AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,512 Commits 3 Branches 0 Tags
bb1295bcdfd72123700cd66e631326ab38e82db8
Commit Graph

5503 Commits

Author SHA1 Message Date
Betigeri, Sourabh 40999496c1 SWDEV-545273 - Respect HIP_LAUNCH_PARAM_BUFFER_SIZE (#770) 
[ROCm/clr commit: 2a02d2c2f3]
 2025-08-03 17:32:52 -07:00
Kudchadker, Saleel a1d3da6bd3 SWDEV-547614 - Demangle graph kernel names (#809) 
[ROCm/clr commit: 1492328894]
 2025-08-01 14:35:30 -07:00
Manocha, Rahul 4a93a614e5 SWDEV-539710 - Defer allocation of managed variable (#652) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/clr commit: 3f6f9d6081]
 2025-07-31 08:30:23 -07:00
Sang, Tao 2296162578 SWDEV-502579 - Remove duplicated symbols (#21) 
Remove duplicated compiler symbols from hip-rt. hip-rt should use symbols such as EF_AMDGPU_MACH_AMDGCN_XXX and
ELFABIVERSION_AMDGPU_HSA_VX defined in compiler header.

[ROCm/clr commit: b15c1657b8]
 2025-07-22 10:41:01 +05:30
Betigeri, Sourabh 680c7fbf64 SWDEV-483895 - Use ROCr to reserve memory for HMM (#590) 
[ROCm/clr commit: a1f056bd11]
 2025-07-15 21:40:13 +05:30
Xie, Jiabao(Jimbo) e5226f2b7e SWDEV-460151 - add gfx1201 to amd-staging clr (#183) 
* SWDEV-460151 - add gfx1201 to amd-staging clr

* SWDEV-460151 - removed pal macro

---------

Co-authored-by: Jimbo Xie <jiabaxie@amd.com>

[ROCm/clr commit: a5d932f160]
 2025-07-11 08:51:47 -07:00
Sang, Tao a777d6eca0 SWDEV-539145 - Simplify host memory pool management (#668) 
* SWDEV-539145 - Simplify host memory pool management

Remove unnecessary variables and functions.
Make code simpler and clear.

* Change cpu_agent_info_ into pointer.

* Restore getPreferredNumaNode()

[ROCm/clr commit: 1351cd7fa8]
 2025-07-11 10:38:40 -04:00
GunaShekar, Ajay 8e1f5f50cd SWDEV-541623 - do not print hip library path on console (#707) 
DeviceTest.exe Unit_Uuid_FntlTstsFor_SetEnv_HIP_VISIBLE_DEVICES

[ROCm/clr commit: b568971718]
 2025-07-10 12:07:03 -07:00
Sang, Tao 7fd322af90 SWDEV-508776 - support VGPRs validation (#274) 
Clarify some VGPRs terms description.
Fix some wrong query logics of availableVGPRs_ and
availableRegistersPerCU_ in device info.
Add hipDeviceAttributeMaxAvailableVgprsPerThread
attribute query.
Remove hardcoding of following
 info_.vgprAllocGranularity_
 info_.vgprsPerSimd_

[ROCm/clr commit: 397f303d97]
 2025-07-09 10:46:52 -04:00
Kudchadker, Saleel 433c25eab0 SWDEV-539378 - Use agent of IPC memory owner (#570) 
- Currently runtime just uses the local agent as it did not check for
  IPCShared()
- With this fix we query hsa_amd_pointer_info and get the right agent
  for the memory to pass it to the HSA copy api

[ROCm/clr commit: 46d766e4e2]
 2025-07-08 12:02:01 -07:00
Belton-Schure, Aidan 88c1717658 SWDEV-515426 - Remove HIP_USE_RUNTIME_UNBUNDLER (#205) 
* remove HIP_USE_RUNTIME_UNBUNDLER
* clang-format
* Generic to use comgr
* Remove HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION flag
* Removes runtime unbundling unused and debug Code
* Removes stale functions

[ROCm/clr commit: 81238db679]
 2025-07-08 21:45:31 +05:30
Manocha, Rahul 8e8dc41cf0 SWDEV-532420 - Fix kokkos P2P copy failure with vmheap (#426) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/clr commit: 22b1ca4d8c]
 2025-07-07 17:27:13 -07:00
Xie, Pengda 8e5921174f SWDEV-540576 - Abort if user request a core dump (#653) 
* SWDEV-539414 - Return error status from runtime handler when HIP_SKIP_ABORT_ON_GPU_ERROR is false

* SWDEV-539414 - default handler when GPU core file is generated

* SWDEV-540576 - Abort if user request a core dump

Change-Id: I9e2c640acf559880bd13641de9103e660ef822a3

---------

Co-authored-by: Assiouras, Ioannis <Ioannis.Assiouras@amd.com>
Co-authored-by: agunashe <ajay.gunashekar@amd.com>

[ROCm/clr commit: 9c1bff0ae7]
 2025-07-03 00:29:14 +05:30
Sang, Tao 287ec83f5c SWDEV-539145 - Support extended fine grained system memory pool (#603) 
* Add hipHostMalloc() new flag hipHostMallocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostAlloc() new flag hipHostAllocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostRegister() new flag hipHostRegisterUncached which will force to map
host memory onto extended fine grained system momory pool.

[ROCm/clr commit: a7d7687b8f]
 2025-07-01 10:10:10 +05:30
Trinh, Ethan 66b125d5dc SWDEV-539861 - add ROCclr version to logs (#612) 
[ROCm/clr commit: 2ce45143d8]
 2025-06-27 16:37:58 -04:00
Guan, Zichuan c43b8ca05c Fix memory leak in opengl interop (#541) 
Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

[ROCm/clr commit: 51508e0bef]
 2025-06-27 09:51:18 -04:00
Lin, Qun ced47b3588 SWDEV-508869 - Replace asicRevision with gfxip triple in paldevice (#601) 
asicRevision is not unique in pal path now, use gfxip triple to match isa is more straight forward in pal path.

[ROCm/clr commit: b584fc8cd1]
 2025-06-27 10:09:21 +08:00
Lin, Qun 3b44884a57 SWDEV-508869 - Fix Linux build error for HIP on PAL (#176) 
[ROCm/clr commit: 9699cc3864]
 2025-06-27 07:51:22 +08:00
Sang, Tao da7c6f57ef SWDEV-539399 - Support ROCCLR_MEM_HSA_CONTIGUOUS (#610) 
Fix missing support of ROCCLR_MEM_HSA_CONTIGUOUS in
hipExtMallocWithFlags().

[ROCm/clr commit: f4d78d427c]
 2025-06-26 14:05:23 -04:00
Patel, Jaydeepkumar 821a1d89b0 SWDEV-536226 - Avoid waiting for lastCommand completion if GPU has already reported an error otherwise it causes hang due to status of cmd is not becoming CL_COMPLETE. (#478) 
[ROCm/clr commit: a60212b9b4]
 2025-06-25 20:59:17 +05:30
Kudchadker, Saleel 13117b0ecd SWDEV-535490 - Fix build break on windows (#618) 
[ROCm/clr commit: 4c2405b108]
 2025-06-24 18:34:55 -07:00
Kudchadker, Saleel 3c9f80b4e4 SWDEV-535490 - Improve logging (#441) 
- Include HIP version/githash in the logs
- Add a new method to print library path

[ROCm/clr commit: 5d53c83806]
 2025-06-24 13:00:00 -07:00
Brzak, Branislav 4eba877aef SWDEV-531996 - Add legacy fallback Mesa loading via dlsym (#512) 
[ROCm/clr commit: 494c0e3201]
 2025-06-11 08:02:51 +05:30
Brzak, Branislav c95ca33e7b SWDEV-531996 SWDEV-530154 - Use *getprocaddress to obtain Mesa functions (#504) 
[ROCm/clr commit: 5fabfedbd1]
 2025-06-10 13:31:32 +05:30
Jayaprakash, Karthik 4691ca2f39 SWDEV-531711 - Fixing compilation error by moving static var to public. (#438) 
[ROCm/clr commit: b72812d324]
 2025-05-30 11:42:50 +05:30
Manocha, Rahul b936e55e81 SWDEV-475482 - [6.4 Preview] Match hipTexObjectCreate with cuda (#408) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/clr commit: b5e9bc55cb]
 2025-05-28 13:21:45 +05:30
Harrymanoharan, Jessey 1868e4e595 SWDEV-531711 - Enable skipping host side abort when GPU crashes. (#380) 
Co-authored-by: kjayapra-amd <karthik.jayaprakash@amd.com>

[ROCm/clr commit: 3930ae2524]
 2025-05-26 17:52:02 +05:30
Andryeyev, German fc2f5aaf22 SWDEV-533074 - Expose hipDeviceAttributeNumberOfXccs attribute (#336) 
[ROCm/clr commit: 5cc172c99c]
 2025-05-21 22:35:42 +05:30
Dittakavi, Satyanvesh 1cc35da9be SWDEV-438790 - Remove DEBUG_HIP_7_PREVIEW env var keeping the hipGetLastError changes by default (#337) 
[ROCm/clr commit: 664bf232dd]
 2025-05-21 22:12:45 +05:30
Jayaprakash, Karthik a17e22a78c SWDEV-529929 - hipMemGetHandleForAddressRange implementation. (#245) 
[ROCm/clr commit: 12131de4a9]
 2025-05-20 15:56:04 -04:00
Jayaprakash, Karthik b59859c52e SWDEV-457749 - Use size of handle for range instead of actual size for physmem. (#342) 
[ROCm/clr commit: bed454caa1]
 2025-05-20 15:24:49 -04:00
Kudchadker, Saleel ee7c5554db SWDEV-523279 - Use preferred engine mask for SDMA (#317) 
- ROCr now reports preferred engine for copy status. We can leverage
this for max bandwidth for inter-GPU copies
- Cleanup logging

[ROCm/clr commit: 1b0ea080e4]
 2025-05-19 16:04:51 -07:00
Kudchadker, Saleel 5fd5e846e2 SWDEV-531518 - Fix offset accumulation (#333) 
srcAddress/dstAddress accumulation was cumulative, which shouldnt be
done if we increment offset.

[ROCm/clr commit: 5712944c7c]
 2025-05-19 18:03:06 +05:30
Jayaprakash, Karthik f4c9056cdc Revert "SWDEV-522707 - Set phys_mem_handle type to sizeof(size_t) to avoid blocking address range. (#105)" (#348) 
This reverts commit 0071d33754.

[ROCm/clr commit: bb7750a946]
 2025-05-19 15:19:16 +05:30
Jayaprakash, Karthik 4ea2d9a5ee SWDEV-531711 - Report correct error code based on device failure. (#286) 
[ROCm/clr commit: f5b8db33f1]
 2025-05-17 06:33:13 -04:00
Andryeyev, German b13eec7049 SWDEV-345024 - Retain the program on Fini kernel execution (#307) 
Fini kernel is executed during the invocation of amd::Program destructor,
but the dispatch logic can retain/release the reference counter and
cause double free. Avoid double free with an extra retain() call

[ROCm/clr commit: bddb8f14d1]
 2025-05-14 21:21:26 +05:30
Assiouras, Ioannis 71f19d7017 SWDEV-529449 - Bug fix when retrieving a memobj from the IPC mem handle 
[ROCm/clr commit: f7482ef0a6]
 2025-05-13 19:18:22 +01:00
Jayaprakash, Karthik a128beeeb5 SWDEV-506467 - Fixing compilation issue seen on clang compilation for ASAN. (#253) 
[ROCm/clr commit: 876de49b11]
 2025-05-12 17:16:56 -04:00
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
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
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
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
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, Jiabao(Jimbo) e1d2194b75 SWDEV-528913 - support gfx950 in rocsetting (#217) 
* SWDEV-528913 - support gfx950 in rocsetting

---------

Co-authored-by: Jimbo Xie <jiabaxie@amd.com>

[ROCm/clr commit: a320a3f214]
 2025-05-07 15:44:49 -04:00
Lambert, Jacob dc1c1e3199 SWDEV-518221 - Don't link against libamd_comgr.so at runtime 
Convention is to always link against .so.* at runtime.
Having it link against .so will break on systems that package
the .so files in their dev/devel package.

This issue was found when building ROCm 6.4 for Fedora.

Commiting on behalf of GitHub user Mystro256

[ROCm/clr commit: 6b12154583]
 2025-05-07 11:56:41 -07:00
Zhang, Victor fbabd2b69d SWDEV-528142 - add error check for KernelParameters::capture (#276) 
* SWDEV-528142 - add error check for KernelParameters::capture

* Update kernel.cpp

---------

Co-authored-by: victzhan <victzhan@amd.com>

[ROCm/clr commit: f960433dcd]
 2025-05-07 09:52:09 -04:00
Jayaprakash, Karthik cde2a250ec SWDEV-493805 - Cleaning up launch parameters arguments. (#241) 
[ROCm/clr commit: fa55557f46]
 2025-05-06 15:06:13 -04:00
Andryeyev, German 3ea758a2d4 SWDEV-528808 - Release all HW queues even if only one is idle (#240) 
Pytorch may not explicitly idle each queue. Thus, some queues can be considered as busy,
but have idle state in reality


[ROCm/clr commit: 65a0181a7c]
 2025-05-05 19:09:01 -04:00
Andryeyev, German c512258e45 SWDEV-528808 - Disable dynamic queue by default (#256) 
Dynamic queue management will be disabled by default and
the original sort logic is restored

[ROCm/clr commit: 9b018165ce]
 2025-05-05 10:56:35 -04:00
Assiouras, Ioannis 3d4ff304d7 SWDEV-521011 - Fix alignment in PalResource::CreateSvm 
[ROCm/clr commit: 9d6a0d1a4d]
 2025-05-01 02:22:49 +01:00