AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
76,348 Commits 3 Branches 0 Tags
f227312867f9417cce3800a959de6bb587445a49
Commit Graph

76348 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
mberenjk 6743f00777 applying the changes from net_ib.cc to rocm_net_ib.cc to ensure DMABUF-disabled configurations are respected. (#2152) 
Co-authored-by: Marzieh Berenjkoub <mberenjk@amd.com>

[ROCm/rccl commit: 3d4813d991]
 2026-01-21 12:11:56 -08:00
mberenjk 3d4813d991 applying the changes from net_ib.cc to rocm_net_ib.cc to ensure DMABUF-disabled configurations are respected. (#2152) 
Co-authored-by: Marzieh Berenjkoub <mberenjk@amd.com>
 2026-01-21 12:11:56 -08:00
vedithal-amd 5fd976da70 Fix typo in Bypass Req metric in 17.3 section for MI350 (#2704) 2026-01-21 15:00:23 -05:00
mberenjk 7069fc936f Adding a check to respect DMABUF being disabled by the user (#2076) 
Co-authored-by: Marzieh Berenjkoub <mberenjk@.amd.com>

[ROCm/rccl commit: 9a443f3054]
 2026-01-21 11:08:12 -08:00
mberenjk 9a443f3054 Adding a check to respect DMABUF being disabled by the user (#2076) 
Co-authored-by: Marzieh Berenjkoub <mberenjk@.amd.com>
 2026-01-21 11:08:12 -08:00
Tao Sang 163e44d0a8 SWDEV-555889 - Support mipmap on rocr (#2082) 
* SWDEV-555889 - Support mipmap on rocr

Support mipmap in hip-rt on rocr backend.
Enable all mipmap tests in Windows.
Some other minor improvement.

Add some SRD logs that will be removed finally.

* Add sampler.mipFilter to fix sampler issues on mipmap in rocr.
Fix format issues of view of leveled image and  mipmap image in blit kernel in rocr.
Enabled disabled mipmap tests.

* Rewrite view logic

* Set word4.f.PITCH = 0 for mipmap SRD on navi31 to fix unstable test issues.
Reset last error in nagative tests.

* Remove SRD dump log from hip-rt
Let Rocr mipmap log be in condition.

* minor format chang

* Exclude mipmap tests for mi200+ which don't support mipmap.
 2026-01-21 09:10:29 -08:00
Sam Ruscica 5daeb14582 SWDEV-547291 - Interop for OpenGL (#2350) 
Updated to convert flags correctly

Added ObjectRegistry to track registered and mapped resources and incorporated it into hip_gl.

Added mip level check

Made functions static in-line

Reworked validation to be more clear.
 2026-01-21 09:08:55 -08:00
Nilesh M Negi 244047310e [DEVICE] Switch to amd-smi from rocm-smi (#1759) 
* Use amd-smi instead of rocm-smi for ROCM_VERSION >= 7.11.0

[ROCm/rccl commit: cd745b1f4b]
 2026-01-21 09:05:47 -06:00
Nilesh M Negi cd745b1f4b [DEVICE] Switch to amd-smi from rocm-smi (#1759) 
* Use amd-smi instead of rocm-smi for ROCM_VERSION >= 7.11.0
 2026-01-21 09:05:47 -06:00
Gopesh Bhardwaj c563286f96 Update changelog for ROCprofiler-SDK 1.1.0 (#2717) 
using only arch name
 2026-01-21 20:15:39 +05:30
Kian Cossettini 28b2ade7d2 Update mentions of OpenMP to reflect newer implementation (#2701) 
Update timemory examples in docs to use the `rocprofiler-sdk` API.
 2026-01-21 07:18:51 -05:00
Jatin Chaudhary 0590a72d4b Rework clock based unit tests (#2646) 2026-01-21 10:55:33 +00:00
hongkzha-amd d94185c5b2 rocrtst: set HSA_ENABLE_INTERRUPT after TestExample creation (#2687) 
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
Co-authored-by: cfreeamd <166262151+cfreeamd@users.noreply.github.com>
 2026-01-21 10:39:50 +08:00
Karthik Jayaprakash 6a84a00208 Use size_t datatype for global dimensions. (#2604) 2026-01-20 20:39:07 -05:00
JeniferC99 50e00d1b94 Update CODEOWNERS (#2705): add /project/amdsmi owner 2026-01-20 15:49:59 -08:00
yugang-amd 05a6d017c6 [ROCmInfo] docs: mono-repo changes and style edits (#2584) 
* initial edits

* mono repo related updates

* standardize component name

* style edits

* more edits
 2026-01-20 18:06:54 -05:00
Yiltan 55aab4d62e [Docs] Clarify ROCSHMEM_HEAP_SIZE (#392) 
* clarify ROCSHMEM_HEAP_SIZE

* Apply suggestions from code review

Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>

---------

Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>

[ROCm/rocshmem commit: 0496586829]
 2026-01-20 17:22:18 -05:00
Yiltan 0496586829 [Docs] Clarify ROCSHMEM_HEAP_SIZE (#392) 
* clarify ROCSHMEM_HEAP_SIZE

* Apply suggestions from code review

Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>

---------

Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
 2026-01-20 17:22:18 -05:00
prasanna-amd 520f309bb1 fix potential segfaults due to use after malloc fails (#2137) 
* fix potential segfaults

* replace NULL with nullptr

---------

Co-authored-by: Prasannakumar Murugesan <prmuruge@amd.com>

[ROCm/rccl commit: 4a32ec2501]
 2026-01-20 14:11:29 -08:00
prasanna-amd 4a32ec2501 fix potential segfaults due to use after malloc fails (#2137) 
* fix potential segfaults

* replace NULL with nullptr

---------

Co-authored-by: Prasannakumar Murugesan <prmuruge@amd.com>
 2026-01-20 14:11:29 -08:00
prasanna-amd bb47eee7cc fix bug in reduce kernel bfloat16 for ROCm >= 6.0 (#2139) 
Co-authored-by: Prasannakumar Murugesan <prmuruge@amd.com>
As part of an earlier commit, bfloat16 handling in reduce kernel for FuncMinMax fell into generic/default template when there is no SPECIALIZE_REDUCE for a particular type, this generic template does a bitwise integer comparison and it broke bfloat16 ops.
change the else-if statement to else statement, that way it covers both ROCm version < 6.0 and >= 6.0 (with ROCm > 6.0, device.h already typedefs __hip_bfloat16 to hip_bfloat16, so no special case is needed here).

[ROCm/rccl commit: fa366ac03f]
 2026-01-20 14:07:20 -08:00
prasanna-amd fa366ac03f fix bug in reduce kernel bfloat16 for ROCm >= 6.0 (#2139) 
Co-authored-by: Prasannakumar Murugesan <prmuruge@amd.com>
As part of an earlier commit, bfloat16 handling in reduce kernel for FuncMinMax fell into generic/default template when there is no SPECIALIZE_REDUCE for a particular type, this generic template does a bitwise integer comparison and it broke bfloat16 ops.
change the else-if statement to else statement, that way it covers both ROCm version < 6.0 and >= 6.0 (with ROCm > 6.0, device.h already typedefs __hip_bfloat16 to hip_bfloat16, so no special case is needed here).
 2026-01-20 14:07:20 -08:00
dependabot[bot] 48d1530205 Bump pynacl from 1.5.0 to 1.6.2 in /docs/sphinx (#2127) 
Bumps [pynacl](https://github.com/pyca/pynacl) from 1.5.0 to 1.6.2.
- [Changelog](https://github.com/pyca/pynacl/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pyca/pynacl/compare/1.5.0...1.6.2)

---
updated-dependencies:
- dependency-name: pynacl
  dependency-version: 1.6.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>

[ROCm/rccl commit: f38665ac9a]
 2026-01-20 14:30:10 -07:00
dependabot[bot] f38665ac9a Bump pynacl from 1.5.0 to 1.6.2 in /docs/sphinx (#2127) 
Bumps [pynacl](https://github.com/pyca/pynacl) from 1.5.0 to 1.6.2.
- [Changelog](https://github.com/pyca/pynacl/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pyca/pynacl/compare/1.5.0...1.6.2)

---
updated-dependencies:
- dependency-name: pynacl
  dependency-version: 1.6.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>
 2026-01-20 14:30:10 -07:00
dependabot[bot] c2fd82c02d Bump rocm-docs-core from 1.26.0 to 1.29.0 in /docs/sphinx (#2051) 
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.26.0 to 1.29.0.
- [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/v1.26.0...v1.29.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-version: 1.29.0
  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>
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

[ROCm/rccl commit: 131900c264]
 2026-01-20 14:28:59 -07:00
dependabot[bot] 131900c264 Bump rocm-docs-core from 1.26.0 to 1.29.0 in /docs/sphinx (#2051) 
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.26.0 to 1.29.0.
- [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/v1.26.0...v1.29.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-version: 1.29.0
  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>
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>
 2026-01-20 14:28:59 -07:00
dependabot[bot] a1bb4108c1 Bump urllib3 from 2.5.0 to 2.6.3 in /docs/sphinx (#2130) 
Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.5.0 to 2.6.3.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/2.5.0...2.6.3)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-version: 2.6.3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>

[ROCm/rccl commit: d94ecb7772]
 2026-01-20 14:27:31 -07:00
dependabot[bot] d94ecb7772 Bump urllib3 from 2.5.0 to 2.6.3 in /docs/sphinx (#2130) 
Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.5.0 to 2.6.3.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/2.5.0...2.6.3)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-version: 2.6.3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>
 2026-01-20 14:27:31 -07:00
Mythreya Kuricheti 73df3f12b3 use message instead of warning for nccl.h C++ check (#2128) 
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>

[ROCm/rccl commit: 0dc31b1a4a]
 2026-01-20 14:21:38 -07:00
Mythreya Kuricheti 0dc31b1a4a use message instead of warning for nccl.h C++ check (#2128) 
Co-authored-by: Corey Derochie <161367113+corey-derochie-amd@users.noreply.github.com>
 2026-01-20 14:21:38 -07:00
Kian Cossettini 7c9361190b [rocprofiler-systems] Fix MPI recv_data calculation (#2694) 
Fix incorrect `mpi_recv` calculation. It was using `_send_size` instead of `_recv_size` for `mpi_recv`.
 2026-01-20 16:17:22 -05:00
Allen Hubbe 3edd56ca23 gda ionic: ccqe cleanup and error check (#389) 
Delete unreachable ccqe polling path, ionic_poll_wave_ccqe().
Move cqe error check to ionic_quiet_internal_ccqe().

Signed-off-by: Allen Hubbe <allen.hubbe@amd.com>

[ROCm/rocshmem commit: 6b00964f32]
 2026-01-20 15:26:53 -05:00
Allen Hubbe 6b00964f32 gda ionic: ccqe cleanup and error check (#389) 
Delete unreachable ccqe polling path, ionic_poll_wave_ccqe().
Move cqe error check to ionic_quiet_internal_ccqe().

Signed-off-by: Allen Hubbe <allen.hubbe@amd.com>
 2026-01-20 15:26:53 -05:00
Nusrat Islam 96f6029a1b revert memcpy use for direct AG (#2146) 
Co-authored-by: Islam <nusislam@amd.com>

[ROCm/rccl commit: f3c5156bbf]
 2026-01-20 13:58:28 -06:00
Nusrat Islam f3c5156bbf revert memcpy use for direct AG (#2146) 
Co-authored-by: Islam <nusislam@amd.com>
 2026-01-20 13:58:28 -06:00
German Andryeyev db792fac37 SWDEV-558849 - Add support for static linking with ROCR (#2659) 2026-01-20 14:53:01 -05:00
mberenjk 9ee8fb0aa9 Merge pull request #2136 from mberenjk/mberenjk/nccl-sync-2.28.3 
Merge remote-tracking branch 'nccl/master' 2.28.3 into develop

[ROCm/rccl commit: 2fdcceaabb]
 2026-01-20 11:38:11 -08:00
mberenjk 2fdcceaabb Merge pull request #2136 from mberenjk/mberenjk/nccl-sync-2.28.3 
Merge remote-tracking branch 'nccl/master' 2.28.3 into develop
 2026-01-20 11:38:11 -08:00
Alysa Liu 9139f5a241 Revert "rocr: Switch back to legacy IPC (#1744)" (#2676) 
This reverts commit 7e4b62290c.
 2026-01-20 14:34:10 -05:00
dependabot[bot] 33e37797e6 Docs - Bump rocm-docs-core[api_reference] from 1.31.2 to 1.31.3 in /docs/sphinx (#220) 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.31.2 to 1.31.3.
- [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/v1.31.2...v1.31.3)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-version: 1.31.3
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

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

[ROCm/rocjpeg commit: a428bae524]
 2026-01-20 11:15:12 -08:00
dependabot[bot] a428bae524 Docs - Bump rocm-docs-core[api_reference] from 1.31.2 to 1.31.3 in /docs/sphinx (#220) 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.31.2 to 1.31.3.
- [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/v1.31.2...v1.31.3)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-version: 1.31.3
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-01-20 11:15:12 -08:00
Marzieh Berenjkoub d7293281f3 Merge remote-tracking branch 'nccl/master' into develop 
[ROCm/rccl commit: 858b4e76eb]
 2026-01-20 13:04:02 -06:00
Marzieh Berenjkoub 858b4e76eb Merge remote-tracking branch 'nccl/master' into develop 2026-01-20 13:04:02 -06:00
Ioannis Assiouras 59aa56a340 hip-issue-3876 : Take into account thread-local capture mode in checks for valid capture (#2177) 2026-01-20 18:42:27 +00:00
Sajina PK 15c82d6da8 [rocprofiler-system]: Enable UCX Communication API tracing (#2306) 
## Motivation

Enable UCX communication tracing and communication metadata 

## Technical Details

Implement UCX API wrappers to trace transport-layer communication. This adds communication data tracking and exposes “UCX Comm Send/Recv” timelines, enabling detailed analysis of MPI, OpenSHMEM, and other UCX-based runtime communication patterns.

- Implements function interception for UCX functions across multiple categories using gotcha component.
- Extended comm_data component to track UCX send/recv operations - Added ucx_send and ucx_recv labels for Perfetto counter tracks. Integrated UCX data tracking with existing MPI/RCCL tracking infrastructure.
- Added ROCPROFSYS_USE_UCX configuration option (enabled by default).
- Created FindUCX.cmake module for UCX header detection. Falls back to internal UCX headers if system headers not found.
- Updated all Dockerfiles  to include UCX dependencies.
 2026-01-20 13:16:43 -05:00
Bindhiya Kanangot Balakrishnan 72f0a41658 [SWDEV-559965] Update Changelog for power cap type (#2647) 
* [SWDEV-559965] Update Changelog for amd-smi set --power-cap

Updated Changelog to mention flexible argument
ordering for power cap type in amdsmi power cap set.
Corrected Changelog documentation on PPT1 reset
power_cap command.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
 2026-01-20 11:28:09 -06:00
Rakesh Roy 5049efdd75 Reset HIP_VERSION_PATCH to 0 (#2590) 2026-01-20 22:54:20 +05:30
Kian Cossettini 698ac6b8bc [rocprofiler-systems] Add build option for "examples" to specify gfx-arch (#2626) 
## Motivation
 - Added `check_rocminfo` function that returns true if the provided regex was found, false otherwise. Can also use `GET_OUTPUT` to get the raw output filtered with or without a regex.
 - Moved `rocprofiler_systems_get_gfx_archs()` to `MacroUtilities.cmake` 
 - Added `rocprofiler_systems_lookup_gfx()`, which detects whether a given `gfx` is from the `instinct`, `radeon` or `apu` family.
 - Added `ROCPROFSYS_GFX_TARGETS` as a build argument. Used to specify the offloading architectures that GPU examples should compile for. If empty, defaults to whatever your system has.
 - GPU examples now check if the given `gfx` targets (from `ROCPROFSYS_GFX_TARGETS`) are supported.
 - OMPVV offload tests now only compile if `amdflang` version is `>= 20`
 - Improve link time by reducing the number of GFX targets that binaries need to support.
   - RCCL is now passed a `GPU_TARGETS` var specifying the architectures to build/link against.
 2026-01-20 12:13:21 -05:00
German Andryeyev 3af2bf4952 Merge branch 'develop' into amd/dev/gandryey/SWDEV-558849 2026-01-20 12:04:53 -05:00
vedithal-amd 4a5cbbfba5 [rocprofiler-compute] Fix kernel/dispatch filtering (#2479) 
* Fix kernel/dispatch fitlering in GUI

* Disallow --kernel and --dispatch filtering in analyze --gui mode since
  GUI frontend offers dropdown menu for kernel and dispatch filtering
    * Update CHANGELOG and documentation

* Gracefully handle N/A values

* Ensure workload path is valid before using it in GUI

* Ignore kernel filters if dispatch filters provided

* Add documentation for dispatch filtering overriding kernel filtering

* Fix typo

* Fix documentation

* remove unnecessary whitespace

* Address review comments

* Allow kernel/dispatch filtering with --gui

* Address review comments

* Address review comments

* Update CHANGELOG

* Fix formatting
 2026-01-20 10:02:31 -05:00