Commit Graph

64562 Commits

Author SHA1 Message Date
Brzak, Branislav cc6bfe71fc SWDEV-528683 - Hardcode valid wavefront compile time options (#306)
[ROCm/clr commit: f9199ac205]
2025-05-12 19:29:39 +02:00
Brzak, Branislav f9199ac205 SWDEV-528683 - Hardcode valid wavefront compile time options (#306) 2025-05-12 19:29:39 +02:00
Andryeyev, German b9669ea266 SWDEV-531678 - Remove split path from the dispatch (#283)
The split path for blit kernels are no longer necessary, since the new blit kernels
don't use the copy size as the global workload

[ROCm/clr commit: da198ac5b2]
2025-05-12 12:50:32 -04:00
Andryeyev, German da198ac5b2 SWDEV-531678 - Remove split path from the dispatch (#283)
The split path for blit kernels are no longer necessary, since the new blit kernels
don't use the copy size as the global workload
2025-05-12 12:50:32 -04:00
Jayaprakash, Karthik 5dff283f4e SWDEV-526855 - Modify the SIMDPerCU calculation for gfx1250/1. (#275)
[ROCm/clr commit: acb1f7e8d5]
2025-05-12 11:09:03 -04:00
Jayaprakash, Karthik acb1f7e8d5 SWDEV-526855 - Modify the SIMDPerCU calculation for gfx1250/1. (#275) 2025-05-12 11:09:03 -04:00
Arandjelovic, Marko 3d862af4df SWDEV-512344 - Unmap all subbuffers (#214)
[ROCm/clr commit: c5ced8c3a2]
2025-05-12 16:56:10 +02:00
Arandjelovic, Marko c5ced8c3a2 SWDEV-512344 - Unmap all subbuffers (#214) 2025-05-12 16:56:10 +02:00
Arandjelovic, Marko 558a26cf98 SWDEV-511204 - Mapped virtual memory should use device instead of host context (#213)
Since the sub-buffer(virtual memory that is mapped to device memory) is associated with device memory, it should utilize the device context instead of the host context. The original implementation caused hipMemcpyPeer to not take the P2P path, as the memory object was treated as host memory.

[ROCm/clr commit: a7492c516d]
2025-05-12 16:55:25 +02:00
Arandjelovic, Marko a7492c516d SWDEV-511204 - Mapped virtual memory should use device instead of host context (#213)
Since the sub-buffer(virtual memory that is mapped to device memory) is associated with device memory, it should utilize the device context instead of the host context. The original implementation caused hipMemcpyPeer to not take the P2P path, as the memory object was treated as host memory.
2025-05-12 16:55:25 +02:00
Mishra, Ashutosh 075edc8875 Restoring the correct installation path (#20)
SWDEV-532187: The installation was failing
because of the same path used in all of the
packages. This patch seprates the same.

[ROCm/rocm-core commit: fb51f1d7d9]
2025-05-12 20:03:03 +05:30
Mishra, Ashutosh fb51f1d7d9 Restoring the correct installation path (#20)
SWDEV-532187: The installation was failing
because of the same path used in all of the
packages. This patch seprates the same.
2025-05-12 20:03:03 +05:30
Ashutosh Mishra 1f395fb3c4 Restoring the correct installation path
SWDEV-532187: The installation was failing
because of the same path used in all of the
packages. This patch seprates the same.

Signed-off-by: Ashutosh Mishra <ashutosh.mishra@amd.com>


[ROCm/rocm-core commit: fcd3952708]
2025-05-12 17:23:54 +05:30
Ashutosh Mishra fcd3952708 Restoring the correct installation path
SWDEV-532187: The installation was failing
because of the same path used in all of the
packages. This patch seprates the same.

Signed-off-by: Ashutosh Mishra <ashutosh.mishra@amd.com>
2025-05-12 17:23:54 +05:30
Bhardwaj, Gopesh 0f877ea176 Replacing ROCm 6.5 mentions with ROCm 7.0 (#391)
[ROCm/rocprofiler-sdk commit: fbab96e552]
2025-05-12 17:05:45 +05:30
Bhardwaj, Gopesh fbab96e552 Replacing ROCm 6.5 mentions with ROCm 7.0 (#391) 2025-05-12 17:05:45 +05:30
Patel, Jaydeepkumar 0a42915f18 SWDEV-521135 - Remove Unit_UUID_setEnv_Thread_Lock and correct uuidList.cc (#31)
[ROCm/hip-tests commit: 8abcd95564]
2025-05-12 17:00:46 +05:30
Patel, Jaydeepkumar 8abcd95564 SWDEV-521135 - Remove Unit_UUID_setEnv_Thread_Lock and correct uuidList.cc (#31) 2025-05-12 17:00:46 +05:30
Patel, Jaydeepkumar 5bd5f3aa6e SWDEV-521135 - Make common way to set/parse UUID bytes from PAL props. (#63)
[ROCm/clr commit: 6858b0fca1]
2025-05-12 17:00:30 +05:30
Patel, Jaydeepkumar 6858b0fca1 SWDEV-521135 - Make common way to set/parse UUID bytes from PAL props. (#63) 2025-05-12 17:00:30 +05:30
Mishra, Ashutosh 6ba697fed4 Adding condition for static package type (#19)
SWDEV-532030 : Static builds are failing
for mainline and release because COMP_TYPE
is empty in case of static builds.
This patch fixes the same.

[ROCm/rocm-core commit: d31bc9e2cc]
2025-05-12 15:55:51 +05:30
Mishra, Ashutosh d31bc9e2cc Adding condition for static package type (#19)
SWDEV-532030 : Static builds are failing
for mainline and release because COMP_TYPE
is empty in case of static builds.
This patch fixes the same.
2025-05-12 15:55:51 +05:30
Ashutosh Mishra a516138584 Adding condition for static package type
SWDEV-532030 : Static builds are failing
for mainline and release because COMP_TYPE
is empty in case of static builds.
This patch fixes the same.

Signed-off-by: Ashutosh Mishra <ashutosh.mishra@amd.com>


[ROCm/rocm-core commit: bbbb0075fc]
2025-05-12 11:45:20 +05:30
Ashutosh Mishra bbbb0075fc Adding condition for static package type
SWDEV-532030 : Static builds are failing
for mainline and release because COMP_TYPE
is empty in case of static builds.
This patch fixes the same.

Signed-off-by: Ashutosh Mishra <ashutosh.mishra@amd.com>
2025-05-12 11:45:20 +05:30
Gollamandala, Srinivasarao 9e2a9eba01 SWDEV-504650-[catch2][dtest]PerfTest-Reduce the lock scope for hipEventRecord and hipEventQuery (#158)
[ROCm/hip-tests commit: e3964c54d6]
2025-05-12 10:23:07 +05:30
Gollamandala, Srinivasarao e3964c54d6 SWDEV-504650-[catch2][dtest]PerfTest-Reduce the lock scope for hipEventRecord and hipEventQuery (#158) 2025-05-12 10:23:07 +05:30
Six, Lancelot fe14cc349b SWDEV-517078: Fix gfx11 trap handler (#212)
Fix incorrect edits done when porting the 2nd level trap handler from
the hsa-runtime.

Change-Id: I7bc5160be47b8f669efe05c4d194bc3c47fc0661

[ROCm/clr commit: c35e9643ec]
2025-05-11 01:12:28 +01:00
Six, Lancelot c35e9643ec SWDEV-517078: Fix gfx11 trap handler (#212)
Fix incorrect edits done when porting the 2nd level trap handler from
the hsa-runtime.

Change-Id: I7bc5160be47b8f669efe05c4d194bc3c47fc0661
2025-05-11 01:12:28 +01:00
Saleel Kudchadker 1eb8694dd2 rocr: Expose hsa_amd_memory_get_preferred_copy_engine api 2025-05-09 17:13:27 -07:00
Saleel Kudchadker c0b0cb1788 rocr: Expose hsa_amd_memory_get_preferred_copy_engine api
[ROCm/ROCR-Runtime commit: 1eb8694dd2]
2025-05-09 17:13:27 -07:00
Xie, AlexBin 142e347aac SWDEV-528860 - reserve some memory in visible frame buffer (#251)
[ROCm/clr commit: faac50c77a]
2025-05-09 20:08:23 -04:00
Xie, AlexBin faac50c77a SWDEV-528860 - reserve some memory in visible frame buffer (#251) 2025-05-09 20:08:23 -04:00
David Galiffi 5906dde2b6 Update containers.yml (#205)
Add the rhel-9.5 container to the recurring updates

[ROCm/rocprofiler-systems commit: 82d5b8c64f]
2025-05-09 17:50:44 -04:00
David Galiffi 82d5b8c64f Update containers.yml (#205)
Add the rhel-9.5 container to the recurring updates
2025-05-09 17:50:44 -04:00
Kuricheti, Mythreya b328f12e4f Fix fold expr (#389)
[ROCm/rocprofiler-sdk commit: f3ea8b1178]
2025-05-09 14:18:19 -07:00
Kuricheti, Mythreya f3ea8b1178 Fix fold expr (#389) 2025-05-09 14:18:19 -07:00
xuchen-amd 6d6609e68e Improve gpu spec tests using chip ids. (#701)
[ROCm/rocprofiler-compute commit: 4e24b2c60a]
2025-05-09 11:48:25 -04:00
xuchen-amd 4e24b2c60a Improve gpu spec tests using chip ids. (#701) 2025-05-09 11:48:25 -04:00
Huang, AnZhong 3decd4f975 SWDEV-527299 - Support HIP_POINTER_ATTRIBUTE_CONTEXT (#180)
* SWDEV-527299 - Support HIP_POINTER_ATTRIBUTE_CONTEXT

As HIP enables UVA by default, it seems we can simply expose the context to support this feature.


[ROCm/clr commit: b434fbe2bd]
2025-05-09 17:34:16 +08:00
Huang, AnZhong b434fbe2bd SWDEV-527299 - Support HIP_POINTER_ATTRIBUTE_CONTEXT (#180)
* SWDEV-527299 - Support HIP_POINTER_ATTRIBUTE_CONTEXT

As HIP enables UVA by default, it seems we can simply expose the context to support this feature.
2025-05-09 17:34:16 +08:00
Chaudhary, Jatin Jaikishan a8630e866d SWDEV-525933 - add constexpr operators for fp16/bf16 (#199)
[ROCm/clr commit: 2f73e1385b]
2025-05-09 09:53:58 +01:00
Chaudhary, Jatin Jaikishan 2f73e1385b SWDEV-525933 - add constexpr operators for fp16/bf16 (#199) 2025-05-09 09:53:58 +01:00
Xie, Pengda dd6d3a6cd3 SWDEV-514841 - Remove invalid stream tests on AMD platform
[ROCm/hip-tests commit: 0c1a7bf155]
2025-05-08 16:25:23 -07:00
Xie, Pengda 0c1a7bf155 SWDEV-514841 - Remove invalid stream tests on AMD platform 2025-05-08 16:25:23 -07:00
Manocha, Rahul 19573225a5 SWDEV-489106 - Cuda mappings for Linker APIs (#8)
Co-authored-by: rmanocha@amd.com <Dragoslav.Sicarov@amd.com>

[ROCm/hipother commit: bb66090875]
2025-05-08 09:34:41 -07:00
Manocha, Rahul bb66090875 SWDEV-489106 - Cuda mappings for Linker APIs (#8)
Co-authored-by: rmanocha@amd.com <Dragoslav.Sicarov@amd.com>
2025-05-08 09:34:41 -07:00
Galantsev, Dmitrii 142d42392e CMAKE - Fix libc6 RPM dep issue
Change-Id: Id68e8a268f1b7e8561b9c9f741ae6e10b4ad7d8a
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rocm_smi_lib commit: 6d33c08346]
2025-05-08 10:56:38 -05:00
Galantsev, Dmitrii 6d33c08346 CMAKE - Fix libc6 RPM dep issue
Change-Id: Id68e8a268f1b7e8561b9c9f741ae6e10b4ad7d8a
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-05-08 10:56:38 -05:00
Shane Xiao 82a88f2e2b rocr: Set rec_sdma_eng_override_ for all gpus
Set the rec_sdma_eng_override_ for other gpus, or DmaCopyOnEngine
will use sdma for D<->D copy, which will trigger invalid argument.
2025-05-08 23:52:12 +08:00
Shane Xiao f8ac975cd2 rocr: Set rec_sdma_eng_override_ for all gpus
Set the rec_sdma_eng_override_ for other gpus, or DmaCopyOnEngine
will use sdma for D<->D copy, which will trigger invalid argument.


[ROCm/ROCR-Runtime commit: 82a88f2e2b]
2025-05-08 23:52:12 +08:00