AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
12,484 Commits 3 Branches 0 Tags
fe2d747bcc363ed2bbd90a03316db5efdef01857
Commit Graph

12484 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ranjith Ramakrishnan 0bafb4683a SWDEV-366823 - Change pragma message to warning 
File reorganization feature was implemented with backward compatibility
The backward compatibility support will be deprecated in future release.
Changed the #pragma message to #warning for a smooth transition

Change-Id: If917a0bef9bbc347f08ca02435d70d517f175afc
 2022-11-17 20:19:55 -05:00
German 79d12df147 SWDEV-363074 - Adjust staging copy limits in Windows 
Pinned copy can cause big performance drops, because slow pinning under Windows.
Use up to 128MB for staging transfers. Change staging buffer size to 4MB.
Linux path should still have the old defaults.

Change-Id: I954edceb3ec89e8e670be116aa2d0a9564c8b11c
 2022-11-17 14:48:16 -05:00
Julia Jiang 30c43056c1 SWDEV-340754 - Update coordinates in coperatative helper 
Change-Id: Ibf4e833d10ea5c317900e83f020c9c23f55f3951
 2022-11-17 14:17:58 -05:00
kjayapra-amd 0d9e1de4e3 SWDEV-241902 - Using COMGR APIs for extracing code object. 
Change-Id: I96f1cee9c28f89f0b0fa5af0c2ae7966beb3207d
 2022-11-17 11:09:59 -05:00
German b40823ccc1 SWDEV-328670 - Enable ROCr interop 
Change-Id: I932afa2a0e75b1f1771c4be1e984b32966636afb
 2022-11-17 09:40:34 -05:00
Juan Manuel MARTINEZ CAAMAÑO bab23480d3 SWDEV-286150 - [NFC] Avoid copying the entire devicePrograms map 
Change-Id: I059f979d9bcdf6604aa3630b40fd47475b75fc30
 2022-11-17 03:15:55 -05:00
Maneesh Gupta 1c45f257b9 Revert "SWDEV-363069 - Disable sync force for MT" 
This reverts commit 52ff4368e5.

Reason for revert: SWDEV-365075, SWDEV-367163, SWDEV-367164, SWDEV-367173

Change-Id: Id2924c60e46e9879038ded358f777c71cd95b2c1
 2022-11-17 01:04:44 -05:00
German 0db20050bc SWDEV-368308 - Remove HW debug extension 
The extension was devloped for AMDIL path only.
OCL runtime doesn't support AMDIL path  anymore.
The new debugger interfaces don't require any runtime calls either.

Change-Id: I6215545f9b6ae5c70b5f076c3cbfbfd3b5eef42b
 2022-11-16 17:37:06 -05:00
Jaydeep Patel c800d2126d SWDEV-366088 - Default case returns -1 as enum value. 
Change-Id: I8dd5cac254c99e4de9f6d492e71060e39b069507
 2022-11-15 22:12:12 -05:00
German 2cde04bf9b SWDEV-367745 - Report hipDeviceAttributeUnifiedAddressing 
Change-Id: I4d1d598f64f613430fecdc0d6b4cfa9845e04687
 2022-11-15 15:53:02 -05:00
pghafari 06edbb8177 SWDEV-356560 - updating error msg to match cuda 
Change-Id: I1c387cf04d041257b4d168b4cf4d8949153fd69f
 2022-11-15 13:19:33 -05:00
Juan Manuel MARTINEZ CAAMAÑO 9b8005d758 SWDEV-287018 - Generate tempraries for _optimized.bc and _linked.bc if -save-temp-all is passed. 
Change-Id: Ie8a7af66f0764f0a94948d45d7deed786f799c96
 2022-11-15 07:49:07 -05:00
Rakesh Roy 2b426a632f SWDEV-362366 - Add validation for hipInit flags 
- Return hipErrorInvalidValue when flags != 0

Change-Id: Ib2a7ea2acf083fa859d6c3bd91a12b39e877b4fd
 2022-11-14 23:52:32 -05:00
Maneesh Gupta 7cb650f154 SWDEV-361840 - Remove duplicate entry in backward-compat.cmake 
Change-Id: I7cc95ce6894f7891aa34188238413036d825daf7
 2022-11-14 23:15:23 -05:00
Daria Materikina 834d9d3a3c make header intel-compatible 
Change-Id: I8f8b68ba23e8f86dfeaf7c7b464f2b6ca6999971
 2022-11-14 17:59:01 -05:00
Siu Chi Chan 3d15f9cbda SWDEV-330775 - Update search path for LLVM 
ROCm's LLVM will be moved into /opt/rocm-<ver>/lib/, teach hipcc and
hipconfig about the new location.

Change-Id: Ie7f17146771aff94c684deb22148226cbb3a2895
 2022-11-14 13:31:07 -05:00
Julia Jiang c9ce9b3300 SWDEV-352687 - fix AlignedAllocMem in hmm 
Change-Id: Icec74ac732a0a6ac2a2600f504aa1ec73717c0ca
 2022-11-14 13:10:02 -05:00
Chauncey Hui 8246c73e3a SWDEV-2 - Change OpenCL version number from 3528 to 3529 2022-11-12 03:00:08 -05:00
Maneesh Gupta 8f4e94d532 SWDEV-342014 - Handle partial fills in hipDeviceGetName 
Change-Id: Ic9f1743c6a8439d88acc6dd1ed496013d551f6ec
 2022-11-11 14:52:48 -05:00
kjayapra-amd 7f1fb925ff SWDEV-361374 - Adding support for hipPointerSetAttributes 
Change-Id: I3ec9627f43b3cbe0aa299c8aa9cd96f8fbd74925
 2022-11-11 12:07:26 -05:00
Chauncey Hui 820d90c6c0 SWDEV-2 - Change OpenCL version number from 3527 to 3528 2022-11-11 03:00:06 -05:00
kjayapra-amd cc9427e969 SWDEV-356947 - Create a new thread if current thread is nullptr. 
Change-Id: Iebd69f22284041ed450d583471d24cb82fb0e47a
 2022-11-10 22:12:02 -05:00
Jason Tang 2c09557d60 SWDEV-1 - Add LOG_ERROR output for Pal::CreatePlatform failure 
Change-Id: Id5c3fdcd8f822bfa67ae570c09ede7ddc8a936ef
 2022-11-10 09:30:10 -05:00
Maneesh Gupta 038d70448e SWDEV-361840 - Fix typo in packaging script 
Change-Id: I0124b5522cb7b797293bab1a949af7baca849728
 2022-11-10 10:49:43 +00:00
Chauncey Hui 0b69480326 SWDEV-2 - Change OpenCL version number from 3526 to 3527 2022-11-10 03:00:07 -05:00
Satyanvesh Dittakavi a6e336a58c SWDEV-361840 - Add hiprtc cmake packaging 
Change-Id: Ib2c2aa5e1890a1a11af2832d7b5e7e1d202808ed
 2022-11-10 01:26:41 -05:00
Satyanvesh Dittakavi b5799c4dbe SWDEV-363536 - HIP_VISIBLE_DEVICES= should disable the device 
Setting HIP_VISIBLE_DEVICES= should be treated as invalid device
which makes all the devices invisible to the app. This matches
the CUDA behavior

Change-Id: I937ac4c0b7dacff776cdbe692d4576c81b86ee2d
 2022-11-10 01:25:46 -05:00
Satyanvesh Dittakavi 1155dbda1e SWDEV-364545 - Fix hiprtc cmake target on Windows 
Change-Id: I360d0d1ee7f6a0c65a4d6cd07620bfa2a503c19f
 2022-11-10 01:23:42 -05:00
Jason Tang e2e223e24a Merge "SWDEV-362451 - Reenable OCLPinnedMemory" into amd-staging 2022-11-09 11:57:14 -05:00
Maneesh Gupta a52f5bda8f SWDEV-299940 - Query global memory available on device with HSA attribute HSA_AMD_AGENT_INFO_MEMORY_AVAIL 
This reverts commit 4afca0647e.

Reason for revert: ROCr query should now be usable in upcoming release.

Change-Id: I2207761ca6af5d585d090bae1af09eb9a8e9bad6
 2022-11-09 10:48:47 -05:00
Chauncey Hui 0b4465efdb SWDEV-2 - Change OpenCL version number from 3525 to 3526 2022-11-09 03:00:07 -05:00
Satyanvesh Dittakavi 30d6497953 SWDEV-363369 - Elapsed time needs only stop event timings if both start and stop events are recorded 
Change-Id: I91c9ce79aacf1014ae77600d1250cfccd9dd6039
 2022-11-09 00:31:06 -05:00
Juan Manuel MARTINEZ CAAMAÑO 40f75306d5 SWDEV-286150 - [NFC] Refactor repeated option parsing code into function 
Change-Id: I606dc1cd48d880974142e523d16f5d9ac6f3aff1
 2022-11-08 10:29:13 -05:00
Juan Manuel MARTINEZ CAAMAÑO f5e982cc07 SWDEV-286150 - [NFC] Avoid copying string when calling HashString 
Change-Id: Ic2f4d469ca319f7d31814b3955430dbbfdad5bb2
 2022-11-08 07:07:06 -05:00
Chauncey Hui 773d85e3d9 SWDEV-2 - Change OpenCL version number from 3524 to 3525 2022-11-08 03:00:07 -05:00
Julia Jiang 9d616ad0f4 SWDEV-360748 - Update return value for hipExtGetLinkTypeAndHopCount_Positive_Basic test on Windows 
Change-Id: I0eb984da6e96c2409e1b1bbda61ae694c8bebe94
 2022-11-07 10:00:32 -05:00
German c1b22840fa SWDEV-286150 - Switch PAL to 775 version 
Change-Id: I8e64cbe0fea273d4bd6f7d3ebd66feb628fac6b9
 2022-11-07 09:54:22 -05:00
kjayapra-amd 5ff27faa04 SWDEV-337452 - Adding__ockl_steadyctr_u64 option for wall_clock64. 
Change-Id: I4ee6fd4d40d500363ef84975078185093dab5ddd
 2022-11-07 08:47:30 -05:00
Anusha GodavarthySurya c974cbcb3d SWDEV-366153 - Fix __ocml_isnan_f16 to pass _Float16 
Change-Id: I7628f21d000cec490f5fb2c91f1b99ca61fb46cf
 2022-11-06 21:57:23 -05:00
Chauncey Hui d0a57e4905 SWDEV-2 - Change OpenCL version number from 3523 to 3524 2022-11-05 03:00:05 -04:00
Saleel Kudchadker feca11d5e3 SWDEV-301667 - Improve logging 
Change-Id: Ifa6da876b85cb503967cf09aac6d477b10db8e63
 2022-11-04 18:23:18 -04:00
pghafari ac2948651e SWDEV-362199 - add vulkan interop apis in nvidia 
Change-Id: I6c5de6174a80be862b6d869927ed704dd1421b41
 2022-11-04 16:49:21 -04:00
sdashmiz 9c83b3e0b2 SWDEV-361592 - allow nullptr for userdata in hiphostfunc 
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I91728d363846ac6417d4a59920509ffacd4c9a58
 2022-11-04 13:37:17 -04:00
Saleel Kudchadker 3e465c5ff8 SWDEV-364052 - Print free memory on queue callback 
Change-Id: I7d15b6f6277326d5f3e9b784a3443f18ec6ba58a
 2022-11-04 13:19:33 -04:00
Todd tiantuo Li 246429bd68 SWDEV-302996 - add gfx1103 Phoenix support - OCL runtime 
Change-Id: Ib6b7efa085b734bda6b5b50c720fe9d93e6dbf95
 2022-11-04 12:07:22 -04:00
sdashmiz 33f02abc41 SWDEV-356569 - check for mempool device 
- mem pool should be from same device

Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Id06a7f070c019548462c235bff3c0cd972e6eb8a
 2022-11-04 09:36:22 -04:00
Chauncey Hui cfd9ced308 SWDEV-2 - Change OpenCL version number from 3522 to 3523 2022-11-04 03:00:06 -04:00
Jaydeep Patel e7a34f9efe SWDEV-365048 - extra marker is required for HW event check, which is done before the callback is finished. 
Change-Id: Ib46bfc4e060a60fb14aa782688d35b34534cca65
 2022-11-04 00:34:14 -04:00
kjayapra-amd ea0ce45ad3 SWDEV-329423 - Enable NV3x target ID related changes on mainline. 
Change-Id: I54fafb371976aaa16a452ec65b0c340c5682c264
 2022-11-03 21:11:24 +00:00
German 473621c008 SWDEV-365121 - Use CP DMA for tiny transfers 
Sync between compute and SDMA engines can be very expensive under Windows.
Use CP DMA for tiny transfers (< 1KiB) to avoid syncs and improve performance.

Change-Id: I9db39a2199f7b9e337ed08fd36d9cbc150502f1f
 2022-11-03 10:04:53 -04:00