AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,938 Commits 3 Branches 0 Tags
f15d0467bcbecafdea95d8771c8dbeb0d5771052
Commit Graph

8938 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
coleramos425 7d34e80567 Replace deprecated roofline warning with logging helper function 
Signed-off-by: coleramos425 <colramos@amd.com>
 2024-04-25 18:43:20 +00:00
Joseph Macaranas 2b777139d3 Add support for external CI builds using Azure Pipelines (#62) 
* Add support for external CI builds using Azure Pipelines

* Change token name to match IT-created token
 2024-04-25 13:41:30 -05:00
coleramos425 0fc620ce79 Add TCC_TOO_MANY_EA_WRREQS_STALL to gfx940 input configs (#349) 
Signed-off-by: coleramos425 <colramos@amd.com>
 2024-04-25 18:22:00 +00:00
coleramos425 46aa20e014 Update names of roofline csv expectation in testing 
Co-authored-by: Jose Santos <josantos@amd.com>
Signed-off-by: coleramos425 <colramos@amd.com>
 2024-04-25 18:10:21 +00:00
amd-jmacaran 587e4287f4 Change token name to match IT-created token 
Change-Id: Ic9189c012024c59cf5bad9daf25f6c2575a100fd
 2024-04-25 12:23:28 -04:00
amd-jmacaran 75803689d1 Change token name to match IT-created token 
Change-Id: Ie08eb15af669d4247c611c122ca0a77eb365f6dd
 2024-04-25 03:57:02 -04:00
Galantsev, Dmitrii cb87eeeae7 Update kBlockNameMap 
Change-Id: I096f40f2b953fad7081d4b9bc05c0291c0f8058d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2024-04-24 23:50:55 -05:00
Galantsev, Dmitrii 0c8827c4b7 CMAKE - Use ADDRESS_SANITIZER env var 
Change-Id: I4727120de2f9d7bded8c24033c252ede718831fc
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2024-04-24 23:04:25 -05:00
David Yat Sin 3d999a1adf Perform HDP flush for SDMA copies gfx10/gfx11 
Perform HDP flush on gfx10/gfx11 PCIe devices.

Exclude gfx101x devices

Change-Id: Ief76c34634b09b0a7942cb71519d4082ca8b4fad
 2024-04-24 18:07:34 -04:00
David Galiffi c24baf3610 Add ".venv" to gitignore file 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-04-24 17:02:52 -05:00
Jonathan R. Madsen 67dbe3f47f Update CMake config install location + env setup files (#821) 
- install cmake config files to CMAKE_INSTALL_LIBDIR instead of CMAKE_INSTALL_DATAROOTDIR per ROCm standards
- Provide setup-env.sh and modulefiles for rocprofiler-sdk and rocprofiler-sdk-roctx
 2024-04-24 14:43:47 -05:00
amd-jmacaran 9a91005354 Add support for external CI builds using Azure Pipelines 
Change-Id: I7658fbc8c52bef551dae8c13413825507a0d8c0a
 2024-04-24 15:25:10 -04:00
Jonathan R. Madsen 8c985543d9 Rework counter collection sample app (#822) 
* Sync more often in counter collection samples

* Update samples/counter_collection/main.cpp

- support command line arguments
  - number of iterations
  - iterations per sync
  - number of devices to use
 2024-04-24 14:00:59 -05:00
David Yat Sin 9af225e1b1 Add support for contiguous memory allocations 
Support contiguous physical memory allocation flag. Allocations with
this flag will have contiguous physical memory. This is dependent on KFD
support for this flag and the AllocateKfdMemory(..) function call will
fail when it is not supported.

Change-Id: I6c51c8b061f7b026fdcc2aa2c37c74ecc13d95b6
 2024-04-24 14:02:07 -04:00
David Yat Sin e539c8dce2 Remove assert for physical vs virtual memory size 
On systems with more than 1 TB of memory per NUMA region, this triggers
unnecessary errors.

Change-Id: I1bc7f209b9c1739b516c9f6b0acf434488ac7b8d
 2024-04-24 08:43:23 -04:00
Jonathan R. Madsen 5d365bb8b8 Fix LICENSE install location + CPACK_RPM_PACKAGE_LICENSE (#820) 
- LICENSE needs to be installed in share/doc/rocprofiler-sdk not share/doc/rocprofiler
- CPACK_RPM_PACKAGE_LICENSE should be set to license type not the license location
 2024-04-24 01:19:32 -05:00
amd-jmacaran 8a893ea0b8 Add support for external CI builds using Azure Pipelines 
Change-Id: I8f4de331f00317a959b86f7e5b7a1025ba03564b
 2024-04-23 21:10:49 -04:00
Ammar ELWazir 777add01d1 Update rocprofiler_config_packaging.cmake (#817) 2024-04-23 18:43:41 -05:00
Ammar ELWazir 28f39abfa4 Barrier Packets are being displayed with kernel dispatches 
Workaround to seperate barrier packets in a separate category named GPU Barriers in JSON to easily navigate dispatches in perfetto and chrome tracing UI

Change-Id: I714975f50a186622612e605b98d0b45426d53aa4
 2024-04-23 19:36:46 -04:00
David Galiffi a8bd453243 Fixed MD linting issue regarding code blocks. 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Change-Id: Id0467b332bf033642a2d403090ffe598e41689f5
 2024-04-23 16:48:15 -04:00
David Galiffi 975c5dd24a Fixed broken link to ROCm documentation 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Change-Id: I9a6bc0ad08a060d83fdc3a0589dfc81c68ce2b0e
 2024-04-23 16:47:50 -04:00
David Galiffi f94c1794bb Fixed MD linting issue regarding headers 
They should start at H1

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Change-Id: Id11a2599c4609255a1a9916f70b58adc41cdddb4
 2024-04-23 16:47:19 -04:00
David Galiffi c9103a00ef Update GitHub links to point to the new organization. 
ie., RadeonOpenCompute --> ROCm

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Change-Id: I6724cbcbbb525f767af297e3986cd61fa69cd49f
 2024-04-23 16:46:42 -04:00
Philip Yang 97497c7efc libhsakmt: Support contiguous VRAM allocation flag 
Add HsaMemFlags Contiguous bit for hsaKmtAllocMemory to allocate
contiguous VRAM, to support RDMA device with limited scatter-gather
ability.

Check KFD ioctl minor version >= 17.

Change-Id: I0db00dad125b2b7be523f343082641f59b850423
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
 2024-04-23 14:27:12 -04:00
Your Name e2d742ac6f libhsakmt: Remove HsaMemFlag reserved bit init 
HsaMemFlag new flags added and the number of the reserved bits is
reduced, and generate value overflow compilanation error.

The reserved bits is not used, remove the init.

Change-Id: I603596977dfd558ce31ead03711d7c5ce5ee5b71
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
 2024-04-23 14:27:12 -04:00
Ammar ELWazir 64a0e626e4 Adding License to core package 2024-04-23 11:50:41 -05:00
Ammar ELWazir f18651d9f1 Update rocprofiler_register_config_packaging.cmake 2024-04-23 11:50:41 -05:00
Galantsev, Dmitrii 913d6fd173 Merge amd-staging into amd-master 20240423 
Change-Id: I55800aeb88b62f85aae2715a9d314aa4530d8576
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2024-04-23 10:53:41 -05:00
Bill(Shuzhou) Liu 6ff95e55da Support thread only mutex 
The environment variable RSMI_MUTEX_THREAD_ONLY=1 to enable thread only mutex.
The RSMI_INIT_FLAG_THRAD_ONLY_MUTEX can also be pass to rsmi_init()
to enable thread only mutex.

Change-Id: I2d9844039b774e386f03bb9bb130d8c342504ea6
 2024-04-23 10:49:17 -05:00
Jonathan R. Madsen 9499e2f521 Remove Critical Trace Support (#327) 
* Delete core critical-trace files

* Update docs and README

* Update workflows

* Update testing

* Update cmake

* Remove critical trace usage in source code

* Update source/docs/critical_trace.md

- fix spelling

* Formatting

* Update bin/omnitrace-avail/avail.cpp

- statically allocate shared pointers for timemory manager and hash id/aliases to prevent use-after-free errors
 2024-04-23 09:35:44 -05:00
David Galiffi b81db80926 Updated links to point to the ROCm organization. (#337) 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-04-23 01:44:02 -05:00
Oliveira, Daniel e95d80f7ef fix: [SWDEV-458101] [rocm/rocm_smi_lib] 
Drops checks that are invalid with the new pp_od_clk_voltage format

Code changes related to the following:
  * get_od_clk_volt_info()
  * get_od_clk_volt_curve_regions()

Change-Id: I5ebe23aa0ed4ea77d5ab5a94ce34ad9b1b51281f
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
 2024-04-23 00:16:53 -05:00
gobhardw dc09052d82 SWDEV-452226-dispatch ids to start from 0 for v1 parity 
Change-Id: Ib60a6c108131f67395ab1f9d35ad605859d39987
 2024-04-23 00:41:55 -04:00
David Galiffi c29f8e8244 Create CODEOWNERS (#338) 2024-04-22 23:22:01 -05:00
Ammar ELWazir c93a55b070 Update docs.yml (#815) 2024-04-22 22:50:34 -05:00
Jonathan R. Madsen 48273d6a65 Remove -Wno-missing-field-initializers from build flags (#810) 
* Remove -Wno-missing-field-initializers

- Compiler errors if missing field initializers

* Update lib/rocprofiler-sdk/counters/evaluate_ast.cpp

- copy over dispatch ID in perform_reduction/evaluate
 2024-04-22 22:26:01 -05:00
Vladimir Indic deabd869b5 Introducing PcSamplingExtTable (#735) 
* pcs: updating the PCS table

* Fixing Clang Tidy errors

* pcs: reverting old table version

* testint wrong table size

* new size

* testing step

* reverting old steps

* hsa_amd_queue_get_info introduced

* pcs: testing table version

* formatting

* removing redundand declarations

* removing unnecessary files

* Apply suggestions from code review

* Apply suggestions from code review

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/hsa/pc_sampling.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Enable function pointer offset check in hsa::pc_sampling::copy_table

- add offset() to HSA_API_META_DEFINITION
- check if offset() >= size of struct

* Support build without PC sampling API table

* ids for ROCr's PC sampling public functions

---------

Co-authored-by: Ammar ELWazir <aelwazir@hpe6u-21.amd.com>
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2024-04-22 20:07:28 -05:00
Ammar ELWazir 1be381d18c Fixing issue related to python support in CentOS 7 
Change-Id: I296fda319ab82505e836a4179c95c3a1e444ae00
 2024-04-22 17:39:36 -05:00
David Yat Sin f2751b7030 Fix queue creation for PC Sampling 
Fix lazy pointer initialization for dedicated PC Sampling queue.
Previous implementation would always create a queue on GPU agent
creation instead of creating the queue on first use.

Change-Id: Icf300f2b162e59143ba61ba182d9bee6e1308fc1
 2024-04-22 19:00:48 +00:00
Ammar ELWazir 7589084197 GPUs not needed for doc action (#804) 2024-04-22 11:00:43 -05:00
Karl W Schulz b5011ff0ae additional mod needed to support roofline binaries potentially 
executing from two different locations

Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-22 09:00:18 -05:00
Karl W Schulz 144843f710 allow override of CPACK_GENERATOR 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz c5cb6ba44f use concurrency instead of cancel-workflow-action 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz f0ec149497 fix module load path 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz 7d24465ee6 include additional omniperf in modulefile install path 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz bd9cf81f17 wip 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz 92f6367f18 wip 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz 9415f5e54b wip 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz ab95711c14 include omniperf subdir 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00
Karl W Schulz 53beac102a update tarball packaging test based on new install paths 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-04-21 14:53:14 -05:00