Wykres commitów

74788 Commity

Autor SHA1 Wiadomość Data
Andryeyev, German 2305f8ae56 SWDEV-465041 - Add support for user events with DD (#321)
* SWDEV-465041 - Add support for user events with DD

User events can be replaced with HSA signals. Add the interface
to allocate HSA signal for user events and update the status on
CL_COMPLETE.
Force pinned path with DD to avoid blocking calls. Pinned memory
can be released only when the command is complete.
Simplify device enqueue path to use generic kernel arg buffer and
signals

* Fix notifyCmdQueue() logic for OCL

* Avoid blocking calls in OCL with DD

* Add event  destruciton in a case of the failure.
2025-08-12 19:04:36 -04:00
Joseph Macaranas 0ba726f8fc [GitHub Actions] Fix label typo (#322) 2025-08-12 17:56:50 -04:00
David Yat Sin a80c19285e rocminfo: Fix comparison to None (#313)
from PEP8 (https://peps.python.org/pep-0008/#programming-recommendations):

> Comparisons to singletons like None should always be done with
is or is not, never the equality operators.

Author: Eisuke Kawashima <e-kwsm@users.noreply.github.com>
2025-08-12 17:14:49 -04:00
Assiouras, Ioannis a7ed228997 SWDEV-543340 - Remove shared memory objects after IPC event cleanup (#745)
This change ensures that shared memory objects (e.g., files in /dev/shm)
are unlinked once all related IPC events have been destroyed.

[ROCm/clr commit: dc34af61d7]
2025-08-12 21:23:09 +01:00
Assiouras, Ioannis dc34af61d7 SWDEV-543340 - Remove shared memory objects after IPC event cleanup (#745)
This change ensures that shared memory objects (e.g., files in /dev/shm)
are unlinked once all related IPC events have been destroyed.
2025-08-12 21:23:09 +01:00
vedithal-amd 63f31859e4 Fix instruction cache metrics (#276)
* Fix IL1 Latency metric

* Add SQC_ICACHE_INFLIGHT_LEVEL counter and corresponding accumulation
  counter to counter definitions

* Add missing coll_level

* Fix descriptions and tests
2025-08-12 14:03:11 -04:00
Milan Radosavljevic b793b183a4 Update rocprofiler-systems github workflows (#193)
* Fix rocprofiler-systems CI

* Fix 'Documentation' jobs

* Python Linting fix

* Add python 3.11, 3.12

* Fix python linting

* Re-add ubuntu-noble workflow

* Remove old workflows from project folder

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

* Update rocprofiler-systems workflows

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

* Retire ubuntu-focal workflow

* Fix path to validation file in `build-docker.sh`

* Update .github/workflows/rocprofiler-systems-python.yml

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

* Revert dockerfile

* Retire rocprofiler-systems-ubuntu-focal workflow

* Include .github directory in cpack workflow sparse-checkout step

* Revert git from ubuntu ci image

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Signed-off-by: Jason Bonnell <Jason.Bonnell@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-08-12 19:42:01 +02:00
Chaudhary, Jatin Jaikishan 442468de96 SWDEV-545100 - rename the template variable (#798)
[ROCm/clr commit: 42730527c6]
2025-08-12 21:58:55 +05:30
Chaudhary, Jatin Jaikishan 42730527c6 SWDEV-545100 - rename the template variable (#798) 2025-08-12 21:58:55 +05:30
Chaudhary, Jatin Jaikishan 430f901b31 SWDEV-539481 - Add _rn variants of fp16 APIs (#582)
* Add _rn variants of fp16 APIs
* cover bf16 as well

[ROCm/clr commit: 4d5fe2206d]
2025-08-12 21:58:38 +05:30
Chaudhary, Jatin Jaikishan 4d5fe2206d SWDEV-539481 - Add _rn variants of fp16 APIs (#582)
* Add _rn variants of fp16 APIs
* cover bf16 as well
2025-08-12 21:58:38 +05:30
Gopesh Bhardwaj efb2aff8cf fix(ci): configure git safe directory before sphinx build (#309)
* fix(ci): configure git safe directory before sphinx build

* using  instead hardcoded path
2025-08-12 21:33:51 +05:30
xuchen-amd 9a4983feac Fix fstring formatting. (#315) 2025-08-12 11:54:58 -04:00
Giovanni Lenzi Baraldi cb77f5af5c Adding new trace decoder record types and new ATT parameters (#195)
* Adding new trace decoder record types and new ATT parameters

* Add compatiblity with decoder 0.1.2

* Added RT

* Format

* Add logging to sdata values

* Review comment

* Review comments

* Update projects/rocprofiler-sdk/source/include/rocprofiler-sdk/experimental/thread-trace/trace_decoder_types.h
2025-08-12 14:31:12 +02:00
systems-assistant[bot] 83971da05e Merge commit 'ea2d79c3e260d5728ecbc843f5367a12e9c301c4' into develop 2025-08-12 12:09:54 +00:00
systems-assistant[bot] 576faeac43 Merge commit 'c60888b0cd135739477e62d400a61138333f1b08' into develop 2025-08-12 12:09:52 +00:00
Dittakavi, Satyanvesh 526b46e9ba SWDEV-545947 - Add Nvidia mapping for hipSetValidDevices (#29)
[ROCm/hipother commit: 98ef2f64b5]
2025-08-12 16:30:30 +05:30
Dittakavi, Satyanvesh 98ef2f64b5 SWDEV-545947 - Add Nvidia mapping for hipSetValidDevices (#29) 2025-08-12 16:30:30 +05:30
Dittakavi, Satyanvesh 04c935d29c SWDEV-545947 - Add Implementation for hipSetValidDevices (#805)
[ROCm/clr commit: c60888b0cd]
2025-08-12 16:29:09 +05:30
Dittakavi, Satyanvesh c60888b0cd SWDEV-545947 - Add Implementation for hipSetValidDevices (#805) 2025-08-12 16:29:09 +05:30
Dittakavi, Satyanvesh 263a0bc57d SWDEV-540272 - copy params 3D struct should be populated even for memcpy 1D graph node (#702)
SWDEV-540272 - copy params 3D struct should be populated even for 1D graph node

[ROCm/clr commit: b50d70564e]
2025-08-12 16:21:53 +05:30
Dittakavi, Satyanvesh b50d70564e SWDEV-540272 - copy params 3D struct should be populated even for memcpy 1D graph node (#702)
SWDEV-540272 - copy params 3D struct should be populated even for 1D graph node
2025-08-12 16:21:53 +05:30
Chaudhary, Jatin Jaikishan 76f4ab5a79 SWDEV-540645 - use utility header for std::forward (#324)
[ROCm/hip commit: ea2d79c3e2]
2025-08-12 15:15:45 +05:30
Chaudhary, Jatin Jaikishan ea2d79c3e2 SWDEV-540645 - use utility header for std::forward (#324) 2025-08-12 15:15:45 +05:30
Chaudhary, Jatin Jaikishan 7fe61f9556 SWDEV-540645 - use single path for code object loading (#773)
* use single path for code object loading
* Remove printf
* Address review comments
* Fix the declaration of ihipMallocManaged

[ROCm/clr commit: d7f90a3120]
2025-08-12 15:15:18 +05:30
Chaudhary, Jatin Jaikishan d7f90a3120 SWDEV-540645 - use single path for code object loading (#773)
* use single path for code object loading
* Remove printf
* Address review comments
* Fix the declaration of ihipMallocManaged
2025-08-12 15:15:18 +05:30
systems-assistant[bot] d5d702a0cd Merge commit '0dde3ce5898815296008b8461a5396a5c3c25a07' into develop 2025-08-12 00:25:16 +00:00
systems-assistant[bot] 2dc8e2f2d4 Merge commit '0d9428135c73bd8d14432f1d8cd64076f5ebfea2' into develop 2025-08-12 00:25:14 +00:00
amd-jmacaran 5b1037d595 Migration update Aug 11 2025-08-11 18:50:59 -04:00
Joseph Macaranas 7e32efe995 Preserve file-path commit history. 2025-08-11 18:40:38 -04:00
Joseph Macaranas 5b82e2c765 Preserve file-path commit history. 2025-08-11 18:32:10 -04:00
Joseph Macaranas 762c088758 Add 'projects/rocm-core/' from commit '942821090f1a81d7ad55f910dffdba93c2cdca8a'
git-subtree-dir: projects/rocm-core
git-subtree-mainline: 92e841646c
git-subtree-split: 942821090f
2025-08-11 18:27:37 -04:00
Joseph Macaranas 92e841646c Reset adding rocm-core to super-repo 2025-08-11 18:26:52 -04:00
Joseph Macaranas d2de5fd30e Preserve file-path commit history. 2025-08-11 18:08:40 -04:00
Rahul Vaidya baa6a61535 [BUILD] Fix UT packaging on Debian family OS (#1854)
* Fix UT packaging on Debian family OSes

Signed-off-by: ravaidya <ravaidya@amd.com>

* Split OR condition when performing Debian checks

Signed-off-by: ravaidya <ravaidya@amd.com>

---------

Signed-off-by: ravaidya <ravaidya@amd.com>

[ROCm/rccl commit: ee9ed3ef87]
2025-08-11 17:03:16 -05:00
Rahul Vaidya ee9ed3ef87 [BUILD] Fix UT packaging on Debian family OS (#1854)
* Fix UT packaging on Debian family OSes

Signed-off-by: ravaidya <ravaidya@amd.com>

* Split OR condition when performing Debian checks

Signed-off-by: ravaidya <ravaidya@amd.com>

---------

Signed-off-by: ravaidya <ravaidya@amd.com>
2025-08-11 17:03:16 -05:00
xuchen-amd 0929e6ecc1 [rocprofiler-compute] Update amd smi lookup (#223) 2025-08-11 17:37:33 -04:00
Chris Sosa 584413b2cb Add CI Badge for tracking CI status in prep for gating changes (#1851)
This PR is intended to move RCCL to gating changes on CI failures. Right now, only build/unittests run per PR consistently. We should eventually add all single and multi-node test status badges once those tests are running in presubmit and continuously on develop

[ROCm/rccl commit: 53977821b5]
2025-08-11 14:02:46 -07:00
Chris Sosa 53977821b5 Add CI Badge for tracking CI status in prep for gating changes (#1851)
This PR is intended to move RCCL to gating changes on CI failures. Right now, only build/unittests run per PR consistently. We should eventually add all single and multi-node test status badges once those tests are running in presubmit and continuously on develop
2025-08-11 14:02:46 -07:00
Luo, Phoebe 17d12dff14 SWDEV-546504 - Improve Catch2 INFO Prints (#496)
SWDEV-546504 Added function to print output to terminal and a debug print that can be toggled

[ROCm/hip-tests commit: 0dde3ce589]
2025-08-11 13:53:04 -07:00
Luo, Phoebe 0dde3ce589 SWDEV-546504 - Improve Catch2 INFO Prints (#496)
SWDEV-546504 Added function to print output to terminal and a debug print that can be toggled
2025-08-11 13:53:04 -07:00
cfallows-amd 3258c69b60 Fix cmake formatting (#222)
Fix formatting of CMakeLists.txt for cmake-format check

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-08-11 16:40:09 -04:00
Ammar ELWazir 4d197f23b5 Fixing Docs for ROCProfiler SDK CI (#273)
* Fixing Docs for ROCProfiler SDK

* Fixing Docs for ROCProfiler SDK

* Fixing Docs for ROCProfiler SDK
2025-08-11 15:36:30 -05:00
Ammar ELWazir 4a9d201a4b ROCProfiler SDK Code Coverage Status (#260) 2025-08-11 14:54:33 -05:00
Ammar ELWazir 11362bb5a6 Fixing CDash AQLProfile (#252) 2025-08-11 14:42:12 -05:00
Ammar ELWazir 22c07f02da ROCProfiler CI Clean up & Testing (#240)
* CI Clean up & Testing

* CI Clean up & Testing
2025-08-11 14:26:09 -05:00
Dimple Prajapati 7436abeaa9 rocSHMEM device API changes for bitcode support (#211)
ROCSHMEM_CTX_DEFAULT's visibility needs to be explicitly set to expose that as external device global variable in device bitcode.

[ROCm/rocshmem commit: c952ffb40e]
2025-08-11 12:23:41 -07:00
Dimple Prajapati c952ffb40e rocSHMEM device API changes for bitcode support (#211)
ROCSHMEM_CTX_DEFAULT's visibility needs to be explicitly set to expose that as external device global variable in device bitcode.
2025-08-11 12:23:41 -07:00
akolliasAMD 1d7206d0d7 Added ability to build for local gpu by env Variable (#204)
* Added the ability to compile for Local gpu by environment variable

* adding gfx950 on default only on rocm 7.0 and above

* Updated docs

* removed xnack+ on specific gfx targets

---------

Co-authored-by: Yiltan Hassan Temucin <yiltan.temucin@amd.com>

[ROCm/rocshmem commit: be630d9b93]
2025-08-11 12:35:50 -06:00
akolliasAMD be630d9b93 Added ability to build for local gpu by env Variable (#204)
* Added the ability to compile for Local gpu by environment variable

* adding gfx950 on default only on rocm 7.0 and above

* Updated docs

* removed xnack+ on specific gfx targets

---------

Co-authored-by: Yiltan Hassan Temucin <yiltan.temucin@amd.com>
2025-08-11 12:35:50 -06:00