Commit Graph
76333 Commits
Author SHA1 Message Date
ROCm CI Service Account 062a53e6a1 SWDEV-318349 - Enable test of graph launched by peer (#2997)
- Enable Unit_hipGraphInstantiateWithFlags_DependencyGraph for AMD.
- Add stream sync for null stream.
- Fix Unit_hipGraphInstantiateWithFlags_DependencyGraph.

change-Id: I5774563fdfed1afd29a43927f3630adbfb75c48a

[ROCm/hip commit: 53599bce3e]
2022-10-19 16:52:06 +05:30
ROCm CI Service Account 53599bce3e SWDEV-318349 - Enable test of graph launched by peer (#2997)
- Enable Unit_hipGraphInstantiateWithFlags_DependencyGraph for AMD.
- Add stream sync for null stream.
- Fix Unit_hipGraphInstantiateWithFlags_DependencyGraph.

change-Id: I5774563fdfed1afd29a43927f3630adbfb75c48a
2022-10-19 16:52:06 +05:30
ROCm CI Service Account 354c91dcfb SWDEV-356559 - update the note on hipIpcOpenMemHandle showing the different from CUDA (#2988)
Change-Id: I4116eaa3a8f31283dda7d7c0c680acdb954036b9

[ROCm/hip commit: acf9688165]
2022-10-19 16:50:51 +05:30
ROCm CI Service Account acf9688165 SWDEV-356559 - update the note on hipIpcOpenMemHandle showing the different from CUDA (#2988)
Change-Id: I4116eaa3a8f31283dda7d7c0c680acdb954036b9
2022-10-19 16:50:51 +05:30
ROCm CI Service Account 28e2c2db5e SWDEV-361129 - [catch2][dtest] Enabling tests hipGraphInstantiateWithFlags for AMD (#2987)
Change-Id: I39227ab51417e55f4ab05c48b61e9735856e58ac

[ROCm/hip-tests commit: 246f0c7d20]
2022-10-19 16:49:18 +05:30
ROCm CI Service Account 246f0c7d20 SWDEV-361129 - [catch2][dtest] Enabling tests hipGraphInstantiateWithFlags for AMD (#2987)
Change-Id: I39227ab51417e55f4ab05c48b61e9735856e58ac
2022-10-19 16:49:18 +05:30
ROCm CI Service Account 5203830518 SWDEV-361129 - [catch2][dtest] Enabling tests hipGraphInstantiateWithFlags for AMD (#2987)
Change-Id: I39227ab51417e55f4ab05c48b61e9735856e58ac

[ROCm/hip commit: 752acff9b2]
2022-10-19 16:49:18 +05:30
ROCm CI Service Account 752acff9b2 SWDEV-361129 - [catch2][dtest] Enabling tests hipGraphInstantiateWithFlags for AMD (#2987)
Change-Id: I39227ab51417e55f4ab05c48b61e9735856e58ac
2022-10-19 16:49:18 +05:30
ROCm CI Service Account b6709256ea SWDEV-337766 - [catch2][dtest]Fix for MI200 failures for tests: Unit_hipMemcpyPeer_Negative and Unit_hipMemcpyPeerAsync_Negative (#2986)
Change-Id: I88aa2580a589f6fcef3a098ee68922e3431aa75a

[ROCm/hip-tests commit: 48d21d8732]
2022-10-19 16:49:04 +05:30
ROCm CI Service Account 48d21d8732 SWDEV-337766 - [catch2][dtest]Fix for MI200 failures for tests: Unit_hipMemcpyPeer_Negative and Unit_hipMemcpyPeerAsync_Negative (#2986)
Change-Id: I88aa2580a589f6fcef3a098ee68922e3431aa75a
2022-10-19 16:49:04 +05:30
ROCm CI Service Account ee7baa1473 SWDEV-337766 - [catch2][dtest]Fix for MI200 failures for tests: Unit_hipMemcpyPeer_Negative and Unit_hipMemcpyPeerAsync_Negative (#2986)
Change-Id: I88aa2580a589f6fcef3a098ee68922e3431aa75a

[ROCm/hip commit: e28f31e1f5]
2022-10-19 16:49:04 +05:30
ROCm CI Service Account e28f31e1f5 SWDEV-337766 - [catch2][dtest]Fix for MI200 failures for tests: Unit_hipMemcpyPeer_Negative and Unit_hipMemcpyPeerAsync_Negative (#2986)
Change-Id: I88aa2580a589f6fcef3a098ee68922e3431aa75a
2022-10-19 16:49:04 +05:30
ROCm CI Service Account a33bf1e10d SWDEV-308368 - Fix coherent test bugs (#2985)
1. Remove hipDeviceAttributePageableMemoryAccess checking as it is used to check xnack+ rather than fine-grained synchronization.
Note: hipHostMalloc() will alloc memory with fine-grained access and atomic by default when env HIP_HOST_COHERENT=1. For more information, see hip_programming_guide.
2. Fix some other bugs.

Change-Id: Ieaaed1b15b4d258193d834104b17d9f03a9e4781

[ROCm/hip-tests commit: 15593f343d]
2022-10-19 16:48:44 +05:30
ROCm CI Service Account 15593f343d SWDEV-308368 - Fix coherent test bugs (#2985)
1. Remove hipDeviceAttributePageableMemoryAccess checking as it is used to check xnack+ rather than fine-grained synchronization.
Note: hipHostMalloc() will alloc memory with fine-grained access and atomic by default when env HIP_HOST_COHERENT=1. For more information, see hip_programming_guide.
2. Fix some other bugs.

Change-Id: Ieaaed1b15b4d258193d834104b17d9f03a9e4781
2022-10-19 16:48:44 +05:30
ROCm CI Service Account 6a87199474 SWDEV-308368 - Fix coherent test bugs (#2985)
1. Remove hipDeviceAttributePageableMemoryAccess checking as it is used to check xnack+ rather than fine-grained synchronization.
Note: hipHostMalloc() will alloc memory with fine-grained access and atomic by default when env HIP_HOST_COHERENT=1. For more information, see hip_programming_guide.
2. Fix some other bugs.

Change-Id: Ieaaed1b15b4d258193d834104b17d9f03a9e4781

[ROCm/hip commit: 15517aaf18]
2022-10-19 16:48:44 +05:30
ROCm CI Service Account 15517aaf18 SWDEV-308368 - Fix coherent test bugs (#2985)
1. Remove hipDeviceAttributePageableMemoryAccess checking as it is used to check xnack+ rather than fine-grained synchronization.
Note: hipHostMalloc() will alloc memory with fine-grained access and atomic by default when env HIP_HOST_COHERENT=1. For more information, see hip_programming_guide.
2. Fix some other bugs.

Change-Id: Ieaaed1b15b4d258193d834104b17d9f03a9e4781
2022-10-19 16:48:44 +05:30
Jonathan R. Madsen 7234e8cf45 Omnitrace sample documentation (#179)
* Documentation for omnitrace-sample

* Improve omnitrace-sample

- improve the printing of the env updates
- remove env settings when something is deactivated
- restore env settings when something is deactivated

[ROCm/rocprofiler-systems commit: 67f7471253]
2022-10-19 03:30:00 -05:00
Jonathan R. Madsen 67f7471253 Omnitrace sample documentation (#179)
* Documentation for omnitrace-sample

* Improve omnitrace-sample

- improve the printing of the env updates
- remove env settings when something is deactivated
- restore env settings when something is deactivated
2022-10-19 03:30:00 -05:00
Chauncey Hui 3db95d8b68 SWDEV-2 - Change OpenCL version number from 3514 to 3515
[ROCm/clr commit: 5cad630425]
2022-10-19 03:00:13 -04:00
Chauncey Hui 5cad630425 SWDEV-2 - Change OpenCL version number from 3514 to 3515 2022-10-19 03:00:13 -04:00
Laurent Morichetti 644e3b5253 Report HSA_OPS activities using the ROCr driver_node_id instead of the device's index
When multiple ranks are used, each rank's first logical device always
has GPU ID 0, regardless of which physical device is selected with
CUDA_VISIBLE_DEVICES. Because of this, when merging trace files from
multiple ranks, GPU IDs from different processes may overlap.

The long term solution is to use the KFD's gpu_id which is stable
across APIs and processes. Unfortunately the gpu_id is not yet exposed
by the ROCr, so for now use the driver's node id.

Change-Id: I2f5af8d2a7e8a89efeb5e0a1b86bdfa547b25fc8


[ROCm/roctracer commit: 799f0323cd]
2022-10-18 20:08:09 -07:00
Laurent Morichetti 799f0323cd Report HSA_OPS activities using the ROCr driver_node_id instead of the device's index
When multiple ranks are used, each rank's first logical device always
has GPU ID 0, regardless of which physical device is selected with
CUDA_VISIBLE_DEVICES. Because of this, when merging trace files from
multiple ranks, GPU IDs from different processes may overlap.

The long term solution is to use the KFD's gpu_id which is stable
across APIs and processes. Unfortunately the gpu_id is not yet exposed
by the ROCr, so for now use the driver's node id.

Change-Id: I2f5af8d2a7e8a89efeb5e0a1b86bdfa547b25fc8
2022-10-18 20:08:09 -07:00
Jonathan R. Madsen 8f8ead76b5 Signal handler backtraces provide line info (#178)
* Signal handler backtraces provide line info

- print backtrace after SIGINT during finalization

* Workflow run-name + jammy rocm CI

* fix jammy matrix indentation

* disable building dyninst in jammy

* Update jammy for rocm

* jammy rocm_agent_enumerator

* Fix rocm install for jammy

* jammy bash

* jammy workflow typo

* revert some changes

* stack-usage + omnitrace-rt symlink + ncclSocketAccept + indiv sigs

- symlink omnitrace-rt in build tree
- exclude ncclSocketAccept
- timemory submodule update accepting individual signal handlers

[ROCm/rocprofiler-systems commit: 78a06e7a42]
2022-10-18 21:45:56 -05:00
Jonathan R. Madsen 78a06e7a42 Signal handler backtraces provide line info (#178)
* Signal handler backtraces provide line info

- print backtrace after SIGINT during finalization

* Workflow run-name + jammy rocm CI

* fix jammy matrix indentation

* disable building dyninst in jammy

* Update jammy for rocm

* jammy rocm_agent_enumerator

* Fix rocm install for jammy

* jammy bash

* jammy workflow typo

* revert some changes

* stack-usage + omnitrace-rt symlink + ncclSocketAccept + indiv sigs

- symlink omnitrace-rt in build tree
- exclude ncclSocketAccept
- timemory submodule update accepting individual signal handlers
2022-10-18 21:45:56 -05:00
Laurent Morichetti 4f0a4afd95 Fix a build error when compiling with clang
Fix the following error:

roctx.cpp:91:25: error: reinterpret_cast from 'const void *' to 'decltype(report_activity.load())' (aka 'int (*)(activity_domain_t, unsigned int, void *)') casts away qualifiers
  report_activity.store(reinterpret_cast<decltype(report_activity.load())>(function),
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

by replacing the 'const void *function' argument with the correct type.

Change-Id: I912239daf6f4a3f00fc753306b84833e5c75f74b


[ROCm/roctracer commit: c95d5dd96f]
2022-10-18 18:20:58 -07:00
Laurent Morichetti c95d5dd96f Fix a build error when compiling with clang
Fix the following error:

roctx.cpp:91:25: error: reinterpret_cast from 'const void *' to 'decltype(report_activity.load())' (aka 'int (*)(activity_domain_t, unsigned int, void *)') casts away qualifiers
  report_activity.store(reinterpret_cast<decltype(report_activity.load())>(function),
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

by replacing the 'const void *function' argument with the correct type.

Change-Id: I912239daf6f4a3f00fc753306b84833e5c75f74b
2022-10-18 18:20:58 -07:00
jatang db848fbcd2 SWDEV-362891 - Incorperate TestLog into ocltst.
So it's no longer needed to setup path to find TestLog

Change-Id: I0c7ae21e426f2d6d832f707b9d37661bbed67100


[ROCm/clr commit: cf9f9e84b8]
2022-10-18 18:01:53 -04:00
jatang cf9f9e84b8 SWDEV-362891 - Incorperate TestLog into ocltst.
So it's no longer needed to setup path to find TestLog

Change-Id: I0c7ae21e426f2d6d832f707b9d37661bbed67100
2022-10-18 18:01:53 -04:00
Jenkins 74c170145f SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: Ib6b22852155bd6d448ddd07ac406a0f36732c5fb


[ROCm/hip commit: 80a14899a1]
2022-10-18 07:10:18 -04:00
Jenkins 80a14899a1 SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: Ib6b22852155bd6d448ddd07ac406a0f36732c5fb
2022-10-18 07:10:18 -04:00
Laurent Morichetti 3b61d6bd8c SWDEV-362165 - Escape argument strings in the JSON file
"a_string\x000" -> \"a_string\\x000\"

Change-Id: I8bf054702b34577f84080080d9538b16abc996fe
2022-10-18 01:47:46 -04:00
Laurent Morichetti ee8efd3e2b SWDEV-362165 - Escape argument strings in the JSON file
"a_string\x000" -> \"a_string\\x000\"

Change-Id: I8bf054702b34577f84080080d9538b16abc996fe


[ROCm/rocprofiler commit: 3b61d6bd8c]
2022-10-18 01:47:46 -04:00
Jonathan R. Madsen 713d08de6d Support for Ubuntu 22.04 and ROCm 5.3 (#48)
* Testing and CI support for Ubuntu 22.04

* Fixes for ROCm

- Jammy does not have ROCm installers

* Name, timeout, and python updates

- renamed ubuntu-jammy-external.yml to ubuntu-jammy.yml
- increased all 5 minute timeouts to 10 minutes
- include python 3.10 in testing

* Update dyninst to remove interposed definition of _r_debug

* Rebuild Dyninst + test install script

* Revert container change

* git safe directory

* pushd -> cd

* fix MPI include

* Fix testing step

* OMPI_ALLOW_RUN_AS_ROOT

* Test script changes

* Fix mismatched malloc / delete[]

* Jammy workflow tweaks

* CPack tweak for boost deb deps

* pthread_mutex_gotcha config returns when not enabled

* fix echoing config in CI

* USE_CLANG_OMP

- option to disable using LLVM OpenMP when building OpenMP test executables
- Jammy workflow sets USE_CLANG_OMP=OFF

* Dyninst submodule boost download

- updated containers workflow to include jammy
- updated workflow to use ci

* Updates to workflows + replace test-install.sh

- test-install.sh in this branch was replaced with one in main branch

* Expand jammy test-install.sh args

* Fix openmp-cg-sampling-duration test

* update timemory submodule

- use-after-free violation in popen::pclose

* revert some tweaks to sampling-duration test

* Fix env of test-install.sh

* cmake format

* jammy bash

* CPack install for jammy

* formatting workflow action version bump

* Update timemory submodule

- libunwind submodule via timemory sets SOVERSION to 99 to avoid ABI conflicts with v8

* Fix help menu for omnitrace-sample

* Support other boolean forms in test-install.sh

* Update docker files and build-docker.sh

- consolidated cases in build-docker.sh
- support rocm version of 0.0 (no rocm install)
- support rocm v5.3
- updated centos handling

* update opensuse actions/checkout version

* Tweaks to ubuntu-focal testing

- actions/checkout@v3
- use test-install script

* update cpack

- ubuntu 22.04
- rocm 5.3
- rename os matrix field to os-version
- remove CI_ROCM_VERSION (no longer necessary)
- remove default-rocm-version matrix field (no longer necessary)
- CentOS packaging

* fix argparsing and omnitrace-sample tests in install-tests.sh

* focal rocm test install workflow fix

* Fix omnitrace-sample build

* Dockerfile.centos + build-docker.sh updates

* Update actions/upload-artifact version

* Dockerfile.ubuntu: install rocm-device-libs

* Refactor cpack

* fix cpack if quotes

* Dockerfile.ubuntu rocm < 5 installs rocm-dev

* build-release.sh defaults to boost version 1.79.0

[ROCm/rocprofiler-systems commit: ede6007f9b]
2022-10-17 12:54:26 -05:00
Jonathan R. Madsen ede6007f9b Support for Ubuntu 22.04 and ROCm 5.3 (#48)
* Testing and CI support for Ubuntu 22.04

* Fixes for ROCm

- Jammy does not have ROCm installers

* Name, timeout, and python updates

- renamed ubuntu-jammy-external.yml to ubuntu-jammy.yml
- increased all 5 minute timeouts to 10 minutes
- include python 3.10 in testing

* Update dyninst to remove interposed definition of _r_debug

* Rebuild Dyninst + test install script

* Revert container change

* git safe directory

* pushd -> cd

* fix MPI include

* Fix testing step

* OMPI_ALLOW_RUN_AS_ROOT

* Test script changes

* Fix mismatched malloc / delete[]

* Jammy workflow tweaks

* CPack tweak for boost deb deps

* pthread_mutex_gotcha config returns when not enabled

* fix echoing config in CI

* USE_CLANG_OMP

- option to disable using LLVM OpenMP when building OpenMP test executables
- Jammy workflow sets USE_CLANG_OMP=OFF

* Dyninst submodule boost download

- updated containers workflow to include jammy
- updated workflow to use ci

* Updates to workflows + replace test-install.sh

- test-install.sh in this branch was replaced with one in main branch

* Expand jammy test-install.sh args

* Fix openmp-cg-sampling-duration test

* update timemory submodule

- use-after-free violation in popen::pclose

* revert some tweaks to sampling-duration test

* Fix env of test-install.sh

* cmake format

* jammy bash

* CPack install for jammy

* formatting workflow action version bump

* Update timemory submodule

- libunwind submodule via timemory sets SOVERSION to 99 to avoid ABI conflicts with v8

* Fix help menu for omnitrace-sample

* Support other boolean forms in test-install.sh

* Update docker files and build-docker.sh

- consolidated cases in build-docker.sh
- support rocm version of 0.0 (no rocm install)
- support rocm v5.3
- updated centos handling

* update opensuse actions/checkout version

* Tweaks to ubuntu-focal testing

- actions/checkout@v3
- use test-install script

* update cpack

- ubuntu 22.04
- rocm 5.3
- rename os matrix field to os-version
- remove CI_ROCM_VERSION (no longer necessary)
- remove default-rocm-version matrix field (no longer necessary)
- CentOS packaging

* fix argparsing and omnitrace-sample tests in install-tests.sh

* focal rocm test install workflow fix

* Fix omnitrace-sample build

* Dockerfile.centos + build-docker.sh updates

* Update actions/upload-artifact version

* Dockerfile.ubuntu: install rocm-device-libs

* Refactor cpack

* fix cpack if quotes

* Dockerfile.ubuntu rocm < 5 installs rocm-dev

* build-release.sh defaults to boost version 1.79.0
2022-10-17 12:54:26 -05:00
Wenkai Du 76414d3230 Support P2P with invisible devices (#636)
* Support P2P with invisible devices

* Update copyright year

[ROCm/rccl commit: 9ddf0e0649]
2022-10-17 10:24:59 -07:00
Wenkai Du 9ddf0e0649 Support P2P with invisible devices (#636)
* Support P2P with invisible devices

* Update copyright year
2022-10-17 10:24:59 -07:00
Wenkai Du 7cb9d872ab Merge pull request #634 from yzygitzh/ziyyang/npkit-fix
Apply several fixes to NPKit

[ROCm/rccl commit: 9916a09818]
2022-10-17 08:01:24 -07:00
Wenkai Du 9916a09818 Merge pull request #634 from yzygitzh/ziyyang/npkit-fix
Apply several fixes to NPKit
2022-10-17 08:01:24 -07:00
ROCm CI Service Account 3fd7a5dc21 SWDEV-353686 - add default value for missing function (#2991)
Change-Id: I76e95636ecf2c50a11d0120f3ffdfcf641841cdb

[ROCm/hip commit: 24c0cb92b3]
2022-10-17 16:57:32 +05:30
ROCm CI Service Account 24c0cb92b3 SWDEV-353686 - add default value for missing function (#2991)
Change-Id: I76e95636ecf2c50a11d0120f3ffdfcf641841cdb
2022-10-17 16:57:32 +05:30
ROCm CI Service Account 11a0279232 SWDEV-356057 - [catch2][dtest] Adding tests for no GPU environment. (#2981)
Change-Id: I1f63bd2abb1b6fe427be7264e0f5fbfa07216727

[ROCm/hip-tests commit: 47defc1840]
2022-10-17 13:41:29 +05:30
ROCm CI Service Account 47defc1840 SWDEV-356057 - [catch2][dtest] Adding tests for no GPU environment. (#2981)
Change-Id: I1f63bd2abb1b6fe427be7264e0f5fbfa07216727
2022-10-17 13:41:29 +05:30
ROCm CI Service Account 9bf1e7a709 SWDEV-356057 - [catch2][dtest] Adding tests for no GPU environment. (#2981)
Change-Id: I1f63bd2abb1b6fe427be7264e0f5fbfa07216727

[ROCm/hip commit: 274edb7725]
2022-10-17 13:41:29 +05:30
ROCm CI Service Account 274edb7725 SWDEV-356057 - [catch2][dtest] Adding tests for no GPU environment. (#2981)
Change-Id: I1f63bd2abb1b6fe427be7264e0f5fbfa07216727
2022-10-17 13:41:29 +05:30
Laurent Morichetti 348bc1afaf SWDEV-362165 - Escape strings in the API function's arguments
Strings ([const] char *, [const] char[]) passed as arguments to API
functions may not always contain printable characters. All string
arguments should be quoted and escaped in the trace logs.

Change-Id: Ie39058f2190048b1a0090df16d9ac6bc6507e28a


[ROCm/roctracer commit: b556f8681e]
2022-10-15 19:03:36 -07:00
Laurent Morichetti b556f8681e SWDEV-362165 - Escape strings in the API function's arguments
Strings ([const] char *, [const] char[]) passed as arguments to API
functions may not always contain printable characters. All string
arguments should be quoted and escaped in the trace logs.

Change-Id: Ie39058f2190048b1a0090df16d9ac6bc6507e28a
2022-10-15 19:03:36 -07:00
raramakr 65bd12b94d Merge pull request #635 from raramakr/swdev
Correct include and library path for new directory layout

[ROCm/rccl commit: b32f38126d]
2022-10-14 15:48:44 -07:00
raramakr b32f38126d Merge pull request #635 from raramakr/swdev
Correct include and library path for new directory layout
2022-10-14 15:48:44 -07:00
Edgar Gabriel 08f9435e5a Merge remote-tracking branch 'nccl-tests/master' into topic/v2.13.4-sync
[ROCm/rccl-tests commit: 3ae371cce7]
2022-10-14 16:02:54 -05:00
Edgar Gabriel 3ae371cce7 Merge remote-tracking branch 'nccl-tests/master' into topic/v2.13.4-sync 2022-10-14 16:02:54 -05:00