Lines Matching refs:in
5 operations in the Trusted Firmware-A Power State Coordination Interface (PSCI)
6 implementation, using the in-built Performance Measurement Framework (PMF) and
38 When using the debug build of TF, there was no noticeable difference in the
42 framework was used because the results in the debug build became skewed; the
43 console output prevented some of the tests from executing in parallel.
50 then initiates the test on all CPUs in parallel.
52 - **Sequential Tests** This type of test powers on each non-lead CPU in
57 In the results below, CPUs 0-3 refer to CPUs in the little cluster (A53) and
58 CPUs 4-5 refer to CPUs in the big cluster (A57). In all cases CPU 4 is the lead
73 Note there is very little variance observed in the values given (~1us), although
74 the values for each CPU are sometimes interchanged, depending on the order in
76 executing the tests sequentially in a single boot or rebooting between tests.
85 ``CPU_SUSPEND`` to deepest power level on all CPUs in parallel
104 A large variance in ``PSCI_ENTRY`` and ``PSCI_EXIT`` times across CPUs is
106 for the 3 other CPUs in the cluster (0-2) to complete ``PSCI_ENTRY`` and release
110 last CPUs in their respective clusters to power down, therefore both the L1 and
117 ``CPU_SUSPEND`` to power level 0 on all CPUs in parallel
136 There is no lock contention in TF generic code at power level 0 but the large
137 variance in ``PSCI_ENTRY`` times across CPUs is due to lock contention in Juno
152 ``CPU_SUSPEND`` to deepest power level on all CPUs in sequence
171 The ``CFLUSH_OVERHEAD`` times for lead CPU 4 and all CPUs in the non-lead cluster
172 are large because all other CPUs in the cluster are powered down during the
184 ``CPU_SUSPEND`` to power level 0 on all CPUs in sequence
207 The ``PSCI_ENTRY`` times for CPUs in the big cluster are slightly smaller than
208 for the CPUs in little cluster due to greater CPU performance.
210 The ``PSCI_EXIT`` times are generally lower than in the last test because the
214 ``CPU_OFF`` on all non-lead CPUs in sequence then ``CPU_SUSPEND`` on lead CPU to deepest power level
219 1. Call ``CPU_ON`` and ``CPU_OFF`` on each non-lead CPU in sequence.
242 CPUs in that cluster are powerered down during the test. The ``CPU_OFF`` call
253 The ``PSCI_EXIT`` times for CPUs in the big cluster are slightly smaller than
254 for CPUs in the little cluster due to greater CPU performance. These times
255 generally are greater than the ``PSCI_EXIT`` times in the ``CPU_SUSPEND`` tests
256 because there is more code to execute in the "on finisher" compared to the
259 ``PSCI_VERSION`` on all CPUs in parallel
263 approximates the round trip latency for handling a fast SMC at EL3 in TF.