Author: Jay Urbanski
Date: 20:28:45 07/07/03
Go up one level in this thread
On July 07, 2003 at 22:42:51, Peter Stayne wrote: >Upon further reading, my assumption is incorrect, but the findings of >single-threaded apps getting a boost still seems to be true. Hence the three >links below and choice quotes: > >http://www6.tomshardware.com/cpu/20021114/p4_306ht-12.html > >http://www.anandtech.com/cpu/showdoc.html?i=1746&p=6 > >On which I quote: > >Fundamentally we still only have one CPU and one set of execution units, so if >the OS dispatches two threads that contend for identical resources in the CPU >then HT could reduce performance. > >In the earlier versions of Hyper-Threading, there were some pretty significant >performance drops in desktop applications with it enabled. Luckily through >revision after revision of the technology and through the addition of a few new >components (flip back a few pages to see what's new) the vast majority of >applications will see a performance increase or no performance loss at all > >http://www.aceshardware.com/read.jsp?id=50000332 > >Quote: > >It is quite remarkable how almost every single threaded benchmark still got a >small performance boost from HyperThreading, between 1 and 5%. This shows that >HyperThreading has matured as it almost never decreased performance, as it did >in the first hyperthreaded Xeons. > > > > >On July 07, 2003 at 21:35:04, Tom Kerrigan wrote: > >>On July 07, 2003 at 19:15:35, Peter Stayne wrote: >> >>>Nah, Daniel is right. Even non-SMP programs do gain a slight advantage in speed >>>with HT enabled, though minimal, benchmarks have shown this. >> >>Which benchmarks? I won't believe this until I see it. Operating systems take a >>fraction of 1% of your CPU to do housekeeping when you're running a chess >>program, and only a fraction of that could be offloaded to a 2nd CPU. >> >>-Tom Even if this were true with a chess engine (which I will require evidence to believe) the answer to the topic "Is Fritz, shredder, or Junior hyper-threading enabled?" is only "Yes" for SMP versions of those engines. Single threaded versions are no more "Hyper-threading enabled" than any other single threaded application. To claim otherwise is to claim that everything is "Hypter-threading enabled".
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.