| /linux/Documentation/admin-guide/acpi/ |
| H A D | cppc_sysfs.rst | 4 Collaborative Processor Performance Control (CPPC)
13 performance of a logical processor on a contiguous and abstract performance
14 scale. CPPC exposes a set of registers to describe abstract performance scale,
15 to request performance levels and to measure per-cpu delivered performance.
40 * highest_perf : Highest performance of this processor (abstract scale).
41 * nominal_perf : Highest sustained performance of this processor
43 * lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
45 * lowest_perf : Lowest performance of this processor (abstract scale).
49 The above frequencies should only be used to report processor performance in
53 * feedback_ctrs : Includes both Reference and delivered performance counter.
[all …]
|
| H A D | fan_performance_states.rst | 4 ACPI Fan Performance States
10 These attributes list properties of fan performance states.
37 where each of the "state*" files represents one performance state of the fan
47 to this performance state (0-9).
71 Here use can look at fan performance states for a reference speed (speed_rpm)
74 not defined in the performance states.
80 This sysfs attribute is presented in the same directory as performance states.
82 ACPI Fan Performance Feedback
90 in the same directory as performance states.
|
| /linux/Documentation/netlink/specs/ |
| H A D | dev-energymodel.yaml | 23 The performance state is inefficient. There is in this perf-domain,
24 another performance state with a higher frequency but a lower or
48 Information on a single performance domains.
57 A unique ID number for each performance domain.
62 Bitmask of performance domain flags.
69 CPUs that belong to this performance domain.
73 Performance states table.
79 A unique ID number for each performance domain.
88 Performance state of a performance domain.
94 name: performance
[all …]
|
| /linux/tools/power/x86/x86_energy_perf_policy/ |
| H A D | x86_energy_perf_policy.8 | 5 x86_energy_perf_policy \- Manage Energy vs. Performance Policy
20 .RB "value: # | default | performance | balance-performance | balance-power | power"
23 displays and updates energy-performance policy settings specific to
27 While \fBx86_energy_perf_policy\fP can manage energy-performance policy
35 and Processor Performance States (P-states).
38 Further, it allows the OS to influence energy/performance trade-offs where there
89 Set a policy with a normal balance between performance and energy efficiency.
90 The processor will tolerate minor performance compromise
95 .I performance
96 Set a policy for maximum performance,
[all …]
|
| /linux/arch/powerpc/include/asm/ |
| H A D | reg_fsl_emb.h | 3 * Contains register definitions for the Freescale Embedded Performance
13 /* Performance Monitor Registers */
37 /* Freescale Book E Performance Monitor APU Registers */
38 #define PMRN_PMC0 0x010 /* Performance Monitor Counter 0 */
39 #define PMRN_PMC1 0x011 /* Performance Monitor Counter 1 */
40 #define PMRN_PMC2 0x012 /* Performance Monitor Counter 2 */
41 #define PMRN_PMC3 0x013 /* Performance Monitor Counter 3 */
42 #define PMRN_PMC4 0x014 /* Performance Monitor Counter 4 */
43 #define PMRN_PMC5 0x015 /* Performance Monitor Counter 5 */
84 #define PMRN_UPMC0 0x000 /* User Performance Monitor Counter 0 */
[all …]
|
| /linux/Documentation/admin-guide/ |
| H A D | perf-security.rst | 9 Usage of Performance Counters for Linux (perf_events) [1]_ , [2]_ , [3]_
14 depends on the nature of data that perf_events performance monitoring
15 units (PMU) [2]_ and Perf collect and expose for performance analysis.
16 Collected system and performance data may be split into several
21 its topology, used kernel and Perf versions, performance monitoring
30 faults, CPU migrations), architectural hardware performance counters
46 So, perf_events performance monitoring and observability operations are
56 all kernel security permission checks so perf_events performance
70 as privileged processes with respect to perf_events performance
73 privilege [13]_ (POSIX 1003.1e: 2.2.2.39) for performance monitoring and
[all …]
|
| /linux/arch/x86/events/ |
| H A D | Kconfig | 2 menu "Performance monitoring"
5 tristate "Intel uncore performance events"
9 Include support for Intel uncore performance events. These are
13 tristate "Intel/AMD rapl performance events"
17 Include support for Intel and AMD rapl performance events for power
21 tristate "Intel cstate performance events"
25 Include support for Intel cstate performance events for power
38 tristate "AMD Uncore performance events"
42 Include support for AMD uncore performance events for use with
|
| /linux/Documentation/scheduler/ |
| H A D | sched-util-clamp.rst | 11 feature that allows user space to help in managing the performance requirement
16 performance requirements and restrictions of the tasks, thus it helps the
23 system run at a certain performance point.
26 performance constraints. It consists of two tunables:
31 These two bounds will ensure a task will operate within this performance range
36 performance point to operate at to deliver the desired user experience. Or one
38 much resources and should not go above a specific performance point. Viewing
39 the uclamp values as performance points rather than utilization is a better
44 performance point required by its display pipeline to ensure no frame is
58 resources background tasks are consuming by capping the performance point they
[all …]
|
| H A D | sched-energy.rst | 38 performance [inst/s]
48 while still getting 'good' performance. It is essentially an alternative
49 optimization objective to the current performance-only objective for the
51 performance.
78 task/CPU is, and to take this into consideration when evaluating performance vs
84 per 'performance domain' in the system (see Documentation/power/energy-model.rst
85 for further details about performance domains).
89 scheduler maintains a singly linked list of all performance domains intersecting
95 necessarily match those of performance domains, the lists of different root
99 Let us consider a platform with 12 CPUs, split in 3 performance domains
[all …]
|
| /linux/Documentation/devicetree/bindings/cpufreq/ |
| H A D | cpufreq-mediatek-hw.yaml | 29 "#performance-domain-cells":
31 Number of cells in a performance domain specifier.
33 performance domains.
39 - "#performance-domain-cells"
53 performance-domains = <&performance 0>;
64 performance: performance-controller@11bc00 {
68 #performance-domain-cells = <1>;
|
| /linux/Documentation/admin-guide/pm/ |
| H A D | amd-pstate.rst | 5 ``amd-pstate`` CPU Performance Scaling Driver
16 ``amd-pstate`` is the AMD CPU performance scaling driver that introduces a
19 Performance Control (CPPC) which provides finer grain frequency management
24 communicate the performance hints to hardware.
27 ``ondemand``, etc. to manage the performance hints which are provided by
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
45 interpreter for performance adjustments. ``amd-pstate`` will initialize a
[all …]
|
| H A D | intel_pstate.rst | 5 ``intel_pstate`` CPU Performance Scaling Driver
17 :doc:`CPU performance scaling subsystem <cpufreq>` in the Linux kernel
25 than just an operating frequency or an operating performance point (see the
30 uses frequencies for identifying operating performance points of CPUs and
59 active mode, it uses its own internal performance scaling governor algorithm or
60 allows the hardware to do performance scaling by itself, while in the passive
62 a certain performance scaling algorithm. Which of them will be in effect
91 active mode: ``powersave`` and ``performance``. The way they both operate
97 Namely, if that option is set, the ``performance`` algorithm will be used by
122 HWP + ``performance``
[all …]
|
| H A D | intel_epb.rst | 5 Intel Performance and Energy Bias Hint
16 Intel Performance and Energy Bias Attribute in ``sysfs``
19 The Intel Performance and Energy Bias Hint (EPB) value for a given (logical) CPU
26 a value of 0 corresponds to a hint preference for highest performance
31 with one of the strings: "performance", "balance-performance", "normal",
|
| /linux/Documentation/admin-guide/perf/ |
| H A D | hns3-pmu.rst | 2 HNS3 Performance Monitoring Unit (PMU)
5 HNS3(HiSilicon network system 3) Performance Monitoring Unit (PMU) is an
6 End Point device to collect performance statistics of HiSilicon SoC NIC.
9 HNS3 PMU supports collection of performance statistics such as bandwidth,
48 Each performance statistic has a pair of events to get two values to
49 calculate real performance data in userspace.
57 computation to calculate real performance data is:::
82 PMU collect performance statistics for all HNS3 PCIe functions of IO DIE.
89 PMU collect performance statistic of one whole physical port. The port id
98 PMU collect performance statistic of one tc of physical port. The port id
[all …]
|
| /linux/Documentation/ABI/testing/ |
| H A D | sysfs-bus-event_source-devices-hv_gpci | 100 runtime by setting "Enable Performance Information Collection" option.
107 * "-EPERM" : Partition is not permitted to retrieve performance information,
108 required to set "Enable Performance Information Collection" option.
132 runtime by setting "Enable Performance Information Collection" option.
139 * "-EPERM" : Partition is not permitted to retrieve performance information,
140 required to set "Enable Performance Information Collection" option.
164 runtime by setting "Enable Performance Information Collection" option.
171 * "-EPERM" : Partition is not permitted to retrieve performance information,
172 required to set "Enable Performance Information Collection" option.
196 runtime by setting "Enable Performance Information Collection" option.
[all …]
|
| H A D | sysfs-class-platform-profile | 21 and performance
22 balanced-performance Balance between performance and low
24 towards performance
25 performance High performance operation
26 max-power Higher performance operation that may exceed
|
| /linux/Documentation/arch/x86/ |
| H A D | amd-hfi.rst | 17 power capabilities: performance-oriented *classic cores* and power-efficient
27 threads to the classic cores. From a performance perspective, sending
32 performance impact.
37 The ``amd_hfi`` driver delivers the operating system a performance and energy
45 describes an efficiency and performance ranking for each classification.
48 represent thread performance/power characteristics that may benefit from
74 about the performance and energy efficiency of each CPU in the system. Each
76 performance value indicates higher performance capability, and a higher
77 efficiency value indicates more efficiency. Energy efficiency and performance
83 a reordering of the performance and efficiency ranking. Table updates happen
[all …]
|
| /linux/kernel/power/ |
| H A D | energy_model.c | 23 * Mutex serializing the registrations of performance domains and letting
29 * Manage performance domains with IDs. One can iterate the performance domains
77 DEFINE_EM_DBG_SHOW(performance, performance);
107 debugfs_create_file("performance", 0444, d, &em_dbg[i], in em_debug_create_ps()
147 /* Create the directory of the performance domain */ in em_debug_create_pd()
164 /* Create a sub-directory for each performance state */ in em_debug_create_pd()
207 * @pd : EM performance domain for which this must be done
242 * Calculate the performance value for each frequency with in em_init_performance()
249 table[i].performance = div64_u64(max_cap * table[i].frequency, in em_init_performance()
264 /* Compute the cost of each performance state. */ in em_compute_costs()
[all …]
|
| /linux/tools/power/cpupower/bench/ |
| H A D | README-BENCH | 7 - Identify worst case performance loss when doing dynamic frequency
12 - Identify cpufreq related performance regressions between kernels
18 - Power saving related regressions (In fact as better the performance
28 For that purpose, it compares the performance governor to a configured
56 takes on this machine and needs to be run in a loop using the performance
58 Then the above test runs are processed using the performance governor
61 on full performance and you get the overall performance loss.
80 trigger of the cpufreq-bench, you will see no performance loss (compare with
84 will always see 50% loads and you get worst performance impact never
|
| /linux/tools/power/cpupower/man/ |
| H A D | cpupower-set.1 | 27 its policy for the relative importance of performance versus energy savings to
31 performance and 15 is maximum energy efficiency.
34 when it must select trade-offs between performance and
37 This policy hint does not supersede Processor Performance states
51 Setting the performance bias value on one CPU can modify the setting on
62 Sets the energy performance policy preference on supported Intel or AMD
68 default performance balance_performance balance_power power
|
| /linux/drivers/perf/hisilicon/ |
| H A D | Kconfig | 6 Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home
7 Agent performance monitor and DDR Controller performance monitor.
13 Provide support for HiSilicon PCIe performance monitoring unit (PMU)
23 Provide support for HNS3 performance monitoring unit (PMU) RCiEP
|
| /linux/tools/testing/selftests/mm/ |
| H A D | test_vmalloc.sh | 9 # a) analyse performance of vmalloc allocations;
26 # Static templates for performance, stressing and smoke tests.
74 echo "Run performance tests to evaluate how fast vmalloc allocation is."
99 echo "for deep performance analysis as well as stress testing."
109 echo -n "Usage: $0 [ performance ] | [ stress ] | | [ smoke ] | "
133 echo "# Performance analysis"
134 echo "./${DRIVER}.sh performance"
187 if [[ "$1" = "performance" ]]; then
|
| /linux/Documentation/admin-guide/mm/ |
| H A D | numaperf.rst | 2 NUMA Memory Performance
10 as CPU cache coherence, but may have different performance. For example,
14 under different domains, or "nodes", based on locality and performance
36 performance when accessing a given memory target. Each initiator-target
56 nodes' access characteristics share the same performance relative to other
65 NUMA Performance
69 be allocated from based on the node's performance characteristics. If
79 The performance characteristics the kernel provides for the local initiators
103 performance characteristics in order to provide large address space of
129 attributes in order to maximize the performance out of such a setup.
|
| /linux/Documentation/driver-api/cxl/linux/ |
| H A D | access-coordinates.rst | 10 A memory region performance coordinates (latency and bandwidth) are typically
15 the performance coordinates by retrieving data from several components.
19 would be the CXL hostbridge. Using this association, the performance
22 performance coordinates between a CPU and a Generic Port (CXL hostbridge).
24 The :doc:`CDAT <../platform/cdat>` provides the performance coordinates for
28 performance coordinates that's tied to a DSMADhandle and this ties the two
29 table entries together to provide the performance coordinates for each DPA
31 then there would be different performance characteristsics for each of those
34 If there's a CXL switch in the topology, then the performance coordinates for the
96 maximizes performance. When asymmetric topology is detected, the calculation
[all …]
|
| /linux/drivers/platform/mellanox/ |
| H A D | Kconfig | 37 providing a high performance switching solution for Enterprise Data
38 Centers (EDC) for building Ethernet based clusters, High-Performance
71 providing a high performance switching solution for Enterprise Data
72 Centers (EDC) for building Ethernet based clusters, High-Performance
99 tristate "Mellanox BlueField Performance Monitoring Counters driver"
105 to performance monitoring counters within various blocks in the
|