|
Advice Beginners BIOS Guide CPUs Links Mainboards Memory Network Storage Video/Sound Cards Contact Forum SiteMap Sponsors WebNews Home |
. | . |
Prices: Mainboards ABIT ASUS Chaintech Shuttle Soyo Tyan CPU Intel P4 2.4C-800 P4 2.6C-800 P4 2.8C-800 P4 3.0-800 P4 3.2-800 AMD AthlonXP XP 1700+ XP 2000+ XP 2400+ XP 2500+ XP 2700+ XP 3000+ XP 3200+ Athlon64 Athlon64 3200+ Athlon64 FX-51 Opteron Opteron 240 Opteron 242 Opteron 244 Opteron 246 Memory Corsair Crucial Kingston Mushkin OCZ |
LOSTCIRCUITS |
|
| Pentium4 3.06 GHz GHz HyperThreading and the Non-Parallel Universe | |
| (Review by MS, Nov. 18, 2002) |
Benchmark Results
Apologies for not going through iteration upon iteration of SiSoft Sandra scores, there is no real impact of HT on those scores and besides, I wouldn't care too much either way.
Instead, let's start with an example of HT in an SMP enabled benchmark, i.e. Caligari TS 5.1
Caligari TrueSpace 5.1 3D-rendering in action.
For better visibility of the two individual scan lines indicating the progress of each logical CPU, raytracing was turned off (for this illustration only). Both logical processors are working at 100% CPU utilization. If HT is turned off in the BIOS, the processor shows as single CPU and will generate a single scan line only.
The only question here is, how does HT influence performance? Remember, both processors are already running at 100% utilization and, therefore, the prediction is very easy, that is, there will be no performance increase, rather a small performance hit.
Runtime in seconds, lower is better. For reference, we show the 2.8GHz P4 running at default as well as overclocked to 3.15GHz. Bottom line here is that HT does result in an approximately 1% performance hit. Even though there are two logical processors at work each of them will work only half as fast as if they would work as a single processor.
next page: => Let's Make It A Bit More Difficult =>
