Commit Graph

64521 Commits

Author SHA1 Message Date
Ioannis Assiouras a55118f63d SWDEV-497636 - Updated CHANGELOG
Updated CHANGELOG to include the performance fix for
kernel launch latency with increasing number of idle streams.

Change-Id: I509e14cb8f8cd3abe61c6ede78808e96ef8f06e1
2024-12-20 19:09:16 -05:00
Ioannis Assiouras b4019892c9 SWDEV-505504 - Disable vectorization in GetHipDispatchTable
Change-Id: Id33144623555a5d25e029ca644f6274610dcd0ad


[ROCm/clr commit: 158b6a29e0]
2024-12-20 17:47:07 -05:00
Ioannis Assiouras 158b6a29e0 SWDEV-505504 - Disable vectorization in GetHipDispatchTable
Change-Id: Id33144623555a5d25e029ca644f6274610dcd0ad
2024-12-20 17:47:07 -05:00
Adam Pryor df170c8801 Implementation for SWDEV-479728:[RDC] - Clock Speed/Power Cap Control
Change-Id: I767a71325527aa3c691e9607953ceafebacfb4d5
Signed-off-by: adapryor <Adam.pryor@amd.com>
2024-12-20 16:03:33 -06:00
Adam Pryor 1c26bf4304 Implementation for SWDEV-479728:[RDC] - Clock Speed/Power Cap Control
Change-Id: I767a71325527aa3c691e9607953ceafebacfb4d5
Signed-off-by: adapryor <Adam.pryor@amd.com>


[ROCm/rdc commit: df170c8801]
2024-12-20 16:03:33 -06:00
Galantsev, Dmitrii 7c91a07a43 Profiler - Migrate from rocprofv1 to rocprofv3
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

Fixed RDC for Rocprofv3

Updates

Signed-off-by: adapryor <Adam.pryor@amd.com>
Change-Id: Ic9162bacf1322b265e6bbcdd9fbb9b1fdef414fd

last updates

Change-Id: I12e168501327c5e4cff8a9273b0512fb0e098fe7

comment

Change-Id: I61da61e66dcc017ec46f98ff4c90fb064c9679e8
2024-12-20 15:39:02 -06:00
Galantsev, Dmitrii 755ae0ee5d Profiler - Migrate from rocprofv1 to rocprofv3
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

Fixed RDC for Rocprofv3

Updates

Signed-off-by: adapryor <Adam.pryor@amd.com>
Change-Id: Ic9162bacf1322b265e6bbcdd9fbb9b1fdef414fd

last updates

Change-Id: I12e168501327c5e4cff8a9273b0512fb0e098fe7

comment

Change-Id: I61da61e66dcc017ec46f98ff4c90fb064c9679e8


[ROCm/rdc commit: 7c91a07a43]
2024-12-20 15:39:02 -06:00
Nagaraj, Sriraksha e5dde1b230 fix dimensions in avail output (#82)
* fix dimensions in avail output

* review comment addressed

[ROCm/rocprofiler-sdk commit: 554537f140]
2024-12-20 13:26:02 -06:00
Nagaraj, Sriraksha 554537f140 fix dimensions in avail output (#82)
* fix dimensions in avail output

* review comment addressed
2024-12-20 13:26:02 -06:00
Julia Jiang 33be5eb841 SWDEV-505803 - Remove environment variable with DEBUG_*
Change-Id: I447743d1caef02592c9f0bcc21fc5569b504ee36


[ROCm/hip commit: c908ad057a]
2024-12-20 11:48:12 -05:00
Julia Jiang c908ad057a SWDEV-505803 - Remove environment variable with DEBUG_*
Change-Id: I447743d1caef02592c9f0bcc21fc5569b504ee36
2024-12-20 11:48:12 -05:00
Indic, Vladimir 47a66adf1f ROCProfV3: fatal message if PC sampling unsupported, but requested (#60)
If a user requests PC sampling on a system that does not support this feature,
report a fatal error message and stop executing the program.

[ROCm/rocprofiler-sdk commit: 0ce75c1043]
2024-12-20 08:04:16 -08:00
Indic, Vladimir 0ce75c1043 ROCProfV3: fatal message if PC sampling unsupported, but requested (#60)
If a user requests PC sampling on a system that does not support this feature,
report a fatal error message and stop executing the program.
2024-12-20 08:04:16 -08:00
sonadeem ad3d2b0679 SWDEV-503436 - Fix incorrect OptionGroup for FSanitize option
NOPTION is meant for component options or alias runtime options so
the option group must not be OA_RUNTIME or OA_MISC_ALIAS must be set,
otherwise we incorrectly assume that it has an option variable and
attempting to write to it causes corruption of OptionVariables.

Change-Id: Iafb5a8f743e5ed0f87be36061c44578178f6cfde


[ROCm/clr commit: caa10572cb]
2024-12-20 10:14:51 -05:00
sonadeem caa10572cb SWDEV-503436 - Fix incorrect OptionGroup for FSanitize option
NOPTION is meant for component options or alias runtime options so
the option group must not be OA_RUNTIME or OA_MISC_ALIAS must be set,
otherwise we incorrectly assume that it has an option variable and
attempting to write to it causes corruption of OptionVariables.

Change-Id: Iafb5a8f743e5ed0f87be36061c44578178f6cfde
2024-12-20 10:14:51 -05:00
Baraldi, Giovanni d0d378897a SWDEV-495749: Adding SIMD_UTILIZATION metric (#74)
* SWDEV-495749: Adding SIMD_UTILIZATION metric

* Fix mfmautil

---------

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

[ROCm/rocprofiler-sdk commit: 200a8624bc]
2024-12-20 14:35:18 +00:00
Baraldi, Giovanni 200a8624bc SWDEV-495749: Adding SIMD_UTILIZATION metric (#74)
* SWDEV-495749: Adding SIMD_UTILIZATION metric

* Fix mfmautil

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
2024-12-20 14:35:18 +00:00
Chris Freehill 67b0082443 rocr: Dynamically allocate IsaMap
This is to avoid use after free at the program's end, when statics
are destructed.

Change-Id: Id6bf26f25a58d13bdf1ee99c852adae8add76569
2024-12-20 09:20:09 -05:00
Chris Freehill 6c04d75c3f rocr: Dynamically allocate IsaMap
This is to avoid use after free at the program's end, when statics
are destructed.

Change-Id: Id6bf26f25a58d13bdf1ee99c852adae8add76569


[ROCm/ROCR-Runtime commit: 67b0082443]
2024-12-20 09:20:09 -05:00
Jaydeep Patel 12ed697705 SWDEV-505205 - Fix hipStreamLegacy segfault with hipStreamWaitEvent.
Change-Id: I17fdaf7ac323507f99a7c071066944296537489c


[ROCm/clr commit: a05a02e527]
2024-12-20 04:18:21 -05:00
Jaydeep Patel a05a02e527 SWDEV-505205 - Fix hipStreamLegacy segfault with hipStreamWaitEvent.
Change-Id: I17fdaf7ac323507f99a7c071066944296537489c
2024-12-20 04:18:21 -05:00
Pankaj Kumar Divedi d4c3bcdc0f SWDEV-485275 - fix using CUID to host-only compilation
Change-Id: I9f818e045090299714e77132e2a036a804ab1856


[ROCm/hip-tests commit: 754644f16e]
2024-12-20 12:18:20 +05:30
Pankaj Kumar Divedi 754644f16e SWDEV-485275 - fix using CUID to host-only compilation
Change-Id: I9f818e045090299714e77132e2a036a804ab1856
2024-12-20 12:18:20 +05:30
Welton, Benjamin 926c1ed153 Add support for device counter collection ioctl (#46)
Add support for device counter colleciton ioctl

Adds support for the device counter collection IOCTL. This IOCTL
allows for device wide counters to be collected even if the queue
is not intercepted by rocprofiler-sdk (required for system profilers).

A test is also included which checks this behavior by creating a queue
that does not have profiling enabled on it and checks to see if SQ
counters can be read from it. Note: this test will be skipped if the KFD
version does not contain this IOCTL.

Right now the check is "soft" in that if the IOCTL is present and there
is an error with permissions, rocprofiler will continue but will print
an error stating that system wide device profiling and collected counter
values may be degraded. This is primarily to avoid breaking existing
users (like PAPI) who may not need the IOCTL's capability and to give
them time to update.

Co-authored-by: Benjamin Welton <ben@amd.com>

[ROCm/rocprofiler-sdk commit: c574881cdb]
2024-12-19 13:27:35 -08:00
Welton, Benjamin c574881cdb Add support for device counter collection ioctl (#46)
Add support for device counter colleciton ioctl

Adds support for the device counter collection IOCTL. This IOCTL
allows for device wide counters to be collected even if the queue
is not intercepted by rocprofiler-sdk (required for system profilers).

A test is also included which checks this behavior by creating a queue
that does not have profiling enabled on it and checks to see if SQ
counters can be read from it. Note: this test will be skipped if the KFD
version does not contain this IOCTL.

Right now the check is "soft" in that if the IOCTL is present and there
is an error with permissions, rocprofiler will continue but will print
an error stating that system wide device profiling and collected counter
values may be degraded. This is primarily to avoid breaking existing
users (like PAPI) who may not need the IOCTL's capability and to give
them time to update.

Co-authored-by: Benjamin Welton <ben@amd.com>
2024-12-19 13:27:35 -08:00
Indic, Vladimir 86417237a6 Remove numpy dependency from rocprofv3.py (#75)
Remove numpy dependency from rocprofv3.py

[ROCm/rocprofiler-sdk commit: 9c21c49aa1]
2024-12-19 20:52:42 +01:00
Indic, Vladimir 9c21c49aa1 Remove numpy dependency from rocprofv3.py (#75)
Remove numpy dependency from rocprofv3.py
2024-12-19 20:52:42 +01:00
David Galiffi c3e2315ce8 Merge 'amd-staging' into 'amd-mainline'
[ROCm/rocprofiler-systems commit: 27f210ea5d]
2024-12-19 12:35:24 -05:00
David Galiffi 27f210ea5d Merge 'amd-staging' into 'amd-mainline' 2024-12-19 12:35:24 -05:00
Maisam Arif 35eb8e7c4b Resolve CI caller merge conflicts
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Icb0389f422b6f158492828e79e44fe00e5db07f5
2024-12-19 10:10:23 -06:00
Maisam Arif a3bc9b7a72 Resolve CI caller merge conflicts
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Icb0389f422b6f158492828e79e44fe00e5db07f5


[ROCm/rdc commit: 35eb8e7c4b]
2024-12-19 10:10:23 -06:00
Vladana Stojiljkovic 573ba928da SWDEV-500407 - Disable atomicMax_system for floats and doubles
Change-Id: Ica73f7692b726f7fd68a53f0b7f0f687eaef1b67


[ROCm/hip-tests commit: 5ebecf35c0]
2024-12-19 11:00:03 -05:00
Vladana Stojiljkovic 5ebecf35c0 SWDEV-500407 - Disable atomicMax_system for floats and doubles
Change-Id: Ica73f7692b726f7fd68a53f0b7f0f687eaef1b67
2024-12-19 11:00:03 -05:00
David Galiffi 7eca1ca69d Update VERSION to 1.0.0
Bumping major version now that rocprofiler-sdk has been integrated.

[ROCm/rocprofiler-systems commit: 33b043b11c]
2024-12-19 09:41:53 -05:00
David Galiffi 33b043b11c Update VERSION to 1.0.0
Bumping major version now that rocprofiler-sdk has been integrated.
2024-12-19 09:41:53 -05:00
Flora Cui ac64c54d74 rocr: skip exception_signal_ handling on exit
if .supports_exception_debugging is not enabled.

Change-Id: I944fe7aa4f3068964f47e23f5259c3802d1e9556
Signed-off-by: Flora Cui <flora.cui@amd.com>
2024-12-19 04:14:32 -05:00
Flora Cui 6a3d0e6412 rocr: skip exception_signal_ handling on exit
if .supports_exception_debugging is not enabled.

Change-Id: I944fe7aa4f3068964f47e23f5259c3802d1e9556
Signed-off-by: Flora Cui <flora.cui@amd.com>


[ROCm/ROCR-Runtime commit: ac64c54d74]
2024-12-19 04:14:32 -05:00
Baraldi, Giovanni f8442415f8 SWDEV-492607: Adding ATT wrapper (#40)
* Adding att parser wrapper

* Adding ATT tests as optional

* Adding decoder API for query capability

* Removed samples

* Formatting

* adding new line

* Removed perfetto and moved to static library

* using default search for lib

* Updated to SDK

* Namespace changes

* Added tests

* Small refactor

* Updated API to receive agent_id

* Fixing tests

* Tidy fixes

* Not write to file

* Switch to filesystem.hpp

* Compilation fixes

* Formatting

* Tidy fix

* Removed likely

* Adding tests

* Added gfx9 test

* Adding gfx12 tests

* Formatting

* Enable tidy

* Fix tests

* Fix deadlock on agent test

* Workaround ASAN

* Moving query outside class.

* Fix standalone tool

* Addressing comments

* Formatting

* Change query name

* Fixed some tests. Updated PR comments.

* Formatting

* Improved coverage

* Formatting

* Fix for comments

* Formatting

* Adding some description. Fix error type.

---------

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

[ROCm/rocprofiler-sdk commit: 2c8e88a76b]
2024-12-18 18:53:32 -08:00
Baraldi, Giovanni 2c8e88a76b SWDEV-492607: Adding ATT wrapper (#40)
* Adding att parser wrapper

* Adding ATT tests as optional

* Adding decoder API for query capability

* Removed samples

* Formatting

* adding new line

* Removed perfetto and moved to static library

* using default search for lib

* Updated to SDK

* Namespace changes

* Added tests

* Small refactor

* Updated API to receive agent_id

* Fixing tests

* Tidy fixes

* Not write to file

* Switch to filesystem.hpp

* Compilation fixes

* Formatting

* Tidy fix

* Removed likely

* Adding tests

* Added gfx9 test

* Adding gfx12 tests

* Formatting

* Enable tidy

* Fix tests

* Fix deadlock on agent test

* Workaround ASAN

* Moving query outside class.

* Fix standalone tool

* Addressing comments

* Formatting

* Change query name

* Fixed some tests. Updated PR comments.

* Formatting

* Improved coverage

* Formatting

* Fix for comments

* Formatting

* Adding some description. Fix error type.

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
2024-12-18 18:53:32 -08:00
Pranjal Swarup 64bb1ea13f Merge proto files from multiprocess run into one file. (#63)
- Added script to merge multiprocess output automatically to one file when there are multiprocess proto files written into output folder
- Execute the merge multiprocess script from the rank 0 process
- Added the scripts folder path to env path, via setup-env.sh
- Installed merge_multiprocess_output.sh to /share/rocprofiler-systems/bin dir

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

[ROCm/rocprofiler-systems commit: 0263e951ff]
2024-12-18 17:34:02 -05:00
Pranjal Swarup 0263e951ff Merge proto files from multiprocess run into one file. (#63)
- Added script to merge multiprocess output automatically to one file when there are multiprocess proto files written into output folder
- Execute the merge multiprocess script from the rank 0 process
- Added the scripts folder path to env path, via setup-env.sh
- Installed merge_multiprocess_output.sh to /share/rocprofiler-systems/bin dir

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2024-12-18 17:34:02 -05:00
German Andryeyev 55d4a75016 SWDEV-504658 - Reduce the lock scope for kernel look-up
The vector with all kernels is preallocated on the executable init.
Thus, reduce the scope  of global lock to the binary creation only.

Change-Id: I73035013a6562175069137e895bba815f466ee35


[ROCm/clr commit: 0640d36019]
2024-12-18 17:04:51 -05:00
German Andryeyev 0640d36019 SWDEV-504658 - Reduce the lock scope for kernel look-up
The vector with all kernels is preallocated on the executable init.
Thus, reduce the scope  of global lock to the binary creation only.

Change-Id: I73035013a6562175069137e895bba815f466ee35
2024-12-18 17:04:51 -05:00
Sajina PK 2d6b4d9988 Enable VCN tracing in Perfetto output (#65)
Enable VCN activity tracing on different instances from the GPU metrics fetched using rsmi_dev_gpu_metrics_info_get in the ROCm-SMI. library.

The tracing can be controlled with ROCPROFSYS_ROCM_SMI_METRICS by setting the value as vcn_activity, Currently this configuration takes the following values: busy, temp, power, mem_usage, vcn_activity.
By default, all the 5 values will be enabled.

Signed-off-by: Sajina P Kandy <Sajina.PuthalathKandy@amd.com>
Co-authored-by: Sajina Kandy <sputhala-amd@amd.com>

[ROCm/rocprofiler-systems commit: 3fa37c991e]
2024-12-18 15:56:48 -05:00
Sajina PK 3fa37c991e Enable VCN tracing in Perfetto output (#65)
Enable VCN activity tracing on different instances from the GPU metrics fetched using rsmi_dev_gpu_metrics_info_get in the ROCm-SMI. library.

The tracing can be controlled with ROCPROFSYS_ROCM_SMI_METRICS by setting the value as vcn_activity, Currently this configuration takes the following values: busy, temp, power, mem_usage, vcn_activity.
By default, all the 5 values will be enabled.

Signed-off-by: Sajina P Kandy <Sajina.PuthalathKandy@amd.com>
Co-authored-by: Sajina Kandy <sputhala-amd@amd.com>
2024-12-18 15:56:48 -05:00
Julia Jiang b39722359a SWDEV-504376 - Update doxygen for hipHostAllocWriteCombined and related definitions
Change-Id: I200e01f7ff62e33e26d838bcea8a10ca3e21eae6


[ROCm/hip commit: 82d37bbd4c]
2024-12-18 15:34:51 -05:00
Julia Jiang 82d37bbd4c SWDEV-504376 - Update doxygen for hipHostAllocWriteCombined and related definitions
Change-Id: I200e01f7ff62e33e26d838bcea8a10ca3e21eae6
2024-12-18 15:34:51 -05:00
Choudhary, Rahul 69be6f1c16 Update rocm_ci_caller.yml: base ref to support pull and push request
The change is present in mainline and was missing in staging
2024-12-18 11:57:44 -08:00
Choudhary, Rahul 61ee9e50e8 Update rocm_ci_caller.yml: base ref to support pull and push request
The change is present in mainline and was missing in staging

[ROCm/rdc commit: 69be6f1c16]
2024-12-18 11:57:44 -08:00
Vladana Stojiljkovic aee10912e0 SWDEV-491257 - Create stream capture tests with Event APIs
Change-Id: I9803a78c3513845f7bf91333a0db0d43bed5b346


[ROCm/hip-tests commit: fd92c47fea]
2024-12-18 13:52:31 -05:00