|
 |
| Hot Hardware Test Systems |
|
A little
taste of some of the latest chipsets |
|
|
TEST BOARDS:
Abit
BH7 (i845PE) Motherboard
VIA
P4PB Ultra (P4X400) Motherboard
Abit BE7 (i845PE) Motherboard
MSI 655 Max (SIS 655) Motherboard
COMMON
HARDWARE:
Intel Pentium 4 2.53GHz 533MHz FSB
512MB Corsair PC3200 DDR for Intel and VIA
boards
2x
256MB Geil PC3500 DDR for MSI 655 Max
Asus V9280S GeForce 4 Ti 4200-8x
Creative Labs Audigy Soundcard
Western Digital WD200BB ATA100 7200rpm 20GB Hard
Drive
Creative Labs 52x CD-ROM
Windows XP Professional with Service Pack 1
VIA P4PB using Hyperion 4.46 drivers
Intel based boards using:
Intel Chipset Drivers, version 4.30.1006
Intel Application Accelerator, version 2.3
GeForce 4 Ti 4200-8x using:
NVIDIA Detonator Drivers, version 42.86
|
TESTING METHODOLOGY:
To
help fully explain the scores we listed in the
following benchmarks, we felt it was necessary to
explain how the systems were setup before running
the benchmarks. On all of the boards, we started off by
manually optimizing the
BIOS settings to the most aggressive system options
available to us. The memory
frequency was manually set to DDR333 with the
CAS timings set to 2-5-5-2 and a 1T command rate
except for the MSI 655 Max, which automatically
detected the RAM as DDR400.
The hard drive was
formatted, and Windows XP Professional with
Service Pack 1 was installed. After the Windows
installation was complete, we installed the
necessary chipset drivers for each platform and
Intel Application
Accelerator on the Intel boards. We then installed the drivers for the rest of
the components, using the drivers supplied on
the CD, except for the GeForce Ti 4200.
For the GeForce card, we downloaded and installed the
latest NVIDIA reference drivers at the time of
testing, version
42.86.
Auto-Updating, Hibernation, and System Restore were disabled,
and then we set up a 768MB permanent page file.
On these test systems we set the visual effects
to "best performance" in system
performance to limit any effects these settings
would have on the benchmarks. With the newer
42.86 drivers, there are options to set the
level of the drivers between "application" and
"aggressive". We set the video driver
settings to "blend", balancing performance with
quality. Lastly, we installed all of the
benchmarking software, defragged the machine,
and rebooted one last time.
|
|
 |
|
Benchmarking with SiSoft Sandra 2003 Pro |
|
Starting with the Synthetic... |
|
SANDRA (the System ANalyzer, Diagnostic
and Reporting Assistant) is an information and
diagnostic utility put out by the folks at SiSoftware.
We have started using the 2003 version with has an updated
database of components to compare.
It's a quick and easy
way to compare the CPU, Memory, and Hard drive performance
of a given system against an internal database of similar
systems and drives. These benchmarks are theoretical scores,
and can't necessarily be measured in real-world terms, but
provide a good way to make comparisons amongst like
components. We ran a set of tests at the stock speed
of 133MHz for the front side bus, and then again after
achieving a stable overclock at 163MHz.
CPU Test
133MHz FSB
 |
CPU Test
163MHz FSB
 |
In the first
picture, we see the Abit BH7 paired with the P4 2.53GHz CPU
sitting pretty between the database scores for a P4 2.4GHz and a P4 2.66GHz. (Side note: there were no
scores in the database for a 2.53GHz P4). In
comparison to AMD Athlon XP chips, the Dhrystone score we
got just topped the 2200+, but fell far off of the pace of
the Athlon 2400+, which was the leader of the pack.
The P4s ruled the whetstones, where our score
was only 170 MFLOPS behind the 2.66GHz P4. As seen in
the overclocked test on the right, we brought out the "big
guns" for comparisons, including the top of the line P4 3.06
and Athlon XP 3000+. The scores we achieved were very
impressive, topping all other whetstone marks, and falling
just shy of the Dhrystone scores for the top CPUs.
Multimedia Test
133MHz FSB
 |
Multimedia Test
163MHz FSB
 |
In the
Multimedia tests, the Integer Point calculations score was
the second lowest of the CPUs rated, but was still a good
showing for a P4 2.53. The Floating Point score tipped
the scales in the other direction. We got the second
highest score on the chart, just nipping on the P4 2.66GHz CPU's
heels. After we ran the test again at a FSB
of 163MHz, we got results that beat out everything Sandra could
throw at us.
|
Memory Test
133MHz FSB
 |
Memory Test
163MHz FSB
 |
For the memory test, we
wanted to pick out chipsets that most closely resembled the
boards we were testing when using DDR333. As there was
no P4X400 score when using PC2700 memory, we substituted a
P4X333 instead. As you can see, for the most part all
of the boards using DDR333 produced similar scores, with the
SIS648 taking a slight lead, the 845PE boards in the middle,
and the VIA board last. All three pale in comparison
to the SIS 655, which uses a Dual DDR setup. Dual DDR
- Remember these words, because you will be hearing them
more and more in the coming months. When we raised the front side bus
up to 163MHz, we were effectively running the memory at
202MHz, a shade better than DDR400. The score we got
was better than the database score for an 845PE with PC3200
DDR, and weren't too far off of the Dual DDR scores from a
Granite Bay (Intel 7205) or the SIS 655.
Hard Drive
Performance
 |
The hard drive performance benchmark was just shy of the 30,000 mark,
and much higher than a relative score for an ATA100 2MB
cache hard drive.
It was right behind the ATA150 score, ostensibly from a
Serial ATA drive. The score was beat only by a
drive with 8MB cache, such as a "Special Edition" Western
Digital hard drive.
Futuremark's benchmarks take
the stage |