AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
76 333 коммитов 3 Ветки 0 Теги
develop
Граф коммитов

76333 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Benjamin Welton 80e32505d5 Convert LOG() -> ROCP_X logging macros. (#695) 
* Convert LOG() -> ROCP_X logging macros.

This patch converts the LOG() macro to the ROCP_X logging macros.
There are the following levels of logs.

Logs whos expressions are not evaluated unless the log level is enabled:

ROCP_TRACE - VLOG(2) (enabeled by env variable GLOG_v=2)
ROCP_INFO - VLOG(1) (enabeled by env variable GLOG_v=1)

Logs whos expressions are always evaluated:

ROCP_WARNING - LOG(WARNING)
ROCP_ERROR - LOG(ERROR)
ROCP_FATAL - LOG(FATAL)
ROCP_DFATAL - DLOG(FATAL) (only fatal in debug mode)

* source formatting (clang-format v11) (#696)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

* Minor fix

* Fixes for VLOG before main

* fix vmodule

* source formatting (clang-format v11) (#718)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

* memory leak fix

* Vlog change

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 41c0ddd72d]
 2024-04-02 17:15:30 -07:00
Benjamin Welton 41c0ddd72d Convert LOG() -> ROCP_X logging macros. (#695) 
* Convert LOG() -> ROCP_X logging macros.

This patch converts the LOG() macro to the ROCP_X logging macros.
There are the following levels of logs.

Logs whos expressions are not evaluated unless the log level is enabled:

ROCP_TRACE - VLOG(2) (enabeled by env variable GLOG_v=2)
ROCP_INFO - VLOG(1) (enabeled by env variable GLOG_v=1)

Logs whos expressions are always evaluated:

ROCP_WARNING - LOG(WARNING)
ROCP_ERROR - LOG(ERROR)
ROCP_FATAL - LOG(FATAL)
ROCP_DFATAL - DLOG(FATAL) (only fatal in debug mode)

* source formatting (clang-format v11) (#696)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

* Minor fix

* Fixes for VLOG before main

* fix vmodule

* source formatting (clang-format v11) (#718)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

* memory leak fix

* Vlog change

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>
 2024-04-02 17:15:30 -07:00
cadolphe 02330a5324 SWDEV-443537 - fix make build warning message 
Add cltrace compile definition for CL_TARGET_OPENCL_VERSION to OpenCL 2.2

Change-Id: Ie868ab0a6e86951afc6d07da58be942c3b736d15


[ROCm/clr commit: f7b1398361]
 2024-04-02 16:42:01 -04:00
cadolphe f7b1398361 SWDEV-443537 - fix make build warning message 
Add cltrace compile definition for CL_TARGET_OPENCL_VERSION to OpenCL 2.2

Change-Id: Ie868ab0a6e86951afc6d07da58be942c3b736d15
 2024-04-02 16:42:01 -04:00
Gopesh Bhardwaj d7781d0b40 README update (#730) 
* README update

* Addressing review comments

[ROCm/rocprofiler-sdk commit: 5e4dd502d9]
 2024-04-02 14:11:05 -05:00
Gopesh Bhardwaj 5e4dd502d9 README update (#730) 
* README update

* Addressing review comments
 2024-04-02 14:11:05 -05:00
Rakesh Roy ff50326d82 SWDEV-454217, SWDEV-454220, SWDEV-453412, SWDEV-453415, SWDEV-453453 - Disable failing tests in PSDB stress test & CI 
- These tests failed/hanged in PSDB stress test & Jenkins CI

Change-Id: Id116528081881ddcf71052ba7f6efee2de22de42


[ROCm/hip-tests commit: 00a5500450]
 2024-04-02 23:40:34 +05:30
Rakesh Roy 00a5500450 SWDEV-454217, SWDEV-454220, SWDEV-453412, SWDEV-453415, SWDEV-453453 - Disable failing tests in PSDB stress test & CI 
- These tests failed/hanged in PSDB stress test & Jenkins CI

Change-Id: Id116528081881ddcf71052ba7f6efee2de22de42
 2024-04-02 23:40:34 +05:30
Aryan Salmanpour bd2767ccab Add initial support for rocJPEG documentation (#9) 
[ROCm/rocjpeg commit: 3c803847f7]
 2024-04-02 13:10:04 -04:00
Aryan Salmanpour 3c803847f7 Add initial support for rocJPEG documentation (#9) 2024-04-02 13:10:04 -04:00
Ammar ELWazir 076fb895ec Update formatting.yml 
[ROCm/rocprofiler-sdk commit: 872aa1b1d2]
 2024-04-02 11:28:44 -05:00
Ammar ELWazir 872aa1b1d2 Update formatting.yml 2024-04-02 11:28:44 -05:00
Shweta Khatri 244ad319ac Revert "Use HybridMutex for IPC locks" 
This reverts commit 5c520f4544c654e5f18e05cabd1c63d64473cfab.

Reason for revert: This patch is introducing a synchronization related bug in Unit_hipGetSetDevice_MultiThreaded testcase.

Change-Id: I367e4d4f1d75b21658ac1127c58982894a97cedb
 2024-04-02 12:27:55 -04:00
Shweta Khatri 89e51e1f63 Revert "Use HybridMutex for IPC locks" 
This reverts commit 5c520f4544c654e5f18e05cabd1c63d64473cfab.

Reason for revert: This patch is introducing a synchronization related bug in Unit_hipGetSetDevice_MultiThreaded testcase.

Change-Id: I367e4d4f1d75b21658ac1127c58982894a97cedb


[ROCm/ROCR-Runtime commit: 244ad319ac]
 2024-04-02 12:27:55 -04:00
Benjamin Welton 19ecb86ee3 Wait for all memory copies to complete before allowing destruction (#725) 
* Wait for all mem copies to complete before destroying.

* Update source/lib/rocprofiler-sdk/hsa/async_copy.cpp

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

* Update async_copy.cpp

---------

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

[ROCm/rocprofiler-sdk commit: 1e612a5e52]
 2024-04-02 08:22:37 -05:00
Benjamin Welton 1e612a5e52 Wait for all memory copies to complete before allowing destruction (#725) 
* Wait for all mem copies to complete before destroying.

* Update source/lib/rocprofiler-sdk/hsa/async_copy.cpp

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

* Update async_copy.cpp

---------

Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>
 2024-04-02 08:22:37 -05:00
Sylvain Jeaugey 792c33598f 2.21.5-1 
Add support for IB SHARP 1PPN operation with user buffers.
Improve support for MNNVL, add NVLS support and multi-clique support.
 * Detect the NVLS clique through NVML
 * Exchange XML between peers in the same NVLS clique and fuse XMLs
   before creating the topology graph.
 * Rework bootstrap allgather algorithms to allow for large allgather
   operations intra-node (XML exchange).
Net/IB: add support for dynamic GID detection.
 * Automatically select RoCEv2/IPv4 interface by default. Allow to
   select IPv6 or even the network/mask.
Reduce NVLS memory usage.
 * Add stepSize as property of a connection to allow for different
   sizes on different peers; set it to 128K for NVLink SHARP.
Improve tuner loading
 * Look for more paths, be more consistent with the network device
   plugin.
 * Also search for tuner support inside the net plugin.
Improve tuner API
 * Add context to support multi-device per process.
Add magic number around comm object to detect comm corruption.
 * Add some basic check around communicators so that we can report a
   problem when a communicator gets corrupted or a wrong comm pointer
   is passed to NCCL.
Fix net/IB error path. Github PR #1164
Fix collnet rail mapping with split comm.
Fix packet reordering issue causing bootstrap mismatch
 * Use a different tag in ncclTransportP2pSetup for the connectInfo
   exchange and the following barrier.
Fix hang when crossNic is inconsistent between ranks.
Fix minCompCap/maxCompCap computation. Github issue #1184


[ROCm/rccl commit: ab2b89c4c3]
 2024-04-02 01:53:21 -07:00
Sylvain Jeaugey ab2b89c4c3 2.21.5-1 
Add support for IB SHARP 1PPN operation with user buffers.
Improve support for MNNVL, add NVLS support and multi-clique support.
 * Detect the NVLS clique through NVML
 * Exchange XML between peers in the same NVLS clique and fuse XMLs
   before creating the topology graph.
 * Rework bootstrap allgather algorithms to allow for large allgather
   operations intra-node (XML exchange).
Net/IB: add support for dynamic GID detection.
 * Automatically select RoCEv2/IPv4 interface by default. Allow to
   select IPv6 or even the network/mask.
Reduce NVLS memory usage.
 * Add stepSize as property of a connection to allow for different
   sizes on different peers; set it to 128K for NVLink SHARP.
Improve tuner loading
 * Look for more paths, be more consistent with the network device
   plugin.
 * Also search for tuner support inside the net plugin.
Improve tuner API
 * Add context to support multi-device per process.
Add magic number around comm object to detect comm corruption.
 * Add some basic check around communicators so that we can report a
   problem when a communicator gets corrupted or a wrong comm pointer
   is passed to NCCL.
Fix net/IB error path. Github PR #1164
Fix collnet rail mapping with split comm.
Fix packet reordering issue causing bootstrap mismatch
 * Use a different tag in ncclTransportP2pSetup for the connectInfo
   exchange and the following barrier.
Fix hang when crossNic is inconsistent between ranks.
Fix minCompCap/maxCompCap computation. Github issue #1184
 2024-04-02 01:53:21 -07:00
Jonathan R. Madsen 6fe6bcc832 Stop all client contexts prior to finalization (#721) 
* Stop all client contexts prior to finalization

* Update lib/common/container/static_vector.hpp

- improve emplace_back for non-{move,copy}-assignable object

* Update samples/intercept_table/client.cpp

- improve robustness against static object destruction

* Update lib/rocprofiler-sdk/context/context.cpp

- change storage of registered context array
  - stable_vector of optional contexts
  - common::static_object wrapper around stable_vector

* Update samples/intercept_table/client.cpp

- use variable template for underlying function pointer

[ROCm/rocprofiler-sdk commit: 939e23e9d1]
 2024-04-02 03:05:11 -05:00
Jonathan R. Madsen 939e23e9d1 Stop all client contexts prior to finalization (#721) 
* Stop all client contexts prior to finalization

* Update lib/common/container/static_vector.hpp

- improve emplace_back for non-{move,copy}-assignable object

* Update samples/intercept_table/client.cpp

- improve robustness against static object destruction

* Update lib/rocprofiler-sdk/context/context.cpp

- change storage of registered context array
  - stable_vector of optional contexts
  - common::static_object wrapper around stable_vector

* Update samples/intercept_table/client.cpp

- use variable template for underlying function pointer
 2024-04-02 03:05:11 -05:00
Gopesh Bhardwaj 3cb4c162f7 SWDEV-451569: bug in tracing options (#728) 
[ROCm/rocprofiler-sdk commit: e3c7eed7c0]
 2024-04-02 03:03:02 -05:00
Gopesh Bhardwaj e3c7eed7c0 SWDEV-451569: bug in tracing options (#728) 2024-04-02 03:03:02 -05:00
dependabot[bot] e5fdc0a747 Bump actions/configure-pages from 4 to 5 (#706) 
Bumps [actions/configure-pages](https://github.com/actions/configure-pages) from 4 to 5.
- [Release notes](https://github.com/actions/configure-pages/releases)
- [Commits](https://github.com/actions/configure-pages/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/configure-pages
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 9d6809d0b6]
 2024-04-02 02:34:32 -05:00
dependabot[bot] 9d6809d0b6 Bump actions/configure-pages from 4 to 5 (#706) 
Bumps [actions/configure-pages](https://github.com/actions/configure-pages) from 4 to 5.
- [Release notes](https://github.com/actions/configure-pages/releases)
- [Commits](https://github.com/actions/configure-pages/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/configure-pages
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-04-02 02:34:32 -05:00
Ammar ELWazir a130be0ccc Formating Issue fix (#726) 
* Update formatting.yml

* Update formatting.yml

* Update client.cpp

* Update formatting.yml

* Update samples/api_buffered_tracing/client.cpp

* Update client.cpp

[ROCm/rocprofiler-sdk commit: ddbcf34da5]
 2024-04-02 02:14:59 -05:00
Ammar ELWazir ddbcf34da5 Formating Issue fix (#726) 
* Update formatting.yml

* Update formatting.yml

* Update client.cpp

* Update formatting.yml

* Update samples/api_buffered_tracing/client.cpp

* Update client.cpp
 2024-04-02 02:14:59 -05:00
Ammar ELWazir 18940a08b8 Update validate.py (#727) 
[ROCm/rocprofiler-sdk commit: c45573f559]
 2024-04-02 01:59:33 -05:00
Ammar ELWazir c45573f559 Update validate.py (#727) 2024-04-02 01:59:33 -05:00
Ammar ELWazir 521e2794e6 Update run-ci.py (#641) 
* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

* Update run-ci.py

* Update run-ci.py

* Update continuous_integration.yml

* Update continuous_integration.yml

running directly using the prepared runner container

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update run-ci.py

* Clean up

* Fixing install paths

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing GPU Agents Test Validation

* python formatting (black) (#712)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* python formatting (black) (#713)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* Fixing static number of async copies and using hsa_api instead for validation

* python formatting (black) (#714)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Increasing the time limit for waiting on active signals

* Update continuous_integration.yml

* Update async_copy.cpp

* Update CMakeLists.txt

* changing node id to logical node id in rocprofv3

* Update tool.cpp

* testing async mem copy signal decrement

* Update logging.cpp

* Update validate.py

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 2905fb5e95]
 2024-04-02 01:39:24 -05:00
Ammar ELWazir 2905fb5e95 Update run-ci.py (#641) 
* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

* Update run-ci.py

* Update run-ci.py

* Update continuous_integration.yml

* Update continuous_integration.yml

running directly using the prepared runner container

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update run-ci.py

* Clean up

* Fixing install paths

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing GPU Agents Test Validation

* python formatting (black) (#712)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* python formatting (black) (#713)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* Fixing static number of async copies and using hsa_api instead for validation

* python formatting (black) (#714)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Increasing the time limit for waiting on active signals

* Update continuous_integration.yml

* Update async_copy.cpp

* Update CMakeLists.txt

* changing node id to logical node id in rocprofv3

* Update tool.cpp

* testing async mem copy signal decrement

* Update logging.cpp

* Update validate.py

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2024-04-02 01:39:24 -05:00
Ammar ELWazir c1c514f743 Use logical_node_id for mapping rocprofiler agents to HSA agents (#708) 
* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 62625d0aa1]
 2024-04-02 01:38:18 -05:00
Ammar ELWazir 62625d0aa1 Use logical_node_id for mapping rocprofiler agents to HSA agents (#708) 
* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2024-04-02 01:38:18 -05:00
Benjamin Welton a79493bbb9 Revert "Add additional debug info and do iteration on per-agent basis" (#723) 
This reverts commit a66d3475b6.

[ROCm/rocprofiler-sdk commit: 4200faf813]
 2024-04-01 22:27:27 -07:00
Benjamin Welton 4200faf813 Revert "Add additional debug info and do iteration on per-agent basis" (#723) 
This reverts commit 6fc239f6eb.
 2024-04-01 22:27:27 -07:00
Charis Poag cdf920f0f4 Merge amd-dev to amd-master 20240401 
Change-Id: Ic4c10b49f58e1f2e220a6c295d54e7ad20f6be2c
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
 2024-04-01 23:04:38 -05:00
Charis Poag b1d422d729 Merge amd-dev to amd-master 20240401 
Change-Id: Ic4c10b49f58e1f2e220a6c295d54e7ad20f6be2c
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: cdf920f0f4]
 2024-04-01 23:04:38 -05:00
Benjamin Welton a66d3475b6 Add additional debug info and do iteration on per-agent basis 
[ROCm/rocprofiler-sdk commit: 6fc239f6eb]
 2024-04-01 18:45:04 -07:00
Benjamin Welton 6fc239f6eb Add additional debug info and do iteration on per-agent basis 2024-04-01 18:45:04 -07:00
Jonathan R. Madsen f2c193a7e6 Update internal threading (#720) 
- update lib/rocprofiler-sdk/internal_threading.*
- use PTL::TaskManager instead of PTL::TaskGroup
  - easier to handle for our needs
  - eliminate data race in rocprofiler_flush_buffer
  - combine memory management of TaskManager and ThreadPool

[ROCm/rocprofiler-sdk commit: 092c428b78]
 2024-04-01 20:31:54 -05:00
Jonathan R. Madsen 092c428b78 Update internal threading (#720) 
- update lib/rocprofiler-sdk/internal_threading.*
- use PTL::TaskManager instead of PTL::TaskGroup
  - easier to handle for our needs
  - eliminate data race in rocprofiler_flush_buffer
  - combine memory management of TaskManager and ThreadPool
 2024-04-01 20:31:54 -05:00
jeffqjiangNew 036a24f829 * rocDecode/AVC: Added support for memory management control operation equal to 5 and fixed an issue in reference picture list modification. (#304) 
Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com>

[ROCm/rocdecode commit: d38931ddae]
 2024-04-01 20:58:31 -04:00
jeffqjiangNew d38931ddae * rocDecode/AVC: Added support for memory management control operation equal to 5 and fixed an issue in reference picture list modification. (#304) 
Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com>
 2024-04-01 20:58:31 -04:00
Kiriti Gowda ed48cecfe0 Setup - Updates (#305) 
[ROCm/rocdecode commit: d6d9c9ed1a]
 2024-04-01 15:53:36 -07:00
Kiriti Gowda d6d9c9ed1a Setup - Updates (#305) 2024-04-01 15:53:36 -07:00
Charis Poag 4d1fab2ef6 Merge amd-staging into amd-master 20240401 
Change-Id: I52c8665735e86deed53645197c11889fc7ece8c5
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/rocm_smi_lib commit: 6fada8c4a6]
 2024-04-01 17:48:06 -05:00
Charis Poag 6fada8c4a6 Merge amd-staging into amd-master 20240401 
Change-Id: I52c8665735e86deed53645197c11889fc7ece8c5
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
 2024-04-01 17:48:06 -05:00
Charis Poag 08a3e76b26 SWDEV-445668 - Align topology JSON 
Updates:
    - [CLI] Updated json output to provide format
      similar to host
      eg.
      [
    {
        "gpu": 0,
        "bdf": "0000:01:00.0",
        "links": [
            {
                "gpu": 0,
                "bdf": "0000:01:00.0",
                "weight": 0,
                "link_status": "ENABLED",
                "link_type": "SELF",
                "num_hops": 0,
                "bandwidth": "N/A",
                "fb_sharing": "ENABLED"
            },
            {
                "gpu": 1,
                "bdf": "0001:01:00.0",
                "weight": 15,
                "link_status": "ENABLED",
                "link_type": "XGMI",
                "num_hops": 1,
                "bandwidth": "50000-100000",
                "fb_sharing": "ENABLED"
            },
        ...
        ]
    },
    {
    ...

Change-Id: I63217f63a4d6ebc23a8a84eaac9dbb7aff5f4cb4
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
 2024-04-01 18:37:06 -04:00
Charis Poag da77ac3975 SWDEV-445668 - Align topology JSON 
Updates:
    - [CLI] Updated json output to provide format
      similar to host
      eg.
      [
    {
        "gpu": 0,
        "bdf": "0000:01:00.0",
        "links": [
            {
                "gpu": 0,
                "bdf": "0000:01:00.0",
                "weight": 0,
                "link_status": "ENABLED",
                "link_type": "SELF",
                "num_hops": 0,
                "bandwidth": "N/A",
                "fb_sharing": "ENABLED"
            },
            {
                "gpu": 1,
                "bdf": "0001:01:00.0",
                "weight": 15,
                "link_status": "ENABLED",
                "link_type": "XGMI",
                "num_hops": 1,
                "bandwidth": "50000-100000",
                "fb_sharing": "ENABLED"
            },
        ...
        ]
    },
    {
    ...

Change-Id: I63217f63a4d6ebc23a8a84eaac9dbb7aff5f4cb4
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 08a3e76b26]
 2024-04-01 18:37:06 -04:00
Aryan Salmanpour 74b4963c90 Add support for passing the correct device id when initializing the va-api decoder (#8) 
[ROCm/rocjpeg commit: 363205c9a8]
 2024-04-01 18:06:44 -04:00
Aryan Salmanpour 363205c9a8 Add support for passing the correct device id when initializing the va-api decoder (#8) 2024-04-01 18:06:44 -04:00