Commit Graph

68629 Commits

Author SHA1 Message Date
systems-assistant[bot] 05a9a528f7 SWDEV-548482 - Address memory leaks in memory tests (#526)
* SWDEV-548482 - Address memory leaks in memory tests

* SWDEV-548482 - Added destroy calls

* SWDEV-548482 - Address one more memory leak

* SWDEV-548482 - Minor tweaks

* SWDEV-548482 - Run clang-format

* SWDEV-548482 - Add new lines

* SWDEV-548482 - Run clang-format

* SWDEV-548482 - Minor fix

---------

Co-authored-by: Marko Arandjelovic <Marko.Arandjelovic@amd.com>
2025-09-02 17:29:29 +02:00
jamessiddeley-amd f3a2bb07a4 [rocprofiler-compute] added ctest coverage and cdash submission (#366)
* added cdash automatic CI upload

* added cdash automatic CI upload

* tweaked wording

* changed nightly to continuous

* removed unnecessary dry-run arg

* updated README.md

* edited workflow description

* update coverage

* formatted cmakelists.txt

* ruff formatting and update coverage
2025-09-02 11:21:40 -04:00
systems-assistant[bot] bfbb005c42 SWDEV-491252 - Add stream capture testcases to host allocation APIs (#590)
* SWDEV-491252 - Add stream capture testcases to host allocation APIs

* SWDEV-491252 - Add stream capture behavior testcase for hipFreeHost

* SWDEV-491252 - Refactor capture testcases

* SWDEV-491252 - Run clang-format

---------

Co-authored-by: Marko Arandjelovic <Marko.Arandjelovic@amd.com>
2025-09-02 16:58:02 +02:00
systems-assistant[bot] 0468340d03 SWDEV-524815 - Specify path to hipconfig.exe instead of hipconfig on windows (#421)
Co-authored-by: Ioannis Assiouras <Ioannis.Assiouras@amd.com>
2025-09-02 15:15:26 +01:00
Ioannis Assiouras a1c30318fb SWDEV-546223 - Get image support info from ISA meta (#773) 2025-09-02 15:05:18 +01:00
systems-assistant[bot] ae874b489d SWDEV-515530 - Re-enable passing tests (#592)
* SWDEV-515530 - Re-enable passing tests

* SWDEV-515530 - Revert back windows config file

* SWDEV-515530 - Fix new line

* SWDEV-515530 - Enable a few more tests

* SWDEV-515530 - Enable passing VMM tests

* SWDEV-515530 - Disable failing tests

* SWDEV-515530 - Fix and enable texture tests

* SWDEV-515530 - Minor fixes

* SWDEV-515530 - Disable one more test

---------

Co-authored-by: Marko Arandjelovic <Marko.Arandjelovic@amd.com>
2025-09-02 16:03:07 +02:00
Mythreya Kuricheti 43ac6b2ef5 [rocprofiler-sdk] Add support for new RCCL API (#771)
* [rocprofiler-sdk] Add support for new RCCL API

Add support for `ncclAllReduceWithBias`

* Move func to be in sync with rccl header
2025-09-02 16:17:44 +05:30
systems-assistant[bot] 4174508dcc SWDEV-545953 - Tests for hipStreamGetId (#529)
Co-authored-by: Satyanvesh Dittakavi <Satyanvesh.Dittakavi@amd.com>
Co-authored-by: ammallya <ameyakeshava.mallya@amd.com>
Co-authored-by: swargamrambabu <rambabu.swargam@amd.com>
Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
2025-08-29 16:07:01 +05:30
Maisam Arif 2c9f3af026 [SWDEV-540665] Change parser to not accept 0 as a power set input
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I510fa5523b8dd7ea33f49e21cc199d4a2cfcf9bb
2025-08-29 04:18:36 -05:00
Maisam Arif db443c025c [SWDEV-540665] Change parser to not accept 0 as a power set input
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I510fa5523b8dd7ea33f49e21cc199d4a2cfcf9bb


[ROCm/amdsmi commit: 2c9f3af026]
2025-08-29 04:18:36 -05:00
ammallya df11d9dcc2 Remove shared to run PSDB 2025-08-28 15:16:03 -07:00
habajpai-amd cd729ab630 Improve library discovery in openmp-target example (#792)
cmake(openmp/target): make libomptarget discovery robust across ROCm layouts
2025-08-28 14:55:55 -04:00
ammallya c10ebdf94c Changing conditional statements 2025-08-28 10:55:35 -07:00
ammallya 5818c3e062 Adding debug statement 2025-08-28 10:44:36 -07:00
ammallya 2e1b6063a7 Change failing checkout logic 2025-08-28 10:25:27 -07:00
ammallya a6e1f61c45 Adding Auth 2025-08-28 10:03:48 -07:00
ammallya cba3213f41 Fix rocm_ci_caller 2025-08-28 09:55:52 -07:00
ammallya f40c04be62 Selective trigger of PSDB jobs (#783)
* Selective trigger of PSDB jobs
2025-08-28 09:50:11 -07:00
gabrpham 94e194eba2 [SWDEV-540377] Fixed segfault in --showevent command (#649)
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
2025-08-28 11:49:36 -05:00
gabrpham_amdeng 39b26104d4 reverted help formatting column width to 80
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
2025-08-28 11:30:24 -05:00
gabrpham_amdeng 51c2ea4731 reverted help formatting column width to 80
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 39b26104d4]
2025-08-28 11:30:24 -05:00
Sam Ruscica 9018e0fc7b SWDEV-546639 monorepo fix for nvidia hip runtime api (#746)
* SWDEV-546639 monorepo fix for nvidia hip runtime api

* Added back hipSetValidDevices.
2025-08-28 09:03:37 -07:00
Tim Huang 51a44bc0c4 Regenerate Rust bindings against latest amdsmi.h header
- Regenerate Rust wrapper against latest amdsmi.h header
- Add libc dependency for proper C memory management
- Fix compilation errors caused by types removed from amdsmi.h
- Add FFI bindings regeneration documentation in README

This update ensures the Rust bindings are synchronized with the latest
C API and provides guidance for developers on regenerating
Bindings.

Signed-off-by: Tim Huang <tim.huang@amd.com>
2025-08-28 09:34:57 -05:00
Tim Huang c3f5771541 Regenerate Rust bindings against latest amdsmi.h header
- Regenerate Rust wrapper against latest amdsmi.h header
- Add libc dependency for proper C memory management
- Fix compilation errors caused by types removed from amdsmi.h
- Add FFI bindings regeneration documentation in README

This update ensures the Rust bindings are synchronized with the latest
C API and provides guidance for developers on regenerating
Bindings.

Signed-off-by: Tim Huang <tim.huang@amd.com>


[ROCm/amdsmi commit: 51a44bc0c4]
2025-08-28 09:34:57 -05:00
usrihari123 2449bfd483 Update the scratch memory docs with the new allocation_size field (#685)
* Update the scratch memory docs with the new allocation_size field

* Address review comment

---------

Co-authored-by: Srihari <srihariu1@gmail.com>
2025-08-28 17:37:06 +05:30
Ioannis Assiouras 1017532916 SWDEV-546631 - Fix hipLaunchHostFunction in stream capture for windows (#654) 2025-08-28 07:51:50 +01:00
Maisam Arif 4ffa468613 [SWDEV-540665] Remove amdsmi_set_power_cap API Guest Restriction
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I682506b48c10eefbd04f9b494ad57fb8ae8842b0
2025-08-27 20:18:43 -05:00
Maisam Arif ed3e242202 [SWDEV-540665] Remove amdsmi_set_power_cap API Guest Restriction
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I682506b48c10eefbd04f9b494ad57fb8ae8842b0


[ROCm/amdsmi commit: 4ffa468613]
2025-08-27 20:18:43 -05:00
Arif, Maisam ed2300516f Revert "[SWDEV-536176] libdrm_amdgpu depdency change (#448)"
This reverts commit 652761de54.
2025-08-27 20:11:17 -05:00
Arif, Maisam 433893c770 Revert "[SWDEV-536176] libdrm_amdgpu depdency change (#448)"
This reverts commit 4d33e79baa.


[ROCm/amdsmi commit: ed2300516f]
2025-08-27 20:11:17 -05:00
itrowbri 4d98a0169f Handle special cases when stream value is hipStreamLegacy (0x01) or hipStreamPerThread (0x02) (#343)
* Updated stream code to handle special cases when stream value is 0x01 or 0x02

* Removed extra definitions and updated tests to account for special case

* Modified stream.cpp so that each thread assigned a unique stream ID when hipStreamPerThread is used as stream value. Modified tests to check that threads are assigned unique, repeated values when hipStreamPerThread is called

* Updated idx_offset, stream_map, and thread counter to be in one struct.

* Update stream.cpp to only use add_stream() and update tests for seperate unit test for hipStreamPerThread

* Remove unecessary comment

* Removed unecessary line

* Updated tests and stream.cpp to update stream ID correctly

* Updated test structure
2025-08-27 20:04:13 -05:00
Oosman Saeed 594d5ce8ee [SWDEV-546239] Match amdsmi output with host output 2025-08-27 18:41:59 -05:00
Oosman Saeed 190ed3953d [SWDEV-546239] Match amdsmi output with host output
[ROCm/amdsmi commit: 594d5ce8ee]
2025-08-27 18:41:59 -05:00
Maisam Arif 978fad01d2 [SWDEV-544299] Fix CLI prefix for amd-smi metric -G
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ic184ec824213421388356417e713d9ed5adeddeb
2025-08-27 18:08:06 -05:00
Maisam Arif 8d5335a8de [SWDEV-544299] Fix CLI prefix for amd-smi metric -G
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ic184ec824213421388356417e713d9ed5adeddeb


[ROCm/amdsmi commit: 978fad01d2]
2025-08-27 18:08:06 -05:00
Arif, Maisam 286c421a49 [SWDEV-552378] Removed First enums in amdsmi_interface.py (#659)
- **Fixed gpuboard and baseboard temperatures enums in amdsmi Python Library**.  
  - AmdSmiTemperatureType had issues with referencing the right attribute, so we removed the following duplicate enums:
    - `AmdSmiTemperatureType.GPUBOARD_NODE_FIRST`
    - `AmdSmiTemperatureType.GPUBOARD_VR_FIRST`
    - `AmdSmiTemperatureType.BASEBOARD_FIRST`

Change-Id: Ia61446b593bd9182d597c4b4c2ac3c5ffdae7493
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-08-27 18:07:17 -05:00
Arif, Maisam 46a2ef944f [SWDEV-552378] Removed First enums in amdsmi_interface.py (#659)
- **Fixed gpuboard and baseboard temperatures enums in amdsmi Python Library**.  
  - AmdSmiTemperatureType had issues with referencing the right attribute, so we removed the following duplicate enums:
    - `AmdSmiTemperatureType.GPUBOARD_NODE_FIRST`
    - `AmdSmiTemperatureType.GPUBOARD_VR_FIRST`
    - `AmdSmiTemperatureType.BASEBOARD_FIRST`

Change-Id: Ia61446b593bd9182d597c4b4c2ac3c5ffdae7493
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 286c421a49]
2025-08-27 18:07:17 -05:00
Julia Jiang 9aaad2017b SWDEV-525231 - Update changelog for 7.0 (#768) 2025-08-27 16:10:31 -04:00
Ioannis Assiouras 5f525ee934 SWDEV-550882 - Expect HSA_EXT_POINTER_TYPE_RESERVED_ADDR pointer type from hsa_amd_pointer_info for hmm (#733) 2025-08-27 19:42:13 +01:00
Karthik Jayaprakash 89070536c0 SWDEV-552141 - Fix handle/fd type passed from app to align with spec. (#759)
* SWDEV-552141 - Fix handle/fd type passed from app to align with spec.

* SWDEV-552141 - Fix handle/fd type passed from app to align with spec.
2025-08-27 14:28:53 -04:00
jonatluu 6bc1ea966f fix lintian warning (#696)
* fix lintian warning

* fix lintian warning
2025-08-27 13:53:54 -04:00
cfallows-amd c68ba44e72 Add single kernel filtering to roofline plots (#757)
* Add single kernel filtering for roofline
* Add --kernel to documentation
* Add kernel labels to roofline pdfs

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

* Add test cases

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

* Add autodetect for mode (profile or analyze) during roof validate and filter
Prevent --kernel from affecting roofline in gui mode- although this may be broken in develop branch anyways

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

* Add note about roof-only usage checking for existing profiling files in the dir. If roof-only is not provided, rocprof-compute currently assumes it has to profile in full regardless. Will look into this another day.

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

* Update CHANGELOG.md

Add line in resolved issues section to highlight that kernel filtering is now working for roofline plots

* Apply changes suggested by docs team

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

* Update projects/rocprofiler-compute/CHANGELOG.md

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

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
2025-08-27 13:41:07 -04:00
systems-assistant[bot] 2e50d88fe6 [ROCProfiler SDK] Removing regex from the tool and output libraries (#170)
* Removing regex from the tool

* Adding alternative for regex regarding  handling

* Adding ROCpd

* Removing regex include

* Apply suggestion from @jomadsen_amdeng

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>

* Apply suggestion from @jomadsen_amdeng

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>

* Apply suggestion from @jomadsen_amdeng

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>

* Adding Standalone Regex Header File

* Fixing Regex to handle grouping and

* Fixing Regex to handle grouping and

* Fixing Regex to handle grouping and

* Formatting Fix

* Update rocprofiler-sdk-restrictions.yml

* Separating regex.hpp to source and header & Adding Tests for parity with std::regex

* Update regex.cpp

* Using snake_case for naming and addressing some comments

* Adding more tests & README for regex implementation

* Updating rocprofiler sdk restrictions workflow

* Updating more tests & README for regex implementation

* Update README_regex.md

* Rename README_regex.md to README.md

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com>
Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
2025-08-27 12:30:12 -05:00
Daniel Su 7055fbfc7f [Ex CI] add hip-clr pipeline ID, add status badge to README (#782) 2025-08-27 13:25:47 -04:00
jamessiddeley-amd f0955f5a83 [rocprof-compute] added f4f6 description and VALU FLOPS split for empirical peaks (#739)
* added f4f6 description and VALU FLOPS split

* changed peak ammolite vars to local

* reverted to dict peak initialization

* ruff check format

* updated VALU descriptions

* updated VALU descriptions

* Update parser.py

* Update parser.py

Added gracefull NameError handling
Moved globals() update to init_metric_evaluation with ammolite__ vars and raw pmc_df

* update formatting
2025-08-27 12:46:41 -04:00
Sourabh U Betigeri 5201efe050 SWDEV-545259 - Adds clang-cl support and missing dispatch table entries (#760) 2025-08-27 09:35:58 -07:00
Pratik Basyal cfd3fee0e2 ROCm Compute Profiler changelog for 7.0 updated (#740)
* ROCm Compute Profiler changelog for 7.0 updated

* Roofline limited support for MI350 removed

* Update CHANGELOG.md
2025-08-27 11:24:49 -04:00
Arif, Maisam 652761de54 [SWDEV-536176] libdrm_amdgpu depdency change (#448)
* Cmake fix updates
* Next fix will be addressing libdrm further

---------

Signed-off-by: adapryor <Adam.pryor@amd.com>
Signed-off-by: Justin Williams <juwillia@amd.com>
2025-08-27 09:32:51 -05:00
Arif, Maisam 4d33e79baa [SWDEV-536176] libdrm_amdgpu depdency change (#448)
* Cmake fix updates
* Next fix will be addressing libdrm further

---------

Signed-off-by: adapryor <Adam.pryor@amd.com>
Signed-off-by: Justin Williams <juwillia@amd.com>

[ROCm/amdsmi commit: 652761de54]
2025-08-27 09:32:51 -05:00
Daniel Su 875d7724d9 create hip-clr combined pipeline trigger (#693) 2025-08-27 10:28:33 -04:00