Author: Vincent Diepeveen
Date: 08:30:16 09/29/00
Go up one level in this thread
On September 28, 2000 at 21:22:09, Vincent Lejeune wrote: >>>>>>So a single lookup in memory is in its most realistic case: >>>>>> 10ns x 11T = 110 clocks. >>>>>> >>>>>>You can do a lot in 110 clocks! >>>>>> >>>>>>If that gets suddenly down to less as 20 clocks, then >>>>>>it's clear that this rocks bigtime. >>>>>> >>>>>>considering the huge number of tables in my program which all together >>>>>>eat hundreds of kilobytes of RAM, i'm estimating that speedup *might* >>>>>>be like 20% or so in the middlegame for DIEP. >>>>>> >>>>>>However programs that are very fast and are basically wasting their system >>>>>>time at hashtables might profit even more. I wouldn't be amazed by a 2 fold >>>>>>speedup for certain programs. >>>>>> >>>>>>That's what EDO ram to SDRAM did for my draughtsprogram at least... >>> >>>I actually tried an RDRAM machine recently. I ran my chess program benchmark >>>(WAC at 1s/posn) on a P3/933 + PC800 and got 1060 knps. I have a P3/933 with >>>SDRAM at home. On that system I get 1083 knps. >>> >>>So, at least with my program, SDRAM is slightly better. I suspect that SDRAM >>>will actually be a whole lot better if your program is at all memory speed >>>bound. Mine isn't apparently: when I set the memory to run at 100 MHz instead >>>of 133 MHz (which I can do independent of the FSB speed with the motherboard >>>I'm using) I get 1066 knps--which is still faster than the RDRAM result... >>>-Dan. >> >>I'm amazed! >> >>What SDRAM133 do you have at home, 2-2-2, 2-3-3 or 3-3-3? >>the difference between 2-2-2 (which is the fastest) and 3-3-3 should >>be a bit less as 10% for latency. >> >>What chipset did the machine have where you tested the rdram at and >>how many banks of RIMMS did it have? >> >>Thanks in advance, >>Vincent > >And new techonology are comming in this area : > >http://www.aceshardware.com/Spades/list_news.php?category=HARDWARE > >-Low latency DDR-II will be based on EDRAM- >...E-DDR II performs, according to independent studies of IBM and the university >of Maryland up to 22% better in SpecInt than DDR-II!... > >The beauty about the EDRAM concept is that it adds very little SRAM and thus die >space to the chip, to be more exact only 1.4%!. Those SRAM buffers contain the >row data, and the controller can read those buffers instead of the sense amps. >While the SRAM buffers are read, the sense amps are free for precharge and >refresh operations. In other words, those SRAM buffers can eliminate latencies >like the precharge latency. ddr sdram is not new technology. it's SDRAM but now chips on both sides of the DIMM. So it's improving upon sdram exactly 2 times in speed.
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.