geoffrey

nah, swings are really typical for linear voltage regulators

no pics, didn't draw any schematics but the mod is explained on the previous page I think: remove L5 on the downside of the board, take a variable linear voltage regulator, feed it from another USB post, hook up both (Vregulator and R-pi) GND lines and attach the regulators Vout to the Raspberry-pi Vcore readout point. Linear is not the best choice though, even with this low current dev-board I notice a lot of voltage swings between idle and load.

I tried the hardware modification with a linear voltage regulator but with no help. It does work, but I could not get higher clocks on the pi, in contrary my SD cards got corrupted as soon as I tried +1200MHz... L5 is back where it belongs now, I'm done with overclocking the pi

can't remember where I red it but somewhere it was stated that for Raspberry Pi changing the batch size to 16 had a positive effect on performance while on other platforms there was no change. What was the value before you changed it to 16?

Hey, I get it working like this: pacman -S vim (I'm used to working with vim to write/edit txt files) wget http://www.java.net/download/jdk8/archive/b100/binaries/jdk-8-ea-b100-linux-arm-vfp-hflt-24_jul_2013.tar.gz (or go to the oracle java 8 website and download from there) tar -xzf jdk-8-ea-b100-linux-arm-vfp-hflt-24_jul_2013.tar.gz -C /opt export PATH=$PATH:/opt/jdk1.8.0/bin (link Java to system variables, you have to do it each time you reboot) java -version (check if Java is working) wget http://downloads.hwbot.org/hwbotprime.jar java -jar hwbotprime.jar

http://www.raspberrypi.org/wp-content/uploads/2012/10/Raspberry-Pi-R2.0-Schematics-Issue2.2_027.pdf it has the caps/resistors/... mentioned in the schematic, so easy to find the correct spot on the pcb

you can find some schematics of the board online. I was just looking at them to notice that one possibility is indeed to do the same thing as mentioned above: Remove L5 and connect some external source to the point where you read the core voltage. Maybe L5 can stay in place and you just connect some external source to the voltage readout point, but it would not be the proper way of doing things. Don't know how things have changed or got better the last few years in overclocking The only thing that bothers me is the voltage feedback which could be monitoring the output voltage for low and high overvoltage. I need my Raspberry for programming stuff so I won't be testing it anyway

nice guide M I've been testing Arch Linux with Java 8 preview, no real gains there. Closing some processes might help you a little bit, but 'ps aux' (linux task manager) doesn't show any process that is taking a lot of cpu time

good luck

any idea how you can get past the ~1100MHz max clock setting? Is there software that allows more?

Testing java 6 vs 7, no difference here with the new hwbot version (1.7.1) I see small difference, up to 3% faster with OpenJDK 7: Raspberry-pi @ 700 MHz OpenJDK 6 (1.6.0_27) 155.02 Primes/second OpenJDK 7 (1.7.0_07) 159.76 Primes/second Raspberry-pi @ 1000 MHz OpenJDK 6 (1.6.0_27) 195.50 Primes/second OpenJDK 7 (1.7.0_07) 197.45 Primes/second

hah, yeah, I could already imagine that would not be a smart thing to do, adding that to the git Well I managed to get it working in netbeans, I don't know exactly where to put the C codes but the program functions without so it seems, I only have the .so file in the same directory as the jar file I build through netbeans. Anyway, looking at the code gives me more questions than was hoping for. I don't really understand for example why you use the return statements in the constructor like you do in the following line of code: @Override public Benchmark instantiateBenchmark() { BenchmarkConfiguration configuration = new BenchmarkConfiguration(); configuration.setValue(PrimeBenchmark.TIME_SPAN, TimeUnit.SECONDS.toMillis(10)); configuration.setValue(PrimeBenchmark.SILENT, false); return new PrimeBenchmark(configuration, super.availableProcessors, super.progressBar); } The ThreadFactory is also something I haven't read upon yet, until now I was always manually creating threads and executing them through calling the start() method. Hmmm, inspiring

ah, hmm, DHCP right? With Raspbian I got it more or less working without much hassle. Me, I'm fine, thanks for asking I'm still in Portugal for a few more weeks, enjoying the sun, beaches, good food and nice parties off course Since I started my school carrier again I haven't been fooling around with hardware anymore. Well... not in a way of making it faster... But one never looses the thrill of playing around with hardware right It's nice to see you're still doing this hwbot thing, I never expected OC to stay so successful, muito fixe

install a java virtual machine: sudo apt-get update sudo apt-get instal openjdk-7-jre download the compiled zip, unzip it, and open the directory with a terminal, then execute the jar file: java -jar filename.jar

offtopic, but: what kind of IDE are you using? In Netbeans I can't properly import the source files without manually creating each file and copying its content.

looking forward to explore the Raspberry-pi in different ways than I'm doing now, but it will have to wait until I get back to Belgium in august. richba5tard, who wrote/writes the code of this benchmark anyway? I've been having the same idea for quite a long time but never came to finish something. Maybe I'll try to write/add openCl functionality, some Java wrapper libraries have appeared but I'm not sure if they allow the same functionality as native OpenCL C/C++ applications. Until now I didn't found OpenCL to be as platform independent as they claim it to be. Code compiled for one system seems to act different on other machines, even though the openCL program is only compiled at runtime.

Arch linux might do a better job as it has less overhead?