AI/rocm-systems
2
0
Fork 0
Code Issues Pull-Requests Actions Pakete Projekte Releases Wiki Aktivität

Commit graph

  • 35201ff32d SWDEV-483586 - Do not take pinned path for read/write Saleel Kudchadker 2024-11-01 00:46:30 +00:00
  • f1e98ab6e4 SWDEV-483586 - Do not take pinned path for read/write Saleel Kudchadker 2024-11-01 00:46:30 +00:00
  • 01c73b561f SWDEV-491967 - Add the right VGPRs per SIMD and VGPR Granularity for gfx12 Satyanvesh Dittakavi 2024-10-30 15:47:28 +00:00
  • a26dc29eb9 SWDEV-491967 - Add the right VGPRs per SIMD and VGPR Granularity for gfx12 Satyanvesh Dittakavi 2024-10-30 15:47:28 +00:00
  • 825440e7ba Rename Omniperf to ROCm Compute Profiler (#428) xuchen-amd 2024-11-01 12:20:21 -04:00
  • 31b4de1a38 Rename Omniperf to ROCm Compute Profiler (#428) xuchen-amd 2024-11-01 12:20:21 -04:00
  • 5b40eefdac SWDEV-490864 - Optimize Alloc Node detection in graph Rahul Manocha 2024-10-14 10:44:28 -07:00
  • 314d4a2c22 SWDEV-490864 - Optimize Alloc Node detection in graph Rahul Manocha 2024-10-14 10:44:28 -07:00
  • 04628d2d1f SWDEV-428601 - Don't enforce 1 isa per device in rocm backend Konstantin Zhuravlyov 2024-10-30 15:33:36 -04:00
  • 3387f48b56 SWDEV-428601 - Don't enforce 1 isa per device in rocm backend Konstantin Zhuravlyov 2024-10-30 15:33:36 -04:00
  • 5fe3dc5bf9 SWDEV-487356 - Fix AMD LOG issue in Win32 Tao Sang 2024-10-17 21:38:00 -04:00
  • 802cacf3e9 SWDEV-487356 - Fix AMD LOG issue in Win32 Tao Sang 2024-10-17 21:38:00 -04:00
  • b606e3dca7 SWDEV-489570 - Update AQL packet in hipDrvGraphExecMemsetNodeSetParams Satyanvesh Dittakavi 2024-10-09 18:06:08 +00:00
  • ba2ebb3b99 SWDEV-489570 - Update AQL packet in hipDrvGraphExecMemsetNodeSetParams Satyanvesh Dittakavi 2024-10-09 18:06:08 +00:00
  • 0f77eeaace SWDEV-491149 - OCL does not need to update scratch as it can't update stack size using API unlike hipDeviceSetLimit. Jaydeep Patel 2024-10-17 08:56:31 +00:00
  • 4aa52155ee SWDEV-491149 - OCL does not need to update scratch as it can't update stack size using API unlike hipDeviceSetLimit. Jaydeep Patel 2024-10-17 08:56:31 +00:00
  • bfbb2f9de7 [SWDEV-412505] Handle mclk permission errors as not supported adapryor 2024-10-24 08:13:18 -05:00
  • 02cbffb42a [SWDEV-412505] Handle mclk permission errors as not supported adapryor 2024-10-24 08:13:18 -05:00
  • 4e399dc383 [SWDEV-412505] Handle mclk permission errors as not supported adapryor 2024-10-31 12:27:04 -05:00
  • 61ed9e13f4 [SWDEV-412505] Handle mclk permission errors as not supported adapryor 2024-10-31 12:27:04 -05:00
  • 73f909cd8b SWDEV-495316 [AMDSMI] In amdsmi.h, change typedef amdsmi_accelerator_partition_profile_t to match definition in Confluence Joe Narlo 2024-10-30 09:55:52 -05:00
  • 54462ab447 SWDEV-495316 [AMDSMI] In amdsmi.h, change typedef amdsmi_accelerator_partition_profile_t to match definition in Confluence Joe Narlo 2024-10-30 09:55:52 -05:00
  • 30571de816 SWDEV-492768 - Match hipStreamAddCallback capture behavior with nvidia Vladana Stojiljkovic 2024-10-21 14:40:09 +02:00
  • f6c8bbf4dc SWDEV-492768 - Match hipStreamAddCallback capture behavior with nvidia Vladana Stojiljkovic 2024-10-21 14:40:09 +02:00
  • 116effa83c SWDEV-491452 - Allow hipMemAdvise capturing only inrelaxed mode Vladana Stojiljkovic 2024-10-15 12:33:18 +02:00
  • 02bbe11e56 SWDEV-491452 - Allow hipMemAdvise capturing only inrelaxed mode Vladana Stojiljkovic 2024-10-15 12:33:18 +02:00
  • 7ff9aa117d SWDEV-493526 - Create kernel node when hipLaunchByPtr is captured Vladana Stojiljkovic 2024-10-24 14:06:37 +02:00
  • e08df57502 SWDEV-493526 - Create kernel node when hipLaunchByPtr is captured Vladana Stojiljkovic 2024-10-24 14:06:37 +02:00
  • 83513d4daf rocr: Adding pointer to the owner driver in Agent class Yiannis Papadopoulos 2024-10-25 18:36:36 +00:00
  • 2837825b14 rocr: Adding pointer to the owner driver in Agent class Yiannis Papadopoulos 2024-10-25 18:36:36 +00:00
  • 4005fd9b9d rocr: Fix supported_isas transient memory issue Chris Freehill 2024-10-30 19:27:58 -05:00
  • c7521a5f2a rocr: Fix supported_isas transient memory issue Chris Freehill 2024-10-30 19:27:58 -05:00
  • d655fa8c66 SWDEV-489571 - Fix ihipGraphAddMemsetNode to allow memset of 3d portions of an array Vladana Stojiljkovic 2024-10-17 15:06:52 +02:00
  • ec60bb1aed SWDEV-489571 - Fix ihipGraphAddMemsetNode to allow memset of 3d portions of an array Vladana Stojiljkovic 2024-10-17 15:06:52 +02:00
  • e751f00ca2 SWDEV-489468 - make resource cache bigger for APU Alex Xie 2024-10-25 17:03:55 -04:00
  • f8c56f6bac SWDEV-489468 - make resource cache bigger for APU Alex Xie 2024-10-25 17:03:55 -04:00
  • dd33820b23 rocr: Fix several rocrtst memory errors Chris Freehill 2024-10-24 17:03:40 -05:00
  • 4256630fd0 rocr: Fix several rocrtst memory errors Chris Freehill 2024-10-24 17:03:40 -05:00
  • 2cce18fb38 SWDEV-492563 - Fix Ocl issues Tao Sang 2024-10-23 10:32:46 -04:00
  • 82dff9a67d SWDEV-492563 - Fix Ocl issues Tao Sang 2024-10-23 10:32:46 -04:00
  • 8444e5fe7f Set minimum ROCm version for MSCCLPP to 6.2 (#1401) corey-derochie-amd 2024-10-30 16:48:54 -06:00
  • 6db2644766 Set minimum ROCm version for MSCCLPP to 6.2 (#1401) corey-derochie-amd 2024-10-30 16:48:54 -06:00
  • 9ae2320ac3 remove cooperative groups Yiltan Hassan Temucin 2024-10-30 20:10:21 +00:00
  • fe767d9abf remove cooperative groups Yiltan Hassan Temucin 2024-10-30 20:10:21 +00:00
  • da3887bafb Memory leak fixes in hostside functions (#1388) Avinash 2024-10-30 14:25:56 -05:00
  • d6006f0425 Memory leak fixes in hostside functions (#1388) Avinash 2024-10-30 14:25:56 -05:00
  • e346e19065 Adjustment for UT Sendrecv (#1400) Tim 2024-10-30 15:13:53 -04:00
  • fd9924cfe7 Adjustment for UT Sendrecv (#1400) Tim 2024-10-30 15:13:53 -04:00
  • f682dcee3f Add example code demonstrating team-based broadcast and alltoall API usage avinashkethineedi 2024-10-29 19:15:26 +00:00
  • 68c893d790 Add example code demonstrating team-based broadcast and alltoall API usage avinashkethineedi 2024-10-29 19:15:26 +00:00
  • 75cdddf403 use a single context for decoding (#68) Aryan Salmanpour 2024-10-30 11:48:47 -04:00
  • 6d31992746 use a single context for decoding (#68) Aryan Salmanpour 2024-10-30 11:48:47 -04:00
  • 3bf096bb71 SWDEV-475482 - Disable Texture Object tests to merge clr change on windows Rahul Manocha 2024-10-10 17:19:34 -07:00
  • 9e77ca3f71 SWDEV-475482 - Disable Texture Object tests to merge clr change on windows Rahul Manocha 2024-10-10 17:19:34 -07:00
  • d8cfdd2887 Refactor API reference docs (#1125) srawat 2024-10-30 19:39:08 +05:30
  • 4204042ac6 Refactor API reference docs (#1125) srawat 2024-10-30 19:39:08 +05:30
  • e1c20e7f24 ext-src: Improved allreduce performance in cpx mode for MI308 (#1393) Nusrat Islam 2024-10-30 08:30:15 -05:00
  • 0fb3b5eba9 ext-src: Improved allreduce performance in cpx mode for MI308 (#1393) Nusrat Islam 2024-10-30 08:30:15 -05:00
  • b69bf8d939 changelog update for release notes (#1171) Gopesh Bhardwaj 2024-10-30 15:48:43 +05:30
  • 762ca819cf changelog update for release notes (#1171) Gopesh Bhardwaj 2024-10-30 15:48:43 +05:30
  • 122cecc59d SWDEV-490062 - Update documentation Istvan Kiss 2024-10-21 16:50:09 +02:00
  • 3d60bd3a64 SWDEV-490062 - Update documentation Istvan Kiss 2024-10-21 16:50:09 +02:00
  • a2b25be61c SWDEV-491375 - Improve MemObjMap perf Saleel Kudchadker 2024-10-23 02:09:03 +00:00
  • e23ff0520b SWDEV-491375 - Improve MemObjMap perf Saleel Kudchadker 2024-10-23 02:09:03 +00:00
  • 22f8106311 Remove serializing Reserved field of HSA_CAPABILITY (#1170) Jonathan R. Madsen 2024-10-30 00:12:48 -05:00
  • 7f416a2f82 Remove serializing Reserved field of HSA_CAPABILITY (#1170) Jonathan R. Madsen 2024-10-30 00:12:48 -05:00
  • f6b0641a2a Update fetch_size metric (#1165) Giovanni Lenzi Baraldi 2024-10-29 21:44:27 -03:00
  • 4acca76edb Update fetch_size metric (#1165) Giovanni Lenzi Baraldi 2024-10-29 21:44:27 -03:00
  • af1e36a7ee Remove MSCCL switch case fall-through by adding break statement. (#1342) corey-derochie-amd 2024-10-29 15:47:59 -06:00
  • ea20af698e Remove MSCCL switch case fall-through by adding break statement. (#1342) corey-derochie-amd 2024-10-29 15:47:59 -06:00
  • f9d38d8858 6.2 final documentation fixes updated for 6.3 (#1252) (#1399) corey-derochie-amd 2024-10-29 15:23:45 -06:00
  • 8ac63e7e70 6.2 final documentation fixes updated for 6.3 (#1252) (#1399) corey-derochie-amd 2024-10-29 15:23:45 -06:00
  • a33cdd7da6 [SWDEV-446215] Update cmake to put test libs in proper lib dir adapryor 2024-10-28 08:59:03 -05:00
  • 6e01df00ca [SWDEV-446215] Update cmake to put test libs in proper lib dir adapryor 2024-10-28 08:59:03 -05:00
  • ce09a178d3 rocr: revert back to old copy behaviour with no xgmi sdma engines Jonathan Kim 2024-10-28 10:37:13 -04:00
  • 7f8676e177 rocr: revert back to old copy behaviour with no xgmi sdma engines Jonathan Kim 2024-10-28 10:37:13 -04:00
  • b1a52b906b Update broadcast function to use stride calculations instead of log_stride avinashkethineedi 2024-10-29 19:10:05 +00:00
  • 5975b8c621 Update broadcast function to use stride calculations instead of log_stride avinashkethineedi 2024-10-29 19:10:05 +00:00
  • 058aa3ccf3 Remove device-side active-set-based broadcast API interface from rocSHMEM avinashkethineedi 2024-10-29 19:04:49 +00:00
  • e1ff06913c Remove device-side active-set-based broadcast API interface from rocSHMEM avinashkethineedi 2024-10-29 19:04:49 +00:00
  • daae6f4d60 Remove active-set-based broadcast test from the functional tests suite avinashkethineedi 2024-10-29 16:18:46 +00:00
  • 9a524046fe Remove active-set-based broadcast test from the functional tests suite avinashkethineedi 2024-10-29 16:18:46 +00:00
  • c39806eede SWDEV-1 - exclude hipExtHostAlloc.cc from nvidia test list Ajay 2024-10-28 09:01:21 -07:00
  • 61f3be259a SWDEV-1 - exclude hipExtHostAlloc.cc from nvidia test list Ajay 2024-10-28 09:01:21 -07:00
  • 862e713a5c SWDEV-494798 - Bump minor version for ROCm 6.4 Rakesh Roy 2024-10-29 12:45:45 +05:30
  • 36739655e4 SWDEV-494798 - Bump minor version for ROCm 6.4 Rakesh Roy 2024-10-29 12:45:45 +05:30
  • 2800fb526f CODEOWNERS Update (#1164) Gopesh Bhardwaj 2024-10-29 11:47:14 +05:30
  • 980b97cc51 CODEOWNERS Update (#1164) Gopesh Bhardwaj 2024-10-29 11:47:14 +05:30
  • fa35b62708 SWDEV-493402: Changing the header format for counter collection (#1148) Manjunath P Jakaraddi 2024-10-28 21:41:29 -07:00
  • f087debe84 SWDEV-493402: Changing the header format for counter collection (#1148) Manjunath P Jakaraddi 2024-10-28 21:41:29 -07:00
  • 5869709dac Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays avinashkethineedi 2024-10-28 22:10:18 +00:00
  • abec29bd6a Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays avinashkethineedi 2024-10-28 22:10:18 +00:00
  • 9f9ecd9a38 Remove the device-side active-set-based reduction API interface from rocSHMEM avinashkethineedi 2024-10-28 21:35:14 +00:00
  • c22048112e Remove the device-side active-set-based reduction API interface from rocSHMEM avinashkethineedi 2024-10-28 21:35:14 +00:00
  • 4e71fa5d22 Remove active-set-based reduction test from the functional tests suite avinashkethineedi 2024-10-28 21:22:46 +00:00
  • e9484bbb86 Remove active-set-based reduction test from the functional tests suite avinashkethineedi 2024-10-28 21:22:46 +00:00
  • da9466f7cc Merge pull request #44 from ROCm/fix-printing Yiltan 2024-10-28 15:45:28 -04:00
  • 9885f984f6 Merge pull request #44 from ROCm/fix-printing Yiltan 2024-10-28 15:45:28 -04:00
  • bd3a07d28b Merge pull request #43 from ROCm/LWPRHMEM-75-API-differences-bug-fix Yiltan 2024-10-28 15:45:15 -04:00
  • 794b888d69 Merge pull request #43 from ROCm/LWPRHMEM-75-API-differences-bug-fix Yiltan 2024-10-28 15:45:15 -04:00