Граф коммитов

1387 Коммитов

Автор SHA1 Сообщение Дата
amd-srinivas1 e99bd0c783 SWDEV-546345-[catch2][dtest]-Added tests for hipMemcpy3DPeer Apis(Memory Management) (#897)
* SWDEV-546345-Added tests for hipMemcpy3DPeer apis

* SWDEV-546345-Removed nested SECTIONS.

* SWDEV-546345-Optimized the code.

* SWDEV-546345-Addressed Review comments

* SWDEV-546345-Added image check support

---------

Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
2025-10-23 14:40:13 +05:30
ywang103-amd 9b562c0e58 pc sampling multi kernel (#1382)
* initial commit

* add csv support extraction for non kernel selection mode

* add --kernel-trace for rocprofiler-sdk mode

* make non kernel selective mode runnable

* make kernel selection work with -k

* remove upper case of arg hint

* update documentation

* display same kernel name at only one place and merge instruction id with same obj id as well as offset

* remove kernel name's display for single kernel selection

* change log added

---------

Co-authored-by: Fei Zheng <44449748+feizheng10@users.noreply.github.com>
2025-10-23 01:26:08 -04:00
Gerardo Hernandez a128884078 SWDEV-541351 - query engine clock frequency via amdsmi to avoid clock tests being flaky (#1186) 2025-10-23 06:09:51 +01:00
Jimbo 37f2be9140 SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister (#962)
* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister

* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister

* SWDEV-554174 Added hipHostRegisterIoMemory flag in test cases

* SWDEV-554174 : Did formatting corrections

* SWDEV-554608 - set HSA_AMD_MEMORY_POOL_UNCACHED_FLAG if IoMemory is set

* SWDEV-554608 - set HSA_AMD_MEMORY_POOL_UNCACHED_FLAG if IoMemory is set

* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister

---------

Co-authored-by: Anavena Venkatesh <Anavena.Venkatesh@amd.com>
Co-authored-by: Rambabu Swargam <rambabu.swargam@amd.com>
2025-10-22 20:25:59 -04:00
Mark Meserve 79076c4ad5 attach: Cleanup docs from initial commmit (#1302)
- Remove unimplemented older API functions
- Remove mentions of reattach API
- Remove details on implementing a process attachment library
  - This will return later as a theory of operation
2025-10-22 16:16:49 -05:00
Todd tiantuo Li bc7898c687 SWDEV-556751 - skip Unit_hipEventRecord (#1239) 2025-10-22 13:49:22 -07:00
xuchen-amd 578589d363 [rocprofiler-compute] metrics generator (#1199) 2025-10-22 15:17:43 -04:00
David Galiffi e453705d9b Check if test exists before adding validation (#1478)
* Check if test exists before adding validation

* Adjust validation parameters for rocpd_string

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

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2025-10-22 12:19:38 -04:00
Swati Rawat 3808f7ea76 rocpd documentation improvements (#1498) 2025-10-22 11:59:22 -04:00
pcritchl-amd 63a991a8b9 SWDEV-543498 - Some compute Ubertrace profiles are missing queue timing data (#1146) 2025-10-22 08:56:33 -07:00
Jatin Chaudhary ee93c9ddab SWDEV-545100 - add two SPIRV targets (#1037) 2025-10-22 11:39:45 -04:00
solaiys eab103d4ed [RDHC] Update rocm-core package scripts to include rdhc script (#1482)
* Add rdhc script in to rocm-core package
  * Create the rdhc symlink within the package itself.
  * rdhc tool support is not enabled for windows.

  * [RDHC] Check if the required pip pkgs are present and warn .
     rdhc checks the required pip packages are present or not.
     if not warns the user and exits gracefully.

Signed-off-by: Saravanan Solaiyappan <saravanan.solaiyappan@amd.com>
2025-10-22 19:54:40 +05:30
marandje aa4dee57b5 SWDEV-555295 - Fix and enable Unit_hipFreeAsync_Negative_Parameters (#991) 2025-10-22 15:57:54 +02:00
Vladimir Indic 920b33c0b9 PCS: Temporarily Masking Trap Handler Latency (#1109)
- Temporarily, masking out the trap handler latency, by detecting
untagged error samples.
- Disabling checks for the number of invalid samples.
2025-10-22 14:18:08 +02:00
Ammar ELWazir 9cf8a5e0b5 [ROCProfiler-SDK] Remove Python library dependency from Python bindings (#1451) 2025-10-21 22:09:36 -05:00
arvindcheru 285061f05b Enhance ROCM-Core for Windows (#1467)
* Enhance Code for support for Windows cpp build
* Updated ROCM-Core README build steps
* File copyright Headers Updated
2025-10-21 23:04:23 -04:00
Kian Cossettini f0a41b65f7 [rocprofiler-systems] Add Fortran main detection to rocprof-sys-instrument to avoid instrumenting around C "main" wrapper (#1322)
* Add check for Fortran main

* Comment change

* MAIN__ -> Fortran main

* Cray Compiler comment change

* Add changelog and troubleshooting comments

* Improve CHANGELOG.md message

* Change CHANGELOG msg to be in 7.2.0

* Apply review change #1

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

* Apply review change #2

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

* Apply review change #3

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

---------

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-10-21 16:41:29 -04:00
systems-assistant[bot] bebe65f104 rocr: fix nullptr dereference (#262)
* rocr: fix nullptr dereference

Return early in the case that malloc fails to avoid dereferencing of a
null pointer on eventDescrp.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>

* rocr: Fix potential nullptr dereference

returns early if sym->section() fails to properly acquire the object.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>

---------

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Co-authored-by: Sunday Clement <Sunday.Clement@amd.com>
2025-10-21 13:49:01 -04:00
Jonathan R. Madsen 55ca813ded roctx annotation in mandelbrot benchmark (#1084) 2025-10-21 11:21:28 -05:00
Jonathan R. Madsen 6b0f87c3a6 [rocprofiler-sdk][rocpd] Optional message field in region/sample extdata (#1170) 2025-10-21 11:20:46 -05:00
David Yat Sin e2f3bd2429 Changes for RDMA with VMM (#801)
* rocr: Add support for VMM and RDMA

Add extra CPU mapping so that kernel-mode drivers can look up the memory
mapping by virtual address.

* Update projects/rocr-runtime/runtime/hsa-runtime/core/runtime/runtime.cpp

Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>

* Update projects/rocr-runtime/runtime/hsa-runtime/core/inc/runtime.h

Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>

* rocr: Honor uncache flag in memory_lock_to_pool()

Also, combined several flag options used in apis into a
single integer.

Signed-off-by: Chris Freehill <cfreehil@amd.com>

* rocr: Fix hsa_amd_pointer_info on CPU agents

Fix hsa_amd_pointer_info query returning allowd on VMM pointers for CPU
agents when CPU mapping was mapped with PROT_NONE.

---------

Signed-off-by: Chris Freehill <cfreehil@amd.com>
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>
Co-authored-by: Chris Freehill <cfreehil@amd.com>
Co-authored-by: cfreeamd <166262151+cfreeamd@users.noreply.github.com>
2025-10-21 12:19:02 -04:00
Sourabh U Betigeri 7926bd593b SWDEV-545245 - Adds new test for hipDeviceGetTExture1DLinearMaxWidth (#763) 2025-10-21 08:22:17 -07:00
Scott Todd 473025ab7d Revert "Update rocm-core package to include rdhc script (#1375)" (#1464)
This reverts commit d348797017.
2025-10-21 07:29:27 -07:00
Giovanni Lenzi Baraldi dbb48c3e33 Fix for dynamic code object loading in the thread trace sample (#1386)
* Fix for dynamic code object loading in the thread trace sample

* Review comments
2025-10-21 16:22:26 +02:00
cfallows-amd c215ace6c3 Update Roofline binaries with improved flops benchmarking (#1402)
* Update roof bins- rebuild from rocm-amdgpu-bench as of oct15/25

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

* Update CHANGELOG.md

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
2025-10-21 10:14:43 -04:00
jamessiddeley-amd a14f0c30ab fix output (#1462) 2025-10-21 09:55:18 -04:00
Fei Zheng 2c59a82fe1 Fix rocprof-compute TUI build err with python 39 (#303)
* Upgrade min python version from 3.8 to 3.9

* Set min version for textual-fspicker for TUI support

* Update workflows to use python 3.9 instead of 3.8

* fix formatting

* fix bug

---------

Co-authored-by: Vignesh Edithal <Vignesh.Edithal@amd.com>
2025-10-21 00:27:35 -04:00
Flora Cui a433e6f48d rocminfo: early detect absence of unsupported GPU in wsl (#1317)
Add an early check in WSL to detect when no supported GPU is available.
otherwise rocm_agent_enumerator will keep retrying rocminfo for one
minute, causing unnecessary delay.

Signed-off-by: Flora Cui <flora.cui@amd.com>
Co-authored-by: harkgill-amd <harkgill@amd.com>
2025-10-21 11:15:44 +08:00
Jonathan R. Madsen 4cca398b56 [rocprofiler-sdk] Update rocprofiler-sdk CONTRIBUTING.md (#1371) 2025-10-20 21:46:24 -05:00
David Galiffi 32f9fa6ca5 Enable some simple ROCpd testing (#834)
* Add for rocpd testing and output validation

Add for transpose, video-decode, jpeg-decode, roctx, and openmp-target
Add JSON check to pre-commit-config

Co-authored-by: Marjan Antic <Marjan.Antic@amd.com>

* Remove redundant environment variable

* Fix spelling typo

* Fix typo in error message

* Fix memory_allocation query

* Incorperate feedback from review. Handle case where there are multiple matching "name_prefix" tables.

* Fix environment settings in `rocprof-sys-testing.cmake`

Accidently removed in previous refactoring.

* Formatting python file

---------

Co-authored-by: Marjan Antic <Marjan.Antic@amd.com>
2025-10-20 17:40:10 -04:00
Ben Richard 35b07e041f [rocprof-compute] Run roofline test on GPU 0 by default (#1390)
* rocprof-compute: Default roofline to GPU 0

Previously was running the roofline test on ALL GPUs but only
selecting the first entry in the roofline.csv. So even in default
ALL case, GPU 0 was selected.

* Update CHANGELOG.MD

* Use better wording in changelog entry
2025-10-20 16:36:55 -04:00
Milan Radosavljevic 48fdcebf62 Add caching of category region for rocpd (#1420)
* Add caching of category region

Fix vaapi traces

Remove region_with_name

* Applied suggestions from code review
2025-10-20 16:05:14 -04:00
Ajay GunaShekar 4a1a4aa472 SWDEV-560725 - remove final from amd_warp_functions (#1395)
final word used as a literal over a keyword.
2025-10-20 12:27:59 -07:00
Pengda Xie 29c2ca8cbc SWDEV-559867 - Fix CU mask printing (#1328) 2025-10-20 09:47:17 -07:00
Ioannis Assiouras 30a14a8a05 SWDEV-559166 - Fix potential data race in ReferenceCountedObject::release() (#1388)
Use fetch_sub(std::memory_order_acq_rel) on release
so the destroying thread acquires prior writes.
2025-10-20 17:15:56 +01:00
systems-assistant[bot] ad3cb435ee SWDEV-507874 - Psdb perf: reduce test iterations (#618)
Change-Id: Ia9af40ecfb2ea121388a3c7a932805b49cef7669

Co-authored-by: agunashe <ajay.gunashekar@amd.com>
2025-10-20 09:00:05 -07:00
Julia Jiang ee4021d6c5 SWDEV-556212 - Update changelog for HIP 7.1 in develop (#1326)
* SWDEV-556212 - Update changelog for HIP 7.1 in develop

* Update CHANGELOG.md

* Update CHANGELOG.md
2025-10-20 11:41:58 -04:00
Danylo Lytovchenko 61fc256db9 Fix memsetD2XX tests (#1405)
* Fix memsetD2XX tests

* Remove redundant interpret_cast
2025-10-20 11:55:17 +02:00
randyh62 fd5ad25615 Add note for setting the HSA_SCRATCH_SINGLE_LIMIT (#1391) 2025-10-19 17:38:06 -07:00
systems-assistant[bot] ffb380a710 SWDEV-491279 - add stream capture test for ExternalMemory APIs (#570)
Co-authored-by: Li, Todd tiantuo <Toddtiantuo.Li@amd.com>
2025-10-17 16:32:00 -07:00
itrowbri e7a26594b7 [rocprofiler-sdk] Fix Stream ID Error for Attachment (#1142)
* Changed stream error warning, remove regex search from attach execute test

* Formatting

* Revert accidental change

* Fix stream hang error due to grabbing same lock twice

* Updated add stream code, need to update tests

* Update attachment tests to use streams, threads, and multiple devices

* Update tests and fix stream issues

* Updated error messages to be more explicit, updated json to csv code in conftest to include streams and threads

* Formatting

* Add attachment label to attachment tests and update validation to fix errors

* Fix attach twice conftest

* Disabled thread san tests for attachment since they no longer work with bin file changes

* Updated for comment

* Added null check for getting attach status
2025-10-17 16:34:05 -05:00
ajanicijamd 620ccbeb82 Reducing the number of iterations for lulesh tests (#1233) 2025-10-17 17:32:27 -04:00
Ammar ELWazir 3eb01da28d [ROCProfiler-SDK] [ROCProfiler-Register] Adding Correct Installation steps (#1150)
* Adding Correct Installation steps

* Update projects/rocprofiler-sdk/source/docs/install/installation.rst

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update projects/rocprofiler-sdk/source/docs/install/installation.rst

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-10-17 15:48:48 -05:00
cfreeamd 911a2f42c1 Revert "rocr: Don't assert in hsa_shut_down when no agents (#1115)" (#1312)
This reverts commit fb8ab442b6.
2025-10-17 08:36:06 -07:00
systems-assistant[bot] 6b109c11c4 [rocprofv3] Reorganize rocprofv3.avail python package (#175)
* Reorganize rocprofv3 python package

adding Python version candidates

review fix

fix test

fix

remove extra line

fix the exception handle

fix Lint fail

fix installation

adding checks to check version format

disable test for address sanitizer

* review comments

* Removing extra lines

* fix format

* Add lib/python3/site-packages to PYTHONPATH in setup-env.sh

* rocprof-compute update rocprofv3 avail lib path

* Make rocprofv3 python binding build commands consistent with other python bindings

* fix cmake

* fix rocprof-compute

* revert cmake changes

* fix rocprofv3 avail python library

* fix cmake

* fix cmake

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Sriraksha Nagaraj <Sriraksha.Nagaraj@amd.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: SrirakshaNag <104580803+SrirakshaNag@users.noreply.github.com>
Co-authored-by: Vignesh Edithal <Vignesh.Edithal@amd.com>
2025-10-17 08:27:17 -07:00
David Bélanger 02294e3852 kfdtest: Fix ExtendedCuMasking on GPUs with inactive CUs (#726)
Modify the code that computes the adjusted CU mask array to take
into account of additional cases for inactive CUs.

Signed-off-by: David Belanger <david.belanger@amd.com>
2025-10-17 08:26:12 -07:00
cfreeamd 9df655088f thunk: Correct kfd_ioctl_create_queue_args comment (#1235) 2025-10-17 08:25:51 -07:00
Julia Jiang 5919671102 SWDEV-560097 - Fix math API doc for __frcp_rn and __drcp_rn (#1393) 2025-10-17 11:20:39 -04:00
systems-assistant[bot] dae5b30a1a SWDEV-534207 - Solve more phoenix mem test failures (#545)
* SWDEV-534207 - fix 'Unit_hipFreeMipmappedArrayImplicitSyncArray - float' out of memory error with extent (1024, 1024, 1024) and 1 levels on 740M iGPUs. totalGlobalMem is not really the amount of device memory available for compute

* SWDEV-534207 - compare expected available memory within a range in Unit_hipMalloc3D_Basic; to take into account some bookkeeping overhead (instead of in exact 64MB chunks)

* SWDEV-534207 - fix missing setting of SvmGpuMemoryCreateInfo::interprocess in the 'fine' and 'fine uncached' memory and 'MemorySubAllocator' cases. Coarse allocation was added first; the flag was missed when the other three cases were added

* SWDEV-534207 - allow more room for the check of available memory after hipFree() in Unit_hipMalloc3D_Basic; it was till failing on 740M

---------

Co-authored-by: Gerardo Hernandez <gerardo.hernandez@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
2025-10-17 15:49:57 +01:00
Jason Bonnell 9664f1dc91 [rocprofiler-systems] Add retries to RHEL install steps (#1384)
* Add GHCR retry logic

* Add retries to Install ROCm Packages step in rocprofiler-systems-redhat.yml

* Update containers-ci.yml file to use latest RHEL9/10 releases

* Use build-docker-ci script in rocprofiler-systems-containers

* Remove working-directory from step in rocprofiler-systems-redhat.yml

* Remove shell bash from Install ROCm Packages step

* Revert RHEL version change in rocprofiler-systems-redhat.yml
2025-10-17 10:20:54 -04:00