Commit Graph

71021 Commits

Author SHA1 Message Date
Geo Min 36a1fd87af Removing landed patch (#1184) 2025-09-30 16:51:41 -07:00
Geo Min b0a9a2386f [ci] Adding TheRock CI coverage for rocm-core (#868)
* TheRock CI points to rocm systems

* Fixing depth

* Fixing cache path

* Adding core components

* Adding more packages

* try this for windows building

* Add math libs

* Adding core only

* Attempt with no ccache

* adding patching

* Adding ls test

* adding this

* removing ls test

* changing dir name

* Adding cleanup for patch

* Adding ref

* adding correct no include

* Adding new temp branch for testing

* empty commit

* empty commit

* Adding commit hash bump

* Adding new hash for removed patches

* Adding TheRock submodule bump

* trying with compiler removed test

* Try dvc pull windows

* Update .github/workflows/therock-ci-linux.yml

Co-authored-by: Marius Brehler <marius.brehler@gmail.com>

* Adding correct env

* revert to ../

* Adding path

* try new var

* Adding new branch

* Adding correct hash

* Update .github/workflows/therock-ci-linux.yml

Co-authored-by: Marius Brehler <marius.brehler@gmail.com>

* Update .github/workflows/therock-ci-windows.yml

Co-authored-by: Marius Brehler <marius.brehler@gmail.com>

---------

Co-authored-by: Marius Brehler <marius.brehler@gmail.com>
2025-09-30 16:08:50 -07:00
Marius Brehler 026a4e82a3 Rollup of build changes needed for compat with TheRock. (#1086)
* Rollup of build changes needed for compat with TheRock.
* When built for a non-default ROCM location, the HIP headers can't be found by a few targets.
* Uses pkg_check for DRM libraries like ROCR-Runtime does (which avoids accidental fallback to system versions).
* Robust fix for nolink targets
* nolink targets essentially exist for include directories
* all nolink targets are automatically added to rocprofiler-sdk-headers with a $<BUILD_INTERFACE:...> generator expression
* Re-add previously used mechanism to find drm libs

---------

Co-authored-by: Marius Brehler <marius.brehler@amd.com>
Co-authored-by: Stella Laurenzo <stellaraccident@gmail.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2025-09-30 18:39:10 -04:00
Jin Jung c6d44b47d4 Fix VulkanTest::CreateMappedStorage _WIN64 segfault (#1173)
* Fix VulkanTest::CreateMappedStorage _WIN64 segfault

* Fix Indentation
2025-09-30 14:52:05 -07:00
ywang103-amd eeeaa06159 attach/detach: change workload of unit test to accommodate SDK's current limitation (#1169)
* add double mode of workload dynamic_share with on remove sleeping and
set ROCP_TOOL_ATTACH=1 for running workload

* add comment in dynamic_shared.hip to exaplain how to use argv

* refactor the attach/detach profiling time in unit tests
2025-09-30 13:16:43 -07:00
abchoudh-amd f45c8d5f6b Bugfixes for test failure (#1106)
- Bugfixes
- Update test instructions using docker
2025-09-30 15:48:41 -04:00
Jason Bonnell 953fd60e9b rocprofiler GHCR Rename (#1112)
- Rename the GHCR packages for rocprofiler Docker images to reduce the number of packages that will be released on the repository
- Changed package name to only include the OS instead of OS+Version - version moved to the tag instead.
- Updated Dockerfile.*.ci files to specify target ROCm version from tarball in name.
2025-09-30 15:15:12 -04:00
Jason Bonnell cec7ce77d6 Add sudo apt-get update command to workflow (#1177)
- 404 Not Found errors when trying to download dependencies in the Get the latest therock build step. Adding `sudo apt-get update` command first to avoid this.
- Added `sudo apt-get update` to the rocprofiler-sdk-build-ci-docker-images.yml workflow.
2025-09-30 14:09:36 -04:00
Venkateshwar Reddy Kandula c441a87a00 [rocprofiler-sdk][RCCL] RCCL New API changes for RCCL_API_TRACE_VERSION_PATCH = 2 (#985)
- Address build issue with RCCL sync with NCCL commit: ROCm/rccl@08a7be2
- Patch Version Bump-up PR: ROCm/rccl#1916
2025-09-30 12:42:42 -04:00
systems-assistant[bot] d1ee1f0cba Upgrade binutils version from 2.42 to newer 2.44 version (#113)
* Upgrade binutils version from 2.42 to newer 2.44

---------

Co-authored-by: Marjan Antic <marantic@amd.com>
Co-authored-by: Sajina Kandy <sputhala@amd.com>
2025-09-29 14:50:33 -04:00
itrowbri 956daca743 [Docs][rocprofv3]Add Consecutive Kernels Parameter Description to Docs (#1111)
* Add consecutive kernels parameter description

* remove space

* Updated docs and CHANGELOG
2025-09-29 11:21:13 -05:00
David DeBonis d23d18f423 Adding usage tip for ignore cpu affinity (#1948)
* Adding usage tip for ignore cpu affinity

* Update docs/how-to/rccl-usage-tips.rst

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

* Update docs/how-to/rccl-usage-tips.rst

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

---------

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
2025-09-29 10:11:21 -06:00
Nilesh M Negi a15d1edaa3 [BUILD] Add rccl_compat.h to src/CMakeLists.txt (#152) 2025-09-28 13:33:33 -05:00
Bhuvan Mital 65b69bf318 changes for hugepages backed host buffer for larger allocations (#1841) 2025-09-28 00:40:22 -05:00
Artem Kuzmitckii 07925ec027 Revert disabling of context tracking for Radeon (#1927)
* Revert disabling of context tracking for Radeon

Original commit 6fc228e2
 `Disable context tracking for the current version. (#1839)`

* Add env variable for disabling of context tracking for Radeon

`export NCCL_DISABLE_CONTEXT_TRACKING=1` to force disable of context tracking

* Update docs/how-to/rccl-usage-tips.rst

Fix grammar, thanks @amd-jnovotny

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

* Rename NCCL_DISABLE_CONTEXT_TRACKING -> RCCL_DISABLE_CONTEXT_TRACKING

* Revert changes in includes and rename util function

---------

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
2025-09-27 15:19:50 -04:00
Ajay GunaShekar 81775169cc SWDEV-1 - hipcc args: --rocm-path to --hip-path in tests (#998) 2025-09-26 15:35:20 -07:00
Arif, Maisam 8758b8f75a [SWDEV-456192] Update process CLI help text (#720)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-09-26 17:33:01 -05:00
Arif, Maisam 9e57c34359 [SWDEV-456192] Update process CLI help text (#720)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 8758b8f75a]
2025-09-26 17:33:01 -05:00
Park, Peter 311eade5b1 docs: Update Doxygen, Sphinx, and readthedocs configs (#719)
* conf: update RTD config to ub24.04 (doxygen 1.9.8) and py3.12
* update generate-docs workflow
* Update "modules" to "topics" due to Doxygen 1.9.8
* bump rocm-docs-core to 1.25.0 and pip-compile requirements.txt
* doxygen: fill in version string in Doxyfile from conf.py
* remove unneeded rocm-smi-lib tutorials
* remove wikipedia references in doxyfile to satisfy ci check

Signed-off-by: Park, Peter <Peter.Park@amd.com>
2025-09-26 17:30:48 -05:00
Park, Peter 83bbbd55a3 docs: Update Doxygen, Sphinx, and readthedocs configs (#719)
* conf: update RTD config to ub24.04 (doxygen 1.9.8) and py3.12
* update generate-docs workflow
* Update "modules" to "topics" due to Doxygen 1.9.8
* bump rocm-docs-core to 1.25.0 and pip-compile requirements.txt
* doxygen: fill in version string in Doxyfile from conf.py
* remove unneeded rocm-smi-lib tutorials
* remove wikipedia references in doxyfile to satisfy ci check

Signed-off-by: Park, Peter <Peter.Park@amd.com>

[ROCm/amdsmi commit: 311eade5b1]
2025-09-26 17:30:48 -05:00
Mustafa Abduljabbar 0c94d4d2b3 Enable viewing algo/proto/channels used in rccl-tests output (#151)
* Enable algo/proto/channel viewing 

* Use dynamic symbol loading to avoid build/runtime issues with non-compatible RCCL versions

* Reduce code duplication
2025-09-26 18:09:01 -04:00
alex-breslow-amd 45166f6586 Gate code by rocm_version (#1945) 2025-09-26 13:28:41 -07:00
Laura Promberger fb3677cad6 fetch_sources: replace flags that the newer version recognizes (#1148)
* fetch_sources: replace flags that the newer version recognizes

* fetch_sources: remove --no-include-rocm-libraries
2025-09-26 11:36:28 -07:00
Maisam Arif e61eac1368 [SWDEV-538483] Fix amdsmi.h doc tag for amdsmi_set_power_cap
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I919eba1745990fd05ca3ff1077317e7b1244fded
2025-09-26 13:28:43 -05:00
Maisam Arif 0d00e3c5ab [SWDEV-538483] Fix amdsmi.h doc tag for amdsmi_set_power_cap
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I919eba1745990fd05ca3ff1077317e7b1244fded


[ROCm/amdsmi commit: e61eac1368]
2025-09-26 13:28:43 -05:00
amd-hsivasun c16b06a7d7 [Ex CI] Enable aqlprofile (#1002)
* [Ex CI] Enable aqlprofile

* [Ex CI] Added PipelineID for aqlprofile
2025-09-26 14:00:41 -04:00
Maisam Arif bd3579a1ac Create symbolic links instead of hard links
This unbreaks having sources on one mount point and builds at another.

Signed-off-by: Marius Brehler <marius.brehler@amd.com>
Change-Id: I68363112382a95baaa867cad91e09bdec2b30d90
2025-09-26 12:17:06 -05:00
Maisam Arif 28fbf0d74f Create symbolic links instead of hard links
This unbreaks having sources on one mount point and builds at another.

Signed-off-by: Marius Brehler <marius.brehler@amd.com>
Change-Id: I68363112382a95baaa867cad91e09bdec2b30d90


[ROCm/amdsmi commit: bd3579a1ac]
2025-09-26 12:17:06 -05:00
Rahul Manocha 538f1c3b74 SWDEV-556205 - fix segfault in hiprtc (#1058)
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
2025-09-26 09:06:37 -07:00
amd-hsivasun b4f4d24dda [Ex CI] Enable rdc (#941)
* [Ex CI] Enable rdc

* Reorder pipelineID list
2025-09-26 11:53:03 -04:00
Mustafa Abduljabbar 0dd2b2f65e Fix extra token typo (#1943) 2025-09-26 11:18:43 -04:00
Gerardo Hernandez e45c56c0f8 SWDEV-1 - if hipconfig process invocation by cmake fails, produce a readable error and abort
* SWDEV-1 - if platform auto-detection via hipconfig fails, provide a meaningful error and do not try to parse the output
* SWDEV-1 - if getting HIP_VERSION via hipconfig fails, provide a meaningful error and do not try to parse the output
2025-09-26 14:50:57 +01:00
German Andryeyev bb1295bcdf SWDEV-547108 - Fix compilation errors under Windows (#1085)
Also correct AQL print under Windows
2025-09-26 09:42:50 -04:00
Laura Promberger 3fd56bfefc Update TheRock CI to use health status script (#1130)
This will update the CI to match TheRocks CI by introducing to use a
python script to report on health status. Commands that were in the
section that modified the status were moved to separate sections
(ccache, git config, ..).

Related PR:
https://github.com/ROCm/TheRock/pull/1516
2025-09-26 10:09:31 +02:00
Maisam Arif 843dfaeed2 Removed unused version config files
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3b00a8c302615026422f6d5d602959989ee0418e
2025-09-25 18:19:14 -05:00
Maisam Arif 4fcf92ee14 Removed unused version config files
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3b00a8c302615026422f6d5d602959989ee0418e


[ROCm/amdsmi commit: 843dfaeed2]
2025-09-25 18:19:14 -05:00
Mario Limonciello ccfdb65b6f Set the SOVERSION in CMake from MAJOR/MINOR/RELEASE variables
Having the SOVERSION derived from the git tags doesn't scale well
for distributions that don't have the git history while building
(such as a tarball).

As part of e7d6590 the strings are parsed from a header.  Re-use
those.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-09-25 18:19:14 -05:00
Mario Limonciello ef8882b4bf Set the SOVERSION in CMake from MAJOR/MINOR/RELEASE variables
Having the SOVERSION derived from the git tags doesn't scale well
for distributions that don't have the git history while building
(such as a tarball).

As part of 8b96ee5 the strings are parsed from a header.  Re-use
those.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>


[ROCm/amdsmi commit: ccfdb65b6f]
2025-09-25 18:19:14 -05:00
Mustafa Abduljabbar 7a329bbd94 Expose symbols for RCCL algo/proto/channels selection functions (#1923)
* Unhide symbols for algo/proto functions

* Add all_gather direct usage detection
2025-09-25 18:58:30 -04:00
Maisam Arif df87246b40 Changed amd_smi_drm.cc to depend on dynamic libdrm
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ie8a794578da1a3ad8893d436e54bbfb67857a7ae
2025-09-25 17:40:05 -05:00
Maisam Arif f20ecc8512 Changed amd_smi_drm.cc to depend on dynamic libdrm
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ie8a794578da1a3ad8893d436e54bbfb67857a7ae


[ROCm/amdsmi commit: df87246b40]
2025-09-25 17:40:05 -05:00
Larry Meadows cb14fccdcc - LL Protocol: Add missing fences for gfx950, this fixes the hang issue (#1932)
- Remove asm flat_store_dwordx4, not needed
2025-09-25 14:07:07 -07:00
Rahul Manocha 2bc561d404 SWDEV-557057 - fix for datatype for hipMemcpy3DBatchAsync (#1114)
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
2025-09-25 13:53:23 -07:00
Bindhiya Kanangot Balakrishnan 3e7e4ab1ac [SWDEV-556005 & SWDEV-556853] Initialize temp-type map
Added back the temp-type map initialization to
RSMI_TEMP_TYPE_INVALID before probing hwmon files. This
prevents std::out_of_range for unsupported or absent
temperature sensor types.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-09-25 12:03:35 -05:00
Bindhiya Kanangot Balakrishnan f4b921c5f5 [SWDEV-556005 & SWDEV-556853] Initialize temp-type map
Added back the temp-type map initialization to
RSMI_TEMP_TYPE_INVALID before probing hwmon files. This
prevents std::out_of_range for unsupported or absent
temperature sensor types.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>


[ROCm/amdsmi commit: 3e7e4ab1ac]
2025-09-25 12:03:35 -05:00
Sourabh U Betigeri b24f922a24 SWDEV-552620 - Adds a new graph benchmark test for different topologies (#1073) 2025-09-25 09:50:10 -07:00
David Yat Sin cd48105282 rocr: Fix ext-fine-grain flag on host memory (#1067)
Fix for extended-fine-grain flag not set in thunk when
allocating host memory.
2025-09-25 11:10:43 -04:00
Godavarthy Surya, Anusha fb72d7f851 SWDEV-524746 - Part-II Add multi device support for hip graph. Updated kernel arg manager for each device (#813)
- Updated kernel arg manager to support allocating kernel args on multiple devices for single graph.
- Updated AQL path to capture on the device where graph node is added.

Co-authored-by: Anusha GodavarthySurya <Anusha.GodavarthySurya@amd.com>
2025-09-25 20:38:18 +05:30
MachineTom 4a31affb76 Users/taosang/SWDEV-510994 - Refractor atomics header and tests (#902)
* SWDEV-550626 - Refactor atomics header and tests

1. Introduce __HIP_ATOMIC_BACKWARD_COMPAT.
By default we define __HIP_ATOMIC_BACKWARD_COMPAT=1 to
let hip atomic functions maintain old assumptions. if
users want to adopt the new behavior, that is , by default
assume no-fine-grained no-remote-memory, then they can
define __HIP_ATOMIC_BACKWARD_COMPAT=0 and get the new
behaviour.

2. Use  __HIP_ATOMIC_BACKWARD_COMPAT_MEMORY to replace
original __HIP_FINE_GRAINED_MEMORY  in atomic header.
And apply __HIP_FINE_GRAINED_MEMORY onto all 
atomicXXX_system() functions to prevent failure on memory
allocated by hipHostMalloc().

3. Replace HIP_TEST_FINE_GRAINED_MEMORY with
HIP_TEST_ATOMIC_BACKWARD_COMPAT_MEMORY in hip-tests.

4. Fix negative test errors.
    Fix managed memory test error on memory order.
    some other minor changes.
    As a result  all originally disabled tests are enabled.

5. Add more atomics tests in some cases.

6. Reduce test time in each case.
     Reduce iteration number to 1 for tests that cost too much time.

8. Put common codes into hip_test_common.hh
2025-09-25 10:58:59 -04:00
systems-assistant[bot] becb4646bd SWDEV-546346 - [catch2][dtest] Tests for hipStreamSetAttribute and hipStreamGetAttribute (#524)
* SWDEV-546346 - [catch2][dtest] Tests for hipStreamSetAttribute and hipStreamGetAttribute

* SWDEV-546346 - Modified Kernel, added info statement

---------

Co-authored-by: Rambabu Swargam <rambabu.swargam@amd.com>
Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
2025-09-25 15:29:26 +05:30