AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,521 Commits 3 Branches 0 Tags
c441a87a00a7ad16c8619ad603feffbaff63fa81
Commit Graph

64521 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Giovanni LB 6defbd0f2e SWDEV-476512: Further rocsys fixes 
Change-Id: I9ae8534a2b6b23f76514920a6c4d39025bc882bc


[ROCm/rocprofiler commit: c4adefccde]
 2024-08-05 10:42:00 -04:00
Rakesh Roy 28cd7da1dc SWDEV-472723 - Correct file format 
- Modify line ending to LF

Change-Id: I2bc840070327b204e2abb118276e2d905c29d096


[ROCm/hip-tests commit: 3bec5e988b]
 2024-08-05 19:26:31 +05:30
Rakesh Roy 3bec5e988b SWDEV-472723 - Correct file format 
- Modify line ending to LF

Change-Id: I2bc840070327b204e2abb118276e2d905c29d096
 2024-08-05 19:26:31 +05:30
Jaydeep Patel c51153f759 SWDEV-470886 - Add maybe_undef attribute for shfl device function due to not all lanes of wave define var and compiler needs to know about this. 
Change-Id: I3a683887e033305ac55362f356838b491a6d50f2


[ROCm/clr commit: 6344ddb2f3]
 2024-08-05 00:53:13 -04:00
Jaydeep Patel 6344ddb2f3 SWDEV-470886 - Add maybe_undef attribute for shfl device function due to not all lanes of wave define var and compiler needs to know about this. 
Change-Id: I3a683887e033305ac55362f356838b491a6d50f2
 2024-08-05 00:53:13 -04:00
David Galiffi 5e5a9cabc9 This fixes the CPACK workflow failures for Ubuntu and RHEL (#368) 
* Add texinfo to Ubuntu and RHEL docker files

* Add the `bison` package to Ubuntu dockerfile

* Update the CI docker files too.

---------

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

[ROCm/rocprofiler-systems commit: d0d97490b4]
 2024-08-02 16:03:19 -04:00
David Galiffi d0d97490b4 This fixes the CPACK workflow failures for Ubuntu and RHEL (#368) 
* Add texinfo to Ubuntu and RHEL docker files

* Add the `bison` package to Ubuntu dockerfile

* Update the CI docker files too.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-08-02 16:03:19 -04:00
srawat 2dc1c0d9f5 rocprofv3 doc updates (#982) 
* updating rocprofv3

* using rocprofv3

* review updates

* naming standardization

* Update source/docs/how-to/using-rocprofv3.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

* review comments

* adding API references

* kernel filtering

* Remove Sphinx warn as error

To bypass false warning for linking between rst and md

* remove unused (duplicate) refs in _toc.yml.in

---------

Co-authored-by: Gopesh Bhardwaj <gopesh.bhardwaj@amd.com>
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>
Co-authored-by: Peter Jun Park <peter.park@amd.com>

[ROCm/rocprofiler-sdk commit: 69caa62b60]
 2024-08-02 14:08:04 -05:00
srawat 69caa62b60 rocprofv3 doc updates (#982) 
* updating rocprofv3

* using rocprofv3

* review updates

* naming standardization

* Update source/docs/how-to/using-rocprofv3.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

* review comments

* adding API references

* kernel filtering

* Remove Sphinx warn as error

To bypass false warning for linking between rst and md

* remove unused (duplicate) refs in _toc.yml.in

---------

Co-authored-by: Gopesh Bhardwaj <gopesh.bhardwaj@amd.com>
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>
Co-authored-by: Peter Jun Park <peter.park@amd.com>
 2024-08-02 14:08:04 -05:00
German Andryeyev 35c7a87014 SWDEV-470612 - Add the optimized multistream path 
- Added the optimized multi stream path in graph execution. It uses a fixed number of async streams in the execution
- Optimize the launch latency, where commands
creation and execution is done at the same time
- Optimize the scheduling to use less barriers and waiting signals if
the same queue  can be detected
- The new path is controlled by  DEBUG_HIP_FORCE_GRAPH_QUEUES
environment variable, where 0 will use the original path and any other
value will force the number of asynchronous queues for execution
- DEBUG_HIP_FORCE_ASYNC_QUEUE can force single queue async
execution in graphs(applicable for Navi families only)

Change-Id: I7eb40bc15c45f508d6911868a6f6d4c3598d380e


[ROCm/clr commit: 9db52f9a46]
 2024-08-02 14:19:44 -04:00
German Andryeyev 9db52f9a46 SWDEV-470612 - Add the optimized multistream path 
- Added the optimized multi stream path in graph execution. It uses a fixed number of async streams in the execution
- Optimize the launch latency, where commands
creation and execution is done at the same time
- Optimize the scheduling to use less barriers and waiting signals if
the same queue  can be detected
- The new path is controlled by  DEBUG_HIP_FORCE_GRAPH_QUEUES
environment variable, where 0 will use the original path and any other
value will force the number of asynchronous queues for execution
- DEBUG_HIP_FORCE_ASYNC_QUEUE can force single queue async
execution in graphs(applicable for Navi families only)

Change-Id: I7eb40bc15c45f508d6911868a6f6d4c3598d380e
 2024-08-02 14:19:44 -04:00
Marko Arandjelovic d5139b29ef SWDEV-476869 - Add mapping to cudaGetTextureReference 
Change-Id: I85a6e4423d7b8b88ed18629225c583b87551414f


[ROCm/hipother commit: ccd569c4bb]
 2024-08-02 12:14:16 +02:00
Marko Arandjelovic ccd569c4bb SWDEV-476869 - Add mapping to cudaGetTextureReference 
Change-Id: I85a6e4423d7b8b88ed18629225c583b87551414f
 2024-08-02 12:14:16 +02:00
Zhang Ava 86acd39029 Merge amd-staging into amd-master 20240801 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I8c9b1a2805e83e5de5873ef8fafaf38143c2ebd8


[ROCm/rocm_smi_lib commit: 481928965f]
 2024-08-02 13:12:38 +08:00
Zhang Ava 481928965f Merge amd-staging into amd-master 20240801 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I8c9b1a2805e83e5de5873ef8fafaf38143c2ebd8
 2024-08-02 13:12:38 +08:00
Anusha GodavarthySurya 31927fefd6 SWDEV-468424 - Add support to capture multiple AQL Packets 
=> Added support to capture multiple AQL Packets.
=> Added Interface to callback to hip runtime from rocclr to allocate
kernel args from the graph kernel arg pool.
=> Enabled Support to capture memset node.

Change-Id: I7e1c2ba06927459e024653058af142bd82192c43


[ROCm/clr commit: bd3a35bde1]
 2024-08-01 23:55:51 -04:00
Anusha GodavarthySurya bd3a35bde1 SWDEV-468424 - Add support to capture multiple AQL Packets 
=> Added support to capture multiple AQL Packets.
=> Added Interface to callback to hip runtime from rocclr to allocate
kernel args from the graph kernel arg pool.
=> Enabled Support to capture memset node.

Change-Id: I7e1c2ba06927459e024653058af142bd82192c43
 2024-08-01 23:55:51 -04:00
Marko Arandjelovic 48ee9f8ae7 SWDEV-441603 - Add hipDrvMemcpy2DUnaligned test 
Change-Id: I44b65867cabeb369fda8a82984fe3f694499942c


[ROCm/hip-tests commit: 639a9c2996]
 2024-08-01 17:44:26 -04:00
Marko Arandjelovic 639a9c2996 SWDEV-441603 - Add hipDrvMemcpy2DUnaligned test 
Change-Id: I44b65867cabeb369fda8a82984fe3f694499942c
 2024-08-01 17:44:26 -04:00
ajanicijamd a705483ebc Fix compilation with GCC 13 and Ubuntu 24.04 (#362) 
* Modified submodules dyninst and timemory.

* Modified PAPI submodule to fix GCC 13 build for Ubuntu 24.04.

* Updated PAPI submodule URL.

* Fixed papi submodule URL.

* Using latest tag (papi-7-1-0-t) for papi submodule.

* Update submodule dyninst to new version

* Added a mirror to elfutils

[ROCm/rocprofiler-systems commit: c11abc4ea1]
 2024-08-01 16:37:06 -04:00
ajanicijamd c11abc4ea1 Fix compilation with GCC 13 and Ubuntu 24.04 (#362) 
* Modified submodules dyninst and timemory.

* Modified PAPI submodule to fix GCC 13 build for Ubuntu 24.04.

* Updated PAPI submodule URL.

* Fixed papi submodule URL.

* Using latest tag (papi-7-1-0-t) for papi submodule.

* Update submodule dyninst to new version

* Added a mirror to elfutils
 2024-08-01 16:37:06 -04:00
David Galiffi 1dc1ba86d3 Add release branches to workflow (#365) 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: c078168944]
 2024-08-01 15:39:36 -04:00
David Galiffi c078168944 Add release branches to workflow (#365) 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-08-01 15:39:36 -04:00
Julia Jiang 13c5e7a3e4 SWDEV-472723 - Correct file format and remove trailing spaces 
Change-Id: Ie40c763e9391fa36d6c890cd0a171659a1502a83


[ROCm/hip-tests commit: 5d042c80fa]
 2024-08-01 15:17:39 -04:00
Julia Jiang 5d042c80fa SWDEV-472723 - Correct file format and remove trailing spaces 
Change-Id: Ie40c763e9391fa36d6c890cd0a171659a1502a83
 2024-08-01 15:17:39 -04:00
Branislav Brzak f9bb3c5f74 SWDEV-441600 - Add hipGraphMemFreeNodeGetParams tests 
Change-Id: I46cc12e9940cf647e3c3dbe4ce87957eb8aa4e33


[ROCm/hip-tests commit: 2b20d3a9af]
 2024-08-01 14:26:32 -04:00
Branislav Brzak 2b20d3a9af SWDEV-441600 - Add hipGraphMemFreeNodeGetParams tests 
Change-Id: I46cc12e9940cf647e3c3dbe4ce87957eb8aa4e33
 2024-08-01 14:26:32 -04:00
Julia Jiang 6fa0563ed6 SWDEV-436608 - Un-deprecate hipHostAlloc() 
Change-Id: I71393e6f536ba84b4e172acf54ba4f72350e2ae8


[ROCm/clr commit: e988e5e448]
 2024-08-01 11:45:20 -04:00
Julia Jiang e988e5e448 SWDEV-436608 - Un-deprecate hipHostAlloc() 
Change-Id: I71393e6f536ba84b4e172acf54ba4f72350e2ae8
 2024-08-01 11:45:20 -04:00
Branislav Brzak f2083ef57c SWDEV-441283 - Add hipMemsetD16Async test 
Change-Id: I66ca44996cfbf061d134ba5c66c3a7211bfcaaa5


[ROCm/hip-tests commit: 987c4bb297]
 2024-08-01 11:16:15 -04:00
Branislav Brzak 987c4bb297 SWDEV-441283 - Add hipMemsetD16Async test 
Change-Id: I66ca44996cfbf061d134ba5c66c3a7211bfcaaa5
 2024-08-01 11:16:15 -04:00
Marko Arandjelovic 7cd2515908 SWDEV-465204 - Fix hipModuleLaunchKernel data validation 
Change-Id: I129f265a5eb79d0a13da4f12e78e06ba307b17ee


[ROCm/clr commit: be5f097e8e]
 2024-08-01 05:09:23 -04:00
Marko Arandjelovic be5f097e8e SWDEV-465204 - Fix hipModuleLaunchKernel data validation 
Change-Id: I129f265a5eb79d0a13da4f12e78e06ba307b17ee
 2024-08-01 05:09:23 -04:00
Vladana Stojiljkovic 91800f18ea SWDEV-465142 - Copy memAllocNodePtrs_ when cloning graph 
Change-Id: I5a0907e59397e71b44db59c44b551b74a6e59ba0


[ROCm/clr commit: d62c1dea72]
 2024-08-01 11:05:06 +02:00
Vladana Stojiljkovic d62c1dea72 SWDEV-465142 - Copy memAllocNodePtrs_ when cloning graph 
Change-Id: I5a0907e59397e71b44db59c44b551b74a6e59ba0
 2024-08-01 11:05:06 +02:00
Vladana Stojiljkovic 6fcb2c655f SWDEV-475127 - Check if hipBindTextureToArray parameters are null before dereferencing them 
Change-Id: Id0173faff0a385d1665194c9033083ef9b2c48b5


[ROCm/clr commit: d7b07b94a0]
 2024-08-01 05:01:55 -04:00
Vladana Stojiljkovic d7b07b94a0 SWDEV-475127 - Check if hipBindTextureToArray parameters are null before dereferencing them 
Change-Id: Id0173faff0a385d1665194c9033083ef9b2c48b5
 2024-08-01 05:01:55 -04:00
Ioannis Assiouras 42e8d3c894 SWDEV-476460 - Fix for a race condition in SysmemPool::Alloc 
Change-Id: Ia94709e68b236c9460589963c0f09ec1f481c306


[ROCm/clr commit: 8e137e8702]
 2024-08-01 04:22:26 -04:00
Ioannis Assiouras 8e137e8702 SWDEV-476460 - Fix for a race condition in SysmemPool::Alloc 
Change-Id: Ia94709e68b236c9460589963c0f09ec1f481c306
 2024-08-01 04:22:26 -04:00
Jonathan R. Madsen 8cea0cae2e Tracing Documentation (#997) 
* Update callback_services.md

* Callback tracing services

* Intercept table

* Buffer tracing

[ROCm/rocprofiler-sdk commit: cfbac19640]
 2024-08-01 13:29:35 +05:30
Jonathan R. Madsen cfbac19640 Tracing Documentation (#997) 
* Update callback_services.md

* Callback tracing services

* Intercept table

* Buffer tracing
 2024-08-01 13:29:35 +05:30
Jonathan R. Madsen 6c6adddb5c Reorganize thread trace codeobj headers (#1001) 
* include/rocprofiler-sdk/cxx/codeobj

- Relocated from include/rocprofiler-sdk/amd_detail/rocprofiler-sdk-codeobj

* Update include/rocprofiler-sdk/cxx

- cmake updates
- correct namespace rocprofiler::codeobj rocprofiler::sdk::codeobj

* Update codeobj tests and samples

[ROCm/rocprofiler-sdk commit: 20e07caad4]
 2024-08-01 00:10:09 -05:00
Jonathan R. Madsen 20e07caad4 Reorganize thread trace codeobj headers (#1001) 
* include/rocprofiler-sdk/cxx/codeobj

- Relocated from include/rocprofiler-sdk/amd_detail/rocprofiler-sdk-codeobj

* Update include/rocprofiler-sdk/cxx

- cmake updates
- correct namespace rocprofiler::codeobj rocprofiler::sdk::codeobj

* Update codeobj tests and samples
 2024-08-01 00:10:09 -05:00
SrirakshaNag 03ff04bbe3 Adding changes for handling abort signals (#979) 
* Adding changes for handling abort signals

* Fix the test failure

* Fixing CmakeLists error

* Addressing review comments

* fixing warnings

* fixing execute test

* Fixing abort app test

* Address review comments

* Apply suggestions from code review

* Apply suggestions from code review

* Fixes for testing issues

* Adding kernel filtering test

* Removing text input file

* fix formatting issues

* misc fix

* Suppress signal-unsafe error in ThreadSanitizer

- rename signal handler to rocprofv3_error_signal_handler to ensure specific filtering

* Fix rocprofv3 aborted-app validation

---------

Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 94b5d9be3f]
 2024-08-01 09:16:01 +05:30
SrirakshaNag 94b5d9be3f Adding changes for handling abort signals (#979) 
* Adding changes for handling abort signals

* Fix the test failure

* Fixing CmakeLists error

* Addressing review comments

* fixing warnings

* fixing execute test

* Fixing abort app test

* Address review comments

* Apply suggestions from code review

* Apply suggestions from code review

* Fixes for testing issues

* Adding kernel filtering test

* Removing text input file

* fix formatting issues

* misc fix

* Suppress signal-unsafe error in ThreadSanitizer

- rename signal handler to rocprofv3_error_signal_handler to ensure specific filtering

* Fix rocprofv3 aborted-app validation

---------

Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2024-08-01 09:16:01 +05:30
Giovanni LB 7edee28288 SWDEV-477001: Fixing line offset and copy command for webui 
Change-Id: I830bc7afd552e314f931514e938ba2214a765e63
 2024-08-01 00:32:58 -03:00
Giovanni LB 9915421ec0 SWDEV-477001: Fixing line offset and copy command for webui 
Change-Id: I830bc7afd552e314f931514e938ba2214a765e63


[ROCm/rocprofiler commit: 7edee28288]
 2024-08-01 00:32:58 -03:00
Ranjith Ramakrishnan 70b29ed8c3 SWDEV-469004 - Append additonal path to system path 
rocm-smi is installed in /opt/rocm-ver/bin , but not as a soft link in wheel package
For rocm-smi to work from bin directory, it need the extra path to find rsmiBindings.py

Change-Id: I41388f680cb2ab9f11dc135639b0d30b66082392


[ROCm/rocm_smi_lib commit: c9201f7736]
 2024-07-31 19:52:46 -04:00
Ranjith Ramakrishnan c9201f7736 SWDEV-469004 - Append additonal path to system path 
rocm-smi is installed in /opt/rocm-ver/bin , but not as a soft link in wheel package
For rocm-smi to work from bin directory, it need the extra path to find rsmiBindings.py

Change-Id: I41388f680cb2ab9f11dc135639b0d30b66082392
 2024-07-31 19:52:46 -04:00
Maisam Arif 1998b57059 [SWDEV-464799] Handle UnicodeEncodeError with non UTF-8 locales 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ifb8e6e3c7891c4f70faba5441fb87cc4ba2302f3


[ROCm/rocm_smi_lib commit: c2235eea35]
 2024-07-31 17:01:01 -04:00