39b9a46025
SWDEV-418904 - Remove hiprtc symbols from hip library ( #370 )
...
[ROCm/clr commit: e9dbd7c99d
2025-05-21 21:22:47 +05:30
6467351f4c
SWDEV-508962 - [6.4 Preview] Update hipPointerGetAttributes to match CUDA > 11.0 behavior ( #120 ) ( #363 )
...
[ROCm/clr commit: 0b64eec921
2025-05-21 21:18:05 +05:30
3ea732b38a
SWDEV-508965 - [6.4 Preview] Remove HIP_MEMSET_NODE_PARAMS struct ( #121 ) ( #364 )
...
[ROCm/clr commit: 968f5599a8
2025-05-21 21:16:42 +05:30
22da169b86
SWDEV-532868 - Disable implicit wait in hipFree for async allocations ( #323 )
...
* SWDEV-532868 - Disable implicit wait in hipFree for async allocations
* Fix compilation error
[ROCm/clr commit: 58df22546b
2025-05-21 21:14:38 +05:30
16aefe62f6
SWDEV-508979 - Match hipModuleLoad negative return with Cuda ( #326 )
...
[ROCm/clr commit: 7a357800dd
2025-05-21 21:09:07 +05:30
10d97b4b3c
SWDEV-508970 - Match hipBindTextureToArray negative return with Cuda ( #325 )
...
[ROCm/clr commit: a46ed60e2e
2025-05-21 20:57:09 +05:30
a17e22a78c
SWDEV-529929 - hipMemGetHandleForAddressRange implementation. ( #245 )
...
[ROCm/clr commit: 12131de4a9
2025-05-20 15:56:04 -04:00
4ea2d9a5ee
SWDEV-531711 - Report correct error code based on device failure. ( #286 )
...
[ROCm/clr commit: f5b8db33f1
2025-05-17 06:33:13 -04:00
7b6e59cbea
SWDEV-530803 - User current device id while cloning graph node. ( #313 )
...
[ROCm/clr commit: 32eb6a5d89
2025-05-15 09:06:15 +05:30
d0b5bee680
SWDEV-527781 - Remove Stream Validation in HIP APIs
...
[ROCm/clr commit: 0457b634f8
2025-05-13 13:45:27 -07:00
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
5dff283f4e
SWDEV-526855 - Modify the SIMDPerCU calculation for gfx1250/1. ( #275 )
...
[ROCm/clr commit: acb1f7e8d5
2025-05-12 11:09:03 -04:00
3d862af4df
SWDEV-512344 - Unmap all subbuffers ( #214 )
...
[ROCm/clr commit: c5ced8c3a2
2025-05-12 16:56:10 +02:00
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
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
cde2a250ec
SWDEV-493805 - Cleaning up launch parameters arguments. ( #241 )
...
[ROCm/clr commit: fa55557f46
2025-05-06 15:06:13 -04:00
086a1c289a
SWDEV-529831 - Return error if the program is empty ( #257 )
...
[ROCm/clr commit: 607f8f26fd
2025-05-06 15:12:12 +05:30
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
6ab34e0924
SWDEV-522634 - Fix device properties in hipInfo ( #203 )
...
[ROCm/clr commit: eb62fe9f62
2025-04-29 11:29:47 -04:00
68deb3d10a
SWDEV-520352 - Remove HostThread and legacy monitor ( #230 )
...
* SWDEV-520352 - Remove HostThread and legacy monitor
Remove HostThread, semaphore and legacy monitor.
Make original logics of thread and command queue stricker.
Add more comments to make logics clearer.
Some other minor improvement.
Also part of SWDEV-458943.
[ROCm/clr commit: 96cadbc9e9
2025-04-29 09:55:24 -04:00
49a527c826
SWDEV-506467 - Skip Abort in case of crash from the device. ( #60 )
...
Change-Id: I964b2f2647d068202e9c38fcddb1337da754df8d
[ROCm/clr commit: b2388dfb88
2025-04-29 11:19:02 +05:30
ae0640131e
SWDEV-528351 - Removes unused code and asserts to improve coverage ( #219 )
...
[ROCm/clr commit: 9cf3f1e461
2025-04-28 14:40:35 -07:00
ff69bcc903
SWDEV-469422 - Avoid using of hipStream_t in internal methods ( #69 )
...
Change-Id: Ifd5362f371c846a88241927383cb95cf046548ef
[ROCm/clr commit: fb92683d86
2025-04-28 15:09:11 +05:30
0eb2e5e8f2
SWDEV-469422 - hipGraphNodeDOTAttribute change std::string members to const char* ( #70 )
...
Compiler creates global variables for every unique string
Change-Id: I4cf8dd3e763d16740096e345da67a7ef72f61515
[ROCm/clr commit: bbcb1f9c70
2025-04-28 14:57:36 +05:30
875468bbfb
SWDEV-526188 - Fix race condition in StatCO::getStatFunc()
...
Make sure that a newly created FatBinaryInfo is assigned to modules only after extractFatBinary has been called for the object.
[ROCm/clr commit: 1099e0a131
2025-04-27 21:14:01 +01:00
a9068182f4
SWDEV-493275 - Support scratch limit ( #20 )
...
Support programmatic query and change of scratch limit on
AMD devices.
Change-Id: Id5da355a77366f97868e462847f3916e87fd2af6
[ROCm/clr commit: 1113eff3f9
2025-04-24 17:15:25 -04:00
d4e36d0900
SWDEV-469423 - hipStreamEndCapture graph* can be nullptr ( #170 )
...
[ROCm/clr commit: e5ce544c45
2025-04-24 13:57:09 +05:30
60110b6c01
SWDEV-518831 - fix streams' sync issue in mthreads ( #123 )
...
* SWDEV-518831 - fix streams' sync issue in mthreads
1. Fix sync issue of null stream and non-null streams in
multithreads.
2. Remove assert(GetSubmissionBatch() == nullptr) as it
is invalid in multithreads.
3. Update getActiveQueues() to deal with the state of
being terminated.
[ROCm/clr commit: 27aad09bd4
2025-04-23 15:08:07 -04:00
34d3f7022b
SWDEV-523281 - CHANGELOG.md and negative test return values : hipLaunchKernelEx, hipLaunchKernelExC, hipDrvLaunchKernelEx ( #155 )
...
[ROCm/clr commit: 64d6f5714a
2025-04-22 21:47:37 +05:30
41c4bea0f5
SWDEV-508538 - Optimize mem access and pack structure ( #71 )
...
Change-Id: Ib05b8891a6d228fc3266918a000d332fddc7438b
[ROCm/clr commit: bf28bbd9ab
2025-04-21 13:43:25 +05:30
6ae4c7278e
SWDEV-525423 - In COMGR Loader don't open file if image is already mapped ( #193 )
...
[ROCm/clr commit: d00b2a0953
2025-04-16 11:00:54 +02:00
963de868ae
SWDEV-523137 - function ptrs should match across all devices ( #171 )
...
[ROCm/clr commit: 5fe080fd67
2025-04-16 10:35:48 +02:00
9c1d61fbb0
SWDEV-518317 - Remove Redundant Error Message in removeFatBinary ( #164 )
...
[ROCm/clr commit: e92ea151b2
2025-04-15 09:00:39 -07:00
c72604a2af
SWDEV-509213 - make cmake_minimum_required consistent across clr ( #51 )
...
Change-Id: Ib0b1df7af8984a37d6bf7ca68ec99597d5978821
[ROCm/clr commit: fcaefe97b8
2025-04-15 15:23:41 +05:30
e9e207d7b0
SWDEV-517941 - use device bitcode before spirv ( #95 )
...
Also add flag: HIP_FORCE_SPIRV_CODEOBJECT to allow override to force use
SPIRV.
* use cache for already compiled code objects
* address review comments and use the two spirv isa names
[ROCm/clr commit: 07e57a1f0d
2025-04-14 23:40:52 +01:00
9264e97cbb
SWDEV-521920 - Fix compilation issues introduced by the reduce sync operations - 2 ( #167 )
...
Fix pytorch 2.5 issues, by defining reduce sync operations for type __half in amd_hip_fp16.h and not in
amd_warp_sync_functions.h which is problematic in case __half does not get included before that header.
Only define types not supported by cuda if HIP_ENABLE_EXTRA_WARP_SYNC_TYPES is defined, to avoid portability issues
[ROCm/clr commit: 66496258b4
2025-04-11 17:00:59 +05:30
b3d1ac7232
Report null stream creation failure ( #152 )
...
Explicitly nulling the pointer causes us to report the error below
instead of keeping a dangling pointer around that will most likely lead
to a subsequent segfault.
[ROCm/clr commit: 199b0f1086
2025-04-10 11:40:05 -07:00
88841d1dee
SWDEV-524188 - Check for VRam and system RAM properly ( #122 )
...
Currently, we check if there's enough system RAM even if we don't allocate on host device. This is incorrect logic.
We should not check for this size on windows because PAL checks for memory allocation. See SWDEV-467263.
Co-authored-by: Jimbo Xie <jiabaxie@amd.com >
[ROCm/clr commit: 0d6e554d92
2025-04-10 21:50:48 +05:30
dea880f9da
SWDEV-508973 - If total # of threads/block is more than HW capacity, it's invalid config issue and should return invalid config error. ( #25 )
...
[ROCm/clr commit: 8531cd3bbe
2025-04-10 15:16:16 +05:30
81a566e397
SWDEV-505795 - Return the same ptr from hipIpcOpenMemHandle if it is called multiple times ( #93 )
...
* SWDEV-505795 - Return the same ptr from hipIpcOpenMemHandle if it is called multiple times
* Move initialization outside of if statement
[ROCm/clr commit: e91cb4f320
2025-04-10 11:20:36 +02:00
ef52738425
Set maxTexture2DLinear fileds in deviceProp ( #89 )
...
[ROCm/clr commit: bc474ea5af
2025-04-09 17:13:49 +02:00
d4275741ba
SWDEV-525653 - Make hipGetDeviceProperties and hipChooseDevice use the new API ( #159 )
...
[ROCm/clr commit: b006380ff6
2025-04-08 18:54:05 +02:00
4c9cc6ba30
SWDEV-497841 - Add VmHeapArray support ( #76 )
...
Add VmHeapArray class to reduce the pressure on VA reservation, since
multiple memory pools can be active at the same time.
[ROCm/clr commit: e974f7fde1
2025-04-03 21:04:18 +05:30
3ceab5ba02
SWDEV-524849 - Fix HIP error returned during capture ( #141 )
...
Always use the latest dependent nodes during hipEventRecord capture
[ROCm/clr commit: 3514f45544
2025-04-03 20:08:25 +05:30
487ede31a9
SWDEV-523281 - [clr] Implementation of hipLaunchKernelExC and hipDrvLaunchKernelEx API with support for cooperative launch ( #92 )
...
[ROCm/clr commit: 8c6b90996e
2025-04-03 20:10:05 +09:00
d49a2a51d6
SWDEV-508863 - Support generic target in compressed fatbin ( #44 )
...
[ROCm/clr commit: 8d90b44a1b
2025-03-27 20:13:51 +05:30
e27e3eb66a
SWDEV-515426 - Use RAII classes for comgr ( #28 )
...
Change-Id: I9f6005542cc88f1e16e22741dcc0ce904fdaa2b0
[ROCm/clr commit: ded41058a0
2025-03-25 20:10:44 +05:30
cc5124241b
Revert SWDEV-512344 - Unmap all subbuffers ( #26 )
...
This reverts commit 0b69120cfcb5b4689d9f2037b1a01e274d85c20f.
[ROCm/clr commit: e7ada4effe
2025-03-19 21:17:36 +05:30
35a15ca3b2
Revert "SWDEV-492049 - Remove the handle of Phy Mem from Memobj" ( #72 )
...
This reverts commit dabe311bd82259a8c01c
2025-03-19 21:16:51 +05:30
00e77db856
SWDEV-497841 - Avoid access to the null stream on mempool alloc
...
Null stream isn't created during the device creation
[ROCm/clr commit: 392ed53c3c
2025-03-17 11:40:14 -04:00
Dittakavi, Satyanvesh
Assiouras, Ioannis
Andryeyev, German
Brzak, Branislav
Jayaprakash, Karthik
Patel, Jaydeepkumar
Xie, Pengda
Arandjelovic, Marko
Huang, AnZhong
Godavarthy Surya, Anusha
Jiang, Julia
Sang, Tao
Betigeri, Sourabh
GunaShekar, Ajay
Chaudhary, Jatin Jaikishan
Hernandez, Gerardo
Haehnle, Nicolai
Xie, Jiabao(Jimbo)
Stojiljkovic, Vladana
Belton-Schure, Aidan