Nilesh M Negi
a6972c0d09
Revert "[SRC] Enable unroll=1 for gfx950 ( #1602 )" ( #1667 )
...
* Revert "[SRC] Enable unroll=1 for gfx950 (#1602 )"
This reverts commit 210f90ae0f .
* Update Changelog
---------
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com >
[ROCm/rccl commit: 329e13efff ]
2025-04-30 23:33:08 -05:00
Nilesh M Negi
329e13efff
Revert "[SRC] Enable unroll=1 for gfx950 ( #1602 )" ( #1667 )
...
* Revert "[SRC] Enable unroll=1 for gfx950 (#1602 )"
This reverts commit 307bc10781 .
* Update Changelog
---------
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com >
2025-04-30 23:33:08 -05:00
Assiouras, Ioannis
3d4ff304d7
SWDEV-521011 - Fix alignment in PalResource::CreateSvm
...
[ROCm/clr commit: 9d6a0d1a4d ]
2025-05-01 02:22:49 +01:00
Assiouras, Ioannis
9d6a0d1a4d
SWDEV-521011 - Fix alignment in PalResource::CreateSvm
2025-05-01 02:22:49 +01:00
deeksha-amd
5580cb7574
Added new tests for improving the code coverage ( #1656 )
...
Signed-off-by: Deeksha Goplani <deeksha.goplani@amd.com >
[ROCm/rccl commit: 2486838465 ]
2025-04-30 18:01:11 -05:00
deeksha-amd
2486838465
Added new tests for improving the code coverage ( #1656 )
...
Signed-off-by: Deeksha Goplani <deeksha.goplani@amd.com >
2025-04-30 18:01:11 -05:00
Cheruvally, Aravindan
4215053152
Re Enable SWDEV-521313 Streamline Version Management ( #10 )
...
Revert "Revert "SWDEV-521313 - Streamline Version Management: Retain Only version-roc…""
This reverts commit c48c9dac80 .
[ROCm/rocm-core commit: de37842d6a ]
2025-04-30 18:56:11 -04:00
Cheruvally, Aravindan
de37842d6a
Re Enable SWDEV-521313 Streamline Version Management ( #10 )
...
Revert "Revert "SWDEV-521313 - Streamline Version Management: Retain Only version-roc…""
This reverts commit 39bd62e592 .
2025-04-30 18:56:11 -04:00
isaki001
de76d7f649
Add Compilation Flag for enabling/disabling clipping, and tune number of blocks for mscclpp allreduce8 ( #1607 )
...
* mscclpp patch apply clip patch and set allreduce8 blocks from 512 to 1024
* add compilation flag for enabling/disabling clipping in mscclpp
* change flag name for consistency, set flag to OFF
* add compilation flag in rccl for enabling clipping in mscclpp
* set 1024 threads for mscclpp allreduce8 only for bfloat16
* fix improper description for ENABLE_MSCCLPP_CLIP flag
* Revert "Merge branch 'clip-patch' of https://github.com/isaki001/rccl into clip-patch"
This reverts commit 6e31857a9db98314b8a748eb024f2c3699ebe2d5, reversing
changes made to 193f4caa8ffa78b4e056893212fd8344aa14e937.
* update clip remove-clip.patch for rebase
[ROCm/rccl commit: 8145c4f3b8 ]
2025-04-30 16:42:28 -05:00
isaki001
8145c4f3b8
Add Compilation Flag for enabling/disabling clipping, and tune number of blocks for mscclpp allreduce8 ( #1607 )
...
* mscclpp patch apply clip patch and set allreduce8 blocks from 512 to 1024
* add compilation flag for enabling/disabling clipping in mscclpp
* change flag name for consistency, set flag to OFF
* add compilation flag in rccl for enabling clipping in mscclpp
* set 1024 threads for mscclpp allreduce8 only for bfloat16
* fix improper description for ENABLE_MSCCLPP_CLIP flag
* Revert "Merge branch 'clip-patch' of https://github.com/isaki001/rccl into clip-patch"
This reverts commit 6e31857a9db98314b8a748eb024f2c3699ebe2d5, reversing
changes made to 193f4caa8ffa78b4e056893212fd8344aa14e937.
* update clip remove-clip.patch for rebase
2025-04-30 16:42:28 -05:00
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