AI/rocm-systems
2
0
Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Actions Packages Projekty Wydania Wiki Aktywność
74 713 Commity 3 Gałęzie 0 Tagi
fc4422d73bbe21d38d13fac621710e663eaec4c9
Wykres commitów

74713 Commity

This Branch
This Branch
Wszystkie gałęzie
Autor SHA1 Wiadomość Data
BertanDogancay 064062ef70 Merge remote-tracking branch 'nccl/master' into develop 
[ROCm/rccl commit: cb6e23ae67]
 2025-04-30 13:31:41 -05:00
BertanDogancay cb6e23ae67 Merge remote-tracking branch 'nccl/master' into develop 2025-04-30 13:31:41 -05:00
Andryeyev, German 13c7977d50 SWDEV-526836 - add PipelineStageBlt flag (#229) 
CP sync requires PipelineStageBlt flag.


[ROCm/clr commit: 84a4f293f4]
 2025-04-30 14:27:41 -04:00
Andryeyev, German 84a4f293f4 SWDEV-526836 - add PipelineStageBlt flag (#229) 
CP sync requires PipelineStageBlt flag.
 2025-04-30 14:27:41 -04:00
Tim 33c390b36e minor fix for empty scope (group) (#1666) 
[ROCm/rccl commit: dc0c5f9153]
 2025-04-30 13:29:13 -04:00
Tim dc0c5f9153 minor fix for empty scope (group) (#1666) 2025-04-30 13:29:13 -04:00
Brzak, Branislav f63e3e9c0a SWDEV-515519 - Synchronize after mem pool trim (#89) 
[ROCm/hip-tests commit: 3f30d6d8ea]
 2025-04-30 16:09:15 +02:00
Brzak, Branislav 3f30d6d8ea SWDEV-515519 - Synchronize after mem pool trim (#89) 2025-04-30 16:09:15 +02:00
Luca Bruni 579596dbba Appropriately filter data based on -D and -H options (#163) 
- Addresses concern that device metric tracks are still shown in Perfetto trace file even when only -H is specified to rocprof-sys-sample (and vice versa).
- Update sampling call-stack docs.

[ROCm/rocprofiler-systems commit: 8ae6651357]
 2025-04-30 09:50:51 -04:00
Luca Bruni 8ae6651357 Appropriately filter data based on -D and -H options (#163) 
- Addresses concern that device metric tracks are still shown in Perfetto trace file even when only -H is specified to rocprof-sys-sample (and vice versa).
- Update sampling call-stack docs.
 2025-04-30 09:50:51 -04:00
Yiltan 835de6be0e Added XNACK support (#94) 
* Added xnack flags
* Updated examples compile command

[ROCm/rocshmem commit: edcd1ed57e]
 2025-04-30 08:57:55 -04:00
Yiltan edcd1ed57e Added XNACK support (#94) 
* Added xnack flags
* Updated examples compile command
 2025-04-30 08:57:55 -04:00
Assiouras, Ioannis 4efd624960 SWDEV-525593, SWDEV-527293 - Acquire active queue after xferQueue is created (#165) 
For xferQueue VirtualGPU::create is called after ProfilingBegin
so the active queue needs to be acquired.

[ROCm/clr commit: d3fb8eda8b]
 2025-04-30 09:21:11 +01:00
Assiouras, Ioannis d3fb8eda8b SWDEV-525593, SWDEV-527293 - Acquire active queue after xferQueue is created (#165) 
For xferQueue VirtualGPU::create is called after ProfilingBegin
so the active queue needs to be acquired.
 2025-04-30 09:21:11 +01:00
Swargam, Rambabu 7e8e711087 SWDEV-515926 - [catch2][dtest] Tests for Memory Manager for memory pool performance (#155) 
[ROCm/hip-tests commit: 1b60d60f5a]
 2025-04-30 10:11:33 +05:30
Swargam, Rambabu 1b60d60f5a SWDEV-515926 - [catch2][dtest] Tests for Memory Manager for memory pool performance (#155) 2025-04-30 10:11:33 +05:30
Bhardwaj, Gopesh 5dcb2cbdd7 updating fmt submodule to latest release tag (#13) 
* updating fmt submodule to latest release tag

* fix configuration error

[ROCm/rocprofiler-register commit: 4427f2bd6d]
 2025-04-30 09:57:37 +05:30
Bhardwaj, Gopesh 4427f2bd6d updating fmt submodule to latest release tag (#13) 
* updating fmt submodule to latest release tag

* fix configuration error
 2025-04-30 09:57:37 +05:30
Williams, Justin 757aa016f4 [SWDEV-500518/SWDEV-527430] CI v4.1 (#316) 
[SWDEV-500518] CI v4.1

Signed-off-by: Justin Williams <Justin.Williams@amd.com>
 2025-04-29 18:52:32 -05:00
Williams, Justin 3a038c212e [SWDEV-500518/SWDEV-527430] CI v4.1 (#316) 
[SWDEV-500518] CI v4.1

Signed-off-by: Justin Williams <Justin.Williams@amd.com>

[ROCm/amdsmi commit: 757aa016f4]
 2025-04-29 18:52:32 -05:00
Saeed, Oosman 9c297639f3 [SWDEV-529266] [MI308][AMDSMI][RAS CPER] CPER dump not working on CPX mode (#319) 
* Do not raise excepction for cper status not found, but keep iterating to next gpu

* Do not raise excepction for cper status not found, but keep iterating to next gpu

* use partition id and skip if non-zero

* reverting un-needed change

* Do not raise excepction for cper status not found, but keep iterating to next gpu

* use partition id and skip if non-zero

---------

Co-authored-by: Oosman Saeed <oossaeed@amd.com>
 2025-04-29 18:52:32 -05:00
Saeed, Oosman 2391516ced [SWDEV-529266] [MI308][AMDSMI][RAS CPER] CPER dump not working on CPX mode (#319) 
* Do not raise excepction for cper status not found, but keep iterating to next gpu

* Do not raise excepction for cper status not found, but keep iterating to next gpu

* use partition id and skip if non-zero

* reverting un-needed change

* Do not raise excepction for cper status not found, but keep iterating to next gpu

* use partition id and skip if non-zero

---------

Co-authored-by: Oosman Saeed <oossaeed@amd.com>

[ROCm/amdsmi commit: 9c297639f3]
 2025-04-29 18:52:32 -05:00
Kanangot Balakrishnan, Bindhiya e26e26e308 [SWDEV-518229] Avoid N/A leaves filtering from static (#326) 
The N/A leaves filering was removing clock in static.
To avoid this, removed N/A filtering from single tier.

Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>
 2025-04-29 18:52:32 -05:00
Kanangot Balakrishnan, Bindhiya 7201649fbf [SWDEV-518229] Avoid N/A leaves filtering from static (#326) 
The N/A leaves filering was removing clock in static.
To avoid this, removed N/A filtering from single tier.

Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>

[ROCm/amdsmi commit: e26e26e308]
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 81c65ed15d Added DRM check back for market name 2025-04-29 18:52:32 -05:00
gabrpham_amdeng c3a39f5439 Added DRM check back for market name 
[ROCm/amdsmi commit: 81c65ed15d]
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 59f0f3f9eb [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 950ba44df5 [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 59f0f3f9eb]
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 4e232e287d [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 903cf4fe57 [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 4e232e287d]
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 1ab57ce7dd [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
 2025-04-29 18:52:32 -05:00
gabrpham_amdeng 640eba7764 [SWDEV-529889] Fixed incorrect vendor_id reporting in amdsmi_get_gpu_asic_info 
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 1ab57ce7dd]
 2025-04-29 18:52:32 -05:00
Maisam Arif ea1b24003e Removed post install pciids udpate 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: If6a3fcec4778c99246e899890f1d586656841d3e
 2025-04-29 18:52:32 -05:00
Maisam Arif 597edb6eb8 Removed post install pciids udpate 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: If6a3fcec4778c99246e899890f1d586656841d3e


[ROCm/amdsmi commit: ea1b24003e]
 2025-04-29 18:52:32 -05:00
Pham, Gabriel 34678cc0ae [SWDEV-522336] Enabled Topology command in Guest (#304) 
Enabled Topology command in Guest

---------

Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
 2025-04-29 18:52:32 -05:00
Pham, Gabriel 4992a7b2bd [SWDEV-522336] Enabled Topology command in Guest (#304) 
Enabled Topology command in Guest

---------

Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: 34678cc0ae]
 2025-04-29 18:52:32 -05:00
Poag, Charis 6a43b64d0c [SWDEV-518561] P1: Inconsistent memory partition change (#315) 
Changes:
- Cleaned up drm connections before changing memory partitions

Change-Id: I08430d22536bb6094c91a06fbf2f74d9b75a4fa7

Signed-off-by: Charis Poag <Charis.Poag@amd.com>
 2025-04-29 18:52:32 -05:00
Poag, Charis cab1c46165 [SWDEV-518561] P1: Inconsistent memory partition change (#315) 
Changes:
- Cleaned up drm connections before changing memory partitions

Change-Id: I08430d22536bb6094c91a06fbf2f74d9b75a4fa7

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

[ROCm/amdsmi commit: 6a43b64d0c]
 2025-04-29 18:52:32 -05:00
David Yat Sin 4ed5950beb rocr: Fix logic for scratch reclaim 
Fix logic error that can cause scratch memory to be reclaimed while a
dispatch is still using it.
 2025-04-29 17:23:45 -04:00
David Yat Sin b48b401a09 rocr: Fix logic for scratch reclaim 
Fix logic error that can cause scratch memory to be reclaimed while a
dispatch is still using it.


[ROCm/ROCR-Runtime commit: 4ed5950beb]
 2025-04-29 17:23:45 -04:00
Edgar Gabriel 38346e5bdd use correct MPI initialization method (#90) 
* use correct MPI initialization method

rocSHMEM requires that the MPI library is initialized using
THREAD_MULTIPLE support. Lets use that function therefore in our
examples.

* Update examples/rocshmem_init_attr_test.cc

Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>

---------

Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>

[ROCm/rocshmem commit: 2e01af22ca]
 2025-04-29 16:22:46 -05:00
Edgar Gabriel 2e01af22ca use correct MPI initialization method (#90) 
* use correct MPI initialization method

rocSHMEM requires that the MPI library is initialized using
THREAD_MULTIPLE support. Lets use that function therefore in our
examples.

* Update examples/rocshmem_init_attr_test.cc

Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>

---------

Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
 2025-04-29 16:22:46 -05:00
Marius Brehler b0b615091e Link Threads::Threads (#119) 
`pthread.h` is included in `src/common.h` but lib is not properly
linked, resulting in the build failing with unresolved symbols when
trying to link.

[ROCm/rccl-tests commit: 5b27b961b2]
 2025-04-29 16:18:51 -05:00
Marius Brehler 5b27b961b2 Link Threads::Threads (#119) 
`pthread.h` is included in `src/common.h` but lib is not properly
linked, resulting in the build failing with unresolved symbols when
trying to link.
 2025-04-29 16:18:51 -05:00
Cheruvally, Aravindan 9d3c82bc22 Update Pre/Post File Permissions to 0755 (#12) 
[ROCm/rocm-core commit: 0578cf70ef]
 2025-04-29 15:49:53 -04:00
Cheruvally, Aravindan 0578cf70ef Update Pre/Post File Permissions to 0755 (#12) 2025-04-29 15:49:53 -04:00
Godavarthy Surya, Anusha e4a499f22e SWDEV-522841 - Graph nodes must be created/launched on device where they are captured/created (#108) 
[ROCm/clr commit: 2538d7f02b]
 2025-04-29 22:20:39 +05:30
Godavarthy Surya, Anusha 2538d7f02b SWDEV-522841 - Graph nodes must be created/launched on device where they are captured/created (#108) 2025-04-29 22:20:39 +05:30
GunaShekar, Ajay d14f5ed76f SWDEV-524925 - hip-tests build with custom hip (#65) 
[ROCm/hip-tests commit: 52e72e9e00]
 2025-04-29 08:51:04 -07:00
GunaShekar, Ajay 52e72e9e00 SWDEV-524925 - hip-tests build with custom hip (#65) 2025-04-29 08:51:04 -07:00