Final run using the same board as used for the heatsink tests now with heatsink and fan together and 1344 MHz unlocked again: http://openbenchmarking.org/result/16031...603114GA85
The benchmark scores are rather irrelevant (at least if you want to compare different boards -- testing different thermal settings in an active benchmarking approach just allowed us to improve performance settings for Pine64 and to identify most if not all benchmarks used as insufficient)
But at least I could verify that the board runs again at these higher clockspeeds so I've to search for the cause of the shutdowns that happened this afternoon somewhere else (will use the 2nd Pine64+ without heatsink on the PMIC to torture with heavy switching between voltages). And I could also verify that using equipment for $3 the A64 is able to run with light workloads constantly at 1344MHz (two times throttling down to 1200MHz for a moment):
![[Image: Pine64_Plus_1344MHz.png]](http://kaiser-edv.de/tmp/mc6CyL/Pine64_Plus_1344MHz.png)
Since the Phoronix test suite uses extremely unoptimised code (and some of the tests run single threaded and scores will be adjusted by the count of CPU cores afterward -- what a joke) the workload is rather light. Using software that makes heavy use of NEON for example and with my cheap heatsink and fan I'm not able to exceed 1008 MHz (eg. using cpuburn-a53).
Now time to drop the Phoronix stuff and start to further optimise settings with real benchmarks like https://github.com/pooler/cpuminer for example
The benchmark scores are rather irrelevant (at least if you want to compare different boards -- testing different thermal settings in an active benchmarking approach just allowed us to improve performance settings for Pine64 and to identify most if not all benchmarks used as insufficient)
But at least I could verify that the board runs again at these higher clockspeeds so I've to search for the cause of the shutdowns that happened this afternoon somewhere else (will use the 2nd Pine64+ without heatsink on the PMIC to torture with heavy switching between voltages). And I could also verify that using equipment for $3 the A64 is able to run with light workloads constantly at 1344MHz (two times throttling down to 1200MHz for a moment):
Since the Phoronix test suite uses extremely unoptimised code (and some of the tests run single threaded and scores will be adjusted by the count of CPU cores afterward -- what a joke) the workload is rather light. Using software that makes heavy use of NEON for example and with my cheap heatsink and fan I'm not able to exceed 1008 MHz (eg. using cpuburn-a53).
Now time to drop the Phoronix stuff and start to further optimise settings with real benchmarks like https://github.com/pooler/cpuminer for example