Posts by bozz4science

81) Questions and Answers : Issue Discussion : All my GPU applications have crushed. (Message 776)
Posted 9 Nov 2020 by bozz4science
Post:
Thanks for the update. Looking forward to try out the GPU version as I didn't catch any GPU test task so far. Will try on a Linux Ubuntu 20.04 LTS and Windows based machine with my 750 Ti. Curious to what performance increase I will be able to observe.
82) Message boards : News : [TWIM Notes] Nov 2 2020 (Message 760)
Posted 3 Nov 2020 by bozz4science
Post:
Thanks for the update! Custom-compiling pytorch surely sounds like a lot of work... Wish you the best of luck for this!
83) Questions and Answers : Issue Discussion : WU RAM? (Message 755)
Posted 1 Nov 2020 by bozz4science
Post:
Thanks for looking into it!
84) Questions and Answers : Issue Discussion : WU RAM? (Message 750)
Posted 1 Nov 2020 by bozz4science
Post:
I also happened to receive this error and had to unselect the 2 options "run test application" as well as the corresponding test application in my computing settings in order to receive new work on my machine. Did acutally return the only test WU that I received successfully prior to receiving this message (CPU version)
85) Message boards : News : [TWIM Notes] Oct 19 2020 (Message 668)
Posted 21 Oct 2020 by bozz4science
Post:
I also appreciate the update. Particularly excited to see GPU and OSX support under active development. Additionally, I really look forward to those ds 4 WU as I think of image classification as a much more exciting research question. Thanks for all your hard work!

86) Questions and Answers : Unix/Linux : GPU update (Message 649)
Posted 14 Oct 2020 by bozz4science
Post:
How is testing coming along? I always happen to see several WUs on the server status page listed as test application and wonder whether internal testing with your system has already made it to beta testing here?
87) Message boards : News : [TWIM Notes] Oct 12 2020 (Message 647)
Posted 13 Oct 2020 by bozz4science
Post:
Thanks for the update! Great that the first big milestone on dataset will soon be reached.

Will those longer ds 1/2 WUs just be the same network but trained for more epochs to assure convergence to a stable network structure?

As always, love that you are so transparent with us and the glimpse on the future pipeline as well! Keep up the good work :)

88) Message boards : News : Scheduled Server Maintenance (Message 634)
Posted 10 Oct 2020 by bozz4science
Post:
Awesome! That server must be a beast then :) I am glad that everything went so smoothly. No issues on my end.
89) Questions and Answers : Issue Discussion : Credits for new "rand_automata" work units (Message 629)
Posted 9 Oct 2020 by bozz4science
Post:
Great! My RAC should quickly jump back then to what it previously was before the introduction of the rand WU. And I am glad I wasn’t wrong about my guess about the average runtime of those WU after all. Have a great weekend!
90) Message boards : Cafe : Motherboard / heatsink advice for AMD Ryzen chips (Message 627)
Posted 8 Oct 2020 by bozz4science
Post:
All right. Already thought this would be the case. Thanks for the advice. I'll definitely keep it in mind though as an alternative to thermal paste for the new (and symmetrical) CPU.
91) Message boards : News : [TWIM Notes] Oct 5 2020 (Message 625)
Posted 8 Oct 2020 by bozz4science
Post:
Looking forward to the EA badge :) Awesome that the server joined in and is now crunching away in the meantime!

I get your points about the paper. Working onto a deadline, especially in an academic setting can be dreadful and I believe the quality of the published article would seriously suffer if the deadline were to take priority over its coherence and a larger data base of results going into it. Still, I am looking forward to see this published in a well known journal to have the science community properly peer review your work and more importantly gain attention that could spark the very cooperation that you were mentioning in your post.

I still remember in the initial post I made here on the forum named "science due diligence" where I tried to get the first impression about you as project leader and the science to be conducted here. Back then you mentioned already topics such as near evolution, HP search, and many more. I would love to see projects such as this making use of the platform that you have built here and that you gain traction in the scientific community.

Just yesterday there was a great event by Stanford's HAI (Human-Centered AI). It was the 2020 virtual fall conference named "triangulating intelligence, melding neuroscience, psychology and AI". Whereas the title is a mouthful, I feel that the field definitely becomes more interdisciplinary by the minute. One interesting take away was that while supercomputers do become more efficient, they still require much more power than the human brain that apparently only runs on a ø of ~20-25W (Thats not even a light bulb). And while computers are awesome at minimising errors in an attempt to maximise precision, human brains are basically working under the principle "just good enough" and apply many heuristics, such as classification and inference, to minimise compute time and maximise power efficiency rather than minimising the probability of errors.

I believe there is a recording on YouTube or their website for the ones who might be interesting to take a peek into some of the talks of this conference.

Would you actually appreciate pointers to other researchers/research groups that could potentially benefit in partnering up with you? I might know some that do lots of data analysis and training with neural networks. Would be great seeing more specific use cases such as brain modelling, neuro evolution, validation of other research, robotics motion planning through neural networks, etc. go along your more broadly oriented explorative science experiments! But let's not get ahead of ourselves.

By the way, recently I saw an awesome YouTube video about a rather similar topic which is about brain-like computer structures and how that differs from the van Neumann architecture. Main takeaway for me here was, that there is an upper limit in terms of power efficiency and compute throughput as long as the working memory (RAM) is physically separated from the CPU running the calculations. That's inadvertently different to the architecture of the human brain that actually stores the information in the same place in which the calculation is performed. The research field is called Neuromorphic computing. https://www.youtube.com/watch?v=Qow8pIvExH4

And btw, I would love for you to take a (quick) long into the rand WU credit adjustment. From what I can tell based on my personal runtimes, the credit equivalence to match the ds 1/2 units, would roughly be 750-925 range depending on the CPU of course. I would love to see what the average runtimes ratio will tell us.

92) Message boards : Cafe : Motherboard / heatsink advice for AMD Ryzen chips (Message 622)
Posted 7 Oct 2020 by bozz4science
Post:
Note about those graphite cooling pads: They are electrically conductive, and somewhat slippery. What several people do, to keep them from sliding off the CPU while you're installing the heatsink, is to use a dab of thermal paste in the corners to anchor the pad in place.
The link you included, basically offers a 30x30mm and 40x40mm version. I currently think about replacing my current thermal paste cooling solution in my laptop with a graphite pad instead. My CPU is a i5 4278U. It is not symmetrically shaped and fused to my laptop's mobo. Now my question, as graphite is electrically conductive, can I simply cut the 40x40 pad into fitting pieces to cover both components individually? Would I be risking to short my mobo if the pad were to overlap the CPU and touch the mobo under operation?
93) Message boards : News : [TWIM Notes] Oct 5 2020 (Message 620)
Posted 7 Oct 2020 by bozz4science
Post:
Thanks for the weekly update and congrats on (almost) reaching your first important milestone on dataset 3 this quickly! Great that you always include the links to other threads when positing your TWIM notes.

Excited to see the EA badge added to my signature soon.

Can you update us on the progress of the paper as well?

Any thoughts in the meantime to adjust the credit for the rand WU after reaching that first milestone. Idk if the numbers that I outlined in the other thread are representative of the overall average of runtime ratios across the majority of hosts, but I would like to see a slight upward adjustment in per WU credit for those WU after further analysis, to match the per hour credit of dataset 1/2 WUs. One host running now only rand WU, essentially lost 60% of RAC by completely switching over to rand WU just by chance. And as they are all the same app, there is no option for us to opt out of those demanding WU at least on less powerful systems. I happily continue crunching those on my main rig, but my laptops seem to be quite overwhelming, clocking those rand WU recently with little over 44,500 s. That is ~2300 vs. ~3550 credits in dataset 1/2 units. No complaint, just a thought that I'd like to share with you. Maybe after reaching the first milestone here (100x100), you could query the results of rand WU on your server and average out their runtimes. The runtime ratio between those dataset 3 to 1/2 WU would be a robust benchmark for maybe revisiting this shortly. Thanks for your consideration!
94) Message boards : Cafe : Motherboard / heatsink advice for AMD Ryzen chips (Message 618)
Posted 6 Oct 2020 by bozz4science
Post:
Thanks for getting back to me! Yeah, I see the first point you made about the higher TDP of lets say the 3600X over the 3600 and 3700X. Currently I see the 3600 retailing at 169€ whereas the 3700X is very steeply priced at around 279€ on average. That's even more than you outlined for me in Germany at least. So the economically sound decision is obvious...

Definitely going to settle for a 65 W TDP rated CPU. Still speccing out my system, but making progress on the case selection. I decided on a MSI MPG 550 Gaming Edge WiFi mobo, that seems to offer all the connectivity and even more than I need. As I plan to run this rig as a dual-GPU system, even though initially only with a 1660Ti paired with a 750Ti, I want to eventually upgrade but time will tell. For that purpose case and airflow planning definitely take a priority right now. Also I don't want to be restricted by the interior size to consider other future upgrades.

It's just not a really big bang and only you know how important the buck is.
Well, coming from a Xeon X5660, the jump to a 3600 will be huge for me :) My laptop based i5 4278U is only making matters worse, but that's currently the latest hardware I own. I skipped a couple generations of CPU and GPU innovation! And my budget is constrained to the 1000-1100€ mark.

Noctuas get good reviews, enthusiastic sometimes, but I don't have personal experiences with them. They're too expensive for me. EKL Brocken 3 was my first choice cooler
I agree on the price front. But apparently they are unmatched performance-wise at air cooling. The Brocken 3 definitely sparks my interest but there's a lot of reports that it is quite load under heavy load.

Don't worry. Air cooling a 65W TDP processor shouldn't be a problem if you don't try to squeeze the last bit of power out of it.
At the moment I am considering a beQuiet dark rock 4 but that is not far off Noctua's price. Don't know yet but the cooling decision definitely should have priority when deciding to run the system 24/7. I don't wanna leave the house, leaving it own, when I see horrendous temps. Would fear to burn the house down. :) Not being able to squeeze the last bit of juice out of the chip would be okay for me.

Regarding the case I am looking into the bequiet! Silent Base 601 Midi Tower. Nothing fancy but not too shabby for the price. Has great opportunities to install lots of fans for great airflow and allows for bigger cpu heatsinks, however restricts GPUs to a size of only 285mm which makes it quite impossible to consider let's say any RTX triple slot cards. So future upgradability is kind of inhibited. Its larger cousin, the be quiet! Silent Base 801 has similar features but allows due to its larger dimensions also to run the rig with most latest gen RTX cards. Probably by then, the room won't be an issue anymore anyway, but rather airflow and cooling issues. Still figuring it out, but thanks so far for the pointers!
95) Questions and Answers : Macintosh : Darling (Message 607)
Posted 5 Oct 2020 by bozz4science
Post:
Nice! Would gladly attach my host if macOS support were to be rolled out :)
96) Questions and Answers : Issue Discussion : Uploads stuck (Message 606)
Posted 5 Oct 2020 by bozz4science
Post:
Thanks for the info and sorting it out. All back to normal on my end.
97) Questions and Answers : Issue Discussion : Credits for new "rand_automata" work units (Message 605)
Posted 5 Oct 2020 by bozz4science
Post:
Note that you do get 2.3 times more credit for those big WUs. They just return less on a per hour runtime basis. And that’s just for my rig. Don’t know if that’s representative. Also don’t really mind as it is also amongst the higher returning projects I have seen so far. GPU Support is coming your way soon. Ultimately your choice...
98) Questions and Answers : Issue Discussion : Uploads stuck (Message 601)
Posted 5 Oct 2020 by bozz4science
Post:
Have a couple of rand WU with a 1 day headroom only until reporting deadline, that successfully uploaded but didn't get reported. BOINC Manager says, project temporarily down for maintenance, but internet connection okay. Any indication to when the maintenance will likely be finished?
99) Message boards : Cafe : Motherboard / heatsink advice for AMD Ryzen chips (Message 596)
Posted 5 Oct 2020 by bozz4science
Post:
Did you already choose a processor? My personal choices for a dedicated cruncher are the Ryzen 3600 or 3900X.
How much performance would be left on the table by choosing a 3600X over a 3700X? And is the 3700X in between the two other mentioned 3600X/3900X really less bang for the buck? Was indeed eyeing the 3700X and 3600X ... I just mentioned the Threadrippers as well not because I was playing with the thought of getting one of these but rather as I thought they would fit well together with the other high-performance Ryzen chips that would all need to handle the cooling issue.

If it's okay for you to replace the cooler later try the boxed one first but expect the temperature to get uncomfortably high either way.
I'll think about it. But I don't want to fry my new processor in the first few weeks of running it 24/7 at unbearable temps. Investing upfront in a decent cooler and accounting for the required space to mount it properly sure doesn't sound like a bad idea.

For air cooling of high power processors it is vital to keep the case as cool as possible which in my experience doesn't work well with small cases. And the most effective CPU coolers are also BIG. Keep that in mind when you choose your case.
I was looking at larger Noctua and Alpenföhn coolers. Think those should be the best aftermarket air coolers that are currently available. Hope that in the end running long term with air cooling won't hurt the chip too much as opposed to water cooling. This is why I also want a case with great ventilation and at least 4 fans that assure a constant air flow.

Currently not sure if a mid-tower case will do it (single GPU, 3600/3700 X, air cooling) or whether I should rather look into big tower cases....

... to keep them from sliding off the CPU while you're installing the heatsink, is to use a dab of thermal paste in the corners ...
That's great to know. I'll certainly give it try! Thanks for the heads-up!
100) Questions and Answers : Issue Discussion : Credits for new "rand_automata" work units (Message 595)
Posted 5 Oct 2020 by bozz4science
Post:
My Xeon 5660 usually crunches dataset 1/2 WU in ~ 8500s (2:20h) and needed ~45000s (12:30h) for those dataset 3 rand WU on average (based solely on <10 so far but very little variance in runtimes lets me think that they are rather representative already). That is factor 5.3x longer runtimes for an increased 595 credit per WU. So at least for my machine, those prior runs WU yield much higher return per runtime. Both types of WU give me on a per hour basis ~110/h vs. ~48/h. Hope that reference helps. Don't know if those ratios are comparative for other rigs.


Previous 20 · Next 20

©2022 MLC@Home Team
A project of the Cognition, Robotics, and Learning (CORAL) Lab at the University of Maryland, Baltimore County (UMBC)