76333 کامیت‌ها

مولف SHA1 پیام تاریخ
Nilesh M Negi ba1adc3316 Merge pull request #116 from nileshnegi/sync/nccl-tests/02-28-2025
[SYNC] NCCL-Tests v2.14.1

[ROCm/rccl-tests commit: 83d38d91b6]
2025-04-21 19:53:35 -05:00
Nilesh M Negi 83d38d91b6 Merge pull request #116 from nileshnegi/sync/nccl-tests/02-28-2025
[SYNC] NCCL-Tests v2.14.1
2025-04-21 19:53:35 -05:00
nileshnegi 8d887aad0d Merge remote-tracking branch 'nccl-tests/master' into develop
[ROCm/rccl-tests commit: 5625599dda]
2025-04-21 19:46:10 -05:00
nileshnegi 5625599dda Merge remote-tracking branch 'nccl-tests/master' into develop 2025-04-21 19:46:10 -05:00
Sohaib Nadeem 160edff37f Initialization fixes (#154)
- Remove tooling initialization from rocprofiler_configure:
when rocprofiler configure is called from __hip_module_ctor
(which in turn is called as a global constructor when loading shared
libraries or before main in a hip program), initializing tooling
in it can cause problems because it is too early to do some of the tasks
that it involves (e.g. opening shared libraries, creating threads).
Instead, we rely on rocprofsys_main to initialize tooling later.

- Skip rocprofiler_configure if ROCPROFSYS_PRELOAD is not set since
preload is required for tooling (such as perfetto, which is used by
the rocprofiler callbacks) to be initialized.

- Revert RCCL initialization changes: These are no longer needed since rocprofsys_init_tooling_hidden will not
be called from rocprofiler_configure

- Force rocprofiler_configure in rocprofsys_init_tooling_hidden if it hasn't been
called through __hip_module_ctor global constructor

[ROCm/rocprofiler-systems commit: 0e535daa93]
2025-04-21 17:04:24 -04:00
Sohaib Nadeem 0e535daa93 Initialization fixes (#154)
- Remove tooling initialization from rocprofiler_configure:
when rocprofiler configure is called from __hip_module_ctor
(which in turn is called as a global constructor when loading shared
libraries or before main in a hip program), initializing tooling
in it can cause problems because it is too early to do some of the tasks
that it involves (e.g. opening shared libraries, creating threads).
Instead, we rely on rocprofsys_main to initialize tooling later.

- Skip rocprofiler_configure if ROCPROFSYS_PRELOAD is not set since
preload is required for tooling (such as perfetto, which is used by
the rocprofiler callbacks) to be initialized.

- Revert RCCL initialization changes: These are no longer needed since rocprofsys_init_tooling_hidden will not
be called from rocprofiler_configure

- Force rocprofiler_configure in rocprofsys_init_tooling_hidden if it hasn't been
called through __hip_module_ctor global constructor
2025-04-21 17:04:24 -04:00
Vaddireddy, Sushma 720441bde2 Grid dimensions update (#329)
* Grid dimensions update

* minor edit

* CI compilation fix

* Adding target_compile_definitions

* Updating changes as per suggestions

* Skip checks for older grid dimension values

---------

Co-authored-by: Sushma Vaddireddy <svaddire@amd.com>

[ROCm/rocprofiler-sdk commit: d1e9e3917e]
2025-04-21 15:33:37 -05:00
Vaddireddy, Sushma d1e9e3917e Grid dimensions update (#329)
* Grid dimensions update

* minor edit

* CI compilation fix

* Adding target_compile_definitions

* Updating changes as per suggestions

* Skip checks for older grid dimension values

---------

Co-authored-by: Sushma Vaddireddy <svaddire@amd.com>
2025-04-21 15:33:37 -05:00
jeffqjiangNew 357c33ac40 Revert "CTest: Added CTest for AV1 elementary stream decode on bitstream read…" (#569)
This reverts commit 5cdfca2a33.

[ROCm/rocdecode commit: 2dea69d26b]
2025-04-21 15:57:15 -04:00
jeffqjiangNew 2dea69d26b Revert "CTest: Added CTest for AV1 elementary stream decode on bitstream read…" (#569)
This reverts commit 5472059e16.
2025-04-21 15:57:15 -04:00
AL Musaffar, Yazen d6954bcc62 Removed CPER tests and adjust the implementation (#269)
- Moved helper functions into amdsmi_utils.cc
- Removed tests since they are not working.

---------

Co-authored-by: Saeed, Oosman <Oosman.Saeed@amd.com>
2025-04-21 14:54:47 -05:00
AL Musaffar, Yazen 0551b2aa67 Removed CPER tests and adjust the implementation (#269)
- Moved helper functions into amdsmi_utils.cc
- Removed tests since they are not working.

---------

Co-authored-by: Saeed, Oosman <Oosman.Saeed@amd.com>

[ROCm/amdsmi commit: d6954bcc62]
2025-04-21 14:54:47 -05:00
Amber Lin bdb6e43b54 Revert "kfdtest: Temporarily blacklist KFDNegativeTest"
This reverts commit fcf3f91379.

MEC v18 starts to support pipe reset
2025-04-21 14:14:10 -04:00
Amber Lin bf3bb1f1a1 Revert "kfdtest: Temporarily blacklist KFDNegativeTest"
This reverts commit fffdffc3ce.

MEC v18 starts to support pipe reset


[ROCm/ROCR-Runtime commit: bdb6e43b54]
2025-04-21 14:14:10 -04:00
Bertan Dogancay aac829125c Fix NPKit for SendRecv (#1651)
[ROCm/rccl commit: ac8ec4c08c]
2025-04-21 12:34:47 -04:00
Bertan Dogancay ac8ec4c08c Fix NPKit for SendRecv (#1651) 2025-04-21 12:34:47 -04:00
Bhardwaj, Gopesh ef8b185a04 Remove SDK as beta from docs (#351)
[ROCm/rocprofiler-sdk commit: 780b96ad3a]
2025-04-21 21:31:14 +05:30
Bhardwaj, Gopesh 780b96ad3a Remove SDK as beta from docs (#351) 2025-04-21 21:31:14 +05:30
Elwazir, Ammar 852bed662c Older Glibc doesn't have gettid (#349)
* Older Glibc doesn't have gettid

* Format fix

* Using internal common get_tid

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>

[ROCm/rocprofiler-sdk commit: 8baea19df7]
2025-04-21 10:22:50 -05:00
Elwazir, Ammar 8baea19df7 Older Glibc doesn't have gettid (#349)
* Older Glibc doesn't have gettid

* Format fix

* Using internal common get_tid

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
2025-04-21 10:22:50 -05:00
Kiriti Gowda 468181845f Update .codecov.yaml (#568)
[ROCm/rocdecode commit: afc605b328]
2025-04-21 08:49:49 -04:00
Kiriti Gowda afc605b328 Update .codecov.yaml (#568) 2025-04-21 08:49:49 -04:00
Godavarthy Surya, Anusha 41c4bea0f5 SWDEV-508538 - Optimize mem access and pack structure (#71)
Change-Id: Ib05b8891a6d228fc3266918a000d332fddc7438b

[ROCm/clr commit: bf28bbd9ab]
2025-04-21 13:43:25 +05:30
Godavarthy Surya, Anusha bf28bbd9ab SWDEV-508538 - Optimize mem access and pack structure (#71)
Change-Id: Ib05b8891a6d228fc3266918a000d332fddc7438b
2025-04-21 13:43:25 +05:30
Tim 58ee618194 RCCL Replayer update (#1603)
RCCL recorder w/ suggested change and UT



[ROCm/rccl commit: 9a55ff60a9]
2025-04-19 00:21:27 -04:00
Tim 9a55ff60a9 RCCL Replayer update (#1603)
RCCL recorder w/ suggested change and UT
2025-04-19 00:21:27 -04:00
David Addison 8d71063e05 Add support for FP8 datatypes
Added new datatypes: f8e4m3, f8e5m2

Only supported on H100+ architectures and NCCL versions >= 2.24.0


[ROCm/rccl-tests commit: 501a149d57]
2025-04-18 19:20:59 -07:00
David Addison 501a149d57 Add support for FP8 datatypes
Added new datatypes: f8e4m3, f8e5m2

Only supported on H100+ architectures and NCCL versions >= 2.24.0
2025-04-18 19:20:59 -07:00
Mustafa Abduljabbar de2b66921a Address nested designator compiler warning issue (#1633)
[ROCm/rccl commit: 52bfdf05dc]
2025-04-18 17:09:50 -04:00
Mustafa Abduljabbar 52bfdf05dc Address nested designator compiler warning issue (#1633) 2025-04-18 17:09:50 -04:00
David Galiffi 17ed9dd925 Fix the rocm installation (#172)
[ROCm/rocprofiler-systems commit: f03dce5fa6]
2025-04-18 16:33:34 -04:00
David Galiffi f03dce5fa6 Fix the rocm installation (#172) 2025-04-18 16:33:34 -04:00
Aryan Salmanpour a7be0436a5 CTest: Add a test to perform negative testing on all rocJPEG APIs (#143)
* CTest: Add a test to perform negative testing on all rocJPEG APIs

* clean up

[ROCm/rocjpeg commit: 232a9c6906]
2025-04-18 10:02:12 -07:00
Aryan Salmanpour 232a9c6906 CTest: Add a test to perform negative testing on all rocJPEG APIs (#143)
* CTest: Add a test to perform negative testing on all rocJPEG APIs

* clean up
2025-04-18 10:02:12 -07:00
Brzak, Branislav 5df4734f71 SWDEV-526612 - Add missing copyright notices (#201)
[ROCm/clr commit: 99142c3dd9]
2025-04-18 20:54:27 +05:30
Brzak, Branislav 99142c3dd9 SWDEV-526612 - Add missing copyright notices (#201) 2025-04-18 20:54:27 +05:30
Nusrat Islam 691e98940c Fix MSCCLPP accuracy issue for allreduce7 (#1634)
* ext-src: fix a graph-mode bug in allreduce7

* change MSCCLPP threshold to 16MB

* ext-src: change message size threshold for allreduce7

* ext-src: address review comments

[ROCm/rccl commit: f20c33effd]
2025-04-18 08:54:32 -05:00
Nusrat Islam f20c33effd Fix MSCCLPP accuracy issue for allreduce7 (#1634)
* ext-src: fix a graph-mode bug in allreduce7

* change MSCCLPP threshold to 16MB

* ext-src: change message size threshold for allreduce7

* ext-src: address review comments
2025-04-18 08:54:32 -05:00
David Galiffi bb4ed0b3ba Add rocm-6.4 to workflows (#165)
* Add rocm-6.4 to workflows

* Update containers.yml

* Update cpack.yml

* Update cpack.yml

* Disable OpenMP Target Examples on GitHub Runners

* Fix build warnings.

Switch statements with unhandled enums.

* Enable testing on 6.3 and 6.4

* Ubuntu 24 workflow. Build both ROCm 6.3 and 6.4

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

---------

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

[ROCm/rocprofiler-systems commit: 169c9a0d49]
2025-04-18 09:32:26 -04:00
David Galiffi 169c9a0d49 Add rocm-6.4 to workflows (#165)
* Add rocm-6.4 to workflows

* Update containers.yml

* Update cpack.yml

* Update cpack.yml

* Disable OpenMP Target Examples on GitHub Runners

* Fix build warnings.

Switch statements with unhandled enums.

* Enable testing on 6.3 and 6.4

* Ubuntu 24 workflow. Build both ROCm 6.3 and 6.4

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

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2025-04-18 09:32:26 -04:00
Nagaraj, Sriraksha 2e7d0b3aec [rocprofv3] signal handler fix (#332)
* rocprofv3: LD_PRELOAD for signal and sigaction

- wrappers around `signal` and `sigaction` to prevent applications which install signal handlers to replace the rocprofv3 signal handlers
- minor tweaks to buffer sizes (use page_size instead of
KiB)

* [DO NOT COMMIT] extra logging

* Switch git submodule url for perfetto

- use GitHub URL as this is more accessible

* Update ring_buffer<Tp>

- account for alignment padding

* Update buffered_output

- track number of bytes stored
- add nullptr checks

* Update tmp_file_buffer

- track number of bytes
- read_tmp_file does not create tmp file if it does not already exist

* Update tmp_file

- add exists member function for checking whether temporary file already exists
- tweak remove() implementation

* Update config.hpp

- add option to enable/disable signal handlers
- add option for minimum_output_bytes

* Make signal, sigaction functions visible

* rocprofv3 tool updates

- chained signals
- override the signal handler(s) installed by the application
- improve cleanup of temporary files
- support minimum output bytes

* Add commandline support

* fixing test

* minor fix

* minor fix

* fix clang issue

* fix

* Adding docs

* review comments

* review changes

* review

* YUV pulldown additions to rocdecode

* More rocdecode changes

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: 87badfbd15]
2025-04-17 21:10:52 -07:00
Nagaraj, Sriraksha 87badfbd15 [rocprofv3] signal handler fix (#332)
* rocprofv3: LD_PRELOAD for signal and sigaction

- wrappers around `signal` and `sigaction` to prevent applications which install signal handlers to replace the rocprofv3 signal handlers
- minor tweaks to buffer sizes (use page_size instead of
KiB)

* [DO NOT COMMIT] extra logging

* Switch git submodule url for perfetto

- use GitHub URL as this is more accessible

* Update ring_buffer<Tp>

- account for alignment padding

* Update buffered_output

- track number of bytes stored
- add nullptr checks

* Update tmp_file_buffer

- track number of bytes
- read_tmp_file does not create tmp file if it does not already exist

* Update tmp_file

- add exists member function for checking whether temporary file already exists
- tweak remove() implementation

* Update config.hpp

- add option to enable/disable signal handlers
- add option for minimum_output_bytes

* Make signal, sigaction functions visible

* rocprofv3 tool updates

- chained signals
- override the signal handler(s) installed by the application
- improve cleanup of temporary files
- support minimum output bytes

* Add commandline support

* fixing test

* minor fix

* minor fix

* fix clang issue

* fix

* Adding docs

* review comments

* review changes

* review

* YUV pulldown additions to rocdecode

* More rocdecode changes

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>
2025-04-17 21:10:52 -07:00
Maisam Arif 925fc6d194 Reduced Monitor Calls to gpu_metrics_info()
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Iffb1ba9e91452016feb16da039ce96d63a5ce3e2
2025-04-17 19:47:17 -05:00
Maisam Arif f635fab179 Reduced Monitor Calls to gpu_metrics_info()
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Iffb1ba9e91452016feb16da039ce96d63a5ce3e2


[ROCm/amdsmi commit: 925fc6d194]
2025-04-17 19:47:17 -05:00
Justin Williams 369afa85eb CI - Add mainline labels automatically
Signed-off-by: Justin Williams <Justin.Williams@amd.com>
2025-04-17 17:53:09 -05:00
Justin Williams 94d451bc03 CI - Add mainline labels automatically
Signed-off-by: Justin Williams <Justin.Williams@amd.com>


[ROCm/amdsmi commit: 369afa85eb]
2025-04-17 17:53:09 -05:00
Castillo, Juan 4d92dea079 [SWDEV-523794] Update to fix MIN_CLK and MAX_CLK incorrect values
(#280)

- Fixed potential issue with min/max values when only one frequency is available
- Improve error handling in GPU frequency range detection
- Refactor clock frequency range detection for better readability
- Added special handling for current frequency indicator (*) in DPM output
- Added comments explaining special case handling for current frequency
- Cleaned up incorrect definitions in hsmp metric table definition

---------

Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
2025-04-17 17:46:04 -05:00
Castillo, Juan 21e32ffe4a [SWDEV-523794] Update to fix MIN_CLK and MAX_CLK incorrect values
(#280)

- Fixed potential issue with min/max values when only one frequency is available
- Improve error handling in GPU frequency range detection
- Refactor clock frequency range detection for better readability
- Added special handling for current frequency indicator (*) in DPM output
- Added comments explaining special case handling for current frequency
- Cleaned up incorrect definitions in hsmp metric table definition

---------

Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 4d92dea079]
2025-04-17 17:46:04 -05:00
Baraldi, Giovanni 3fc9374295 SWDEV-527202: Moving ATT to experimental (#335)
* Moving ATT to experimental

* Formatting + rebase

* Addressing review comments

* Formatting

* Update source/lib/att-tool/waitcnt/analysis.cpp

---------

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

[ROCm/rocprofiler-sdk commit: 46818b0167]
2025-04-17 14:43:15 -05:00
Baraldi, Giovanni 46818b0167 SWDEV-527202: Moving ATT to experimental (#335)
* Moving ATT to experimental

* Formatting + rebase

* Addressing review comments

* Formatting

* Update source/lib/att-tool/waitcnt/analysis.cpp

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
2025-04-17 14:43:15 -05:00