AI/rocm-systems
2
0
Fork 0
Código Issues Pull Requests Ações Pacotes Projetos Versões Wiki Atividade

Gráfico de Commits

  • 995429869a Add missing rocm6 and ubuntu2204 elements to roofline binary colramos-amd 2024-01-25 12:55:32 -06:00
  • be606e6ccb Add missing rocm6 and ubuntu2204 elements to roofline binary colramos-amd 2024-01-25 12:55:32 -06:00
  • b229abc692 Add codeowners for documentation (#1061) Sam Wu 2024-01-25 09:33:28 -07:00
  • 7d6da4c66b Add codeowners for documentation (#1061) Sam Wu 2024-01-25 09:33:28 -07:00
  • f83e9be99c SWDEV-347670 - StreamWait test issues Ajay 2024-01-19 12:04:45 -08:00
  • 8c0a6f1cdb SWDEV-347670 - StreamWait test issues Ajay 2024-01-19 12:04:45 -08:00
  • 15127c6f85 Optimize and fix SDMA gang copies Jonathan Kim 2024-01-24 11:35:00 -05:00
  • 62f3f250ce Optimize and fix SDMA gang copies Jonathan Kim 2024-01-24 11:35:00 -05:00
  • fc7620136f SWDEV-442439 - Removed references to HIT from catch tests Ioannis Assiouras 2024-01-21 08:15:11 -05:00
  • 2cdcbf4d24 SWDEV-442439 - Removed references to HIT from catch tests Ioannis Assiouras 2024-01-21 08:15:11 -05:00
  • 8eac06c5fd amdsmi README updated for python interface Deepak Mewar 2024-01-25 02:00:15 -05:00
  • 3aabb927b4 amdsmi README updated for python interface Deepak Mewar 2024-01-25 02:00:15 -05:00
  • 95eb873d90 SWDEV-442606 - Add gfx90a and gfx942 in GPU arch list. Jaydeep Patel 2024-01-24 09:22:20 +00:00
  • cf461b2f8c SWDEV-442606 - Add gfx90a and gfx942 in GPU arch list. Jaydeep Patel 2024-01-24 09:22:20 +00:00
  • d7fec53720 SWDEV-388833 - [catch2][dtest] Sync tests migrated from dtests to catch2 SrinivasaRao 2023-11-15 14:55:06 +05:30
  • 902c993615 SWDEV-388833 - [catch2][dtest] Sync tests migrated from dtests to catch2 SrinivasaRao 2023-11-15 14:55:06 +05:30
  • 95f4b4eaf3 Updated engine_activity api Maisam Arif 2024-01-24 21:18:35 -06:00
  • 0550c9352c Updated engine_activity api Maisam Arif 2024-01-24 21:18:35 -06:00
  • f357c180e7 Fix metric type error output + re-align with ROCm SMI metrics Charis Poag 2024-01-24 20:43:47 -06:00
  • 34bd26c68e Fix metric type error output + re-align with ROCm SMI metrics Charis Poag 2024-01-24 20:43:47 -06:00
  • 99564b560c Remove enhcompat.cc Wenkai Du 2024-01-24 17:13:30 -08:00
  • 6afabf0d0b Remove enhcompat.cc Wenkai Du 2024-01-24 17:13:30 -08:00
  • 919dcafc80 Docs - Cleanup User Guide (#198) Kiriti Gowda 2024-01-24 16:45:03 -08:00
  • 5d77fbf40a Docs - Cleanup User Guide (#198) Kiriti Gowda 2024-01-24 16:45:03 -08:00
  • a7a60a06ec Fix sendrecv merge Wenkai Du 2024-01-24 16:23:53 -08:00
  • 4aafb2a3c5 Fix sendrecv merge Wenkai Du 2024-01-24 16:23:53 -08:00
  • 05b2113af4 update headers for 2024 calendar year Karl W. Schulz 2024-01-24 17:11:39 -06:00
  • d7b6cf81e6 update headers for 2024 calendar year Karl W. Schulz 2024-01-24 17:11:39 -06:00
  • 5bb19f170a Merge amd-dev into amd-master 20240124 Part 3 Maisam Arif 2024-01-24 17:30:10 -06:00
  • fc5ecc166a Merge amd-dev into amd-master 20240124 Part 3 Maisam Arif 2024-01-24 17:30:10 -06:00
  • 25ffbb0304 Unified API Bill(Shuzhou) Liu 2024-01-24 10:16:35 -06:00
  • 0b67c2ccc4 Unified API Bill(Shuzhou) Liu 2024-01-24 10:16:35 -06:00
  • 404d398bac Merge remote-tracking branch 'nccl/v2.19' into develop BertanDogancay 2024-01-24 15:25:33 -08:00
  • 81ddf9de89 Merge remote-tracking branch 'nccl/v2.19' into develop BertanDogancay 2024-01-24 15:25:33 -08:00
  • a0e7d3c29f Changed rocDecode API header variable naming to Google C++ style. (#196) jeffqjiangNew 2024-01-24 18:03:46 -05:00
  • cd6401750e Changed rocDecode API header variable naming to Google C++ style. (#196) jeffqjiangNew 2024-01-24 18:03:46 -05:00
  • cefb7bc8d6 HIP API Tracing (#357) Jonathan R. Madsen 2024-01-24 16:32:54 -06:00
  • c641749fe6 HIP API Tracing (#357) Jonathan R. Madsen 2024-01-24 16:32:54 -06:00
  • dcdd64b6bd Patch specs enhancement for Mi300 colramos-amd 2024-01-24 12:58:13 -06:00
  • f49d7f7f0c Patch specs enhancement for Mi300 colramos-amd 2024-01-24 12:58:13 -06:00
  • ee21c4d5ba Responding to Karls review colramos-amd 2024-01-24 12:44:42 -06:00
  • e5ac5ccf7d Responding to Karls review colramos-amd 2024-01-24 12:44:42 -06:00
  • f427785b26 Add license delimiter to new file colramos-amd 2024-01-23 14:27:27 -06:00
  • bd600bce49 Add license delimiter to new file colramos-amd 2024-01-23 14:27:27 -06:00
  • 3856b8d7fb Remove old omniperf_analyze implementation colramos-amd 2024-01-22 16:36:07 -06:00
  • 3ba03b7df7 Remove old omniperf_analyze implementation colramos-amd 2024-01-22 16:36:07 -06:00
  • 0be51fc2fe Catch ROCm-6.0.0 headers for replacement and standardization colramos-amd 2024-01-22 16:13:09 -06:00
  • 88ef7b7550 Catch ROCm-6.0.0 headers for replacement and standardization colramos-amd 2024-01-22 16:13:09 -06:00
  • 662c4abf68 Add implementation for gfx940 arch colramos-amd 2024-01-22 16:11:00 -06:00
  • a15857cd1d Add implementation for gfx940 arch colramos-amd 2024-01-22 16:11:00 -06:00
  • d9c5cd355a Adding support for Mi300X-A0 colramos-amd 2024-01-22 11:11:04 -06:00
  • f229b36277 Adding support for Mi300X-A0 colramos-amd 2024-01-22 11:11:04 -06:00
  • e1f82cb8a5 Improved --list-metric pretty print colramos-amd 2024-01-19 15:29:26 -06:00
  • 7120f87963 Improved --list-metric pretty print colramos-amd 2024-01-19 15:29:26 -06:00
  • bf27665e99 Fixing typo in KernelName header colramos-amd 2024-01-19 15:01:37 -06:00
  • c36578578b Fixing typo in KernelName header colramos-amd 2024-01-19 15:01:37 -06:00
  • 0d72d942b4 Fix small typo colramos-amd 2024-01-19 14:07:29 -06:00
  • 8ba3d8e45f Fix small typo colramos-amd 2024-01-19 14:07:29 -06:00
  • 18e3b98535 Update headers based on latest rocprofv2 output. Overwrite old headers. colramos-amd 2024-01-19 13:46:01 -06:00
  • a171e776e4 Update headers based on latest rocprofv2 output. Overwrite old headers. colramos-amd 2024-01-19 13:46:01 -06:00
  • afa73c9e9b Build out gfx942 SoC class and improve SoC detection coleramos425 2024-01-19 11:02:52 -06:00
  • 7846a663fd Build out gfx942 SoC class and improve SoC detection coleramos425 2024-01-19 11:02:52 -06:00
  • 249144eb7c Add config files for Mi300_A1 and modify run_prof utility to use XCC modes coleramos425 2024-01-19 11:01:01 -06:00
  • 0432f77a7e Add config files for Mi300_A1 and modify run_prof utility to use XCC modes coleramos425 2024-01-19 11:01:01 -06:00
  • eca3a0e5f2 Improved communication between SoC and profiler classes coleramos425 2024-01-19 10:56:45 -06:00
  • 4c1e516fb6 Improved communication between SoC and profiler classes coleramos425 2024-01-19 10:56:45 -06:00
  • 77ca223de8 Decode specs using utf-8 for backwards compatibility in rocprof coleramos425 2024-01-17 15:36:51 -06:00
  • d9a6832e30 Decode specs using utf-8 for backwards compatibility in rocprof coleramos425 2024-01-17 15:36:51 -06:00
  • 20ccf05fa9 Re-enable TCP_TCC_READ_REQ_LATENCY_sum in mi200 coleramos425 2024-01-17 13:41:12 -06:00
  • 1fd91959a2 Re-enable TCP_TCC_READ_REQ_LATENCY_sum in mi200 coleramos425 2024-01-17 13:41:12 -06:00
  • 7b9b4c90e6 Enable Standalone GUI. Note L2 per channel graphics haven't been ported to new format coleramos425 2024-01-17 13:40:31 -06:00
  • df4f15ff47 Enable Standalone GUI. Note L2 per channel graphics haven't been ported to new format coleramos425 2024-01-17 13:40:31 -06:00
  • 6da5e58dd5 Enable specs correction, detection of cli_style property, and hbm stack num coleramos425 2024-01-16 10:07:46 -06:00
  • 92f429f8b2 Enable specs correction, detection of cli_style property, and hbm stack num coleramos425 2024-01-16 10:07:46 -06:00
  • 924b421c3f Add new submodule for mem chart coleramos425 2024-01-15 17:11:36 -06:00
  • e3f76599b3 Add new submodule for mem chart coleramos425 2024-01-15 17:11:36 -06:00
  • 28e83fb63d Update rocprof config files for counter updates coleramos425 2024-01-15 17:10:43 -06:00
  • c86334466a Update rocprof config files for counter updates coleramos425 2024-01-15 17:10:43 -06:00
  • 8b021ccb30 Add new plotille module coleramos425 2024-01-15 17:07:43 -06:00
  • 60be13cebd Add new plotille module coleramos425 2024-01-15 17:07:43 -06:00
  • 219cc0d16a Update config files for new l2 cache per channel structure and general counter updates coleramos425 2024-01-15 17:07:08 -06:00
  • 19ad88a04e Update config files for new l2 cache per channel structure and general counter updates coleramos425 2024-01-15 17:07:08 -06:00
  • c20a76f03d Modify schema to reflect new l2 cache per channel coleramos425 2024-01-15 16:56:50 -06:00
  • 8fadbb070f Modify schema to reflect new l2 cache per channel coleramos425 2024-01-15 16:56:50 -06:00
  • 26f27cdf82 Fix bug in coalescing TCC per channel counters coleramos425 2024-01-15 16:47:59 -06:00
  • ff09288c83 Fix bug in coalescing TCC per channel counters coleramos425 2024-01-15 16:47:59 -06:00
  • bdda466109 Implement specs correction function coleramos425 2024-01-15 12:27:18 -06:00
  • 8534cec3a6 Implement specs correction function coleramos425 2024-01-15 12:27:18 -06:00
  • a75180dbd2 Add options for --specs and --specs-correction coleramos425 2024-01-15 12:24:28 -06:00
  • 224d627438 Add options for --specs and --specs-correction coleramos425 2024-01-15 12:24:28 -06:00
  • 035c6ec7a3 Fix bug in profiling for Mi100 colramos-amd 2024-01-11 16:30:46 -06:00
  • d4a649a926 Fix bug in profiling for Mi100 colramos-amd 2024-01-11 16:30:46 -06:00
  • e8ec84a854 Separate aggregation of TCC and TCC2 counters colramos-amd 2024-01-11 12:55:31 -06:00
  • 4ffcaa1b4a Separate aggregation of TCC and TCC2 counters colramos-amd 2024-01-11 12:55:31 -06:00
  • 3bc71d87e9 Optimizations to run_prof() utility colramos-amd 2024-01-11 12:52:27 -06:00
  • a1b5c252e2 Optimizations to run_prof() utility colramos-amd 2024-01-11 12:52:27 -06:00
  • 5a1281e375 Moving the join_prof func into parent class and adding output_headers specific to rocprof ver colramos-amd 2024-01-10 12:49:27 -06:00
  • 42dd2cbcac Moving the join_prof func into parent class and adding output_headers specific to rocprof ver colramos-amd 2024-01-10 12:49:27 -06:00
  • 84748197bf Adding sbios, vbios, and partitioning info to specs. Also reorganizing fields. colramos-amd 2024-01-10 11:34:54 -06:00
  • 987f612489 Adding sbios, vbios, and partitioning info to specs. Also reorganizing fields. colramos-amd 2024-01-10 11:34:54 -06:00