Commit Graph

76347 Commits

Author SHA1 Message Date
arvindcheru 21afa807a9 Enable Lintian Support for ROCM-SMI, ROCMINFO (#1650)
* Enable Lintian Support for ROCM-SMI

* Enable Lintian Support for ROCMINFO

* Updated Lintian Override File Processing

* Update UT Fix for Lintian rocmsmi,rocminfo

* Update UT Fixes, Review Comments

* Update Review Comments - removed extra white spaces, added error check for gzip, date commands

* Update Review Comments - Correcting License Type

* Sync Lintian ChangeLog

* Changelog data sync enhanced

* Update Review Comments, UT fix

* white space cleanup - precommit check
2025-12-15 14:35:28 -06:00
randyh62 1240b592a5 Git url fix (#2285)
* Update README-doc.md

Correct GitHub URL for components moved into rocm-systems

* Update amd_clr.rst

Update github.com URLs

* Update Dockerfile

Update rocm-systems paths

* Update CONTRIBUTING.md

update for rocm-systems

* Update CONTRIBUTING.md

minor change

* Update CONTRIBUTING.md

* Update CONTRIBUTING.md

* Update hip_runtime_api.rst

Update for rocm-systems

* Update installation.rst

update URL to libhsakmt

* Update what_is_hip.rst

* Update projects/clr/CONTRIBUTING.md

Co-authored-by: Dominic Widdows <dwiddows@gmail.com>

* Update projects/clr/README-doc.md

Co-authored-by: Dominic Widdows <dwiddows@gmail.com>

* Update Dockerfile

Update git clone for sparse checkout

* Update projects/hip/CONTRIBUTING.md

* Update projects/clr/CONTRIBUTING.md

* Update projects/hipother/CONTRIBUTING.md

---------

Co-authored-by: Dominic Widdows <dwiddows@gmail.com>
2025-12-15 11:57:18 -08:00
Mario Limonciello 08949cb884 Run pre-commit's whitespace related hooks on projects/amdsmi (#2119)
* Run pre-commit's whitespace related hooks on projects/amdsmi

In order for pre-commit to be useful, everything needs to meet a common
baseline.

* Add whitespace back to Changelog for formatting

---------

Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-12-15 13:20:47 -06:00
gabrpham 48e57d3e2a Version bump and Changelog update for ROCm version 7.2 (#2201)
* Update projects/amdsmi/CHANGELOG.md
* Bump to 26.2.1
---------

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
2025-12-15 13:19:30 -06:00
Jonathan R. Madsen a71cc3cc88 [rocprofiler-sdk] Optimize rocprofiler-sdk find_clients() (#2267) 2025-12-15 11:47:37 -06:00
systems-assistant[bot] b002c6a739 SWDEV-538607 - Add SIMDe as a build dependency, remove naked intrinsic use. (#500)
Co-authored-by: Alex Voicu <alexandru.voicu@amd.com>
Co-authored-by: Ioannis Assiouras <Ioannis.Assiouras@amd.com>
2025-12-15 17:40:51 +00:00
Ajay GunaShekar b9dc8f729a SWDEV-566268 - skip 2 failing tests on rock Windows (#2308) 2025-12-15 12:32:37 -05:00
Matt Arsenault 49565f9d9f SWDEV-548892 - Always declare used ocml and ockl device libs functions (#2230)
Ignore __CLANG_HIP_RUNTIME_WRAPPER_INCLUDED__. This should not be relying
on declarations from the clang builtin headers. There is no issue declaring
the same intrinsics multiple times. This will enable removal of declarations
from the clang builtin headers.
2025-12-15 17:23:33 +01:00
Fábio Mestre 447beeb00b Replace usages of __ockl_gws_init with __builtin_amdgcn_ds_gws_init (#2235) 2025-12-15 16:56:14 +01:00
Jason Bonnell 3b732edb0b Move submodule definitions from projects/rccl/.gitmodules to root .gitmodules (#2298) 2025-12-15 09:27:32 -05:00
Yiltan 43363894a8 remove cq lock (#357)
[ROCm/rocshmem commit: b28a56bd54]
2025-12-15 09:23:24 -05:00
Yiltan b28a56bd54 remove cq lock (#357) 2025-12-15 09:23:24 -05:00
Yiltan 5e2ba952f3 [GDA/BNXT] Remove doorbell arbitration (#363)
[ROCm/rocshmem commit: fe1a28e409]
2025-12-15 09:23:01 -05:00
Yiltan fe1a28e409 [GDA/BNXT] Remove doorbell arbitration (#363) 2025-12-15 09:23:01 -05:00
Edgar Gabriel f9fd5d3cdd use 64 threads for reduction test (#360)
* use 64 threads for reduction test

much faster with IPC backend.

* change all relevant collective tests.

[ROCm/rocshmem commit: c35210f174]
2025-12-15 08:14:18 -06:00
Edgar Gabriel c35210f174 use 64 threads for reduction test (#360)
* use 64 threads for reduction test

much faster with IPC backend.

* change all relevant collective tests.
2025-12-15 08:14:18 -06:00
yangsu13 a7be322dfd wsl/librocdxg: vmm api support for rocr on windows
PR:https://github.com/ROCm/rocm-systems/pull/1761/commits

Signed-off-by: Yang Su <Yang.Su2@amd.com>
Reviewed-by: Flora Cui <flora.cui@amd.com>
2025-12-15 16:08:38 +08:00
Ioannis Assiouras 13561fb8cd Bump hash for theRock to 2025-12-12 commit (#2289) 2025-12-13 23:56:08 +00:00
Mustafa Abduljabbar 88652b53d0 Add fix for WarpSpeed auto mode (#2104)
[ROCm/rccl commit: 5787c960fc]
2025-12-12 17:56:52 -05:00
Mustafa Abduljabbar 5787c960fc Add fix for WarpSpeed auto mode (#2104) 2025-12-12 17:56:52 -05:00
jamessiddeley-amd 706a8382a5 [rocprof-compute] added graceful exit with corrupt roofline.csv in profile and analyze mode (#1811)
* added graceful errors/exit in profile/analyze roofline.csv

* edit if statement truth

* restore if statement truth (roofline_csv needs at least 2 rows)

* addressed comments and skipped showing roof metrics when data invalid

* fix workload merge

* changed warning to error

* removed redundant variable definition

* added roofline csv validate check in TUI

* add test cases to test validation function

* ruff format

* simplified TUI roofline handling
2025-12-12 17:06:37 -05:00
jamessiddeley-amd 81720183ad [rocprof-compute] Merge CDash Nightly and Continuous workflow files (#2279)
* merged code-coverage and continuous workflow files

* fixed runner typos and added build mode

* add actor name to Continuous build

* improve error handling and remove redundant verbose

* fixed workflow file log output

* revert logs output in run_ci.py

* ruff format
2025-12-12 17:04:56 -05:00
Dominic Widdows 9a8ed9f45d Doc updates updating internal links from deprecated repos to rocm-systems project locations (#2294)
* Update README documentation links for clarity and consistency across projects

- Changed links in the README files for `clr`, `hipother`, and `hip-tests` to use relative paths instead of absolute URLs, improving navigation within the repository.

* Update CONTRIBUTING documentation to use relative links for improved navigation

- Changed absolute URLs to relative paths in the CONTRIBUTING.md files for the hip and hipother projects, enhancing consistency and ease of access within the repository.
2025-12-12 13:21:42 -08:00
Aryan Salmanpour 8b6cfde1dd Sample & Test - Add rocdecDecode to the ctest and decouple the rocdecode-host from it (#685)
* Add rocdecDecode to the ctest and decouple the rocdecode-host from it

* clean up

[ROCm/rocdecode commit: 158f7fd2ba]
2025-12-12 11:57:39 -08:00
Aryan Salmanpour 158f7fd2ba Sample & Test - Add rocdecDecode to the ctest and decouple the rocdecode-host from it (#685)
* Add rocdecDecode to the ctest and decouple the rocdecode-host from it

* clean up
2025-12-12 11:57:39 -08:00
Eiden Yoshida a9de523e0d Add rccl and rccl-tests to auto-labeler yaml (#2286) 2025-12-12 12:47:20 -07:00
Ajay GunaShekar 0bb5638481 Rock: hip-tests installation path to remain same for linux/windows (#2187)
* Rock: hip-tests installation path remains same for linux and windows

On theRock - installation path remains same linux/windows
share/hip/catch_tests

On internal win build - hip-tests will be installed to catch_tests
flag is passed internally which controls the path.
2025-12-12 08:45:28 -08:00
Dominic Widdows 2073cf2172 Skip running TheRock CI on docs-only changes(#2246)
Following the pattern from ROCm/rocm-libraries#2679, add logic to skip
CI builds when only documentation files are modified.

Changes:
- Add SKIPPABLE_PATH_PATTERNS for docs, markdown, and .gitignore files
- Return empty projects list when only skippable paths are modified
- No workflow changes needed - existing projects != '[]' check handles it
- Add unit tests for doc-filtering logic
- Fix existing tests with proper subprocess mocking

Reference: https://github.com/ROCm/rocm-libraries/pull/2679
2025-12-12 08:30:59 -08:00
vedithal-amd 4870725a62 Do not absolute python path when adding tests (#2282) 2025-12-12 10:57:19 -05:00
vedithal-amd 793732a04e [rocprofiler-compute] Improve amdsmi interface (#2245)
* Improve amdsmi interface

* Fix issue where max mem clock was being set as max gfx clock

* Handle the case when all device handles might not be usable due to
  devices being hidden by ROCR and HIP environment variables

* Fix get gpu vram size to return str in KB

* Improve testing of amdsmi interface functions
2025-12-12 09:02:37 -05:00
Jan Stephan ca0f3a6b5a Fix code highlighting (#2254)
Signed-off-by: Jan Stephan <jan.stephan@amd.com>
2025-12-12 14:06:53 +01:00
Jan Stephan 4cc8ff3c54 HIPRTC: Fix CDNA CU description (#2252)
Signed-off-by: Jan Stephan <jan.stephan@amd.com>
2025-12-12 14:06:16 +01:00
Todd tiantuo Li 0eccbf0534 SWDEV-554372 - cuda mappings for GetProcAddress API and flags (#1089) 2025-12-11 23:59:51 -08:00
SaleelK 840301e12d clr: Minor fixes for error return (#2153) 2025-12-11 16:59:56 -08:00
Mustafa Abduljabbar 2621e0254e [Device] WarpSpeed enablement and single node CU and perf opt for MI350 (#2073)
[ROCm/rccl commit: d009ab144e]
2025-12-11 19:04:35 -05:00
Mustafa Abduljabbar d009ab144e [Device] WarpSpeed enablement and single node CU and perf opt for MI350 (#2073) 2025-12-11 19:04:35 -05:00
Ahmed Khan f17357d0d4 Add ncclCommDump API (#2068)
* Add ncclCommDump API

* remove trailing whitespace changes

* Add more proxy trace timestamps

* Add facebook_rccl namespace before proxyTrace timestamp call

* Clean up ProxyTrae construction

* Move updateProxyOpCounter to member function

* Move setProxyOpTimestamp to member function

* Move addNewProxyOp to member function

* Make internal methods private

* Make ProxyTrace thread safe

* Fix unit tests

* Fix overwritten ProxyTrace DONE setting in net.cc

[ROCm/rccl commit: 08dd75712f]
2025-12-11 15:02:35 -07:00
Ahmed Khan 08dd75712f Add ncclCommDump API (#2068)
* Add ncclCommDump API

* remove trailing whitespace changes

* Add more proxy trace timestamps

* Add facebook_rccl namespace before proxyTrace timestamp call

* Clean up ProxyTrae construction

* Move updateProxyOpCounter to member function

* Move setProxyOpTimestamp to member function

* Move addNewProxyOp to member function

* Make internal methods private

* Make ProxyTrace thread safe

* Fix unit tests

* Fix overwritten ProxyTrace DONE setting in net.cc
2025-12-11 15:02:35 -07:00
amd-jiali d5e8f372dc Fix Out of Memory issue when allocating bias buffer (#160)
* Add argument to select performance test with bias or not; if with bias, the maximum memory usage should be re-calculated and reduce the data size to avoid the Out of Memory issue; if without bias, no need to allocate buffers for bias

* Remove argument option for bias; memory calculation and buffer allocation are determined by the exec name.

---------

Co-authored-by: Li <jialili@ctr2-alola-ctrl-01.amd.com>

[ROCm/rccl-tests commit: 5272cd16ef]
2025-12-11 14:00:29 -08:00
amd-jiali 5272cd16ef Fix Out of Memory issue when allocating bias buffer (#160)
* Add argument to select performance test with bias or not; if with bias, the maximum memory usage should be re-calculated and reduce the data size to avoid the Out of Memory issue; if without bias, no need to allocate buffers for bias

* Remove argument option for bias; memory calculation and buffer allocation are determined by the exec name.

---------

Co-authored-by: Li <jialili@ctr2-alola-ctrl-01.amd.com>
2025-12-11 14:00:29 -08:00
Mario Limonciello b106e6f175 Run pre-commit's whitespace related hooks on projects/rocminfo (#2115)
In order for pre-commit to be useful, everything needs to meet a common
baseline.

Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
2025-12-11 15:41:47 -06:00
Mario Limonciello bfb13f2b43 Run pre-commit's whitespace related hooks on projects/rocm-smi-lib (#2117)
* Run pre-commit's whitespace related hooks on projects/rocm-smi-lib

In order for pre-commit to be useful, everything needs to meet a common
baseline.

Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>

* Added Changelog Spaces for formatting

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

---------

Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
2025-12-11 15:41:24 -06:00
Ameya Keshava Mallya 56fd780e32 Add 'projects/rccl-tests/' from commit '6405c76e6826663bbb67bd40aeee8c70aa5d3094'
git-subtree-dir: projects/rccl-tests
git-subtree-mainline: 42d84317cf
git-subtree-split: 6405c76e68
2025-12-11 20:46:38 +00:00
Ameya Keshava Mallya 42d84317cf Add 'projects/rccl/' from commit '1f2f9f33bac3e8ecfd84c69af6063d7352c362fc'
git-subtree-dir: projects/rccl
git-subtree-mainline: 3fd8a0d393
git-subtree-split: 1f2f9f33ba
2025-12-11 20:46:05 +00:00
Thomas Huber e5c20187ed Update gfx950 tuner conf to include broadcast (#2065)
Signed-off-by: Thomas Huber <thomas.huber@amd.com>

[ROCm/rccl commit: 1f2f9f33ba]
2025-12-11 14:36:03 -05:00
Thomas Huber 1f2f9f33ba Update gfx950 tuner conf to include broadcast (#2065)
Signed-off-by: Thomas Huber <thomas.huber@amd.com>
2025-12-11 14:36:03 -05:00
vedithal-amd 3fd8a0d393 [rocprofiler-compute] Remove hip dependency during analysis (#2276)
* Remove hip dependency during analysis

* dont dynamic import when roofline skipped
2025-12-11 14:33:43 -05:00
jamessiddeley-amd 8f452d29df [rocprof-compute] Update Docs 7.2 + Dual Issue Detection (#2160)
* modified changelog for docs updates 7.2

* update documentation for 7.2

* update FAQ wording

* Update projects/rocprofiler-compute/docs/reference/faq.rst

Co-authored-by: cfallows-amd <Carrie.Fallows@amd.com>

* addressed comments

* fixed header for 'On MI350 and newer platforms'

* Update projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx950/1100_compute_units_compute_pipeline.yaml

Co-authored-by: cfallows-amd <Carrie.Fallows@amd.com>

* ruff format

---------

Co-authored-by: cfallows-amd <Carrie.Fallows@amd.com>
2025-12-11 14:23:34 -05:00
SakaSitharammurthy 9de72d438d Updated amd-smi.h documentation (#2031)
Signed-off-by: Saka, Sitharam Murthy <SitharamMurthy.Saka@amd.com>
2025-12-11 11:42:23 -06:00
systems-assistant[bot] c72b0558a4 [SWDEV-555654] Enable Driver reload on SRIOV (#1898)
Enabled reload argmument. Reload is supported
on SRIOV systems.

Fixes:
sudo amd-smi reset -g all
AttributeError: 'Namespace' object has no attribute 'reload_driver'

Change-Id: Ib75ba043e29ae6e668c18451b93e766a7528739f

Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>
2025-12-11 11:38:40 -06:00