aadfa kfdtest: update PersistentIterateIsa for gfx12 
1, Use s_wait_* instead of s_waitcnt
2, Remove a redundant s_waitcnt

Change-Id: Id0f31db0fc520adadd81eb574ad389f63859303a
Signed-off-by: Lang Yu <lang.yu@amd.com>
 2024-12-02 19:59:57 -05:00
Choudhary, Rahul 8b3d9ce7cd Update PSDB.yml - removing trigger for synchronize events 
very minor change , merging directly to reduce PSDB load

[ROCm/rocprofiler-sdk commit: 91d98befd7]
 2024-12-02 15:26:23 -08:00
Choudhary, Rahul 91d98befd7 Update PSDB.yml - removing trigger for synchronize events 
very minor change , merging directly to reduce PSDB load
 2024-12-02 15:26:23 -08:00
dependabot[bot] c2a1506cbf Bump rocm-docs-core[api_reference] from 1.9.1 to 1.10.0 in /docs/sphinx 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.9.1 to 1.10.0.
- [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/v1.9.1...v1.10.0)

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

Signed-off-by: dependabot[bot] <support@github.com>

[ROCm/rocprofiler-systems commit: 7580eb950b]
 2024-12-02 17:55:06 -05:00
dependabot[bot] 7580eb950b Bump rocm-docs-core[api_reference] from 1.9.1 to 1.10.0 in /docs/sphinx 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.9.1 to 1.10.0.
- [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/v1.9.1...v1.10.0)

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

Signed-off-by: dependabot[bot] <support@github.com>
 2024-12-02 17:55:06 -05:00
Sourabh Betigeri 2ca644cf22 Revert "SWDEV-440866 - [hip-roclr] Adds support to batch memory operations APIs" 
This reverts commit bd5d8e9baf.

Reason for revert: hipInfo fails on windows. Updating llvm amd-mainline-closed

Change-Id: I57e1fa1945188b0bc0a799c4f3d540f2b7713003
 2024-12-02 16:46:12 -05:00
Marko Arandjelovic 08aee16573 SWDEV-499794 - Update AQL packet after updating GraphNode 
Change-Id: I332d70bdf42a276894a548a02d636e370c2ca08c
 2024-12-02 12:29:35 -05:00
Mark Meserve 09f2b0aa2a SWDEV-495956: Fix for bad characters in HSA trace 
- Fixes issue where invalid UTF-8 characters in a trace log would crash
  the program
- Bad characters could appear with hsa_amd_enable_logging
  - The first parameter of type uint8_t* is interpreted as a cstring
    during log creation
  - This change only fixes the crash, not this issue

Change-Id: I66771a66deee347000a98a91c4aa9cfb674c8f08
 2024-12-02 10:48:56 -06:00
Mark Meserve 7398620acc SWDEV-495956: Fix for bad characters in HSA trace 
- Fixes issue where invalid UTF-8 characters in a trace log would crash
  the program
- Bad characters could appear with hsa_amd_enable_logging
  - The first parameter of type uint8_t* is interpreted as a cstring
    during log creation
  - This change only fixes the crash, not this issue

Change-Id: I66771a66deee347000a98a91c4aa9cfb674c8f08


[ROCm/rocprofiler commit: 09f2b0aa2a]
 2024-12-02 10:48:56 -06:00
zichguan-amd c042b4f582 Make ROCM_DIR default ROCm path for rocprof 
Signed-off-by: zichguan-amd <zichuan.guan@amd.com>
 2024-12-02 11:19:56 -05:00
zichguan-amd a5227aa61b Make ROCM_DIR default ROCm path for rocprof 
Signed-off-by: zichguan-amd <zichuan.guan@amd.com>


[ROCm/rdc commit: c042b4f582]
 2024-12-02 11:19:56 -05:00
taosang2 df250a49a5 rocr: Support different address modes 
Support different address modes in X, Y, Z directions

Change-Id: If1db5a8af33c92ddc4b48968c3d8eceb97daea6a
 2024-12-02 09:07:56 -05:00
Aidan Belton-Schure f0063ba8da SWDEV-485827 release hostcall listener memory regardless of thread status 
The early return if the thread is not alive causes memory leaks.
Neither doorbell_ or urilocator are released if the thread is not alive.

This change alters the logic so regardless of the thread status the
HostcallListener releases its memory.

Change-Id: Ie912360ec0e2ee257de9937b1a8d7375e6aebd83
 2024-12-02 04:42:56 -05:00
Sameer Sahasrabuddhe 4e2fd192eb SWDEV-491314 - enable _sync() functions with 64-bit mask argument 
Change-Id: Ieb13a9e1b2fc49ff225a05a51056d1212d95ae57
 2024-12-01 10:16:59 -05:00
Sourabh Betigeri bd5d8e9baf SWDEV-440866 - [hip-roclr] Adds support to batch memory operations APIs 
Change-Id: I449ffca44bbb04d13348d112e896d603c70fd485
 2024-11-30 17:54:32 -05:00
Anusha GodavarthySurya c47f9dda58 SWDEV-469422 - Cleanup graph code remove parallellists and nodewaitlists 
Change-Id: I00c7b2894333bd13d47b913d3fcdd6e1ffcb741f
 2024-11-30 04:40:51 -05:00
David Yat Sin 147abb6ca0 rocr: Move _loader_debug_state to rocr namespace 
This avoids exposing the symbol to the default namespace

Change-Id: I2fe5fbab4b59f271effacab93eeb2d95c236ae02
 2024-11-29 10:44:23 -05:00
taosang2 f1f4f40c5b SWDEV-447973 - Support generic targets 
Change-Id: I32db83843e45e0f013591493aafd7a532c881e16
 2024-11-29 10:12:10 -05:00
Vladana Stojiljkovic b75b0d9a53 SWDEV-494612- Add capture support for hipLaunchCooperativeKernel 
Change-Id: I6b3c6af55c60cffd43ce6f47b75998f750b75703
 2024-11-29 08:17:41 -05:00
Anusha GodavarthySurya fb7ad8361c SWDEV-489084 - Update max streams for graph 
Change-Id: I6d0992b2e80ebf3184911593a4f3574327b2e9c3
 2024-11-29 08:16:16 -05:00
Anusha GodavarthySurya 06e6561eb5 SWDEV-489084 - Avoid using queue colliding with the graph launch stream 
Change-Id: I3ecaf8836c8e0883441275139041c702aba0937e
 2024-11-29 08:15:58 -05:00
Marko Arandjelovic 66367f3ec6 SWDEV-483312 - Add cuda driver API's interfaces 
Change-Id: Ib37cc6085898ae9dc86e509503cd52b61c1a5356
 2024-11-29 12:16:06 +02:00
Sebastian Luzynski 019abdc3bd SWDEV-465085 - replace asserts inside API calls 
This change replaces some asserts, that were only available in debug
mode, with standard error handling.

Signed-off-by: Sebastian Luzynski <Sebastian.Luzynski@amd.com>
Change-Id: I112f9e56f921abd72daf0d11e4ecdcb7b1a9f9e6
 2024-11-29 04:11:39 -05:00
Marko Arandjelovic e94d9b1763 SWDEV-489617 - Make any host to any host memcpy synchronous 
Change-Id: I2a29d1a433508f9b4b67b48c47bb4a4eebac0cb3
 2024-11-29 03:48:28 -05:00
Apurv Mishra c066ec13dd hsakmt: modified to free all_gpu_id_array in fmm.c 
Add free() for 'all_gpu_id_array' in
hsakmt_fmm_destroy_process_apertures() and
removed it from 'hsakmt_fmm_clear_all_mem()'

Change-Id: I32d2d22e7152f62a3f2e7da4f601f0db7cebd534
Signed-off-by: Apurv Mishra <apurv.mishra@amd.com>
 2024-11-28 13:08:03 -05:00
Apurv Mishra 79f0ac2534 hsakmt: minor code cleanup and refactor topology.c 
removed unused value assignment for HSAKMT_STATUS,
restructured 'topology_sysfs_check_node_supported'

Change-Id: I21cdccb3e3c5e42981f10597426de479d0f4ee6a
Signed-off-by: Apurv Mishra <apurv.mishra@amd.com>
 2024-11-28 13:06:23 -05:00
Aidan Belton-Schure f42a87dc2f SWDEV-485827 release initial_heap_buffer_ 
This PR adds the initialization and release of initial_heap_buffer_
to prevent memory leaks.

Change-Id: I4ab8721b439a1a3a6f6e53d63d870e572f7c984a
 2024-11-28 10:31:26 -05:00
Satyanvesh Dittakavi e3b8754448 SWDEV-477584 - Match hipGetLastError behavior with CUDA using env var 
Change-Id: I4c5acff180ae904028f7c5fdf4e109ffd1f0c4ef
 2024-11-28 01:33:52 -05:00
dependabot[bot] 81d7eaede9 Bump rocm-docs-core[api_reference] from 1.9.0 to 1.9.1 in /docs/sphinx 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.9.0 to 1.9.1.
- [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/v1.9.0...v1.9.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

[ROCm/rocprofiler-systems commit: ffcc0b6f3d]
 2024-11-27 22:38:29 -05:00
dependabot[bot] ffcc0b6f3d Bump rocm-docs-core[api_reference] from 1.9.0 to 1.9.1 in /docs/sphinx 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.9.0 to 1.9.1.
- [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/v1.9.0...v1.9.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-11-27 22:38:29 -05:00
Emily Deng 1f9c080932 kfdtest: fix event leaks issue 
DisableCpQueueByUpdateWithZeroPercentage need to destroy event to avoid
event leak.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Change-Id: I4fb51b670fbff1edcd7fd61517f5c8a6674003c0
 2024-11-27 19:33:10 -05:00
Chris Freehill eec2130443 rocr: Dynamically allocate supported_isas map 
This was missing from a previous commit regarding
dynamically allocated static data structures.

Change-Id: Iae1c674e762f85e3aebf338210ba96942ba80278
 2024-11-27 11:11:22 -05:00
Anusha GodavarthySurya 17e7b7c2ef SWDEV-472840 SWDEV-461980 - Fix null stream sync performance 
=> If null stream is not created during sync skip nullstrm creation
=> Do cpu wait on blocking & null stream if it exists

Change-Id: I90d6ced6a2dd1782ba58f3fed4e3608fc0efa55a
 2024-11-27 10:29:15 -05:00
Apurv Mishra 89115369cc rocr: declare 'args' as class member in 'os_thread' 
Removed 'args' as a unique pointer and deletion in
'ThreadTrampoline', then declared as a class member.

Change-Id: Ia52058392d0170e8b5e57cfdd2c587f47a6f93f0
Signed-off-by: Apurv Mishra <apurv.mishra@amd.com>
 2024-11-27 10:27:40 -05:00
David Galiffi 8159a9cc13 Fix packaging for upgrading 
Specify that "rocprofiler-systems" replaces / obsoletes the "omnitrace" package in the CPACK configuration.

Signed-off-by: David Galiffi <David.Galiffi@amd.com>


[ROCm/rocprofiler-systems commit: eb1af12177]
 2024-11-27 10:23:47 -05:00
David Galiffi eb1af12177 Fix packaging for upgrading 
Specify that "rocprofiler-systems" replaces / obsoletes the "omnitrace" package in the CPACK configuration.

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-11-27 10:23:47 -05:00
Aidan Belton-Schure 58a132446d SWDEV-481102 - Update install docs 
Change-Id: Ib73867259538374420a2f7bdf4958dc461761b84
 2024-11-27 05:39:13 -05:00
Aidan Belton-Schure 9652d69575 SWDEV-436099 Use new amdgcn_ballot builtin 
Change-Id: I024fabc6c5b3f39c66885eb7615953f4d0432e9a
 2024-11-27 04:34:50 -05:00
Emily Deng c8031f2a69 kfdtest: Fix the dead lock SignalHandling 
The issue arises in the CatchSignal function, which attempts to write to
the standard error stream upon receiving a signal. However, the standard
error stream may already be locked at this point, as the parent process
also attempts to write to the standard error stream after mapping the GPU
memory. This leads to a deadlock, with the program waiting for the
release of the lock on the standard error stream.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Change-Id: Ie69354f4342b96ffe1f2a87f655687da1cbee4b9
 2024-11-26 19:39:45 -05:00
Mallya, Ameya Keshava efe96fc045 Created OSDB workflow for mainline promotion 
[ROCm/rocprofiler-sdk commit: 09cf9540fe]
 2024-11-26 13:22:30 -08:00
Mallya, Ameya Keshava 09cf9540fe Created OSDB workflow for mainline promotion 2024-11-26 13:22:30 -08:00
Galantsev, Dmitrii b5272fb99c CI - Use vars instead of secrets 
Change-Id: Ib917b8677c204a75bedcb345978f2b09216b115f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2024-11-26 11:17:50 -06:00
Galantsev, Dmitrii 3f11f0e76b CI - Use vars instead of secrets 
Change-Id: Ib917b8677c204a75bedcb345978f2b09216b115f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: b5272fb99c]
 2024-11-26 11:17:50 -06:00