AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13,501 Commits 3 Branches 0 Tags
e56ff3716d7b8d04ee60e42d2ebb6ebf5d0d58db
Commit Graph

13501 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Evgeny ef61a39603 SWDEV-249924 : hip correlation id explicite propogation; tracer debug instrumentation; 
Change-Id: Ibbc411541f5610ce739f3fc1efa1ab7f605220f5

initial commmit

Change-Id: I34b360be62c2083819dc5c3acc8268bd69f2f58a
 2020-10-06 13:25:51 -04:00
Chris Freehill c6f02b4d62 Fail gracefully if drm directory is not found 
Change-Id: I0f3ab2721108355752caf0280124469b98af4967
 2020-10-05 21:12:11 -04:00
Chris Freehill 946bf93dfb Support for RSMI_EVNT_GRP_XGMI_DATA_OUT counters 
Also some format fixes

Change-Id: Id3c0f6b3cf5b327bb9ca6acb6091dc67764c8032
 2020-10-05 17:22:19 -05:00
Laurent Morichetti 2ed2e46b9b Update the context save area size 
Reserve some space in the context save area for the debugger's
use. There should be 32 bytes per wave for a given queue.

Change-Id: I65ddb6123d0f6afd3149844617ad19023009101d
 2020-10-05 12:10:58 -07:00
Pareshkumar Ghanshyambhai Patel be34751495 Merge "SWDEV-253997 : packaging fix: installing hsa_ostream_ops.h" into amd-staging 
[ROCm/roctracer commit: 7b6c94e9e9]
 2020-10-03 23:06:11 -04:00
Pareshkumar Ghanshyambhai Patel 7b6c94e9e9 Merge "SWDEV-253997 : packaging fix: installing hsa_ostream_ops.h" into amd-staging 2020-10-03 23:06:11 -04:00
Divya Shikre 8b48564ce3 Adding functionality that will parse gpu_metrics sysfs file 
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I3a84870b83eb4cd0ed46f10bb19169c91f99fd8e
 2020-10-02 10:25:41 -04:00
Chris Freehill 3522e94ed0 Add gtest lib dir to library search path 
Change-Id: I57bb20e2a67a4eaac2d0e24314e22d1a5fbe3533
 2020-10-01 23:46:33 -04:00
Evgeny 7a430d1260 SWDEV-251491 : disabling hipModuleUnload tracing which is called on exit 
Change-Id: I99c22eec3fea6ac8820d574c44df099febdd27c4


[ROCm/roctracer commit: bb8f2f6785]
 2020-10-01 12:47:40 -04:00
Evgeny bb8f2f6785 SWDEV-251491 : disabling hipModuleUnload tracing which is called on exit 
Change-Id: I99c22eec3fea6ac8820d574c44df099febdd27c4
 2020-10-01 12:47:40 -04:00
Evgeny 8d021eb401 SWDEV-249924 : hip correlation id explicite propogation 
Change-Id: If5799a812b7789a805797aed8be4ab52d417221f
 2020-10-01 12:40:41 -04:00
Evgeny 617098d096 SWDEV-249924 : hip correlation id explicite propogation 
Change-Id: If5799a812b7789a805797aed8be4ab52d417221f


[ROCm/rocprofiler commit: 8d021eb401]
 2020-10-01 12:40:41 -04:00
Evgeny 6f19938892 SWDEV-251491 : gen_ostream_ops.py porting to python3 
Change-Id: I7081b6ad21b038040267067bd73d8a44df46e4ff


[ROCm/roctracer commit: 9562675382]
 2020-10-01 00:52:23 -05:00
Evgeny 9562675382 SWDEV-251491 : gen_ostream_ops.py porting to python3 
Change-Id: I7081b6ad21b038040267067bd73d8a44df46e4ff
 2020-10-01 00:52:23 -05:00
Evgeny 29191089cc SWDEV-254810 : JSON generator cleanup 
Change-Id: Iacf782ee1e33443e9efb35b1adfcd2a43feda91d
 2020-10-01 00:48:56 -05:00
Evgeny e6be2dd03a SWDEV-254810 : JSON generator cleanup 
Change-Id: Iacf782ee1e33443e9efb35b1adfcd2a43feda91d


[ROCm/rocprofiler commit: 29191089cc]
 2020-10-01 00:48:56 -05:00
Chris Freehill 2b41fb9fdc Add README for rocrtst 
Change-Id: Icd43a243ccfc9caf5ade3cd0e7ffc00e251fc0a2
 2020-09-28 20:27:53 -05:00
Jay Cornwall 44f80d170d libhsakmt: Limit control stack size on gfx10 
The queue control stack size cannot exceed 0x7000 on ASICs
gfx1010 through gfx1031. The lower limit is not achievable
with AQL so this should have no practical effect.

Fixes control stack size overflow on large ASICs.

Change-Id: Ib78cf6e4c5f096044bf8de24debe211689891caa
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
 2020-09-28 18:14:57 -05:00
Evgeny 8ba4e41e68 SWDEV-253997 : packaging fix: installing hsa_ostream_ops.h 
Change-Id: Ib739cbb7538473afc9744e12d2bd568635e78616


[ROCm/roctracer commit: 1d975e5ba5]
 2020-09-28 13:19:51 -04:00
Evgeny 1d975e5ba5 SWDEV-253997 : packaging fix: installing hsa_ostream_ops.h 
Change-Id: Ib739cbb7538473afc9744e12d2bd568635e78616
 2020-09-28 13:19:51 -04:00
Sean Keely a3c4aaf95a Correct return type error in hsa_amd_signal_wait_any. 
The error checking macro IS_OPEN returns an hsa_signal_t.
This conflicts with the return type of uint32_t.

Add an assert and rely on spurious return rule to return zero
when rocr is not initialized.

Change-Id: Ifc9bb75e22ecdd675273de59b31e5026a69c62e0
 2020-09-25 21:33:23 -04:00
Sean Keely 248904ab26 Add try/catch blocks to image APIs. 
Change-Id: I724dcc8015ac556649278dd6cdf1ad4097aaa846
 2020-09-22 19:49:36 -04:00
Sean Keely 33a57ddf72 Correct image limits tables to SI limits. 
Limits remain unchanged through gfx1030.

Change-Id: Ibdd39b7b97101ea0133af6cebdf295aeef81ac45
 2020-09-22 19:49:08 -04:00
Ori Messinger 4ed1c1d492 ROCm SMI Python CLI: Implement --setclock for all Valid Clocks 
The purpose of this patch is to implement --setclock functionality for
all of the valid clocks (can be set with --setclock TYPE LEVEL).

The valid clocks are: dcefclk, fclk, mclk, pcie, sclk, socclk.
This functionality uses the existing 'setClocks' method.

Change-Id: I1d62baf372427ac1c0642c26a949663b673ef335
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
 2020-09-22 15:41:51 -04:00
Evgeny 0d164ba672 enable contexts wait 
Change-Id: Ie2adf04662fddc8051fb5418904c9c659e264d78
 2020-09-21 21:06:03 -04:00
Evgeny fc99b9a657 enable contexts wait 
Change-Id: Ie2adf04662fddc8051fb5418904c9c659e264d78


[ROCm/rocprofiler commit: 0d164ba672]
 2020-09-21 21:06:03 -04:00
Evgeny Shcherbakov e519076939 Merge "JSON flow timestamp fix" into amd-staging 2020-09-21 20:50:58 -04:00
Evgeny Shcherbakov cd9fdbbb47 Merge "JSON flow timestamp fix" into amd-staging 
[ROCm/rocprofiler commit: e519076939]
 2020-09-21 20:50:58 -04:00
Harish Kasiviswanathan 3311785c7b libhsakmt: add device ID for gfx1030 
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I3024bf706f88c0e612391f6d8045020101007bdc
 2020-09-21 14:23:46 -04:00
Mukul Joshi fb2ed24372 Use correct string conversion function for VRAM and SDMA usage 
VRAM and SDMA usage can be 64-bit long numbers. Use stoull()
instead of stoi() to convert the VRAM and SDMA usage strings to
numbers.

Change-Id: Ifadbada9f33320fc67666036ce8439823c1d1fb7
 2020-09-21 12:28:22 -04:00
Chengming Gui befc7edaea kfdtest: fix MTYPE error when init sdma fence packet 
Signed-off-by: Chengming Gui <Jack.Gui@amd.com>
Change-Id: I14a1ef204dbd5ab1e9f1840b9555f88b0df361c0
 2020-09-21 03:57:12 -04:00
Evgeny a87d41c6e4 JSON flow timestamp fix 
Change-Id: I2dacc29250f2d9c5d56bf8ab3ca7f621cb7b663a
 2020-09-21 03:53:03 -04:00
Evgeny e508fd72cc JSON flow timestamp fix 
Change-Id: I2dacc29250f2d9c5d56bf8ab3ca7f621cb7b663a


[ROCm/rocprofiler commit: a87d41c6e4]
 2020-09-21 03:53:03 -04:00
Evgeny Shcherbakov a239df1bcc Merge "codeobj tracing prof protocol" into amd-staging 
[ROCm/roctracer commit: 093844ba0e]
 2020-09-20 22:17:33 -04:00
Evgeny Shcherbakov 093844ba0e Merge "codeobj tracing prof protocol" into amd-staging 2020-09-20 22:17:33 -04:00
Evgeny 4760ef556a HCC_HOME env cleanup 
Change-Id: I2b00e5d310e6349fc52d5df60aae85f4c06adebe


[ROCm/roctracer commit: 8bdf282645]
 2020-09-19 17:50:57 -04:00
Evgeny 8bdf282645 HCC_HOME env cleanup 
Change-Id: I2b00e5d310e6349fc52d5df60aae85f4c06adebe
 2020-09-19 17:50:57 -04:00
Evgeny f7549dfde3 codeobj tracing prof protocol 
Change-Id: Ib49c8ee034fb7481b21f950490e10b350f2a1b79


[ROCm/roctracer commit: 6567c48e98]
 2020-09-19 16:49:46 -05:00
Evgeny 6567c48e98 codeobj tracing prof protocol 
Change-Id: Ib49c8ee034fb7481b21f950490e10b350f2a1b79
 2020-09-19 16:49:46 -05:00
Bill(Shuzhou) Liu 151520b97e Support watch() and unwatch() in RDC module framework 
The framework now supports watch() and unwatch(), which can be used
by the telemetry library to init events or pre-fetch fields when recording
starts.
* A new header file RdcTelemetryLibInterface.h is defined for library to
  include it.
* The RdcWatchTable will not talk to RdcMetricFetcher directly anymore.
  It will call the framework watch/unwatch to dispatch it to the libraries.
* Make the python binding consistent with the current code.

Change-Id: Ie5731d920ed5928f901369d60c23bd450807a562
 2020-09-18 16:02:31 -04:00
Cole Nelson a80454b35d CMakeLists.txt: set release/revision fields for pkg names 
Change-Id: I575c1a593b8798c93611d77444ff096fc272e3c3
Signed-off-by: Cole Nelson <cole.nelson@amd.com>
 2020-09-17 16:29:45 -07:00
Evgeny 1ce5f46737 testing using v3 object 
Change-Id: Ifca31d632726ab83f4c672b46cd9b97f817e757d


[ROCm/roctracer commit: bada601e64]
 2020-09-16 20:34:42 -04:00
Evgeny bada601e64 testing using v3 object 
Change-Id: Ifca31d632726ab83f4c672b46cd9b97f817e757d
 2020-09-16 20:34:42 -04:00
Mukul Joshi 8b95705e6f Add support for GPU reset SMI events 
Add handling for both pre GPU reset and post GPU reset SMI
events.

Change-Id: I64d5e006bef58cb28b1c580c75f482a4590427da
 2020-09-16 13:25:06 -04:00
Mukul Joshi aff75c955f Add support for KFD Thermal Throttling SMI event 
Add handling for receiving thermal throttling SMI event from the
kernel.
Also, update the event notification test to work with the new event.

Change-Id: Ib89c12b244f90998ccbae0a38b37f25705d156e0
 2020-09-16 13:24:57 -04:00
Mukul Joshi 406859ca8a Update KFD SMI event notification handling 
Event bitmask in KFD SMI event is now replaced with event index in
the SMI event message. Sending a event bitmask, which was a 64-bit
field with only 1 bit set, was quite wasteful of memory and also
potentially limiting to 64 events. Instead the kernel would send
event index in the SMI event message. As a result, update the
KFD SMI event handling to expect the event index in the message.

Change-Id: I3e74620788d3c1f7c0bdaa69e9d9ab3d1aba2c92
 2020-09-16 13:24:50 -04:00
Chris Freehill 8f9f9433d8 Enable library-based rocm_smi.py 
Change-Id: I5443308905456defc9818fac07ac2f20fe9426fd
 2020-09-16 09:31:30 -05:00
Jinzhou.Su 7efa823ec8 kfdtest: fix gfx90c blacklist issue 
This patch is the hot fix to update gfx90c blacklist 

Change-Id: I41f48154ad5ec3035fcb7891a224fc940dca991f
 2020-09-16 09:42:01 +08:00
Chris Freehill 6fb4c79784 Update README with ldconfig instructions 
Change-Id: Id033122d0b2f74b52a95a2ace99889c5d090cab3
(cherry picked from commit 29a3aee72f9546743d25ebae8c356b33933d3657)
 2020-09-15 10:11:34 -04:00
Jinzhou.Su 36249ddc0e kfdtest:Update gfx90c blacklist 
1. Add KFDEvictTest.* for gfx90c based on CI test results

2. Remove SDMA blacklist based on SDMA issue fixed:

Change-Id: I86910fc98a5141f29959b35248a900f0c098a6e8
 2020-09-14 22:49:53 -04:00