1 .. SPDX-License-Identifier: GPL-2.0
2 .. include:: <isonum.txt>
4 ===============================================
5 ``amd-pstate`` CPU Performance Scaling Driver
6 ===============================================
8 :Copyright: |copy| 2021 Advanced Micro Devices, Inc.
10 :Author: Huang Rui <ray.huang@amd.com>
16 ``amd-pstate`` is the AMD CPU performance scaling driver that introduces a
17 new CPU frequency control mechanism on modern AMD APU and CPU series in
18 Linux kernel. The new mechanism is based on Collaborative Processor
19 Performance Control (CPPC) which provides finer grain frequency management
20 than legacy ACPI hardware P-States. Current AMD CPU/APU platforms are using
21 the ACPI P-states driver to manage CPU frequency and clocks with switching
22 only in 3 P-states. CPPC replaces the ACPI P-states controls and allows a
23 flexible, low-latency interface for the Linux kernel to directly
24 communicate the performance hints to hardware.
26 ``amd-pstate`` leverages the Linux kernel governors such as ``schedutil``,
27 ``ondemand``, etc. to manage the performance hints which are provided by
28 CPPC hardware functionality that internally follows the hardware
29 specification (for details refer to AMD64 Architecture Programmer's Manual
30 Volume 2: System Programming [1]_). Currently, ``amd-pstate`` supports basic
31 frequency control function according to kernel governors on some of the
32 Zen2 and Zen3 processors, and we will implement more AMD specific functions
33 in future after we verify them on the hardware and SBIOS.
37 =======================
39 Collaborative Processor Performance Control (CPPC) interface enumerates a
40 continuous, abstract, and unit-less performance value in a scale that is
41 not tied to a specific performance state / frequency. This is an ACPI
42 standard [2]_ which software can specify application performance goals and
43 hints as a relative target to the infrastructure limits. AMD processors
44 provide the low latency register model (MSR) instead of an AML code
45 interpreter for performance adjustments. ``amd-pstate`` will initialize a
46 ``struct cpufreq_driver`` instance, ``amd_pstate_driver``, with the callbacks
47 to manage each performance update behavior. ::
49 Highest Perf ------>+-----------------------+ +-----------------------+
55 Nominal Perf ------>+-----------------------+ +-----------------------+
62 | | Desired Perf ---->| |
73 linear perf ------>+-----------------------+ +-----------------------+
75 | | Lowest perf ---->| |
77 Lowest perf ------>+-----------------------+ +-----------------------+
81 0 ------>+-----------------------+ +-----------------------+
83 AMD P-States Performance Scale
88 AMD CPPC Performance Capability
89 --------------------------------
91 Highest Performance (RO)
92 .........................
94 This is the absolute maximum performance an individual processor may reach,
95 assuming ideal conditions. This performance level may not be sustainable
96 for long durations and may only be achievable if other platform components
97 are in a specific state; for example, it may require other processors to be in
98 an idle state. This would be equivalent to the highest frequencies
99 supported by the processor.
101 Nominal (Guaranteed) Performance (RO)
102 ......................................
104 This is the maximum sustained performance level of the processor, assuming
105 ideal operating conditions. In the absence of an external constraint (power,
106 thermal, etc.), this is the performance level the processor is expected to
107 be able to maintain continuously. All cores/processors are expected to be
108 able to sustain their nominal performance state simultaneously.
110 Lowest non-linear Performance (RO)
111 ...................................
113 This is the lowest performance level at which nonlinear power savings are
114 achieved, for example, due to the combined effects of voltage and frequency
115 scaling. Above this threshold, lower performance levels should be generally
116 more energy efficient than higher performance levels. This register
117 effectively conveys the most efficient performance level to ``amd-pstate``.
119 Lowest Performance (RO)
120 ........................
122 This is the absolute lowest performance level of the processor. Selecting a
123 performance level lower than the lowest nonlinear performance level may
124 cause an efficiency penalty but should reduce the instantaneous power
125 consumption of the processor.
127 AMD CPPC Performance Control
128 ------------------------------
130 ``amd-pstate`` passes performance goals through these registers. The
131 register drives the behavior of the desired performance target.
133 Minimum requested performance (RW)
134 ...................................
136 ``amd-pstate`` specifies the minimum allowed performance level.
138 Maximum requested performance (RW)
139 ...................................
141 ``amd-pstate`` specifies a limit the maximum performance that is expected
142 to be supplied by the hardware.
144 Desired performance target (RW)
145 ...................................
147 ``amd-pstate`` specifies a desired target in the CPPC performance scale as
148 a relative number. This can be expressed as percentage of nominal
149 performance (infrastructure max). Below the nominal sustained performance
150 level, desired performance expresses the average performance level of the
151 processor subject to hardware. Above the nominal performance level,
152 the processor must provide at least nominal performance requested and go higher
153 if current operating conditions allow.
155 Energy Performance Preference (EPP) (RW)
156 .........................................
158 This attribute provides a hint to the hardware if software wants to bias
159 toward performance (0x0) or energy efficiency (0xff).
162 Key Governors Support
163 =======================
165 ``amd-pstate`` can be used with all the (generic) scaling governors listed
166 by the ``scaling_available_governors`` policy attribute in ``sysfs``. Then,
167 it is responsible for the configuration of policy objects corresponding to
168 CPUs and provides the ``CPUFreq`` core (and the scaling governors attached
169 to the policy objects) with accurate information on the maximum and minimum
170 operating frequencies supported by the hardware. Users can check the
171 ``scaling_cur_freq`` information comes from the ``CPUFreq`` core.
173 ``amd-pstate`` mainly supports ``schedutil`` and ``ondemand`` for dynamic
174 frequency control. It is to fine tune the processor configuration on
175 ``amd-pstate`` to the ``schedutil`` with CPU CFS scheduler. ``amd-pstate``
176 registers the adjust_perf callback to implement performance update behavior
177 similar to CPPC. It is initialized by ``sugov_start`` and then populates the
178 CPU's update_util_data pointer to assign ``sugov_update_single_perf`` as the
179 utilization update callback function in the CPU scheduler. The CPU scheduler
180 will call ``cpufreq_update_util`` and assigns the target performance according
181 to the ``struct sugov_cpu`` that the utilization update belongs to.
182 Then, ``amd-pstate`` updates the desired performance according to the CPU
185 .. _processor_support:
188 =======================
190 The ``amd-pstate`` initialization will fail if the ``_CPC`` entry in the ACPI
191 SBIOS does not exist in the detected processor. It uses ``acpi_cpc_valid``
192 to check the existence of ``_CPC``. All Zen based processors support the legacy
193 ACPI hardware P-States function, so when ``amd-pstate`` fails initialization,
194 the kernel will fall back to initialize the ``acpi-cpufreq`` driver.
196 There are two types of hardware implementations for ``amd-pstate``: one is
197 `Full MSR Support <perf_cap_>`_ and another is `Shared Memory Support
198 <perf_cap_>`_. It can use the :c:macro:`X86_FEATURE_CPPC` feature flag to
199 indicate the different types. (For details, refer to the Processor Programming
200 Reference (PPR) for AMD Family 19h Model 51h, Revision A1 Processors [3]_.)
201 ``amd-pstate`` is to register different ``static_call`` instances for different
202 hardware implementations.
204 Currently, some of the Zen2 and Zen3 processors support ``amd-pstate``. In the
205 future, it will be supported on more and more AMD processors.
210 Some new Zen3 processors such as Cezanne provide the MSR registers directly
211 while the :c:macro:`X86_FEATURE_CPPC` CPU feature flag is set.
212 ``amd-pstate`` can handle the MSR register to implement the fast switch
213 function in ``CPUFreq`` that can reduce the latency of frequency control in
214 interrupt context. The functions with a ``pstate_xxx`` prefix represent the
215 operations on MSR registers.
217 Shared Memory Support
218 ----------------------
220 If the :c:macro:`X86_FEATURE_CPPC` CPU feature flag is not set, the
221 processor supports the shared memory solution. In this case, ``amd-pstate``
222 uses the ``cppc_acpi`` helper methods to implement the callback functions
223 that are defined on ``static_call``. The functions with the ``cppc_xxx`` prefix
224 represent the operations of ACPI CPPC helpers for the shared memory solution.
227 AMD P-States and ACPI hardware P-States always can be supported in one
228 processor. But AMD P-States has the higher priority and if it is enabled
229 with :c:macro:`MSR_AMD_CPPC_ENABLE` or ``cppc_set_enable``, it will respond
230 to the request from AMD P-States.
233 User Space Interface in ``sysfs`` - Per-policy control
234 ======================================================
236 ``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
237 control its functionality at the system level. They are located in the
238 ``/sys/devices/system/cpu/cpufreq/policyX/`` directory and affect all CPUs. ::
240 root@hr-test1:/home/ray# ls /sys/devices/system/cpu/cpufreq/policy0/*amd*
241 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_highest_perf
242 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_lowest_nonlinear_freq
243 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_max_freq
246 ``amd_pstate_highest_perf / amd_pstate_max_freq``
248 Maximum CPPC performance and CPU frequency that the driver is allowed to
249 set, in percent of the maximum supported CPPC performance level (the highest
250 performance supported in `AMD CPPC Performance Capability <perf_cap_>`_).
251 In some ASICs, the highest CPPC performance is not the one in the ``_CPC``
252 table, so we need to expose it to sysfs. If boost is not active, but
253 still supported, this maximum frequency will be larger than the one in
255 This attribute is read-only.
257 ``amd_pstate_lowest_nonlinear_freq``
259 The lowest non-linear CPPC CPU frequency that the driver is allowed to set,
260 in percent of the maximum supported CPPC performance level. (Please see the
261 lowest non-linear performance in `AMD CPPC Performance Capability
263 This attribute is read-only.
265 ``energy_performance_available_preferences``
267 A list of all the supported EPP preferences that could be used for
268 ``energy_performance_preference`` on this system.
269 These profiles represent different hints that are provided
270 to the low-level firmware about the user's desired energy vs efficiency
271 tradeoff. ``default`` represents the epp value is set by platform
272 firmware. This attribute is read-only.
274 ``energy_performance_preference``
276 The current energy performance preference can be read from this attribute.
277 and user can change current preference according to energy or performance needs
278 Please get all support profiles list from
279 ``energy_performance_available_preferences`` attribute, all the profiles are
280 integer values defined between 0 to 255 when EPP feature is enabled by platform
281 firmware, if EPP feature is disabled, driver will ignore the written value
282 This attribute is read-write.
284 Other performance and frequency values can be read back from
285 ``/sys/devices/system/cpu/cpuX/acpi_cppc/``, see :ref:`cppc_sysfs`.
288 ``amd-pstate`` vs ``acpi-cpufreq``
289 ======================================
291 On the majority of AMD platforms supported by ``acpi-cpufreq``, the ACPI tables
292 provided by the platform firmware are used for CPU performance scaling, but
293 only provide 3 P-states on AMD processors.
294 However, on modern AMD APU and CPU series, hardware provides the Collaborative
295 Processor Performance Control according to the ACPI protocol and customizes this
296 for AMD platforms. That is, fine-grained and continuous frequency ranges
297 instead of the legacy hardware P-states. ``amd-pstate`` is the kernel
298 module which supports the new AMD P-States mechanism on most of the future AMD
299 platforms. The AMD P-States mechanism is the more performance and energy
300 efficiency frequency management method on AMD processors.
303 AMD Pstate Driver Operation Modes
304 =================================
306 ``amd_pstate`` CPPC has 3 operation modes: autonomous (active) mode,
307 non-autonomous (passive) mode and guided autonomous (guided) mode.
308 Active/passive/guided mode can be chosen by different kernel parameters.
310 - In autonomous mode, platform ignores the desired performance level request
311 and takes into account only the values set to the minimum, maximum and energy
312 performance preference registers.
313 - In non-autonomous mode, platform gets desired performance level
314 from OS directly through Desired Performance Register.
315 - In guided-autonomous mode, platform sets operating performance level
316 autonomously according to the current workload and within the limits set by
317 OS through min and max performance registers.
322 ``amd_pstate=active``
324 This is the low-level firmware control mode which is implemented by ``amd_pstate_epp``
325 driver with ``amd_pstate=active`` passed to the kernel in the command line.
326 In this mode, ``amd_pstate_epp`` driver provides a hint to the hardware if software
327 wants to bias toward performance (0x0) or energy efficiency (0xff) to the CPPC firmware.
328 then CPPC power algorithm will calculate the runtime workload and adjust the realtime
329 cores frequency according to the power supply and thermal, core voltage and some other
335 ``amd_pstate=passive``
337 It will be enabled if the ``amd_pstate=passive`` is passed to the kernel in the command line.
338 In this mode, ``amd_pstate`` driver software specifies a desired QoS target in the CPPC
339 performance scale as a relative number. This can be expressed as percentage of nominal
340 performance (infrastructure max). Below the nominal sustained performance level,
341 desired performance expresses the average performance level of the processor subject
342 to the Performance Reduction Tolerance register. Above the nominal performance level,
343 processor must provide at least nominal performance requested and go higher if current
344 operating conditions allow.
349 ``amd_pstate=guided``
351 If ``amd_pstate=guided`` is passed to kernel command line option then this mode
352 is activated. In this mode, driver requests minimum and maximum performance
353 level and the platform autonomously selects a performance level in this range
354 and appropriate to the current workload.
356 User Space Interface in ``sysfs`` - General
357 ===========================================
362 ``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
363 control its functionality at the system level. They are located in the
364 ``/sys/devices/system/cpu/amd_pstate/`` directory and affect all CPUs.
367 Operation mode of the driver: "active", "passive" or "disable".
370 The driver is functional and in the ``active mode``
373 The driver is functional and in the ``passive mode``
376 The driver is functional and in the ``guided mode``
379 The driver is unregistered and not functional now.
381 This attribute can be written to in order to change the driver's
382 operation mode or to unregister it. The string written to it must be
383 one of the possible values of it and, if successful, writing one of
384 these values to the sysfs file will cause the driver to switch over
385 to the operation mode represented by that string - or to be
386 unregistered in the "disable" case.
388 ``cpupower`` tool support for ``amd-pstate``
389 ===============================================
391 ``amd-pstate`` is supported by the ``cpupower`` tool, which can be used to dump
392 frequency information. Development is in progress to support more and more
393 operations for the new ``amd-pstate`` module with this tool. ::
395 root@hr-test1:/home/ray# cpupower frequency-info
398 CPUs which run at the same hardware frequency: 0
399 CPUs which need to have their frequency coordinated by software: 0
400 maximum transition latency: 131 us
401 hardware limits: 400 MHz - 4.68 GHz
402 available cpufreq governors: ondemand conservative powersave userspace performance schedutil
403 current policy: frequency should be within 400 MHz and 4.68 GHz.
404 The governor "schedutil" may decide which speed to use
406 current CPU frequency: Unable to call hardware
407 current CPU frequency: 4.02 GHz (asserted by call to kernel)
411 AMD PSTATE Highest Performance: 166. Maximum Frequency: 4.68 GHz.
412 AMD PSTATE Nominal Performance: 117. Nominal Frequency: 3.30 GHz.
413 AMD PSTATE Lowest Non-linear Performance: 39. Lowest Non-linear Frequency: 1.10 GHz.
414 AMD PSTATE Lowest Performance: 15. Lowest Frequency: 400 MHz.
417 Diagnostics and Tuning
418 =======================
423 There are two static trace events that can be used for ``amd-pstate``
424 diagnostics. One of them is the ``cpu_frequency`` trace event generally used
425 by ``CPUFreq``, and the other one is the ``amd_pstate_perf`` trace event
426 specific to ``amd-pstate``. The following sequence of shell commands can
427 be used to enable them and see their output (if the kernel is
428 configured to support event tracing). ::
430 root@hr-test1:/home/ray# cd /sys/kernel/tracing/
431 root@hr-test1:/sys/kernel/tracing# echo 1 > events/amd_cpu/enable
432 root@hr-test1:/sys/kernel/tracing# cat trace
435 # entries-in-buffer/entries-written: 47827/42233061 #P:2
438 # / _----=> need-resched
439 # | / _---=> hardirq/softirq
440 # || / _--=> preempt-depth
442 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
444 <idle>-0 [015] dN... 4995.979886: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=15 changed=false fast_switch=true
445 <idle>-0 [007] d.h.. 4995.979893: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=7 changed=false fast_switch=true
446 cat-2161 [000] d.... 4995.980841: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=0 changed=false fast_switch=true
447 sshd-2125 [004] d.s.. 4995.980968: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=4 changed=false fast_switch=true
448 <idle>-0 [007] d.s.. 4995.980968: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=7 changed=false fast_switch=true
449 <idle>-0 [003] d.s.. 4995.980971: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=3 changed=false fast_switch=true
450 <idle>-0 [011] d.s.. 4995.980996: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=11 changed=false fast_switch=true
452 The ``cpu_frequency`` trace event will be triggered either by the ``schedutil`` scaling
453 governor (for the policies it is attached to), or by the ``CPUFreq`` core (for the
454 policies with other scaling governors).
460 ``amd_pstate_tracer.py`` can record and parse ``amd-pstate`` trace log, then
461 generate performance plots. This utility can be used to debug and tune the
462 performance of ``amd-pstate`` driver. The tracer tool needs to import intel
465 Tracer tool located in ``linux/tools/power/x86/amd_pstate_tracer``. It can be
466 used in two ways. If trace file is available, then directly parse the file
469 ./amd_pstate_trace.py [-c cpus] -t <trace_file> -n <test_name>
471 Or generate trace file with root privilege, then parse and plot with command ::
473 sudo ./amd_pstate_trace.py [-c cpus] -n <test_name> -i <interval> [-m kbytes]
475 The test result can be found in ``results/test_name``. Following is the example
476 about part of the output. ::
478 common_cpu common_secs common_usecs min_perf des_perf max_perf freq mperf apef tsc load duration_ms sample_num elapsed_time common_comm
479 CPU_005 712 116384 39 49 166 0.7565 9645075 2214891 38431470 25.1 11.646 469 2.496 kworker/5:0-40
480 CPU_006 712 116408 39 49 166 0.6769 8950227 1839034 37192089 24.06 11.272 470 2.496 kworker/6:0-1264
482 Unit Tests for amd-pstate
483 -------------------------
485 ``amd-pstate-ut`` is a test module for testing the ``amd-pstate`` driver.
487 * It can help all users to verify their processor support (SBIOS/Firmware or Hardware).
489 * Kernel can have a basic function test to avoid the kernel regression during the update.
491 * We can introduce more functional or performance tests to align the result together, it will benefit power and performance scale optimization.
493 1. Test case descriptions
497 Test prerequisite and basic functions for the ``amd-pstate`` driver.
499 +---------+--------------------------------+------------------------------------------------------------------------------------+
500 | Index | Functions | Description |
501 +=========+================================+====================================================================================+
502 | 1 | amd_pstate_ut_acpi_cpc_valid || Check whether the _CPC object is present in SBIOS. |
504 | | || The detail refer to `Processor Support <processor_support_>`_. |
505 +---------+--------------------------------+------------------------------------------------------------------------------------+
506 | 2 | amd_pstate_ut_check_enabled || Check whether AMD P-State is enabled. |
508 | | || AMD P-States and ACPI hardware P-States always can be supported in one processor. |
509 | | | But AMD P-States has the higher priority and if it is enabled with |
510 | | | :c:macro:`MSR_AMD_CPPC_ENABLE` or ``cppc_set_enable``, it will respond to the |
511 | | | request from AMD P-States. |
512 +---------+--------------------------------+------------------------------------------------------------------------------------+
513 | 3 | amd_pstate_ut_check_perf || Check if the each performance values are reasonable. |
514 | | || highest_perf >= nominal_perf > lowest_nonlinear_perf > lowest_perf > 0. |
515 +---------+--------------------------------+------------------------------------------------------------------------------------+
516 | 4 | amd_pstate_ut_check_freq || Check if the each frequency values and max freq when set support boost mode |
517 | | | are reasonable. |
518 | | || max_freq >= nominal_freq > lowest_nonlinear_freq > min_freq > 0 |
519 | | || If boost is not active but supported, this maximum frequency will be larger than |
520 | | | the one in ``cpuinfo``. |
521 +---------+--------------------------------+------------------------------------------------------------------------------------+
525 Test and monitor the cpu changes when running tbench benchmark under the specified governor.
526 These changes include desire performance, frequency, load, performance, energy etc.
527 The specified governor is ondemand or schedutil.
528 Tbench can also be tested on the ``acpi-cpufreq`` kernel driver for comparison.
532 Test and monitor the cpu changes when running gitsource benchmark under the specified governor.
533 These changes include desire performance, frequency, load, time, energy etc.
534 The specified governor is ondemand or schedutil.
535 Gitsource can also be tested on the ``acpi-cpufreq`` kernel driver for comparison.
537 #. How to execute the tests
539 We use test module in the kselftest frameworks to implement it.
540 We create ``amd-pstate-ut`` module and tie it into kselftest.(for
541 details refer to Linux Kernel Selftests [4]_).
545 + open the :c:macro:`CONFIG_X86_AMD_PSTATE` configuration option.
546 + set the :c:macro:`CONFIG_X86_AMD_PSTATE_UT` configuration option to M.
551 $ make -C tools/testing/selftests
559 2). Installation & Steps ::
561 $ make -C tools/testing/selftests install INSTALL_PATH=~/kselftest
562 $ cp tools/perf/perf /usr/bin/perf
563 $ sudo ./kselftest/run_kselftest.sh -c amd-pstate
565 3). Specified test case ::
567 $ cd ~/kselftest/amd-pstate
568 $ sudo ./run.sh -t basic
569 $ sudo ./run.sh -t tbench
570 $ sudo ./run.sh -t tbench -m acpi-cpufreq
571 $ sudo ./run.sh -t gitsource
572 $ sudo ./run.sh -t gitsource -m acpi-cpufreq
574 ./run.sh: illegal option -- -
575 Usage: ./run.sh [OPTION...]
577 [-o <output-file-for-dump>]
578 [-c <all: All testing,
579 basic: Basic testing,
580 tbench: Tbench testing,
581 gitsource: Gitsource testing.>]
582 [-t <tbench time limit>]
583 [-p <tbench process number>]
584 [-l <loop times for tbench>]
585 [-i <amd tracer interval>]
586 [-m <comparative test: acpi-cpufreq>]
593 When you finish test, you will get the following log info ::
595 $ dmesg | grep "amd_pstate_ut" | tee log.txt
596 [12977.570663] amd_pstate_ut: 1 amd_pstate_ut_acpi_cpc_valid success!
597 [12977.570673] amd_pstate_ut: 2 amd_pstate_ut_check_enabled success!
598 [12977.571207] amd_pstate_ut: 3 amd_pstate_ut_check_perf success!
599 [12977.571212] amd_pstate_ut: 4 amd_pstate_ut_check_freq success!
603 When you finish test, you will get selftest.tbench.csv and png images.
604 The selftest.tbench.csv file contains the raw data and the drop of the comparative test.
605 The png images shows the performance, energy and performan per watt of each test.
606 Open selftest.tbench.csv :
608 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
609 + Governor | Round | Des-perf | Freq | Load | Performance | Energy | Performance Per Watt |
610 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
611 + Unit | | | GHz | | MB/s | J | MB/J |
612 +=================================================+==============+==========+=========+==========+=============+=========+======================+
613 + amd-pstate-ondemand | 1 | | | | 2504.05 | 1563.67 | 158.5378 |
614 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
615 + amd-pstate-ondemand | 2 | | | | 2243.64 | 1430.32 | 155.2941 |
616 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
617 + amd-pstate-ondemand | 3 | | | | 2183.88 | 1401.32 | 154.2860 |
618 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
619 + amd-pstate-ondemand | Average | | | | 2310.52 | 1465.1 | 156.1268 |
620 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
621 + amd-pstate-schedutil | 1 | 165.329 | 1.62257 | 99.798 | 2136.54 | 1395.26 | 151.5971 |
622 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
623 + amd-pstate-schedutil | 2 | 166 | 1.49761 | 99.9993 | 2100.56 | 1380.5 | 150.6377 |
624 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
625 + amd-pstate-schedutil | 3 | 166 | 1.47806 | 99.9993 | 2084.12 | 1375.76 | 149.9737 |
626 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
627 + amd-pstate-schedutil | Average | 165.776 | 1.53275 | 99.9322 | 2107.07 | 1383.84 | 150.7399 |
628 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
629 + acpi-cpufreq-ondemand | 1 | | | | 2529.9 | 1564.4 | 160.0997 |
630 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
631 + acpi-cpufreq-ondemand | 2 | | | | 2249.76 | 1432.97 | 155.4297 |
632 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
633 + acpi-cpufreq-ondemand | 3 | | | | 2181.46 | 1406.88 | 153.5060 |
634 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
635 + acpi-cpufreq-ondemand | Average | | | | 2320.37 | 1468.08 | 156.4741 |
636 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
637 + acpi-cpufreq-schedutil | 1 | | | | 2137.64 | 1385.24 | 152.7723 |
638 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
639 + acpi-cpufreq-schedutil | 2 | | | | 2107.05 | 1372.23 | 152.0138 |
640 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
641 + acpi-cpufreq-schedutil | 3 | | | | 2085.86 | 1365.35 | 151.2433 |
642 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
643 + acpi-cpufreq-schedutil | Average | | | | 2110.18 | 1374.27 | 152.0136 |
644 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
645 + acpi-cpufreq-ondemand VS acpi-cpufreq-schedutil | Comprison(%) | | | | -9.0584 | -6.3899 | -2.8506 |
646 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
647 + amd-pstate-ondemand VS amd-pstate-schedutil | Comprison(%) | | | | 8.8053 | -5.5463 | -3.4503 |
648 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
649 + acpi-cpufreq-ondemand VS amd-pstate-ondemand | Comprison(%) | | | | -0.4245 | -0.2029 | -0.2219 |
650 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
651 + acpi-cpufreq-schedutil VS amd-pstate-schedutil | Comprison(%) | | | | -0.1473 | 0.6963 | -0.8378 |
652 +-------------------------------------------------+--------------+----------+---------+----------+-------------+---------+----------------------+
656 When you finish test, you will get selftest.gitsource.csv and png images.
657 The selftest.gitsource.csv file contains the raw data and the drop of the comparative test.
658 The png images shows the performance, energy and performan per watt of each test.
659 Open selftest.gitsource.csv :
661 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
662 + Governor | Round | Des-perf | Freq | Load | Time | Energy | Performance Per Watt |
663 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
664 + Unit | | | GHz | | s | J | 1/J |
665 +=================================================+==============+==========+==========+==========+=============+=========+======================+
666 + amd-pstate-ondemand | 1 | 50.119 | 2.10509 | 23.3076 | 475.69 | 865.78 | 0.001155027 |
667 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
668 + amd-pstate-ondemand | 2 | 94.8006 | 1.98771 | 56.6533 | 467.1 | 839.67 | 0.001190944 |
669 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
670 + amd-pstate-ondemand | 3 | 76.6091 | 2.53251 | 43.7791 | 467.69 | 855.85 | 0.001168429 |
671 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
672 + amd-pstate-ondemand | Average | 73.8429 | 2.20844 | 41.2467 | 470.16 | 853.767 | 0.001171279 |
673 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
674 + amd-pstate-schedutil | 1 | 165.919 | 1.62319 | 98.3868 | 464.17 | 866.8 | 0.001153668 |
675 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
676 + amd-pstate-schedutil | 2 | 165.97 | 1.31309 | 99.5712 | 480.15 | 880.4 | 0.001135847 |
677 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
678 + amd-pstate-schedutil | 3 | 165.973 | 1.28448 | 99.9252 | 481.79 | 867.02 | 0.001153375 |
679 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
680 + amd-pstate-schedutil | Average | 165.954 | 1.40692 | 99.2944 | 475.37 | 871.407 | 0.001147569 |
681 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
682 + acpi-cpufreq-ondemand | 1 | | | | 2379.62 | 742.96 | 0.001345967 |
683 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
684 + acpi-cpufreq-ondemand | 2 | | | | 441.74 | 817.49 | 0.001223256 |
685 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
686 + acpi-cpufreq-ondemand | 3 | | | | 455.48 | 820.01 | 0.001219497 |
687 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
688 + acpi-cpufreq-ondemand | Average | | | | 425.613 | 793.487 | 0.001260260 |
689 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
690 + acpi-cpufreq-schedutil | 1 | | | | 459.69 | 838.54 | 0.001192548 |
691 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
692 + acpi-cpufreq-schedutil | 2 | | | | 466.55 | 830.89 | 0.001203528 |
693 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
694 + acpi-cpufreq-schedutil | 3 | | | | 470.38 | 837.32 | 0.001194286 |
695 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
696 + acpi-cpufreq-schedutil | Average | | | | 465.54 | 835.583 | 0.001196769 |
697 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
698 + acpi-cpufreq-ondemand VS acpi-cpufreq-schedutil | Comprison(%) | | | | 9.3810 | 5.3051 | -5.0379 |
699 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
700 + amd-pstate-ondemand VS amd-pstate-schedutil | Comprison(%) | 124.7392 | -36.2934 | 140.7329 | 1.1081 | 2.0661 | -2.0242 |
701 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
702 + acpi-cpufreq-ondemand VS amd-pstate-ondemand | Comprison(%) | | | | 10.4665 | 7.5968 | -7.0605 |
703 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
704 + acpi-cpufreq-schedutil VS amd-pstate-schedutil | Comprison(%) | | | | 2.1115 | 4.2873 | -4.1110 |
705 +-------------------------------------------------+--------------+----------+----------+----------+-------------+---------+----------------------+
710 .. [1] AMD64 Architecture Programmer's Manual Volume 2: System Programming,
711 https://www.amd.com/system/files/TechDocs/24593.pdf
713 .. [2] Advanced Configuration and Power Interface Specification,
714 https://uefi.org/sites/default/files/resources/ACPI_Spec_6_4_Jan22.pdf
716 .. [3] Processor Programming Reference (PPR) for AMD Family 19h Model 51h, Revision A1 Processors
717 https://www.amd.com/system/files/TechDocs/56569-A1-PUB.zip
719 .. [4] Linux Kernel Selftests,
720 https://www.kernel.org/doc/html/latest/dev-tools/kselftest.html