76333 Коммитов

Автор SHA1 Сообщение Дата
akolliasAMD bc7df769a2 AllReduceTests,fixed the number of roots (#925)
[ROCm/rccl commit: d8dc282eeb]
2023-10-20 10:25:11 -06:00
akolliasAMD d8dc282eeb AllReduceTests,fixed the number of roots (#925) 2023-10-20 10:25:11 -06:00
dependabot[bot] 187e9c1958 Bump urllib3 from 1.26.17 to 1.26.18 in /docs/sphinx (#921)
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.17 to 1.26.18.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/1.26.17...1.26.18)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-type: indirect
...

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

[ROCm/rccl commit: b173c13831]
2023-10-20 10:15:42 -06:00
dependabot[bot] b173c13831 Bump urllib3 from 1.26.17 to 1.26.18 in /docs/sphinx (#921)
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.17 to 1.26.18.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/1.26.17...1.26.18)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-10-20 10:15:42 -06:00
searlmc1 40b869acca Merge pull request #926 from ROCmSoftwarePlatform/searlmc1-patch-1
Remove quotes causing asan build breakage

[ROCm/rccl commit: dd5f01aeaf]
2023-10-20 07:52:39 -07:00
searlmc1 dd5f01aeaf Merge pull request #926 from ROCmSoftwarePlatform/searlmc1-patch-1
Remove quotes causing asan build breakage
2023-10-20 07:52:39 -07:00
jeffqjiangNew 9b158f2b07 Add debug functions to log parsed parameter set and header content. (#19)
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.

* rocDecode/HEVC: Changed variable naming to Google style.

* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.

* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.

[ROCm/rocdecode commit: ebe1748888]
2023-10-20 10:39:21 -04:00
jeffqjiangNew ebe1748888 Add debug functions to log parsed parameter set and header content. (#19)
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.

* rocDecode/HEVC: Changed variable naming to Google style.

* rocDecode/HEVC: Added VPS, SPS, PPS, and slice segment header content logging functions for debug purposes.

* rocDecode/HEVC: Compacted opening bracket lines to keep coding style consistency.
2023-10-20 10:39:21 -04:00
Ammar ELWazir c9b5d73ca8 Fixing Usage of session after free
If hsa_shut_down() is not called from the application then we may still have async calls back
to the rocprofiler to use session parameters, thats why we need to leak the session up till
this is fixed in the ROCR-Runtime

Change-Id: Ia8fcdaa859815d88a272296770d702968132e3e6
2023-10-19 23:29:39 -04:00
Ammar ELWazir c0bc40fd5d Fixing Usage of session after free
If hsa_shut_down() is not called from the application then we may still have async calls back
to the rocprofiler to use session parameters, thats why we need to leak the session up till
this is fixed in the ROCR-Runtime

Change-Id: Ia8fcdaa859815d88a272296770d702968132e3e6


[ROCm/rocprofiler commit: c9b5d73ca8]
2023-10-19 23:29:39 -04:00
Jonathan R. Madsen 178bb0c300 Separate agent cache from queue controller (#145)
* Update lib/rocprofiler/agent.{hpp,cpp}

- get_agents() function for internal access to agent pointers

* Update AgentCache

- make member variables and member functions distinguish b/t hsa agent and rocprofiler agent clear

* Change ctor of AgentCache

* Update lib/rocprofiler/hsa/queue_controller.cpp

- QueueController::init uses agent::get_agent_cache

* Update lib/rocprofiler/hsa/agent_cache.*

- member function to get index
- operator== for rocprofiler_agent_t and hsa_agent_t
- removed hsa_iterate_agents from ctor (now in agent.cpp)

* Update lib/rocprofiler/agent.*

- construct_agent_cache function
- functions for rocprofiler agent <-> HSA agent
- functions for getting agent cache

* Update lib/rocprofiler/registration.cpp

- invoke construct_agent_cache when HSA table is receieved

* Update lib/rocprofiler/agent.cpp

- loosen failure conditions
- handle spurious duplicate entry warning

* Update lib/rocprofiler/agent.cpp

- improve read_map diagnostics

* Update lib/rocprofiler/agent.cpp

- avoid infinite loop in read_map

* Update lib/rocprofiler/agent.cpp

- handle empty kfd node properties file

* Update lib/rocprofiler/agent.cpp

- check for permissions to read a node properties file

* Update lib/rocprofiler/agent.cpp

- more checks on file readability

* Update lib/rocprofiler/tests/agent.cpp

- print virtual kfd topology

* Update lib/rocprofiler/tests/agent.cpp

- verify id.handle == hsa_agent internal node id

* Update lib/rocprofiler/tests/agent.cpp

- check node_id
- check location id
- check device id
- update abi test

* Update include/rocprofiler/agent.h

- add node_id field
- add reserved0 field to ensure new field increases struct size

* Update lib/rocprofiler/agent.cpp

- node_id instead of id.handle

* Update lib/rocprofiler/agent_cache.cpp

- node_id instead of id.handle

* Update samples/pc_sampling

- node_id for agent instead of id.handle

* Update lib/rocprofiler/buffer.cpp

- remove debug prints

[ROCm/rocprofiler-sdk commit: 7f631de401]
2023-10-19 19:04:02 -05:00
Jonathan R. Madsen 7f631de401 Separate agent cache from queue controller (#145)
* Update lib/rocprofiler/agent.{hpp,cpp}

- get_agents() function for internal access to agent pointers

* Update AgentCache

- make member variables and member functions distinguish b/t hsa agent and rocprofiler agent clear

* Change ctor of AgentCache

* Update lib/rocprofiler/hsa/queue_controller.cpp

- QueueController::init uses agent::get_agent_cache

* Update lib/rocprofiler/hsa/agent_cache.*

- member function to get index
- operator== for rocprofiler_agent_t and hsa_agent_t
- removed hsa_iterate_agents from ctor (now in agent.cpp)

* Update lib/rocprofiler/agent.*

- construct_agent_cache function
- functions for rocprofiler agent <-> HSA agent
- functions for getting agent cache

* Update lib/rocprofiler/registration.cpp

- invoke construct_agent_cache when HSA table is receieved

* Update lib/rocprofiler/agent.cpp

- loosen failure conditions
- handle spurious duplicate entry warning

* Update lib/rocprofiler/agent.cpp

- improve read_map diagnostics

* Update lib/rocprofiler/agent.cpp

- avoid infinite loop in read_map

* Update lib/rocprofiler/agent.cpp

- handle empty kfd node properties file

* Update lib/rocprofiler/agent.cpp

- check for permissions to read a node properties file

* Update lib/rocprofiler/agent.cpp

- more checks on file readability

* Update lib/rocprofiler/tests/agent.cpp

- print virtual kfd topology

* Update lib/rocprofiler/tests/agent.cpp

- verify id.handle == hsa_agent internal node id

* Update lib/rocprofiler/tests/agent.cpp

- check node_id
- check location id
- check device id
- update abi test

* Update include/rocprofiler/agent.h

- add node_id field
- add reserved0 field to ensure new field increases struct size

* Update lib/rocprofiler/agent.cpp

- node_id instead of id.handle

* Update lib/rocprofiler/agent_cache.cpp

- node_id instead of id.handle

* Update samples/pc_sampling

- node_id for agent instead of id.handle

* Update lib/rocprofiler/buffer.cpp

- remove debug prints
2023-10-19 19:04:02 -05:00
searlmc1 212453b2fb Remove quotes causing asan build breakage
The quotes around "-fsanitize=address -shared-libasan" cause the BUILD_ADDRESS_SANITIZER build to fail; remove the quotes

[ROCm/rccl commit: f59de10524]
2023-10-19 16:13:39 -07:00
searlmc1 f59de10524 Remove quotes causing asan build breakage
The quotes around "-fsanitize=address -shared-libasan" cause the BUILD_ADDRESS_SANITIZER build to fail; remove the quotes
2023-10-19 16:13:39 -07:00
Bertan Dogancay 1a538d0218 Update install.sh --fast and README (#924)
[ROCm/rccl commit: 3807c203fc]
2023-10-19 16:35:10 -06:00
Bertan Dogancay 3807c203fc Update install.sh --fast and README (#924) 2023-10-19 16:35:10 -06:00
Galantsev, Dmitrii e579cb04b2 Upgrade gRPC v1.44.0 -> v1.59.1
Change-Id: Ib43a41c61d4028ec029a8c179a94060315870fbb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2023-10-19 17:29:36 -05:00
Galantsev, Dmitrii ff9f16b7b5 Upgrade gRPC v1.44.0 -> v1.59.1
Change-Id: Ib43a41c61d4028ec029a8c179a94060315870fbb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: e579cb04b2]
2023-10-19 17:29:36 -05:00
Wenkai Du 6f0f614d0b Remove LDS based software barriers from MSCCL (#923)
[ROCm/rccl commit: dbb5611a3a]
2023-10-19 16:39:41 -05:00
Wenkai Du dbb5611a3a Remove LDS based software barriers from MSCCL (#923) 2023-10-19 16:39:41 -05:00
Galantsev, Dmitrii e211b6838a rocm_smi.py - Fix checkIfSecondaryDie duplicate
fixes:
https://github.com/RadeonOpenCompute/rocm_smi_lib/issues/128

Change-Id: I9b01c3fc4d255e01423cca25b9c924630b8cf326
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rocm_smi_lib commit: 2254d3e376]
2023-10-19 16:57:08 -04:00
Galantsev, Dmitrii 2254d3e376 rocm_smi.py - Fix checkIfSecondaryDie duplicate
fixes:
https://github.com/RadeonOpenCompute/rocm_smi_lib/issues/128

Change-Id: I9b01c3fc4d255e01423cca25b9c924630b8cf326
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2023-10-19 16:57:08 -04:00
Nirmal Unnikrishnan ece91364b7 SWDEV-427268 SWDEV-427256 : Removing dependency with patchelf completely
Change-Id: I71ccebdbbd9b3c79ea8412acd54a71a96af3e26f


[ROCm/rocm-core commit: 628b2c04f6]
2023-10-19 15:42:23 -05:00
Nirmal Unnikrishnan 628b2c04f6 SWDEV-427268 SWDEV-427256 : Removing dependency with patchelf completely
Change-Id: I71ccebdbbd9b3c79ea8412acd54a71a96af3e26f
2023-10-19 15:42:23 -05:00
Nirmal Unnikrishnan 5756d661e3 SWDEV-427268 SWDEV-427256 : Changing the patchelf package from requirement to recommends
Change-Id: I2c909f2a7a7fc601be1890bfbcef50177695931b


[ROCm/rocm-core commit: 0f9d273351]
2023-10-19 15:42:23 -05:00
Nirmal Unnikrishnan 0f9d273351 SWDEV-427268 SWDEV-427256 : Changing the patchelf package from requirement to recommends
Change-Id: I2c909f2a7a7fc601be1890bfbcef50177695931b
2023-10-19 15:42:23 -05:00
Nirmal Unnikrishnan f65997eb83 SWDEV-310152 : Adding script to convert RUNPATH to RPATH in libs/bins
Change-Id: Ic6c49544cb7450384592b4f5609fb394f1f12f02


[ROCm/rocm-core commit: 5f59a6e538]
2023-10-19 15:42:23 -05:00
Nirmal Unnikrishnan 5f59a6e538 SWDEV-310152 : Adding script to convert RUNPATH to RPATH in libs/bins
Change-Id: Ic6c49544cb7450384592b4f5609fb394f1f12f02
2023-10-19 15:42:23 -05:00
Ranjith Ramakrishnan d10d2fdd6f SWDEV-415345 - Correct the installation path of rocm_version.h header file
Added file reorg backward compatibility support by creating wrapper header file.

Change-Id: Iee4644c8ae51ba508c21abb765a1e1d974dc6e97


[ROCm/rocm-core commit: 1e6cde3478]
2023-10-19 15:38:56 -05:00
Ranjith Ramakrishnan 1e6cde3478 SWDEV-415345 - Correct the installation path of rocm_version.h header file
Added file reorg backward compatibility support by creating wrapper header file.

Change-Id: Iee4644c8ae51ba508c21abb765a1e1d974dc6e97
2023-10-19 15:38:56 -05:00
Benjamin Welton cb190b72f1 Migrate tracer performance fixes from roctracer
Change-Id: If9e1349537cce23b7be1d8530d795744a8cd07b1
2023-10-19 20:34:12 +00:00
Benjamin Welton 1e6d394c7a Migrate tracer performance fixes from roctracer
Change-Id: If9e1349537cce23b7be1d8530d795744a8cd07b1


[ROCm/rocprofiler commit: cb190b72f1]
2023-10-19 20:34:12 +00:00
Jonathan R. Madsen 6c26870c8c Query callback and buffered tracing names (#135)
* Update include/rocprofiler/buffer_tracing.h

- add query functions for kind name, and kind operation name
- tweak iterate functions to not be specifically dedicated to names

* Update include/rocprofiler/callback_tracing.h

- add query functions for kind name, and kind operation name
- tweak iterate functions to not be specifically dedicated to names

* Update lib/rocprofiler/callback_tracing.cpp

- implement rocprofiler_query_callback_tracing_kind_name
- implement rocprofiler_query_callback_tracing_kind_name_buf
- implement rocprofiler_query_callback_tracing_kind_operation_name
- implement rocprofiler_query_callback_tracing_kind_operation_name_buf
- implement rocprofiler_iterate_callback_tracing_kinds
- implement rocprofiler_iterate_callback_tracing_kind_operations

* Update lib/rocprofiler/buffer_tracing.cpp

- implement rocprofiler_query_buffer_tracing_kind_name
- implement rocprofiler_query_buffer_tracing_kind_name_buf
- implement rocprofiler_query_buffer_tracing_kind_operation_name
- implement rocprofiler_query_buffer_tracing_kind_operation_name_buf
- implement rocprofiler_iterate_buffer_tracing_kinds
- implement rocprofiler_iterate_buffer_tracing_kind_operations

* Update lib/rocprofiler/tests/registration.cpp

- use new implementation for getting callback/buffer tracing names

* Update samples/api_buffered_tracing

- use new implementation for getting callback/buffer tracing names

* Update samples/api_callback_tracing

- use new implementation for getting callback/buffer tracing names

* Remove buffered query functions

- *_buf variants of the rocprofiler_query_X_tracing_Y functions were removed since we currently have no names requiring these functions

* Rename ROCPROFILER_STATUS_ERROR_DOMAIN_NOT_FOUND

- "DOMAIN" changed to "KIND" since former is more specific tracing whereas kind is used more generically

[ROCm/rocprofiler-sdk commit: 87cc748c3d]
2023-10-19 15:21:07 -05:00
Jonathan R. Madsen 87cc748c3d Query callback and buffered tracing names (#135)
* Update include/rocprofiler/buffer_tracing.h

- add query functions for kind name, and kind operation name
- tweak iterate functions to not be specifically dedicated to names

* Update include/rocprofiler/callback_tracing.h

- add query functions for kind name, and kind operation name
- tweak iterate functions to not be specifically dedicated to names

* Update lib/rocprofiler/callback_tracing.cpp

- implement rocprofiler_query_callback_tracing_kind_name
- implement rocprofiler_query_callback_tracing_kind_name_buf
- implement rocprofiler_query_callback_tracing_kind_operation_name
- implement rocprofiler_query_callback_tracing_kind_operation_name_buf
- implement rocprofiler_iterate_callback_tracing_kinds
- implement rocprofiler_iterate_callback_tracing_kind_operations

* Update lib/rocprofiler/buffer_tracing.cpp

- implement rocprofiler_query_buffer_tracing_kind_name
- implement rocprofiler_query_buffer_tracing_kind_name_buf
- implement rocprofiler_query_buffer_tracing_kind_operation_name
- implement rocprofiler_query_buffer_tracing_kind_operation_name_buf
- implement rocprofiler_iterate_buffer_tracing_kinds
- implement rocprofiler_iterate_buffer_tracing_kind_operations

* Update lib/rocprofiler/tests/registration.cpp

- use new implementation for getting callback/buffer tracing names

* Update samples/api_buffered_tracing

- use new implementation for getting callback/buffer tracing names

* Update samples/api_callback_tracing

- use new implementation for getting callback/buffer tracing names

* Remove buffered query functions

- *_buf variants of the rocprofiler_query_X_tracing_Y functions were removed since we currently have no names requiring these functions

* Rename ROCPROFILER_STATUS_ERROR_DOMAIN_NOT_FOUND

- "DOMAIN" changed to "KIND" since former is more specific tracing whereas kind is used more generically
2023-10-19 15:21:07 -05:00
taosang2 28524520e6 SWDEV-364236 - Fix layered Image issue
Fix wrong logic to get layer index;
Make layered image's layout match cuda spec;
Fix wrong comparision of element size.
Remove amd::BufferRect from ihipMemcpyAtoHCommand()
and ihipMemcpyHtoACommand().
Change-Id: Icc6a4233fbce2e9b2dc6feb79e6bfbd761684c7d


[ROCm/clr commit: 5a0085e516]
2023-10-19 16:06:20 -04:00
taosang2 5a0085e516 SWDEV-364236 - Fix layered Image issue
Fix wrong logic to get layer index;
Make layered image's layout match cuda spec;
Fix wrong comparision of element size.
Remove amd::BufferRect from ihipMemcpyAtoHCommand()
and ihipMemcpyHtoACommand().
Change-Id: Icc6a4233fbce2e9b2dc6feb79e6bfbd761684c7d
2023-10-19 16:06:20 -04:00
Bertan Dogancay c07676388b Fixing hipcc location for develop CI (#52)
[ROCm/rccl-tests commit: 8bfb67faf3]
2023-10-19 13:29:42 -06:00
Bertan Dogancay 8bfb67faf3 Fixing hipcc location for develop CI (#52) 2023-10-19 13:29:42 -06:00
Benjamin Welton d05031db89 Limit the number of HSA signals that are active (#140)
* Limit the number of HSA signals that are active

There is a hard limit currently to the number of
signals that HSA allows to be created (before weird stuff
happens such as hangs or straight up crashes in HSA). While
there is some work going on to fix this in HSA/AQL. Lets limit the
number we create.

Increased the counter colleciton example to 200K launches, which
with this change no longer hangs/crashes randomly in HSA.

* source formatting (clang-format v11) (#142)

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

* Up timout

---------

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

[ROCm/rocprofiler-sdk commit: de685246a7]
2023-10-19 13:18:42 -05:00
Benjamin Welton de685246a7 Limit the number of HSA signals that are active (#140)
* Limit the number of HSA signals that are active

There is a hard limit currently to the number of
signals that HSA allows to be created (before weird stuff
happens such as hangs or straight up crashes in HSA). While
there is some work going on to fix this in HSA/AQL. Lets limit the
number we create.

Increased the counter colleciton example to 200K launches, which
with this change no longer hangs/crashes randomly in HSA.

* source formatting (clang-format v11) (#142)

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

* Up timout

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
2023-10-19 13:18:42 -05:00
jeffqjiangNew b51ce09f9b Jj/hevc decode wip (#18)
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.

* rocDecode/HEVC: Changed variable naming to Google style.

[ROCm/rocdecode commit: 94ff35e03c]
2023-10-19 14:07:36 -04:00
jeffqjiangNew 94ff35e03c Jj/hevc decode wip (#18)
* rocDecode/HEVC parsing: Implemented correct logic to set active VPS, SPS and PPS: start from slice header and up. Added video image size change detection. Fixed slice_segment_address bits calculation in slice segment header parsing.

* rocDecode/HEVC: Changed variable naming to Google style.
2023-10-19 14:07:36 -04:00
Saurabh Verma 1e1692e6c0 SWDEV-427921: Fixing rocprof v1 counter collection for PAPI on MI300
Change-Id: I8589fe78fca481ed326e584ea1d01c0f90de655e
2023-10-19 13:40:32 -04:00
Saurabh Verma 87654ec8b2 SWDEV-427921: Fixing rocprof v1 counter collection for PAPI on MI300
Change-Id: I8589fe78fca481ed326e584ea1d01c0f90de655e


[ROCm/rocprofiler commit: 1e1692e6c0]
2023-10-19 13:40:32 -04:00
Jonathan R. Madsen 162c77d349 Conditional Queue Interception (#141)
- only intercept queue if there is a context that requires it
- make copy of HSA API table after internal modifications to the table to prevent those changes being lost when HSA API tracing is enabled

[ROCm/rocprofiler-sdk commit: 5819ca589f]
2023-10-19 11:43:15 -05:00
Jonathan R. Madsen 5819ca589f Conditional Queue Interception (#141)
- only intercept queue if there is a context that requires it
- make copy of HSA API table after internal modifications to the table to prevent those changes being lost when HSA API tracing is enabled
2023-10-19 11:43:15 -05:00
Nirmal Unnikrishnan 54209af6da SWDEV-427268 SWDEV-427256 : Removing dependency with patchelf completely
Change-Id: I71ccebdbbd9b3c79ea8412acd54a71a96af3e26f


[ROCm/rocm-core commit: 1544e398c6]
2023-10-19 10:39:03 -05:00
Nirmal Unnikrishnan 1544e398c6 SWDEV-427268 SWDEV-427256 : Removing dependency with patchelf completely
Change-Id: I71ccebdbbd9b3c79ea8412acd54a71a96af3e26f
2023-10-19 10:39:03 -05:00
Benjamin Welton f08a32bed2 Replace direct file out with stringstream
Change-Id: Id0a00d918df88d0031f9c8f847e65b416c09bf77


[ROCm/roctracer commit: 54777ece26]
2023-10-19 15:28:16 +00:00
Benjamin Welton 54777ece26 Replace direct file out with stringstream
Change-Id: Id0a00d918df88d0031f9c8f847e65b416c09bf77
2023-10-19 15:28:16 +00:00