Commit Graph

8938 Commits

Author SHA1 Message Date
Lancelot SIX 6a4785f650 Fix Stochastic sampling trap handler
The trap handler should read the PERF_SNAPSHOT_DATA after all of
PERF_SNAPSHOT_DATA, PERF_SNAPSHOT_PC_LO and PERF_SNAPSHOT_PC_HI.  This
patch fixes this.

Change-Id: I7f78e16d7a0d8bfebb34906b4dff73c2eaeb5658
2025-03-31 10:20:19 +01:00
Lancelot SIX eece210a5c trap_handler.s: Clear PERF_SNAPSHOT/HOST_TRAP before returning
Make sure to clear the HOST_TRAP and PERF_SNAPSHOT bits before returning
from the second level trap handler.  As those bits are sticky, this
ensures future re-entry to the trap handler (for context save for
example) will not be confused with a sampling trap.

Change-Id: I05e5e58779a650b324ac6e30d574dc6931340f13
Signed-off-by: Lancelot SIX <lancelot.six@amd.com>
2025-03-31 10:20:19 +01:00
Yuan, Perry 3bdca8b8b6 Implement CPU discovery support (#77)
* Implement CPU discovery support

SWDEV-482949:

enable the CPU model name info support to the RDC, rdci command
can detect GPU and CPU modules at the same time.
It will query the CPU info through the amdsmi interface like below:

1 GPUs found.
-----------------------------------------------------------------
GPU Index        Device Information
0               AMD Radeon PRO W7800
=================================================================
1 CPUs found.
-----------------------------------------------------------------
CPU Index        Device Information
0               AMD Ryzen Threadripper PRO 7995WX 96-Cores
-----------------------------------------------------------------

Change-Id: Ibc6533c9a61000cd86c45b1bae14c3eb6788c119
Signed-off-by: Perry Yuan <perry.yuan@amd.com>

* CMAKE - Add required version for amdsmi

Change-Id: I341a89351d196ec66cce215a5d1d3953302fcc66
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

---------

Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Co-authored-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-31 10:58:36 +08:00
Galantsev, Dmitrii 80ee980cdb CMAKE - Fix build types
Addresses issue https://github.com/ROCm/rdc/issues/43

Change-Id: I456184358524a6feef4bf83eecb655678c3bc42d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-30 18:54:54 -05:00
Fei Zheng 9bacad0876 Support host-trap PC Sampling on CLI (beta version) 2025-03-28 16:51:49 -06:00
Arif, Maisam 91f30c5756 [SWDEV-524528] Nullptr check correction for TestErrCntRead (#38)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-03-28 12:14:28 -05:00
Baraldi, Giovanni 6301f46d13 SWDEV-520093+SWDEV-521137+SWDEV-523996: Fix for missing AMDGPU_HSA_V6 (#20)
* Adding AMDGPU_HSA_V6

* Fix segment

* Fix conflicts

* ident fix

* Symbol lookup fix

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
2025-03-28 10:02:49 -07:00
Mallya, Ameya Keshava 5c8c974e71 Added KWS check for amd-mainline (#9) 2025-03-28 09:19:43 -07:00
Mallya, Ameya Keshava f17b7e8c3e Added KWS check for amd-mainline 2025-03-28 08:39:23 -07:00
Mallya, Ameya Keshava 05c81b6855 Added KWS check for amd-mainline
Signed-off-by: Mallya, Ameya Keshava <AmeyaKeshava.Mallya@amd.com>
2025-03-28 08:27:05 -07:00
Mallya, Ameya Keshava 4067831731 Added KWS check for amd-mainline (#140) 2025-03-28 08:23:38 -07:00
Mallya, Ameya Keshava b0563f4590 Added KWS check for amd-mainline 2025-03-28 08:13:07 -07:00
Mallya, Ameya Keshava fb8d0c256b Added KWS check for amd-mainline 2025-03-28 08:10:45 -07:00
Ben Richard 9bd45f5135 Read Accum_VGPR_Count from rocprof output if provided (#645) 2025-03-28 10:43:24 -04:00
Nagaraj, Sriraksha 10a16aacbf fix changelog (#322) 2025-03-28 12:11:42 +05:30
Galantsev, Dmitrii bdb2367010 RVS - Add long-running tests
Change-Id: Iddeb7f2d4fdcd69d7ac1ae94b2fa128ee3011b1a
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-27 23:42:56 -05:00
Galantsev, Dmitrii 58350a8bb8 Profiler - Remove bootstrap link
Change-Id: Ieea57515d77c2d521d95568c3bc2660cc829d829
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-27 23:29:30 -05:00
Galantsev, Dmitrii ea7ccd0660 Fix diagnostic example and allow building
Change-Id: Icc85e8018a11b66d1190fa910151acb79cd17b83
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-27 23:29:30 -05:00
Galantsev, Dmitrii 059d015ea4 CMAKE - Add BUILD_INTERFACE include dirs for rdc_bootstrap
Change-Id: I93df878b21e245277c7a8d9589102a15c2517f4f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-27 23:29:30 -05:00
Arif, Maisam 847ac53444 [SWDEV-524147] Patch for handling new ras filenames (#34)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-03-27 22:14:28 -05:00
Galantsev, Dmitrii 51de344be7 Profiler - Add CPC and CPF metrics
Change-Id: I27fd725e9e1868c9afe7624d6e4aafad2a42d47e
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-27 19:01:23 -05:00
ywang103-amd 7c1f14123a fix the wrong number of channels of TCC counters to put in pmc txt file (#633) 2025-03-27 18:15:41 -04:00
Apurv Mishra 10530fa2a7 kfdtest: support for upstream kernel driver
detect if the loaded driver is upstream or DKMS version and
add a filter for for the tests that fail in upstream driver

Signed-off-by: Apurv Mishra <Apurv.Mishra@amd.com>
2025-03-27 16:55:21 -04:00
ywang103-amd cdb93b7a4c fix ip block test by changing ways of extracting agent id (#639) 2025-03-27 16:28:00 -04:00
David Galiffi b6b39af011 Fix "ROCPROFSYS_USE_ROCM" runtime config setting. (#144) 2025-03-27 16:03:46 -04:00
Pryor, Adam 47692d3ed5 [SWDEV-498711] RDC Partition Implementation (#119)
* [SWDEV-498711] RDC Partition Implementation

Change-Id: Ibfc3709793770537e4c9d36458f34c6b4f461724
Signed-off-by: adapryor <Adam.pryor@amd.com>
2025-03-27 14:10:11 -05:00
Yiannis Papadopoulos 0bd4acb5d4 rocr/aie: Returning error code if query not recognized 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos e55503e7f8 rocr/aie: Bundling XDNA BOs and addresses, adding cleanup guard in case of error 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos f4e1c9b0ba rocr/aie: Avoiding XdnaDriver class in queue API 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos 8dcbbf31c7 rocr/aie: Remove unused struct from HSA API 2025-03-27 13:15:13 -04:00
Aleksandar Djordjevic 2bad0e941b Disable RCCL, load libamdhip64.so (#150)
Disable RCCL and load libamdhip64.so as a fix for sw509497.
2025-03-27 16:02:17 +01:00
Yiannis Papadopoulos bf8ab493c4 rocr: Remove unused lambda 2025-03-27 10:33:40 -04:00
Yiannis Papadopoulos b066e0eefa rocr/aie: Resolve parentheses warning 2025-03-27 10:33:40 -04:00
vedithal-amd af76525baa Inject SQ_ACCUM_PREV_HIRES for LEVEL counters only (#641) 2025-03-27 10:24:21 -04:00
Wileam Phan 2805631ccd Fix rocprof-sys-instrument default linkage and visibility criteria (#95)
* Fix default linkage and visibility criteria
* Fix processing of linkage and visibility CLI flags
* Format source

Signed-off-by: Wileam Yonatan Phan <wileamyonatan.phan@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-03-27 18:33:35 +08:00
Bhardwaj, Gopesh 633a32bad7 Deprecation message update (#320)
* Deprecation message update

* Updated Support DL
2025-03-27 12:29:34 +05:30
cfallows-amd 6cb5bcdbe9 Add datatypes for roofline profiling (#642)
Rebuild of rocm-amdgpu-bench roofline binaries for MI200/MI300 systems with rocm6.
Added datatype options to roofline feature.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-03-26 21:07:48 -04:00
Su, Daniel 172707cbd3 External CI: enable trigger for amd-mainline (#30) 2025-03-26 08:24:51 -05:00
Meserve, Mark a1fcdf7f83 Additional 1.0.0 changes (#317)
* Additional 1.0.0 changes

- Update VERSION
- Add beta compatibility for rocprofiler_agent_set_profile_callback_t

* Fix location of deprecated typedef rocprofiler_agent_set_profile_callback_t

* rocprofiler_record_counter_t -> rocprofiler_counter_record_t

* Experimental + deprecated annotations

* rocprofiler_record_dimension_info_t -> rocprofiler_counter_record_dimension_info_t

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2025-03-26 02:12:03 -05:00
lyndonli 38e9f399a2 Remove WSL checks for displaying UUID and BDFID
Signed-off-by: lyndonli <Lyndon.Li@amd.com>
2025-03-26 13:26:34 +08:00
Bhardwaj, Gopesh 6d6eec230c doc improvements and fixes SWDEV-523395,SWDEV-516979 (#314)
* doc improvements and fixes SWDEV-523395,SWDEV-516979

* Adding changes from PR 231
2025-03-26 10:09:08 +05:30
Cole Ramos 04f92b72a9 Fix incorrect logging in mi_gpu_spec.py (#626)
* Move console logging to logger function to avoid circular dependency in utils module

Signed-off-by: coleramos425 <colramos@amd.com>

* Apply python formatting

Signed-off-by: coleramos425 <colramos@amd.com>

* Remove the default StreamHandler before adding the custom

 If you are not explicitly removing this default handler, it could be causing duplicate outputs.

Signed-off-by: coleramos425 <colramos@amd.com>

* Fix lingering bugs from merge conflict resolution

Signed-off-by: coleramos425 <colramos@amd.com>

* Comply to python formatting and update pre-commit hook helper

Signed-off-by: coleramos425 <colramos@amd.com>

* Removing redundant console_log call as the get_mi300_num_xcds() call, otherwise ALL Mi200 profiling runs will print this message

Signed-off-by: coleramos425 <colramos@amd.com>

---------

Signed-off-by: coleramos425 <colramos@amd.com>
2025-03-25 17:06:37 -05:00
xuchen-amd 3294c495f5 Improve readability. (#628) 2025-03-25 17:49:42 -04:00
Cole Ramos 38c7dce84a Generalize locale checker to support more UTF-8 types (#623)
Signed-off-by: coleramos425 <colramos@amd.com>
2025-03-25 16:39:02 -05:00
David Galiffi 85bbea4954 Reapply "Upgrade ROCm-SMI to AMD SMI (#86)" (#147)
* Reapply "Upgrade ROCm-SMI to AMD SMI (#86)"

This reverts commit b3eee295dd.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-03-25 17:31:27 -04:00
ywang103-amd 983f902fa0 fix the crash related to agent id in rocprofv3 (#631) 2025-03-25 16:33:12 -04:00
ywang103-amd a92bf96e56 disable TCC flattern for rocprofv1 to avoid its crash becasue of unsupported implementation (#629) 2025-03-25 15:12:19 -04:00
cfallows-amd a492e92034 Datatype selection option for roofline (#624)
Added command line option to specify which datatype(s) to capture into the roofline PDF(s).
All datatypes are still collected by roofline call if applicable, but only specific datatypes are plotted into PDF outputs. Will dump out all datatypes into one graph, but separate FP from Int into two graphs if needed. Will skip datatype and give error message if the datatype is not valid on a particular gpu arch.
Default is FP32

Reworked roofline calls and plotting to be general enough such that any new datatypes added into rocm-amdgpu-bench can easily be reflected in rocprof-compute with simple modifications in roofline_calc.py.

Adjusted ctest to reflect expected default pdf outputs from roofline.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-03-25 15:02:09 -04:00
David Yat Sin 947391deac rocr: Release agent resources before pools
Adding a general stage for agents to release their resources on
shutdown. This avoids a circular dependency during shutdown because
we have to delete allocated resources before deleting memory pools, but
we also have to delete memory pools before destroying agents.
2025-03-25 14:25:04 -04:00
Yiannis Papadopoulos a66130bc48 rocr: Release vmem handles before agent destruction 2025-03-25 14:25:04 -04:00