Commit Graph

40 Commits

Author SHA1 Message Date
Chris Freehill 32645f25a6 Add rsmi_dev_serial_number_get()
Also correct whitespace issues

Change-Id: I7ffe23672304c31ed08d7148b04a19a7d4c3d7ef


[ROCm/rocm_smi_lib commit: cf13d6f4d8]
2019-07-22 07:09:53 -05:00
Harish Kasiviswanathan 0d25538efb Test rsmi_dev_drm_render_minor_get()
Change-Id: I5c0702efc8ed1bc155292e4c3a73d74e5c66204e
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>


[ROCm/rocm_smi_lib commit: 904ea5fc27]
2019-07-11 13:13:03 -04:00
Chris Freehill 93f23ef9b6 Add rsmi_dev_firmware_version_get()
Change-Id: Iba3e5f3eaa0eb031fc013fc168bded22bc249b5c


[ROCm/rocm_smi_lib commit: 31e02fdc61]
2019-07-09 22:50:44 -05:00
Chris Freehill e2c96d703a Add xgmi error_status and error_reset functions
Also, comment corrections and added check for invalid arguments

Change-Id: I891cbf9b37bfda629914a008811b840323872c02


[ROCm/rocm_smi_lib commit: 557e1f5704]
2019-07-09 09:55:05 -04:00
Chris Freehill fb87f41beb Add initial support for getting process information
Added implementation of and tests for
rsmi_dev_compute_process_info_by_pid_get() and
rsmi_dev_compute_process_info_get()

Change-Id: I4c4f5f39fe6701da37916c9ad41449b5d35ac7af


[ROCm/rocm_smi_lib commit: 9b93cbe21d]
2019-07-03 20:01:43 -05:00
Chris Freehill 4fa6f2f5bb Add rsmi_dev_memory_busy_percent_get()
Change-Id: Ide683b6c72870af547331f4502c5bb8c445d61b5


[ROCm/rocm_smi_lib commit: 1c5e090507]
2019-06-25 19:09:13 -05:00
Chris Freehill bdbd81c02a Event counter support
XGMI related events are supported

Change-Id: If17036fe890c8be45da3654353599821b5828c14


[ROCm/rocm_smi_lib commit: ea26baec20]
2019-06-24 17:40:01 -05:00
Kent Russell 25a1d039a2 Add support for reading GPU's unique ID
Add support and testing for reading the Unique ID associated with a
specific GPU. This ID will persist across reboots, even if the GPU is
moved to a different machine. Note that this is per-GPU, not per-card,
as some cards have multiple GPUs, and each GPU will get a unique
identifier

Change-Id: Idce50c6febc2ceb1a4c1200d2489ec8b9d8fe174


[ROCm/rocm_smi_lib commit: 35d2807196]
2019-06-21 08:39:36 -04:00
Chris Freehill a8fb2a5f29 Add support for junction, edge and memory temperature sensors (#42)
* If vendor/device/subsystem name is not found, use device ID string

* Update documentation for get-name functions

* Add support for junction, edge and memory temperature sensors


[ROCm/rocm_smi_lib commit: 11f714326b]
2019-05-24 15:24:49 -05:00
Chris Freehill 1ace8338c9 Updated google test to googletest-release-1.8.1
[ROCm/rocm_smi_lib commit: 98c2ad6aaf]
2019-05-15 10:21:37 -05:00
Chris Freehill d7f029f172 By default, only consider AMD GPU's in RSMI device list
With newly added initialization parameters that can be
passed to rsmi_init(), you can tell RSMI to consider other
devices.

Also:
-fixed incorrect header file name that would break in C
builds
-modified rsmi_init() and rsmi_shut_down() to reinitialize and
clear static structures


[ROCm/rocm_smi_lib commit: 1dfef717bb]
2019-05-09 18:55:15 -05:00
Chris Freehill 2a87e5bc44 Added rsmi_dev_pci_replay_counter_get()
Also, added code to destroy/recreate mutex if we can't get a lock
within 3 seconds, when shared memory mutex is initialized.


[ROCm/rocm_smi_lib commit: 34c977bd06]
2019-05-06 11:26:40 -05:00
Chris Freehill a42ab41d65 Added rsmi_version_str_get()
[ROCm/rocm_smi_lib commit: bb73c2607f]
2019-04-24 17:46:53 -05:00
Chris Freehill 55f8aa632a Add "Disabled" state to ECC states
[ROCm/rocm_smi_lib commit: 84e3c541d1]
2019-04-04 15:27:15 -05:00
Chris Freehill c777f1f63f Added ECC enabled, status and get functions
[ROCm/rocm_smi_lib commit: 4e679b9324]
2019-04-03 11:17:43 -05:00
Chris Freehill 93055a1698 Added new clock types
Also added missing error code strings and improved test output
messages


[ROCm/rocm_smi_lib commit: c77f3c0ebd]
2019-03-28 17:01:35 -05:00
Chris Freehill 2b903fceca Added new id and id name string look up functions
Also, updated docs with typo corrections and a new section


[ROCm/rocm_smi_lib commit: cbdfac7bdc]
2019-03-15 16:21:37 -05:00
Chris Freehill da2abd9adc Add table for GPU name look to give better name than just "amdgpu"
[ROCm/rocm_smi_lib commit: d39752cee7]
2019-03-10 17:56:06 -05:00
Chris Freehill 5d91dac776 Add rsmi_dev_memory_total_get()and rsmi_dev_memory_usage_get()
[ROCm/rocm_smi_lib commit: ddd292f1b5]
2019-03-04 18:26:11 -06:00
Chris Freehill 41c8ca9bb6 Re-organize function documentation into sections
[ROCm/rocm_smi_lib commit: 89fb40fbe5]
2019-03-03 23:11:50 -06:00
Chris Freehill 8bd8217df8 Use "_t" suffix consistently for RSMI types
[ROCm/rocm_smi_lib commit: bc0d801478]
2019-03-02 16:30:30 -06:00
Chris Freehill dfe3b9822b Added rsmi_dev_error_count_get()
[ROCm/rocm_smi_lib commit: fb5f41fc10]
2019-03-01 16:33:11 -06:00
Chris Freehill 9fa25de22a Add rsmi_dev_pci_throughput_get()
[ROCm/rocm_smi_lib commit: 18ce553dce]
2019-02-27 15:10:26 -06:00
Chris Freehill 168ac647dd Add VBIOS version get function
Also, consolidate "get version" type function tests into 1 test.


[ROCm/rocm_smi_lib commit: 021f13a68f]
2019-02-24 11:01:18 -06:00
Chris Freehill 011b4fc51a Documentation and volt-curve read updates
[ROCm/rocm_smi_lib commit: 68b5e2ee0d]
2019-02-22 15:05:44 -06:00
Chris Freehill 3bc7d827b0 Add get_version test; remove sanity test
Also, don't fail pcie bandwidth test when the pp_dpm_pcie file
does not correctly show the current bandwidth.


[ROCm/rocm_smi_lib commit: f3fa9a036c]
2019-02-12 18:07:26 -06:00
Chris Freehill c7c971f6e2 Break down monolithic test into many smaller tests
Also, added boot up default power profile, and modified to
accomodate new profile format


[ROCm/rocm_smi_lib commit: 17bf80dcb2]
2019-02-11 22:53:24 -06:00
Chris Freehill bd3b84e353 Add dont_fail option to not fail entire test on a single failure
[ROCm/rocm_smi_lib commit: dd450e963c]
2019-02-09 12:18:49 -06:00
Chris Freehill 301aaa28ab Replace fan test failure with warning
In some cases, the fan sysfs files will exist even if the device
doesn't have a fan. In these cases, the tests will give apparently
random results.

Also, remove documentation and ifdef'd test of debugfs related
power functions.


[ROCm/rocm_smi_lib commit: 4ab27528be]
2019-02-08 09:51:10 -06:00
Chris Freehill 00cb1f966b Don't assert or fail tests that are unsupported by system
[ROCm/rocm_smi_lib commit: 08ec2a9804]
2019-01-24 16:07:25 -06:00
Chris Freehill 1600173571 Add support for reading frequency-volt curve data
[ROCm/rocm_smi_lib commit: b6ce6d30f4]
2019-01-09 23:17:16 -06:00
Chris Freehill 80eeb7960f Add support for reading frequency-volt curva data
[ROCm/rocm_smi_lib commit: 639a4e3503]
2019-01-07 08:44:23 -06:00
Chris Freehill 0e337468b7 Handle case where PCIe information is not implemented in system
Also add a new error code for this.


[ROCm/rocm_smi_lib commit: 5e6424cab3]
2018-12-19 17:24:27 -06:00
Chris Freehill d1eead8c64 Add rsmi_version_get() function
Also, modify CMakeLists.txt to use git tags to determine the
shared library version for the SONAME and the ROCm build for the
package name.


[ROCm/rocm_smi_lib commit: 5a9a729b31]
2018-12-06 13:48:59 -06:00
Chris Freehill c56ac1825e Add get and set routines for PCIe bandwidth
[ROCm/rocm_smi_lib commit: 9c897ab86d]
2018-11-16 15:55:38 -06:00
Chris Freehill 78b05ede52 Add rsmi_dev_busy_percent_get()
Also: correct some comments, ifdef out unused code


[ROCm/rocm_smi_lib commit: 861c2c2e33]
2018-11-12 17:25:14 -06:00
Chris Freehill 3ccce7ddbb Add rsmi_dev_pci_id_get() to return BDFID for given device
Also:
* add some exception handling;
* chop newline character off of device name returned from
rsmi_dev_id_get()


[ROCm/rocm_smi_lib commit: 59a952666f]
2018-11-05 11:22:12 -06:00
Chris Freehill 8a6704659d Use sysfs file to get average power instead of debugfs
[ROCm/rocm_smi_lib commit: 62ba2f578e]
2018-10-29 17:59:24 -05:00
Chris Freehill cf2b565985 Add support for new performance levels
Also added tests for new performance levels and clean up some
formatting/style issues.


[ROCm/rocm_smi_lib commit: 767fa53d8c]
2018-10-25 14:13:55 -05:00
Chris Freehill 71d80e88c2 Add gtest based testing
[ROCm/rocm_smi_lib commit: b9c6a5a443]
2018-10-24 11:57:03 -05:00