コミットグラフ

28 コミット

作成者 SHA1 メッセージ 日付
Divya Shikre 60d0f3052f Adding Performance Determinism Mode to rocm_smi lib, CLI & gtest.
A special mode of operation to achieve minimal performance variation by letting
the user have the ability to provide the desired frequency to be set as the soft limit.
The user can control the entry and exit to the mode via rocm-smi a mechanism to
enter / exit performance determinism mode as below.

Enter performance determinism mode:
- hold a lock
- write performance_determinism to power_dpm_force_performance_level
- write input clk_freq to pp_dpm_sclk
- release lock

Exit performance determinism_mode:
- hold a lock
- write auto to power_dpm_force_performance_level
- release lock

Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ia24e27954cdf1c4337ffc83d8948fbdfaf4552d2
2020-12-02 11:11:00 -05:00
Ori Messinger c0c1fd2098 ROCm SMI Python CLI: Fix --gpureset Bug
The purpose of this patch is to fix a bug present when using the
--gpureset option on a machine that has both an AMD GPU and a
non-AMD GPU (such as a motherboard's integrated graphics).

This bug occurs due to non-AMD GPUs being ignored by the LIB when
enumerating a list of valid AMD GPUs, causing the gpuReset method
to attempt a reset on the integrated graphics.

Change-Id: I1c03a3c41f905786e3c8246ec0c2b42786ff1770
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
2020-11-25 11:21:36 -05:00
Ori Messinger 015c7d59d0 ROCm SMI Python CLI: GPU showproductname SKU Fix
The purpose of this patch is to fix a bug present when using the
--showproducname option, resulting in the following error:
undefined symbol: rsmi_dev_sku_get

This bug fix uses a substring from vbios version instead of using the
LIB's rsmi_dev_sku_get to avoid getting the undefined symbol error.

Change-Id: I56d72a481d5dde44c56106ae297f4bcff40ac15f
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
2020-11-12 15:38:52 -05:00
Chris Freehill 438d28612f Use relative path to find librocm_smi
Change-Id: Ifca3f54d680a802c1c5fa360d17e64338b9ac9a8
2020-10-29 14:36:48 -05:00
Elena Sakhnovitch 4117719edd 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
2020-10-22 17:22:13 -04:00
Chris Freehill 1982fdc4fb Add new XGMI counter events to rsmiBindings.py
Also, correct RSMI_EVNT_LAST to new value.

Change-Id: I9f693cb398bba583201f6b5b5f0e2d45ede2e4e0
2020-10-22 17:21:50 -04:00
Divya Shikre 94291bf882 Fix for weight/hops not being updated
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I333d49fa011b85d41eca63c082c0615febe2f7e9
2020-10-20 15:01:06 -04:00
Ori Messinger 20ae72b078 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>
2020-10-15 21:21:32 -04:00
Ramesh Errabolu 328878343c Update ROCm SMI library with ability to read CU occupancy
Change-Id: Ib9882fa2d81c13604af282279bfa116bc2fd05a4
2020-10-14 09:33:37 -04:00
Ori Messinger e3c9aec714 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>
2020-10-08 11:17:45 -04:00
Kent Russell df7c3434cd 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
2020-10-07 14:09:23 -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
Chris Freehill 8f9f9433d8 Enable library-based rocm_smi.py
Change-Id: I5443308905456defc9818fac07ac2f20fe9426fd
2020-09-16 09:31:30 -05:00
Elena Sakhnovitch 91f8fcb7b1 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
2020-09-10 12:57:14 -04:00
Elena Sakhnovitch edcae88fe9 Add README.md starter file
signed-off-by: Elena Sakhnovitch
Change-Id: I677b7d643c6559693c5ad627b704ee36631cc32e
2020-09-10 11:09:42 -04:00
Elena Sakhnovitch 8b82621e72 ROCm SMI Python CLI: Implement --showbw
PCIE bandwidth functionality

Signed-off-by: Elena Sakhnovitch
Change-Id: I5a9ddc589846b6032739d491319078ead5723a27
2020-09-09 14:52:58 -04:00
Harish Kasiviswanathan f1786a3095 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
2020-09-08 19:29:09 -04:00
Divya Shikre 54d4b9d500 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
2020-09-08 18:42:39 -04:00
Ori Messinger 95d43e30e3 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>
2020-09-08 14:24:11 -04:00
Ori Messinger 2d59d0877b 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>
2020-09-02 06:40:59 -04:00
Divya Shikre d1f4c252b0 Adding voltage range functionality to rocm cli
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I9288c0c6cda2a984c34cfd2570deec640b6c9f0d
2020-08-28 12:04:36 -04:00
Divya Shikre 49734f8d34 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
2020-08-20 10:44:28 -04:00
Harish Kasiviswanathan 9f5d4a698e Update rsmi_process_info_t with sdma_usage field
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: Ie326e75674127a2e13f17fac344e2b672e877ce1
2020-08-19 17:54:15 -04:00
Divya Shikre 1276e4b9e9 Adding gpu reset functionality to rocm cli
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ifc0a239e8e8046fd7f56893d0101e0866cc3185f
2020-08-19 13:37:47 -04:00
Divya Shikre 2e8dc4f2a9 Adding Sdma Usage to showpids
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com
Change-Id: I72a9e1adc61eba382f1ac17c8e50b2a8bd6d6898
2020-08-14 12:12:34 -04:00
Divya Shikre 4032898d1b Adding Hw Topology option to ROCm SMI Python CLI
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com
Change-Id: Ic46334567703f705e38b3a8b4a08ab388c749251
2020-08-13 18:51:21 -04:00
Ori Messinger b568270f55 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>
2020-08-13 04:34:08 -04:00
Ori Messinger 2b909252ac 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>
2020-08-05 12:38:11 -04:00