Posts by Drago75

1) Message boards : Number crunching : Not enough memory (Windows vbox) (Message 1735) Posted 27 Apr 2022 by Drago75 Post: No I do not. But I never asked for them either. When it comes to Linux, which distro did you try, Ubuntu? I know Linux can be pain in the butt. As a Windows user you are used to how certain things are done. To type in any system change via the Terminal is somewhat 1980′s. What makes it less complicated is that once you have set it up it works. My favourite distro is Mint which resembles Windows in a lot of ways. When you install it choose "Mate" which doesn¹t install a lot of programs which you won′t use anyway. One advantage over Ubuntu is that you can edit the app_config.xml and propably also all other files of BOINC without having to edit permissions. Meanwhile BOINC manager is already included in the software library where you can install it from without any typing. There is also a BOINC meta package for cuda or AMD OpenCL-savvy available which should set up your GPU for optimum use. I havent tried those yet but I am sure they work. If you need a tool to limit your Intel′s CPU frequency to keep the temperature down use "cpupower-gui" which is also available in the library, "cpu-x" shows you all your hardware information like temp, ram usage and so fourth. Nvidia drivers are found under driver settings. Make sure the open source xorg driver is not selected and choose nvidia driver 470 instead which is known to run stable. And than you are good to go... I suggest you install it on a USB 3.x stick (16 gb or bigger is enough) or external SSD so it doesn¹t interfere with your Windows installation in any way.
2) Message boards : Number crunching : Not enough memory (Windows vbox) (Message 1733) Posted 25 Apr 2022 by Drago75 Post: Hey Peter. I can't help you with your VM as I have given up trying to deal with them. That virtualization stuff is pretty complex and very ressource demanding. On my two Ryzen 9's I installed one Mint and one Ubuntu Linux on fast USB sticks. When I support projects that run better under Linux I just boot those PC's from the USB sticks and run BOINC from there, too. Works nicely. You could propably run 24 tasks at once without problem if your CPU has sufficient level 3 cache as I just learned the other day. My Ryzen 9 3900X have 64 mb which is sufficient. Other projects which run better under Linux are Universe and TNGrid. Possibly also others.
3) Message boards : Number crunching : use hyper threading? (Message 1728) Posted 24 Apr 2022 by Drago75 Post: I ran a full set of 16 wu's at once on my 8 core Linux machine but they seem to finish a lot slower than if I let only 8 tasks run at once. It is a bit difficult to compare since the times necessary to finish them are usually all over the place but on average I would say they finish quicker if only one task per actual cpu core is assigned. Does anybody have any data about this? Does hyper threading make sense with this project? Memory of 16 GB is sufficient in both cases. you are indeed running 16 WUs concurrently with 16GB RAM? So the RAM requirements seem to differ substantially between Linux and Windows. My Windows machines with 8GB RAM (and 6 "real" cores) don't allow more than 3 WUs concurrently. For each WU 1.900MB RAM is allocated, although the peak working set size does not exceed around 58MB. This is really too bad, as I can only use half of the CPU capacity on 3 such machines :-( Hey Erich56. The problem with the Windows version of QuChem is that it needs virtualization which requires a lot of resources. You can run QuChem under Linux natively and yes 16 wu's at once do fit into 16 GB of ram. :-) If you want to try out Linux you can set up a fast USB stick with a Mint or Ubuntu distro and boot your PC from there if you don't want two OS's on the same hard drive. You can run BOINC also from that USB stick as it doesn't require fast read and write access. It works perfectly. I do that on my two Ryzen 9 when I support projects that run faster under Linux like QuChem or Universe.
4) Message boards : Number crunching : use hyper threading? (Message 1727) Posted 24 Apr 2022 by Drago75 Post: Hey Aurum. Thanks for your input. That may really explain it. Iam noticing a major difference in completion times on my Ryzen 7 5800H which has only 16 mb of L3 cache and not so much on my Ryzen 9's if I let them run a full stack. They are equipped with 64 mb. If the problem is not HT so much then I will experiment a little and try to find out an optimum setting for the R7 if the question isn't just 8 or 16 wu's at once. Yesterday I read that AMD is starting to introduce a new processor design with 3D stacked level 3 cache wich increases it's amount significantly. That may be a useful feature for crunchers.
5) Message boards : Number crunching : use hyper threading? (Message 1723) Posted 12 Apr 2022 by Drago75 Post: I ran a full set of 16 wu's at once on my 8 core Linux machine but they seem to finish a lot slower than if I let only 8 tasks run at once. It is a bit difficult to compare since the times necessary to finish them are usually all over the place but on average I would say they finish quicker if only one task per actual cpu core is assigned. Does anybody have any data about this? Does hyper threading make sense with this project? Memory of 16 GB is sufficient in both cases.
6) Questions and Answers : Windows : Error Creation (Message 1394) Posted 27 Mar 2021 by Drago75 Post: Two thirds of my results turn out to be invalid. But not all of them. Anyone got a clue what the problem could be? I am using a Ryzen 9 3900X, Windows 10, 64 bit.