|
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
|
|
| AMD K6-III+ and K6-2+ Shaptooth's Final Bite | |
|
(Review by Aaron Vienot, July 13, 2001) |
| AMD Athlon64 3200+ At: |
The test system used the following hardware:
Installed software and drivers at test time included the following:
The 4.2GB system hard drive is divided into two 2.1GB FAT16 partitions. Drive C: hosts Windows95 and a 256MB fixed-size swap file. DMA transfers are enabled for the hard drive. The AGP aperture BIOS setting is at the default 64MB. The SDRAM is set to CAS Level 2 in the BIOS. PCI Latency is set at 64 cycles. For questions regarding BIOS settings, please consult the LostCircuits BIOS Guide .
The benchmarking suite
The applications used here were selected from the suite employed in the ClickOn-CPU article . These applications reflect a mix of synthetic tools, older and newer real-world applications, and tools that are somewhat a blend of the two.
Synthetic benchmarks
This category includes Ziff-Davis CPUMark99, Sandra 2001se, and Distributed.net's RC5 64-bit decryption client. These tools will provide a base for establishing general performance trends.

Real-world
Included here are two older applications, 3Finger's Quake2 Crusher demo and Rage Software's Expendable as well as Quake3: Arena as representative of newer games.
Hybrid
The two benchmarks used are MadOnion.com's 3DMark 2000 testing suite and the VNU/Remedy demo of Final Reality.
The K6-III has been established as the fastest processor clock-for-clock in business applications, as the K6-III review demonstrates and the K6-III+'s die shrink would not be expected to significantly alter function or performance profile. Moreover, somebody strictly hooked on business applications will probably see no need to upgrade in this particular manner.
RC5 results are reported as the average of six runs; all other results are the average of three unless otherwise indicated. Quake2 and Q3A timedemos were allowed to stabilize before data recording was performed. Q3A and Expendable numbers were recorded without a soundcard in the system. Having sound enabled can cause a performance hit of up to 17% in these two applications. (Other applications were unaffected.)
next page: => RC5, CPUMark, Sandra Memory =>
All advice and educational articles on LostCircuits are free, but if you feel you can, please make a small donation to us!