Граф коммитов

204 Коммитов

Автор SHA1 Сообщение Дата
Chris Freehill a061e62b2b Add disclaimer to README and update pdf manual
Change-Id: I19c957e5a1de9f87f1834d341221fad6c826b252


[ROCm/amdsmi commit: af5227cdf7]
2020-11-10 17:36:51 -06:00
Chris Freehill bd9e47a53c rsmitst address sanitizer support
Also, add libasan flag variants for librocm_smi

Change-Id: Ibd012e40d26907addf8c0550aaf9f78c11b8d51f


[ROCm/amdsmi commit: bf6af90908]
2020-11-10 15:45:56 -06:00
Chris Freehill c6a58d91cb Quiet address sanitizer warnings
Also,
* Fix some doxygen issues
* Fix address sanitizer issues in rsmitst

Change-Id: Ie6c6fd9af5c418210b7064e79650fb92cd4a5e2b


[ROCm/amdsmi commit: 63064b0000]
2020-11-10 14:16:39 -06:00
Chris Freehill fa475d307a Make CMakeLists.txt recognize ADDRESS_SANITIZER
Change-Id: Ic80ac42c62cd400e48fb26d504547931fdd6863a


[ROCm/amdsmi commit: e7c8dfe2a2]
2020-11-04 17:57:31 -06:00
Chris Freehill b5e575875c Use relative path to find librocm_smi
Change-Id: Ifca3f54d680a802c1c5fa360d17e64338b9ac9a8


[ROCm/amdsmi commit: 438d28612f]
2020-10-29 14:36:48 -05:00
Elena Sakhnovitch 61b8cdbe43 ROCm SMI Python CLI: --rasinject partial support
This implementation is copied directly from the previous rocm_smi.py
script; This feature is experimental and will be updated or removed with
feauture releases.

Signed-off-by: Elena Saknovitch
Change-Id: I5cd38266946302bc4123aeafaa825e13f704235e


[ROCm/amdsmi commit: 4117719edd]
2020-10-22 17:22:13 -04:00
Chris Freehill cac03f5a0e Add new XGMI counter events to rsmiBindings.py
Also, correct RSMI_EVNT_LAST to new value.

Change-Id: I9f693cb398bba583201f6b5b5f0e2d45ede2e4e0


[ROCm/amdsmi commit: 1982fdc4fb]
2020-10-22 17:21:50 -04:00
Divya Shikre 33ccef9a1e Fix for weight/hops not being updated
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I333d49fa011b85d41eca63c082c0615febe2f7e9


[ROCm/amdsmi commit: 94291bf882]
2020-10-20 15:01:06 -04:00
Ori Messinger 297f89a62a ROCm SMI Python CLI: Add CU Occupancy to showPids function
The purpose of this patch is to add CU occupancy functionality to showPids
by calling rsmi_compute_process_info_get from the LIB.

Now showPids shows the following information on (KFD compute) processes:
PID, process name, GPU(s), VRAM used, SDMA used, and CU occupancy.

Change-Id: Ie005901e0eb946ef0fbb3523245ca451c4eed595
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: 20ae72b078]
2020-10-15 21:21:32 -04:00
Ramesh Errabolu c69c210a6e Update ROCm SMI library with ability to read CU occupancy
Change-Id: Ib9882fa2d81c13604af282279bfa116bc2fd05a4


[ROCm/amdsmi commit: 328878343c]
2020-10-14 09:33:37 -04:00
Divya Shikre 207d6339ec Adding gtest for gpu metrics read
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I66edb15c8b7380f3427822b33e845202bfac7a2b


[ROCm/amdsmi commit: f397cba414]
2020-10-08 13:37:47 -04:00
Ori Messinger 6ea0c8b524 ROCm SMI Python CLI: Check for amdgpu Driver Initialization
The purpose of this patch is to check for amdgpu driver initialization
before attempting to initialize rocmsmi in the CLI.

Additionally, since the '--help' functionality does not rely on anything
external to the CLI, it can now be called without the driver initialized.

Change-Id: I2fcce60ca6d9f77835549e3558c4bb1747499c5c
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: e3c9aec714]
2020-10-08 11:17:45 -04:00
Chris Freehill 137e33a1e6 Revert "Revert "Support for RSMI_EVNT_GRP_XGMI_DATA_OUT counters""
This reverts commit 1be2933806.



Change-Id: Ic412a64d35aab74caf12bf4c791f0a66ac15b061


[ROCm/amdsmi commit: 5465d872aa]
2020-10-08 10:36:30 -04:00
Kent Russell fb687f2c68 Remove extraneous mutexes
We already grab the mutex before getting the device name, so we don't
need to grab it again

Change-Id: Ib627ba3a39c485f6069af052cfd3e6c522873d43


[ROCm/amdsmi commit: e350278b68]
2020-10-08 07:55:07 -04:00
Chris Freehill 1be2933806 Revert "Support for RSMI_EVNT_GRP_XGMI_DATA_OUT counters"
This reverts commit dc48f149f0.

Temporarily reverting until the driver side of this is upstream

Change-Id: I2d8243208c1271ebad90bc2ee0fda2dfefb0831b


[ROCm/amdsmi commit: ae6d3fbdd0]
2020-10-07 18:42:56 -04:00
Kent Russell d41e3be1b0 Check FRU-based product information if available
WKS and server cards have an FRU with product information, so try to use
that for product name and product SKU if it exists.

Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: I40bbd3bf62f4cb02e96015ed1630112691cacbc3


[ROCm/amdsmi commit: df7c3434cd]
2020-10-07 14:09:23 -04:00
Chris Freehill 17f6a43fa1 Fail gracefully if drm directory is not found
Change-Id: I0f3ab2721108355752caf0280124469b98af4967


[ROCm/amdsmi commit: c6f02b4d62]
2020-10-05 21:12:11 -04:00
Chris Freehill dc48f149f0 Support for RSMI_EVNT_GRP_XGMI_DATA_OUT counters
Also some format fixes

Change-Id: Id3c0f6b3cf5b327bb9ca6acb6091dc67764c8032


[ROCm/amdsmi commit: 946bf93dfb]
2020-10-05 17:22:19 -05:00
Divya Shikre 5cddbccec6 Adding functionality that will parse gpu_metrics sysfs file
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I3a84870b83eb4cd0ed46f10bb19169c91f99fd8e


[ROCm/amdsmi commit: 8b48564ce3]
2020-10-02 10:25:41 -04:00
Chris Freehill e775527ffc Add gtest lib dir to library search path
Change-Id: I57bb20e2a67a4eaac2d0e24314e22d1a5fbe3533


[ROCm/amdsmi commit: 3522e94ed0]
2020-10-01 23:46:33 -04:00
Ori Messinger eca48bfd0b 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>


[ROCm/amdsmi commit: 4ed1c1d492]
2020-09-22 15:41:51 -04:00
Mukul Joshi ffc473d40a 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


[ROCm/amdsmi commit: fb2ed24372]
2020-09-21 12:28:22 -04:00
Mukul Joshi cdb6fd8870 Add support for GPU reset SMI events
Add handling for both pre GPU reset and post GPU reset SMI
events.

Change-Id: I64d5e006bef58cb28b1c580c75f482a4590427da


[ROCm/amdsmi commit: 8b95705e6f]
2020-09-16 13:25:06 -04:00
Mukul Joshi e6f5d59edf 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


[ROCm/amdsmi commit: aff75c955f]
2020-09-16 13:24:57 -04:00
Mukul Joshi d7e3e0f579 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


[ROCm/amdsmi commit: 406859ca8a]
2020-09-16 13:24:50 -04:00
Chris Freehill 63d066c560 Enable library-based rocm_smi.py
Change-Id: I5443308905456defc9818fac07ac2f20fe9426fd


[ROCm/amdsmi commit: 8f9f9433d8]
2020-09-16 09:31:30 -05:00
Chris Freehill fca52ec7ca Make sure all sensor labels have valid mappings
There may not be label files for some sensors on older
devices. We need to make sure there is a valid dummy
mapping in these cases.

Change-Id: Id6a8b71e554552be84a0e42a477070b504151e7f


[ROCm/amdsmi commit: b015052a07]
2020-09-11 17:32:54 -05:00
Chris Freehill 34fd068d3c Add missing docs section for EvntNotif
Change-Id: I69187c734d2618ddb4272c58bb76d04646908793


[ROCm/amdsmi commit: cafd678d5d]
2020-09-11 15:48:56 -05:00
Elena Sakhnovitch a738bab044 ROCm SMI CLI: Add JSON support for topo functions
-Add divider between devices for --showclocks to increase readibility.
-Fix fan rounding error
-Fix spaces to comply with coding standard
-Fix @param description error in topo functions
-JSON result for topology:
{
  "card0": {
    "(Topology) Numa Node": "0",
    "(Topology) Numa Affinity": "4294967295"
  },
  "card1": {
    "(Topology) Numa Node": "0",
    "(Topology) Numa Affinity": "4294967295"
  },
  "system": {
    "(Topology) Weight between DRM devices 0 and 1": "40",
    "(Topology) Hops between DRM devices 0 and 1": "2",
    "(Topology) Link type between DRM devices 0 and 1": "PCIE"
  }
}

Signed-off-by: Elena Sakhnovitch <Elena.Sakhnovitch@amd.com>
Change-Id: I711c100362826ed729ff90edd407009237d64f8f


[ROCm/amdsmi commit: 91f8fcb7b1]
2020-09-10 12:57:14 -04:00
Elena Sakhnovitch a44008b347 Add README.md starter file
signed-off-by: Elena Sakhnovitch
Change-Id: I677b7d643c6559693c5ad627b704ee36631cc32e


[ROCm/amdsmi commit: edcae88fe9]
2020-09-10 11:09:42 -04:00
Elena Sakhnovitch 06ed863443 ROCm SMI Python CLI: Implement --showbw
PCIE bandwidth functionality

Signed-off-by: Elena Sakhnovitch
Change-Id: I5a9ddc589846b6032739d491319078ead5723a27


[ROCm/amdsmi commit: 8b82621e72]
2020-09-09 14:52:58 -04:00
Harish Kasiviswanathan b7082cb0be Don't hard code rocm_smi_lib path
During rocm_smi_lib installation the path should be set using ldconfig

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I0cab18f492013b783d1ce632591ce295f934a168


[ROCm/amdsmi commit: f1786a3095]
2020-09-08 19:29:09 -04:00
Divya Shikre b0b388b538 Adding setsrange, setmrange, setvc, setslevel and setmlevel functionality to rocm lib and cli
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I5fd65ea7bcd5403aaf2e42d2aa28d837929da253


[ROCm/amdsmi commit: 54d4b9d500]
2020-09-08 18:42:39 -04:00
Ori Messinger f99a2a83c0 ROCm SMI Python CLI: Implement show/set mclk OverDrive
The purpose of this patch is to implement show and set mclk OverDrive.
This implementation is copied directly from the previous rocm_smi.py
script since this functionality is mostly deprecated.

Change-Id: I705430f873a73f954b6812c222a385ff4e9b6eb2
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: 95d43e30e3]
2020-09-08 14:24:11 -04:00
Ori Messinger 914d835494 ROCm SMI Python CLI: Implement Valid Clocks
The purpose of this patch is to implement the remaining valid clocks.
The valid clocks are: dcefclk, fclk, mclk, pcie, sclk, socclk
This functionality is needed for the 'setClocks' method.

Change-Id: Ie648fb29dbbd61f0f064d4462ac566911f1ca2aa
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: 2d59d0877b]
2020-09-02 06:40:59 -04:00
Divya Shikre 279b34a7e9 Adding voltage range functionality to rocm cli
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I9288c0c6cda2a984c34cfd2570deec640b6c9f0d


[ROCm/amdsmi commit: d1f4c252b0]
2020-08-28 12:04:36 -04:00
Divya Shikre 202006e30a Adding logic to skip the loop if src and dest device are the same in HW Topology.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ib9cfbf5a7238ba75f6463e8fa6250bb9946b7979


[ROCm/amdsmi commit: 49734f8d34]
2020-08-20 10:44:28 -04:00
Harish Kasiviswanathan 5a9e1017c3 Update rsmi_process_info_t with sdma_usage field
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: Ie326e75674127a2e13f17fac344e2b672e877ce1


[ROCm/amdsmi commit: 9f5d4a698e]
2020-08-19 17:54:15 -04:00
Divya Shikre 2c35b82c5c Adding gpu reset functionality to rocm cli
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ifc0a239e8e8046fd7f56893d0101e0866cc3185f


[ROCm/amdsmi commit: 1276e4b9e9]
2020-08-19 13:37:47 -04:00
Chris Freehill 01f61b49f1 Clean up comments for rsmitst
Change-Id: Iea5322a5fd3bffe77557fa2cecbce70716e1258c


[ROCm/amdsmi commit: 7be97ec2aa]
2020-08-17 11:48:07 -05:00
Divya Shikre bdda71d7a7 Adding Sdma Usage to showpids
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com
Change-Id: I72a9e1adc61eba382f1ac17c8e50b2a8bd6d6898


[ROCm/amdsmi commit: 2e8dc4f2a9]
2020-08-14 12:12:34 -04:00
Divya Shikre 8acb8b76cf Adding Hw Topology option to ROCm SMI Python CLI
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com
Change-Id: Ic46334567703f705e38b3a8b4a08ab388c749251


[ROCm/amdsmi commit: 4032898d1b]
2020-08-13 18:51:21 -04:00
Ori Messinger 5c4a5806a8 ROCm SMI Python CLI: properly cast pid to int
The purpose of this patch is to fix --showpids and --showpidgpus functionality.
When pid is passed into a LIB function, it must be cast to int first.

Change-Id: I5cb7ac41052abeefff0dedf2384c4bb3c8d577a3
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: b568270f55]
2020-08-13 04:34:08 -04:00
Chris Freehill 9cc6b4f260 Move README back to root
README should be at root to display in github main page.
Also, removed paragraph related to API changes early
in development.

Change-Id: I2e92573a31d3caa7790364de9356c6d7e7be553d


[ROCm/amdsmi commit: da64e284dc]
2020-08-06 09:27:48 -05:00
Chris Freehill 596799c441 Correct event counter documentation example
Change-Id: I74c41de8e4aacbd42d9e156983369eb76bec3367


[ROCm/amdsmi commit: 0468aa4971]
2020-08-06 08:49:21 -05:00
Ori Messinger 4f698bda12 ROCm SMI Python CLI
This tool acts as a command line interface for manipulating
and monitoring the Radeon Open Compute Kernel, similar to the
rocm_smi.py python tool.

The purpose of this commit is for the initial upload and cleanup
of the (incomplete) rocmSmiLib_cli.py and rsmiBindings.py files.

In the near future, this tool should have full feature parity with
rocm_smi.py by relying on the available rocm_smi_lib functions.

Change-Id: Ifbafd5118c15c68c240e3c83a47d2690a27c9353
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: 2b909252ac]
2020-08-05 12:38:11 -04:00
Chris Freehill 97d838b927 Replace "." in pkg name with "-"
Package name should have a hyphen (not a period) between
NumCommitsSinceLastTag and ROCMIntegrationJobIdentifier.

Fixes SWDEV-245838

Change-Id: I28c4337af6f92ac51a4aed03a09af23b92bd89b5


[ROCm/amdsmi commit: 92c258c364]
2020-07-27 20:54:52 -04:00
Chris Freehill 43fd9d8044 Correct usage of bitwise &
Also, fix warning related to catch() and cpplint error.

Change-Id: I4292170538d0f700fccb605814c5058543abe74a


[ROCm/amdsmi commit: c2439d28e8]
2020-07-26 20:08:24 -05:00
Ashutosh Mishra 2e7d7b3238 Adding "BUILD_SHARED_LIBS" flag to cmake files
JIRA : SWDEV-234471
Changing cmake for dynamically creation of shared / archive libs depending upon the parameret to cmake

Adapted comments.

Change-Id: Ice5925719b8c307c32310b252f61cbc211d1af27


[ROCm/amdsmi commit: d325613220]
2020-07-16 22:32:55 -04:00
Chris Freehill 77fc313a36 Update xgmi event counter documentation
Also:
* fix doxygen manual generation that was altered during
  OAM refactor
* quiet some compile warnings.

Change-Id: I548a3cf00eb887bea3dbf58e362ca6dfe90bde28


[ROCm/amdsmi commit: 52514835f0]
2020-07-16 17:42:56 -05:00