| /rk3399_ARM-atf/docs/design_documents/ |
| H A D | psci_osi_mode.rst | 17 A power domain topology is a logical hierarchy of power domains in a system that 18 arises from the physical dependencies between power domains. 20 Local power states describe power states for an individual node, and composite 21 power states describe the combined power states for an individual node and its 24 Entry into low-power states for a topology node above the core level requires 25 coordinating its children nodes. For example, in a system with a power domain 26 that encompasses a shared cache, and a separate power domain for each core that 27 uses the shared cache, the core power domains must be powered down before the 28 shared cache power domain can be powered down. 30 PSCI supports two modes of power state coordination: platform-coordinated and [all …]
|
| /rk3399_ARM-atf/docs/design/ |
| H A D | psci-pd-tree.rst | 9 populate a tree that describes the hierarchy of power domains in the 13 It would be much simpler for the platform to describe its power domain tree 16 #. The generic PSCI code generates MPIDRs in order to populate the power domain 20 levels in the power domain tree to four. 23 mechanism used to populate the power domain topology tree. 25 #. The current arrangement of the power domain tree requires a binary search 26 over the sibling nodes at a particular level to find a specified power 27 domain node. During a power management operation, the tree is traversed from 28 a 'start' to an 'end' power level. The binary search is required to find the 36 #. The attributes of a core power domain differ from the attributes of power [all …]
|
| /rk3399_ARM-atf/docs/perf/ |
| H A D | psci-performance-n1sdp.rst | 21 ``CPU_SUSPEND`` to deepest power level 23 .. table:: ``CPU_SUSPEND`` latencies (ns) to deepest power level in parallel (v2.14) 37 .. table:: ``CPU_SUSPEND`` latencies (ns) to deepest power level in parallel (v2.13) 51 .. table:: ``CPU_SUSPEND`` latencies (ns) to deepest power level in serial (v2.14) 65 .. table:: ``CPU_SUSPEND`` latencies (ns) to deepest power level in serial (v2.13) 79 ``CPU_SUSPEND`` to power level 0 82 .. table:: ``CPU_SUSPEND`` latencies (ns) to power level 0 in parallel (v2.14) 96 .. table:: ``CPU_SUSPEND`` latencies (ns) to power level 0 in parallel (v2.13) 110 .. table:: ``CPU_SUSPEND`` latencies (ns) to power level 0 in serial (v2.14) 124 .. table:: ``CPU_SUSPEND`` latencies (ns) to power level 0 in serial (v2.13) [all …]
|
| H A D | psci-performance-juno.rst | 25 Juno supports CPU, cluster and system power down states, corresponding to power 46 ``CPU_SUSPEND`` to deepest power level 49 .. table:: ``CPU_SUSPEND`` latencies (µs) to deepest power level in 68 .. table:: ``CPU_SUSPEND`` latencies (µs) to deepest power level in 87 .. table:: ``CPU_SUSPEND`` latencies (µs) to deepest power level in 106 .. table:: ``CPU_SUSPEND`` latencies (µs) to deepest power level in 125 ``CPU_SUSPEND`` to power level 0 128 .. table:: ``CPU_SUSPEND`` latencies (µs) to power level 0 in 147 .. table:: ``CPU_SUSPEND`` latencies (µs) to power level 0 in 166 .. table:: ``CPU_SUSPEND`` latencies (µs) to power level 0 in serial (v2.14) [all …]
|
| H A D | psci-performance-instr.rst | 43 power states used by the platform. The service tracks residency time and 44 entry count. Residency time is the total time spent in a particular power 46 the power state. PSCI Statistics implements the optional functions 73 The implementation provides residency statistics only for low power states, 97 * Entry to low power state 98 * Exit from low power state 111 captured after normal return from the PSCI SMC handler, or, if a low power state
|
| H A D | psci-performance-methodology.rst | 45 enters the low power state (WFI). Referring to the TF runtime instrumentation points, this 49 Time taken from the point the hardware exits the low power state to exiting
|
| /rk3399_ARM-atf/docs/components/ |
| H A D | mpmm.rst | 4 |MPMM| is an optional microarchitectural power management mechanism supported by 7 assist in |SoC| processor power domain dynamic power budgeting and limit the 16 external power controller can use these metrics to budget SoC power by
|
| /rk3399_ARM-atf/plat/intel/soc/n5x/soc/ |
| H A D | n5x_clock_manager.c | 24 uint32_t power = 1; in clk_get_pll_output_hz() local 54 power *= 2; in clk_get_pll_output_hz() 58 return ((clock * 2 * (divf + 1)) / ((divr + 1) * power)); in clk_get_pll_output_hz()
|
| /rk3399_ARM-atf/docs/ |
| H A D | porting-guide.rst | 152 Defines the total number of nodes in the power domain topology 153 tree at all the power domain levels used by the platform. 155 data structures to represent power domain topology. 159 Defines the maximum power domain level that the power management operations 160 should apply to. More often, but not always, the power domain level 162 to know the highest power domain level that it should consider for power 165 number of CPUs and it reports the maximum power domain level as 1. 169 Defines the local power state corresponding to the deepest power down 170 possible at every power domain level in the platform. The local power 173 value to initialize the local power states of the power domain nodes and [all …]
|
| /rk3399_ARM-atf/plat/mediatek/mt8186/drivers/spm/ |
| H A D | mt_spm_vcorefs.c | 455 int power = 0; in spm_vcorefs_vcore_setting() local 477 power = (int)devinfo_table[idx]; in spm_vcorefs_vcore_setting() 480 if (power > 0 && power <= 40) { in spm_vcorefs_vcore_setting()
|
| /rk3399_ARM-atf/docs/plat/ |
| H A D | allwinner.rst | 50 to be loaded into the ARISC SCP (A64, H5), or the power sequence control 59 This allows more advanced power saving techniques, like suspend to RAM. 66 power management controller, BL31 tries to set up all needed power rails, 68 software like U-Boot to ignore power control via the PMIC.
|
| H A D | imx8ulp.rst | 4 i.MX 8ULP is part of the ULP family with emphasis on extreme low-power techniques 12 Tensilica Fusion DSP for low-power audio and a HiFi4 DSP for advanced audio and machine 16 separate power, clocking and peripheral islands, but the bus fabric of each domain
|
| H A D | xilinx-versal-net.rst | 49 * `CPU_PWRDWN_SGI`: Select the SGI for triggering CPU power down request to 50 secondary cores on receiving power down callback from
|
| H A D | xilinx-zynqmp.rst | 114 The following power domain tree represents the power domain model used by TF-A 130 The 4 leaf power domains represent the individual A53 cores, while resources 131 common to the cluster are grouped in the power domain on the top.
|
| H A D | nvidia-tegra.rst | 53 Denver also features new low latency power-state transitions, in addition 54 to extensive power-gating and dynamic voltage and clock scaling based on 141 The PSCI implementation expects each platform to expose the 'power state' 151 be enabled by Tegrs SoCs during 'Cluster power up' or 'System Suspend' exit.
|
| H A D | hikey.rst | 122 - Make sure Pin3-Pin4 on J15 are connected for recovery mode. Then power on HiKey. 151 - Make sure Pin3-Pin4 on J15 are open for normal boot mode. Then power on HiKey.
|
| /rk3399_ARM-atf/plat/arm/board/fvp/fdts/ |
| H A D | fvp_tsp_sp_manifest.dts | 26 power-management-messages = <0x7>;
|
| /rk3399_ARM-atf/plat/allwinner/common/ |
| H A D | arisc_off.S | 32 # - Finally turn off the core's power switch by writing 0xff to the 64 1: l.lwz r5, 0x1c30(r13) # CPU power-on reset 74 l.sw 0x1540(r6), r5 # core power switch registers
|
| /rk3399_ARM-atf/plat/imx/imx8ulp/scmi/ |
| H A D | scmi_sensor.c | 68 desc->power = 0; in imx_scmi_sensor_description_get()
|
| /rk3399_ARM-atf/drivers/st/bsec/ |
| H A D | bsec2.c | 36 static uint32_t bsec_power_safmem(bool power); 741 static uint32_t bsec_power_safmem(bool power) in bsec_power_safmem() argument 750 if (power) { in bsec_power_safmem() 758 if (power) { in bsec_power_safmem()
|
| /rk3399_ARM-atf/drivers/scmi-msg/ |
| H A D | sensor.h | 49 uint32_t power; member
|
| /rk3399_ARM-atf/docs/plat/arm/ |
| H A D | arm-build-options.rst | 56 for the construction of composite state-ID in the power-state parameter. 61 field of power-state parameter. 133 instead of SCPI/BOM driver for communicating with the SCP during power 139 require all the CPUs to execute the CPU specific power down sequence to 140 complete a warm reboot sequence in which only the CPUs are power cycled.
|
| /rk3399_ARM-atf/docs/resources/diagrams/plantuml/ |
| H A D | rse_attestation_flow.puml | 38 Rnote over RMM: Platform token is\n\ cached. It is not\n\ changing within\n\ a power cycle.
|
| /rk3399_ARM-atf/docs/about/ |
| H A D | features.rst | 17 - Library support for CPU specific reset and power down sequences. This 31 - |PSCI| library support for CPU, cluster and system power management 37 - A generic |SCMI| driver to interface with conforming power controllers, for
|
| /rk3399_ARM-atf/docs/plat/nxp/ |
| H A D | nxp-layerscape.rst | 13 Layerscape family, combines FinFET process technology's low power and 61 power supply and single clock design. The new 0.9V versions of the LS1043A 62 and LS1023A deliver addition power savings for applications such as Wireless 100 The LS1046A is a cost-effective, power-efficient, and highly integrated 102 line of QorIQ communications processors. Featuring power-efficient 64-bit
|