mersenneforum.org Search Results
 Register FAQ Search Today's Posts Mark Forums Read

 Showing results 1 to 25 of 329 Search took 0.06 seconds. Search: Posts Made By: Mysticial
 Forum: Hardware 2020-05-25, 00:01 Replies: 19 Views: 842 Posted By Mysticial The 8121U Cannon Lake. Discontinued though I... The 8121U Cannon Lake. Discontinued though I think.
 Forum: y-cruncher 2020-02-07, 10:14 Replies: 17 Views: 6,811 Posted By Mysticial To answer your actual question of how I do the... To answer your actual question of how I do the conversion "in place". The algorithm is the scaled remainder tree. The only operations are multiplications. There are no additions or subtractions at...
 Forum: y-cruncher 2020-02-07, 09:47 Replies: 17 Views: 6,811 Posted By Mysticial Woah, I go away for a while and didn't notice all... Woah, I go away for a while and didn't notice all these new posts! It's not fully in-place in that it doesn't need any auxiliary memory. It needs a lot actually - especially to perform the...
 Forum: y-cruncher 2020-01-30, 18:56 Replies: 17 Views: 6,811 Posted By Mysticial 50 Trillion Digits of Pi So when Google set the record of 31.4 trillion digits last year, I gave it a 50/50 chance that record would fall before the end of the year. Didn't quite work out that way. This latest computation...
 Forum: Math 2019-12-05, 00:16 Replies: 1 Views: 662 Posted By Mysticial Ideas: I'm not familiar with the structure... Ideas: I'm not familiar with the structure of an optimized mersenne-transform (due to its asymmetry). But if the FFT is out-of-place and you're expending bandwidth to save the integer...
 Forum: Miscellaneous Math 2019-12-04, 23:55 Replies: 18 Views: 1,206 Posted By Mysticial Easy to check for yourself. Mathematica/Wolfram... Easy to check for yourself. Mathematica/Wolfram Alpha says they're all composite.
 Forum: Hardware 2019-11-05, 21:47 Replies: 14 Views: 1,616 Posted By Mysticial Turn on XMP. Hardly any non-server memory is... Turn on XMP. Hardly any non-server memory is above "stock" 2133. Anything above it usually implies XMP. Btw, my 7940X (ES) will do 3466 with a full load of 8 x 16GB.
 Forum: y-cruncher 2019-10-30, 18:33 Replies: 0 Views: 715 Posted By Mysticial Parallel Disk I/O The topic of parallel disk I/O has been a recurring topic and has just come up again. So I figured I create a thread to keep everything together. First of all, there's multiple forms of parallel...
 Forum: y-cruncher 2019-10-29, 16:33 Replies: 15 Views: 2,528 Posted By Mysticial Not sure if I understand what you're referring... Not sure if I understand what you're referring to. Right now, swap mode uses one thread per logical path. So you can get multiple threads by using multiple logical paths - thus it's advantageous...
 Forum: Hardware 2019-10-24, 19:15 Replies: 14 Views: 1,616 Posted By Mysticial Not even close. You'd probably need 8 - 16... Not even close. You'd probably need 8 - 16 channels to keep LL from bottlenecking on 18-core Skylake X. The high core count Skylake X's aren't a good value for LL for this reason. You're probably...
 Forum: Hardware 2019-10-24, 18:44 Replies: 14 Views: 1,616 Posted By Mysticial If you're not overclocking it, you can pop any... If you're not overclocking it, you can pop any large AIO on it and it'll stay quiet. And if you intend to run LL on it, it'll be memory-bound anyways. So it won't be able to sustain a high power...
 Forum: y-cruncher 2019-10-23, 06:15 Replies: 15 Views: 2,528 Posted By Mysticial That's strange. I've also never seen things die... That's strange. I've also never seen things die on Linux without some sort of "killed" or "segfault" message. When it dies from OOM, it will (at least on out-of-the-box Ubuntu) will say killed. ...
 Forum: y-cruncher 2019-10-21, 20:14 Replies: 15 Views: 2,528 Posted By Mysticial Awesome! I've actually never heard of... Awesome! I've actually never heard of Ctrl+D in this context, lol. Ctrl+C is how I break out of the program. In all cases, I'm not sure how "cleanly" it terminates the program and whether...
 Forum: y-cruncher 2019-10-19, 08:05 Replies: 15 Views: 2,528 Posted By Mysticial New beta is out: ... New beta is out: http://www.numberworld.org/y-cruncher/y-cruncher%20v0.7.8.9503.zip http://www.numberworld.org/y-cruncher/y-cruncher%20v0.7.8.9503-static.tar.xz ...
 Forum: Astronomy 2019-10-18, 22:12 Replies: 35 Views: 1,766 Posted By Mysticial During the 2012 Venus transit, I was barely able... During the 2012 Venus transit, I was barely able to see Venus through just eclipse shades. I had to really squint to see it. And I couldn't see any of the sunspots. Once I projected it through...
 Forum: y-cruncher 2019-10-11, 23:59 Replies: 15 Views: 2,528 Posted By Mysticial Looks like 9502 will not be the final release. 3... Looks like 9502 will not be the final release. 3 issues came up. 2 are trivial and harmless, the 3rd is embarrassing and non-trivial to fix. Not sure how I screwed this one up. The non-trivial one...
 Forum: Hardware 2019-10-09, 21:45 Replies: 16 Views: 1,344 Posted By Mysticial There's enough stuff in AVX512 not related to... There's enough stuff in AVX512 not related to 512-bit that AMD can't sit on it forever. So they'll either need to adopt AVX512 as is, or build a competing version (highly unlikely). When I spoke...
 Forum: Information & Answers 2019-09-22, 12:27 Replies: 18 Views: 1,670 Posted By Mysticial I have no idea what prime95 does, but for an FFT... I have no idea what prime95 does, but for an FFT that has N bytes of data, there will be N/4 bytes* of unique twiddle factor data. So an FFT implementation that caches all twiddle factors with no...
 Forum: y-cruncher 2019-09-22, 06:41 Replies: 15 Views: 2,528 Posted By Mysticial As promised, v0.7.8 public betas: ... As promised, v0.7.8 public betas: http://www.numberworld.org/y-cruncher/y-cruncher%20v0.7.8.9502.zip http://www.numberworld.org/y-cruncher/y-cruncher%20v0.7.8.9502-static.tar.xz ...
 Forum: y-cruncher 2019-09-20, 18:06 Replies: 15 Views: 2,528 Posted By Mysticial Looks like you beat me to it. Well then,... Looks like you beat me to it. Well then, screw that and the Zen 2 binary/optimizations. Public beta for v0.7.8 will go out this weekend since it's now feature-complete. Looking at my priories and...
 Forum: y-cruncher 2019-09-18, 16:31 Replies: 15 Views: 2,528 Posted By Mysticial Paper launch at best. They're not fooling anyone.... Paper launch at best. They're not fooling anyone. But I'd love to be proven wrong. The 16-core is the one that has a comparable compute/bandwidth ratio as the high-end Rome Epyc (which is what...
 Forum: y-cruncher 2019-09-18, 07:43 Replies: 15 Views: 2,528 Posted By Mysticial We're now half-way through September: ... We're now half-way through September: There is still no official release date for the 3950X. The 3900X can't stay in stock for more than a few minutes at a time. None of the stores I've...
 Forum: y-cruncher 2019-09-09, 16:31 Replies: 17 Views: 1,606 Posted By Mysticial From what I've seen (and maybe it's just a... From what I've seen (and maybe it's just a symptom of the test), the variation is huge. Individual latencies have a standard deviation comparable to the mean. And the location of the sync variable in...
 Forum: y-cruncher 2019-09-09, 07:03 Replies: 17 Views: 1,606 Posted By Mysticial In the power-of-two core-count case, the workload... In the power-of-two core-count case, the workload has near perfect static load-balancing. Thus, any form of "negative" imbalance may have a disproportionate effect on performance due to stragglers....
 Forum: y-cruncher 2019-08-30, 20:14 Replies: 17 Views: 1,606 Posted By Mysticial That is soooo strange. Haven't heard of it... That is soooo strange. Haven't heard of it before. Shot in the dark: Was Superfetch enabled? I've seen weird things with the memory compression that it does. But not like this. 48 GB is...
 Showing results 1 to 25 of 329

All times are UTC. The time now is 22:05.

Sat May 30 22:05:41 UTC 2020 up 66 days, 19:38, 1 user, load averages: 1.13, 1.19, 1.26