Revīziju grafs

956 Revīzijas

Autors SHA1 Ziņojums Datums
guanyu12 34a4fb2cbd Merge amd-dev into amd-master 20231012
Signed-off-by: guanyu12 <guanyu12@amd.com>
Change-Id: Id5894b0e5f8ff748b20de51860b946f9ffd4578e


[ROCm/amdsmi commit: 58f0a01447]
2023-10-12 16:42:47 +08:00
Dmitrii Galantsev 837611e992 Merge "Merge rocmsmi/amd-staging into amd-dev 20231010" into amd-dev
[ROCm/amdsmi commit: cb9875b056]
2023-10-12 00:46:08 -04:00
Galantsev, Dmitrii 41355173fe Fix amdsmi.h and update wrapper
Having an unnamed struct confuses our wrapper generator.
Adding a name solved it.

Change-Id: Iab3e73317fb21fb3667beef04878d4f3da96eadf
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: c988ff1730]
2023-10-11 22:55:27 -04:00
Galantsev, Dmitrii e3ee60fc5e Merge rocmsmi/amd-staging into amd-dev 20231010
Change-Id: I492562094a004eb78b2cc2b52d14d013d9f97112
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 6d72d65c48]
2023-10-11 18:58:12 -05:00
Maisam Arif d7399f690b Placeholders for new ras values
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I66cea253b19a5029172af0a3f4dd2f993c13b309
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: c6e54e09e7]
2023-10-11 19:39:38 -04:00
Maisam Arif 6a15f48028 Added xgmi physical id to static --asic
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I9e9f5929da635d22495aa394f2a9e5e6ce441706


[ROCm/amdsmi commit: 262b5b0254]
2023-10-11 13:28:27 -05:00
Galantsev, Dmitrii 73357843fe Fix rocm_smi.cc
Change-Id: Ib074dd542d8d37a6a618e10bd3bd389ad0cef108
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 3f0071599d]
2023-10-11 11:46:49 -05:00
guanyu12 aff83b3273 Merge amd-dev into amd-master 20231011
Signed-off-by: guanyu12 <guanyu12@amd.com>
Change-Id: Ic795b4135f34b883287346610e5b24726b865e12


[ROCm/amdsmi commit: 5b603ea770]
2023-10-11 11:22:49 +08:00
Galantsev, Dmitrii 4e46b9ebf1 Fix amdsmi.h and update wrapper
Having an unnamed struct confuses our wrapper generator.
Adding a name solved it.

Change-Id: Iab3e73317fb21fb3667beef04878d4f3da96eadf
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 1b606acf73]
2023-10-10 17:58:25 -05:00
Maisam Arif 51f4bf1794 Corrected total ecc counts
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I48b85d6476b829604044daab420883f94551abe2


[ROCm/amdsmi commit: b46ae13011]
2023-10-10 13:23:45 -05:00
Maisam Arif c89e49a0f5 Removed uncountable blocks from metric --ecc-block
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: Iab8ed3f80c8ebd7ffd3bfcf197e1a0b03782b498


[ROCm/amdsmi commit: b47d028da2]
2023-10-10 10:32:20 -05:00
Bill(Shuzhou) Liu dc0d637136 Add support to XGMI physical id
Get XGMI physical id from sysfs.

Change-Id: Ifd9e431bc2fbfd759d888a71b99046a5eb07b6ed


[ROCm/amdsmi commit: 6ca95c1a2d]
2023-10-10 09:29:05 -04:00
Charis Poag d54164d733 Add rsmi_dev_power_get
* Updates:
  - [API] Added rsmi_dev_power_get(uint32_t dv_ind,
                                   uint64_t *power,
                                   RSMI_POWER_TYPE
                                   *type)
          provides generic get to average or
          current power & provides backwards
          compatibility
  - Added a utility function to get MonitorTypes
    (monitor_type_string(type)) &
    RSMI_POWER_TYPE (power_type_string(type))
    strings
  - [Tests] Added rsmi_dev_power_get tests and
    provided better verification of return values for
    all power APIs
  - [Tests] Updated power outputs to show correct
    units
  - [example] Now uses avg, current, and generic
    power functions with type output response

Change-Id: I5ca06ca37fd5f61e100f2835b664d6cdd1ca42e6
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 31a1fcce7d]
2023-10-10 00:34:19 -05:00
Deepak Mewar fe29a848bc added metric table wrapper APIS & test code
Change-Id: I24207b3c32d7294337140a1f5108b81f3bf33580


[ROCm/amdsmi commit: 192fb538be]
2023-10-10 00:03:11 -04:00
Deepak Mewar 69c642a720 Updated the sample test for esmi wrappers
Change-Id: Ie382b84a0aed4ae40f4befa0e922c19ae8a316c8


[ROCm/amdsmi commit: 7a2f3c8d56]
2023-10-10 00:03:11 -04:00
Maisam Arif e3d24255c8 Updated human readable output for numa affinity
Change-Id: Id9767100061bd6e0f3b42cd2af80da7b588276b6
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 4c66db6b03]
2023-10-10 00:00:09 -04:00
guanyu12 911bbd9f3b Merge amd-dev into amd-master 20231010
Signed-off-by: guanyu12 <guanyu12@amd.com>
Change-Id: Ic4007101f8fef74e2642458ccda6056e74089082


[ROCm/amdsmi commit: 06ac6db82d]
2023-10-10 10:50:24 +08:00
Oliveira, Daniel 52f3e90525 rocm_smi_lib: Fix Modernize and refactor gpu_metrics
Adds support for 'gpu_metrics_v1_4' and new counters

Code changes related to the following:
  * rsmi gpu_metrics APIs
  * rsmi gpu_metrics Logs
  * The new gpu_metrics are now part of the Device

Build changes related to the following: None

Change-Id: Ie748e977cd0a01c6a2fb82260014c0699605dbb3
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>


[ROCm/amdsmi commit: 4e4ebde640]
2023-10-09 21:43:22 -05:00
Maisam Arif 9837144454 Updated bad-page output error handling
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: Ibcf4129d1b1cbe0f3df1d4751c61f6a318bb1323


[ROCm/amdsmi commit: 7ce46dcc24]
2023-10-09 17:41:08 -05:00
Maisam Arif 18a2b2fa49 Updated metrics --clock to include vclk0 & vclk1
Change-Id: I3b5df9da603fbd6be52a3d443ba7e0fe1a69fe6e
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 12882e7e39]
2023-10-09 17:41:08 -05:00
Maisam Arif 60147ba09a SWDEV-418008 - Added placeholders for pcie metric info
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I7975a6fdda3a480866c39253a33723e154a841ce


[ROCm/amdsmi commit: 3f6d677eb6]
2023-10-09 17:41:08 -05:00
Maisam Arif f975a96012 Enabled static --board for guest systems
Change-Id: I80e496139e20d8e328a6669f59de8922484c4315
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 816a020873]
2023-10-09 17:41:08 -05:00
Maisam Arif 8a9387cdec Added memory information to Guest
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I3e6b4bba3746c9498d34e6d2840461489eb3bc61
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 02b4b67ca0]
2023-10-09 17:41:08 -05:00
Maisam Arif 657d011f57 Updated static --bus output building
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I8f75cfcf1dae96d567ad86bda1467f1cb54e744c


[ROCm/amdsmi commit: 669b9eaedd]
2023-10-09 17:41:08 -05:00
Charis Poag 5d15251762 Rename NPS -> memory partition + compute partition node fix
* Updates:
        - rocm_smi_lib + CLI:
          Rename all "NPS mode" -> "memory partition"
          related files/functions/API/CLI to align with correct
          technical naming
        - rocm_smi_main: fixed identifying primary card's unique id
          utilize rsmi_dev_unique_id_get to map which
          KFD nodes belong to it
        - rsmi_dev_*_partition*: now have better logging output
        - compute partition tests:
          Added 20 sec delay for workaround until GPU
          busy is confirmed as the issue
        - CPPLint fixes/formatting
        - [Example] Moved all endl to "\n" for efficiency
        - [Example] Added Edge & Junction temperature examples
        - [Example] Added rsmi_minmax_bandwidth_get() example - WIP

Change-Id: Ida6db6fda7e0ac9d696a34cb15b4746e69d58d51
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: b251bb0c9f]
2023-10-06 11:51:09 -04:00
Galantsev, Dmitrii ea4c01c310 Merge amd-dev into amd-master 20231005
Change-Id: Ifa10a154ea9c0c656208f112c687e75fb63bd6d0
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 593b6b6513]
2023-10-05 16:31:23 -05:00
Galantsev, Dmitrii d10fcd31e5 Update package version
Change-Id: Ie094f75d028a09f862729094815f8a2b6ea8ad78
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 8244a677db]
2023-10-05 12:49:11 -05:00
Bill(Shuzhou) Liu c1a7a09f30 APIs for the cache level and size
Read the cache level and size from topoogy sysfs file.

Change-Id: Id3c558c95bcb79139a19e4adbaa7ff333d06098f


[ROCm/amdsmi commit: 1a233f93fb]
2023-10-05 11:10:54 -05:00
Bill(Shuzhou) Liu 528161560d Read PCIe slot type from sysfs
Read the PCIe slot type from sysfs instead of libdrm.

Change-Id: I9392b9e18a209ac7332f6902bcafb3b6062c86c1


[ROCm/amdsmi commit: 656f12e0f3]
2023-10-05 09:58:36 -04:00
Galantsev, Dmitrii 1b4acb28f8 Merge remote-tracking branch 'rocmsmi/amd-staging' into amd-dev
Change-Id: I6037383a3efa777cc281a992fd9aa11d8e9ced28


[ROCm/amdsmi commit: 3d3759061a]
2023-10-04 19:11:59 -05:00
Galantsev, Dmitrii bbe4ff9139 TESTS - Don't fail on TestFrequenciesRead
- Return from freq_output function early if clock is unsupported
- Right-align frequencies

Change-Id: I799c9351dac8a5be161bc9243cd3816539728357
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: e962d3b281]
2023-10-04 18:24:56 -05:00
Maisam Arif 401d3f229c Added driver_name to amdsmi_cli tool
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I8f3d52e0b23298443b2b16afec418cbbbc5f77e0


[ROCm/amdsmi commit: 572bf563d1]
2023-10-04 08:54:19 -04:00
Galantsev, Dmitrii 0a655243a4 TESTS - Disable same tests as in rocm-smi
Change-Id: I2587baf8a76e4e3a54880e73941b1d973440e7d3
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 6c8767a69a]
2023-10-03 09:58:58 -04:00
Galantsev, Dmitrii 40bc553d06 Add --version to CLI
Change-Id: Id2a8f10f544ed04e874db773820534eddd73f55d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: d862bee754]
2023-10-02 17:57:02 -05:00
Bill(Shuzhou) Liu 0d22f058c0 rocm-smi shows wrong fwinfo
Add new fw block into the rocm-smi tool.

Change-Id: Id5c7ccc2fc491f7e5d0390aeb4c6f81fd12fa644


[ROCm/amdsmi commit: d665157cd1]
2023-10-02 16:28:31 -04:00
Maisam Arif 76d025cff0 SWDEV-410230 - Added slot_type to amd-smi static --bus
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I2006a3525a8aa9091bf54501461d364f7237f00f


[ROCm/amdsmi commit: fadf1b6cc9]
2023-10-02 10:15:34 -04:00
Maisam Arif a489c16044 Adjust static --board output to be inline with Host
Change-Id: Ia6dcca5be077ef9e04533b632628a62633b63556
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: b58665e77b]
2023-10-02 09:30:25 -04:00
Maisam Arif 491ce167cb Sync commands w/ Host
Added ucode as alias to firmware
	Changed pcie_width to pcie_lanes

Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: Ia95a13d937c8e1b7bf092b5001de38ea9c008606


[ROCm/amdsmi commit: f7d631b9cd]
2023-10-02 09:30:25 -04:00
Ori Messinger a57b146e56 ROCm SMI CLI: Add Missing Firmware Blocks
The purpose of this patch is to add the following missing firmware
blocks to the SMI CLI:
-RSMI_FW_BLOCK_MES
-RSMI_FW_BLOCK_MES_KIQ

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: If9cabdc60ffcf08f27c9e6bdc20e8a26b192a738


[ROCm/amdsmi commit: aa89f2e125]
2023-09-29 18:13:16 -04:00
Galantsev, Dmitrii b376d27d7a Upgrade to CXX-17 gtest-1.14 and cmake-3.14
Change-Id: I3bceb90f79235a9c0616c5d7ef9e37e458ffdce6
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 871fae8b25]
2023-09-29 13:18:48 -04:00
Galantsev, Dmitrii 406c11f567 Upgrade to CXX-17 gtest-1.14 and cmake-3.14
Also change the TARGET from amd_smi_libraries to rocm_smi_libraries
This helps reduce confusion between rocm-smi and amd-smi

Change-Id: Ie54cedd831ba24bd9afc341ad15b7e8e20732059
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: cf6bcbbb27]
2023-09-28 12:44:51 -05:00
Bill(Shuzhou) Liu 90c9c8de4e Get PCIe slot type
Add API to get the PCIe slot type.

Change-Id: If6894af53894c524d61c7586c59768541bbf0ac6


[ROCm/amdsmi commit: 9eccf20f0c]
2023-09-27 23:31:09 -04:00
Maisam Arif 4fceaa7c5c Updated Driver Error Logging & Exceptions
Change-Id: Idd14904b33e82e4cb5d9f84c75978fe686a9b603
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 3fa96a9e02]
2023-09-27 19:24:55 -04:00
Bill(Shuzhou) Liu febbffb508 Do not print the library name if in default folder
The rocm-smi python tool will not print the library name on default
folder.

Change-Id: I203a872ebe2fc994766a2628049ca50c8bfa7120


[ROCm/amdsmi commit: 016dbf8aa3]
2023-09-27 12:14:33 -04:00
Maisam Arif cbdb61c9c5 Made driver N/A population consistent
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I4bd6d6f9729e62447ad765acc4908f124046e861


[ROCm/amdsmi commit: af4f954ae8]
2023-09-26 19:13:31 -05:00
Maisam Arif 2fa5035c3b Merge amd-dev into amd-master 20230926
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: Idb7329ba87dacbf0f1f9364c337b4ba46d98106c


[ROCm/amdsmi commit: 788bad5f43]
2023-09-26 15:31:39 -05:00
Maisam Arif fb0440d493 Added sleep state to amd-smi metric --clock
Change-Id: Idb5fbc84a787ef1affdf0449b6dd77ab6e50e91d
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 95337c88fc]
2023-09-26 15:21:25 -05:00
Galantsev, Dmitrii 245a8381e4 Merge remote-tracking branch 'rocmsmi/amd-staging' into HEAD
Change-Id: I18c19dc54eedc9a9c851e5d8d0fdfa7b632e23a5


[ROCm/amdsmi commit: aa1dd8391e]
2023-09-26 14:03:23 -05:00
Galantsev, Dmitrii 555ff6a653 Fix out-of-bounds array access for --showvc
get_od_clk_volt_info assumed the size of the file instead of checking
the length. This caused out-of-bounds array element access.

Change-Id: Ibda8f0c3a6d1623d48964641ae5ef610d2072e94
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 8eb9f892d3]
2023-09-26 13:59:37 -05:00
Maisam Arif 3cb76f4149 Merge amd-dev into amd-master 20230925
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: Ib028fd7749f8c38bcf64b11682468c464ca567c7


[ROCm/amdsmi commit: b452c8e2a3]
2023-09-25 20:18:36 -05:00