aaecfd6fff
Adjust how we read ECC block counter status
...
This change corresponds to kernel changes.
Change-Id: Ibd977e8b3338349036cb16e55fb0b2c9c187726d
2019-08-09 16:06:43 -05:00
a34832f11e
Fix RAS change
...
RAS formatting changed, so get it to handle both types of sysfs output
until it's normalized
Change-Id: I56f2a2495af8ff4d01011bc614283376afb9ad0a
2019-08-08 12:09:18 -04:00
73c54e1fd0
Add support for rsmi_dev_memory_reserved_pages_get()
...
Also, don't return an error for empty sysfs files. The reserved memory
page file will often have no lines. We don't want it to appear that
this function is not supported if the file is empty.
Change-Id: I1d28bb184ea587bb578fe71dd75adc2a812d09a8
2019-08-06 11:42:03 -05:00
cf13d6f4d8
Add rsmi_dev_serial_number_get()
...
Also correct whitespace issues
Change-Id: I7ffe23672304c31ed08d7148b04a19a7d4c3d7ef
2019-07-22 07:09:53 -05:00
68cb303a44
Add rsmi_dev_drm_render_minor_get()
...
Function to get the drm minor number associated with ROCm device
Change-Id: I9356b9ca75151882acbb075076bc072f08b73aae
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com >
2019-07-11 13:12:34 -04:00
31e02fdc61
Add rsmi_dev_firmware_version_get()
...
Change-Id: Iba3e5f3eaa0eb031fc013fc168bded22bc249b5c
2019-07-09 22:50:44 -05:00
557e1f5704
Add xgmi error_status and error_reset functions
...
Also, comment corrections and added check for invalid arguments
Change-Id: I891cbf9b37bfda629914a008811b840323872c02
2019-07-09 09:55:05 -04:00
9b93cbe21d
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
2019-07-03 20:01:43 -05:00
1c5e090507
Add rsmi_dev_memory_busy_percent_get()
...
Change-Id: Ide683b6c72870af547331f4502c5bb8c445d61b5
2019-06-25 19:09:13 -05:00
ea26baec20
Event counter support
...
XGMI related events are supported
Change-Id: If17036fe890c8be45da3654353599821b5828c14
2019-06-24 17:40:01 -05:00
35d2807196
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
2019-06-21 08:39:36 -04:00
11f714326b
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
2019-05-24 15:24:49 -05:00
59538cd004
If vendor/device/subsystem name is not found, use device ID string ( #41 )
...
* If vendor/device/subsystem name is not found, use device ID string
2019-05-16 16:15:17 -05:00
7b9ff01a37
Check for root access early for functions that require it
2019-05-15 16:54:20 -05:00
53489c1f3d
Correct return code of isAMDGpu()
...
Also, correct some comments, whitespace.
2019-05-13 18:02:03 -05:00
1dfef717bb
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
2019-05-09 18:55:15 -05:00
34c977bd06
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.
2019-05-06 11:26:40 -05:00
5e24a77193
Add mutex for multi-process access to device sysfs files
...
This commit uses a pthread mutex in shared memory to prevent
almost all cases of multiple processes simultaneously
reading/writing to device sysfs files. The main existing race
condition is when 2 processes are starting at the same time,
setting up their shared memory and mutexes. Since this is meant
to prevent collisions among thread and processes, the small
shared memory segments (big enough for a pthread_mutex) will
persist until reboot.
2019-05-04 15:10:58 -05:00
bb73c2607f
Added rsmi_version_str_get()
2019-04-24 17:46:53 -05:00
84e3c541d1
Add "Disabled" state to ECC states
2019-04-04 15:27:15 -05:00
4e679b9324
Added ECC enabled, status and get functions
2019-04-03 11:17:43 -05:00
c77f3c0ebd
Added new clock types
...
Also added missing error code strings and improved test output
messages
2019-03-28 17:01:35 -05:00
cbdfac7bdc
Added new id and id name string look up functions
...
Also, updated docs with typo corrections and a new section
2019-03-15 16:21:37 -05:00
58d5ff7509
Use system files to look up gpu names instead of internal table
2019-03-11 18:06:50 -05:00
eaa5def17f
Use system files to look up gpu names instead of internal table
2019-03-11 17:56:58 -05:00
d39752cee7
Add table for GPU name look to give better name than just "amdgpu"
2019-03-10 17:56:06 -05:00
ddd292f1b5
Add rsmi_dev_memory_total_get()and rsmi_dev_memory_usage_get()
2019-03-04 18:26:11 -06:00
bc0d801478
Use "_t" suffix consistently for RSMI types
2019-03-02 16:30:30 -06:00
fb5f41fc10
Added rsmi_dev_error_count_get()
2019-03-01 16:33:11 -06:00
18ce553dce
Add rsmi_dev_pci_throughput_get()
2019-02-27 15:10:26 -06:00
4771996d99
Fix sysfs write operations
2019-02-25 15:14:46 -06:00
021f13a68f
Add VBIOS version get function
...
Also, consolidate "get version" type function tests into 1 test.
2019-02-24 11:01:18 -06:00
68b5e2ee0d
Documentation and volt-curve read updates
2019-02-22 15:05:44 -06:00
17bf80dcb2
Break down monolithic test into many smaller tests
...
Also, added boot up default power profile, and modified to
accomodate new profile format
2019-02-11 22:53:24 -06:00
dd450e963c
Add dont_fail option to not fail entire test on a single failure
2019-02-09 12:18:49 -06:00
08ec2a9804
Don't assert or fail tests that are unsupported by system
2019-01-24 16:07:25 -06:00
b6ce6d30f4
Add support for reading frequency-volt curve data
2019-01-09 23:17:16 -06:00
639a4e3503
Add support for reading frequency-volt curva data
2019-01-07 08:44:23 -06:00
5e6424cab3
Handle case where PCIe information is not implemented in system
...
Also add a new error code for this.
2018-12-19 17:24:27 -06:00
5a9a729b31
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.
2018-12-06 13:48:59 -06:00
9c897ab86d
Add get and set routines for PCIe bandwidth
2018-11-16 15:55:38 -06:00
861c2c2e33
Add rsmi_dev_busy_percent_get()
...
Also: correct some comments, ifdef out unused code
2018-11-12 17:25:14 -06:00
59a952666f
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()
2018-11-05 11:22:12 -06:00
62ba2f578e
Use sysfs file to get average power instead of debugfs
2018-10-29 17:59:24 -05:00
767fa53d8c
Add support for new performance levels
...
Also added tests for new performance levels and clean up some
formatting/style issues.
2018-10-25 14:13:55 -05:00
b2f1ee1764
Comment corrections, debug output and assert added
2018-10-22 17:26:38 -05:00
53b7ae1113
ROCm 1.9.0 update
2018-09-16 00:13:29 -05:00
e948ee5e00
first commit
2017-10-30 12:12:40 -05:00
Chris Freehill
Kent Russell
Harish Kasiviswanathan
Chris Freehill