Lines Matching refs:intel_pstate
5 ``intel_pstate`` CPU Performance Scaling Driver
16 ``intel_pstate`` is a part of the
20 may not be supported. [To understand ``intel_pstate`` it is necessary to know
24 For the processors supported by ``intel_pstate``, the P-state concept is broader
28 by ``intel_pstate`` internally follows the hardware specification (for details
32 ``intel_pstate`` maps its internal representation of P-states to frequencies too
34 practical for ``intel_pstate`` to supply the ``CPUFreq`` core with a table of
38 Since the hardware P-state selection interface used by ``intel_pstate`` is
40 CPUs. Consequently, if ``intel_pstate`` is in use, every ``CPUFreq`` policy
46 ``intel_pstate`` is not modular, so it cannot be unloaded, which means that the
57 ``intel_pstate`` can operate in two different modes, active or passive. In the
68 This is the default operation mode of ``intel_pstate`` for processors with
71 contains the string "intel_pstate".
84 ``intel_pstate`` is not a counterpart of the generic ``powersave`` governor
87 There are two P-state selection algorithms provided by ``intel_pstate`` in the
102 to avoid enabling it by passing the ``intel_pstate=no_hwp`` argument to the
105 If the HWP feature has been enabled, ``intel_pstate`` relies on the processor to
112 ``intel_pstate`` registers utilization update callbacks with the CPU scheduler
120 In this configuration ``intel_pstate`` will write 0 to the processor's
137 In this configuration ``intel_pstate`` will set the processor's
148 feature or when the ``intel_pstate=no_hwp`` argument is passed to the kernel in
150 ``intel_pstate=active`` argument is passed to the kernel in the command line.
151 In this mode ``intel_pstate`` may refuse to work with processors that are not
152 recognized by it. [Note that ``intel_pstate`` will never refuse to work with
155 In this mode ``intel_pstate`` registers utilization update callbacks with the
198 This is the default operation mode of ``intel_pstate`` for processors without
200 ``intel_pstate=passive`` argument is passed to the kernel in the command line
202 ``intel_pstate=no_hwp`` setting causes the driver to start in the passive mode
203 if it is not combined with ``intel_pstate=active``.] Like in the active mode
204 without HWP support, in this mode ``intel_pstate`` may refuse to work with
215 While in this mode, ``intel_pstate`` can be used with all of the (generic)
223 the entire range of available P-states is exposed by ``intel_pstate`` to the
236 ``intel_pstate`` can be divided into two sub-ranges that correspond to
288 Unlike ``_PSS`` objects in the ACPI tables, ``intel_pstate`` always exposes
291 generally causes turbo P-states to be set more often when ``intel_pstate`` is
295 Moreover, since ``intel_pstate`` always knows what the real turbo threshold is
299 always should prevent ``intel_pstate`` from using them).
305 To handle a given processor ``intel_pstate`` requires a number of different
325 For this reason, there is a list of supported processors in ``intel_pstate`` and
329 HWP feature, which is why ``intel_pstate`` works with all of them.]
335 Some processors supported by ``intel_pstate`` contain two or more types of CPU
338 hybrid processors. To support them, ``intel_pstate`` requires HWP to be enabled
348 one core, ``intel_pstate`` assigns performance-based priorities to CPUs. Namely,
370 ``intel_pstate`` by default on hybrid processors without SMT. CAS generally
386 CPUs, so ``intel_pstate`` provides it with the requisite information.
394 CPU capacity into account. All of this happens when ``intel_pstate`` has
402 ``intel_pstate`` runs on a hybrid processor without SMT, in addition to enabling
405 ``schedutil`` is used as the ``CPUFreq`` governor which requires ``intel_pstate``
408 The Energy Model registered by ``intel_pstate`` is artificial (that is, it is
427 The Energy Model created by ``intel_pstate`` can be inspected by looking at
438 ``intel_pstate`` exposes several global attributes (files) in ``sysfs`` to
440 ``/sys/devices/system/cpu/intel_pstate/`` directory and affect all CPUs.
442 Some of them are not present if the ``intel_pstate=per_cpu_perf_limits``
451 ``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
460 ``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
491 [Note that ``intel_pstate`` does not support the general ``boost``
501 This attribute is only present if ``intel_pstate`` works in the
554 Documentation/admin-guide/pm/cpufreq.rst is special with ``intel_pstate``
560 multiplier to the internal P-state representation used by ``intel_pstate``.
579 ``intel_pstate`` works in the `active mode <Active Mode_>`_:
582 List of P-state selection algorithms provided by ``intel_pstate``.
585 P-state selection algorithm provided by ``intel_pstate`` currently in
603 Additionally, the value of the ``scaling_driver`` attribute for ``intel_pstate``
605 "intel_pstate" (in the `active mode <Active Mode_>`_) or "intel_cpufreq" (in the
611 ``intel_pstate`` allows P-state limits to be set in two ways: with the help of
642 Additionally, if the ``intel_pstate=per_cpu_perf_limits`` command line argument
651 attributes, intended to allow user space to help ``intel_pstate`` to adjust the
687 ``intel_pstate`` vs ``acpi-cpufreq``
690 On the majority of systems supported by ``intel_pstate``, the ACPI tables
697 ``acpi-cpufreq`` scaling driver. On systems supported by ``intel_pstate``
704 be used by ``intel_pstate`` on the same system, with one exception: the whole
742 Apart from the above, ``acpi-cpufreq`` works like ``intel_pstate`` in the
747 Kernel Command Line Options for ``intel_pstate``
751 parameters to ``intel_pstate`` in order to enforce specific behavior of it. All
752 of them have to be prepended with the ``intel_pstate=`` prefix.
755 Do not register ``intel_pstate`` as the scaling driver even if the
759 Register ``intel_pstate`` in the `active mode <Active Mode_>`_ to start
763 Register ``intel_pstate`` in the `passive mode <Passive Mode_>`_ to
767 Register ``intel_pstate`` as the scaling driver instead of
776 ``intel_pstate`` and on platforms where the ``pcc-cpufreq`` scaling
784 Register ``intel_pstate`` as the scaling driver only if the
809 There are two static trace events that can be used for ``intel_pstate``
812 to ``intel_pstate``. Both of them are triggered by ``intel_pstate`` only if
825 If ``intel_pstate`` works in the `passive mode <Passive Mode_>`_, the
834 ``intel_pstate``. For example, to check how often the function to set a