Author: Vincent Diepeveen
Date: 11:24:29 09/25/01
Go up one level in this thread
On September 25, 2001 at 06:26:33, Slater Wold wrote: >On September 24, 2001 at 21:46:56, Vincent Diepeveen wrote: > >>On September 24, 2001 at 00:46:35, Slater Wold wrote: >> >>>*Perhaps* when I sell my 2x1.7Ghz Intel, I will invest in an Alpha. That should >>>be interesting! >> >>dual alpha 833Mhz 21264, standard edition: $20000.00 > >Looking around, I've seen some *reasonibly* priced used AlphaServers. buying a second hand alpha 21164is not a good plan. For diep at least. For diep a second hand 21164 at 633Mhz , if those are secondhand available anyway, it's performing like a 380Mhz PII for DIEP. >It was just a thought! > >> >>$20k and don't expect you can ever upgrade it to a faster Mhz those >>cpu's, whereas you sure can update your intels and amds to some extend. >> >>It's impossible to clock those alpha's higher than 1Ghz. >> >>Alpha died btw. It's called intel now. IA64 is going to be the future >>for 64 bits land. Poor 64 bitters... >> >>>One question: Obviously a node on an Alpha is not equal to a node on a x86 >>>system. Mind sharing why? Or giving me some references to read up on. I've >>>only been around a few Alpha machines, and that was pretty recently. And they >>>were all running Windows! >> >>Tim Mann noted, perhaps he can explain that here again as i might have >>misunderstood, that the alpha duals are not factor 2.0 HARDWARE speedup >>like intel, AMD is. those 64 bits cpus suffer somehow from being put in dual. >> >>Don't ask me why. >> >>I'm no expert on buses, but i heart >>the P4 has a wider bus than the P3. It didn't speed DIEP up a bit AFAIK. >>A single read from RDRAM is 128 bytes wide. that's 1024 bits btw. >> >>That 256 bits wide bus from alpha, that's just 32 bytes? >> >>Note DDR ram is 64 bytes at once AFAIK. That's 512 bits. latency 1.5 times >>faster than that from RDRAM though. >> >>>Thanks Bob! >> >>>Slate >>> >>>> >>>> >>>> >>>> >>>>>Slate >>>> >>>> >>>> >>>> >>>> >>>>> >>>>>> >>>>>>Don't just assume that 375mhz is bad. The PPC is _not_ a bad machine. I >>>>>>have run on SP's... >>>>>> >>>>>> >>>>>> >>>>>> >>>>>>> >>>>>>>Still probably optimistic number of nodes a second. >>>>>>> >>>>>>>So at 8192 processors, from which you can perhaps use a 1000 at a time, >>>>>>>I would get 15M nodes a second. >>>>>>> >>>>>>>Now that looks great, but that's of course on a CLUSTER. Speedup perhaps >>>>>>>10%. 1.5M nodes a second effectively, but the bigger the depth the less >>>>>>>the speedup gets as the branching factor will be worse, unless i accept >>>>>>>that the thing first slows down at each processor (which is a likely >>>>>>>approach) and pray that the latency is more than fast at this thing. >>>>>>> >>>>>>>So you sure outsearch deep blue by many plies, but not if a new deep >>>>>>>blue would be pressed on a chip using nullmove and DDR-RAM at it. >>>>>>> >>>>>>>So you are not faster in NPS, but search improvements would let it >>>>>>>search deeper. that still wouldn't make my DIEP faster on this machine >>>>>>>than DB was in nodes a second. >>>>>>> >>>>>>>Of course DBs focus upon only getting the maximum number of NPS (that's >>>>>>>how they advertised the thing. search depths have no commercial value) >>>>>>>sure made it faster than what i would get on this machine. >>>>>>> >>>>>>>>Is this really so for those in the know with hardware and these types of >>>>>>>>machines?
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.