Archives
 
 
 
  Special
 
 
 
  About Us
 
 
 

Newsletter
Free E-mail Newsletter from BYTE.com

 
    
           
Visit the home page Browse the four-year online archive Download platform-neutral CPU/FPU benchmarks Find information for advertisers, authors, vendors, subscribers Request free information on products written about or advertised in BYTE Submit a press release, or scan recent announcements Talk with BYTE's staff and readers about products and technologies

ArticlesTest Results


January 1998 / BYTE Hardware Lab Report / Test Results

No single benchmark can tell you everything you may want to know about how well a system will perform. However, run seven industry-standard benchmarks ranging from real-world business applications to high-end OpenGL graphics tests, and you'll have a pretty good idea .

We asked vendors to send us workstations loaded with a single partition of NT Workstation 4.0 (with Service Pack 3). All systems had to conform to our specification minimums, including a PCI-based, OpenGL gr aphics card with a minimum of 4 MB of video RAM, 128 MB of system RAM, and a 3-GB or higher hard drive.

Performance

The C++ test helped us gauge how well a syst em would perform while compiling Microsoft Foundation Classes (MFC). We ran the multiprocessor test that measures how fast the system can build (compile and link) a big chunk of source code by running two simultaneous instances of Visual C++ 4.2.

Three single-threaded suites from Spec's Viewperf 5.0 comprised our high-end graphics tests for judging high-end graphics performance. The Viewperf CDRS-03 makes works of industrial- design elements, DX-03 tests scientific visualization elements, and AWADVS-01 tests 3-D animation. All tests were run at 1024- by 768-pixel resolution with true color.

To analyze each system's raw floating-point power, which is crucial to many applications such as advanced spreadsheets, we used the Fourier test. This program analyzes the spectral content of a WAV file and loads two simultaneous copies of the test, while NT handles the multiprocessing session.

Also, release 2.0 of the BYTEmark benchmark helped us expose the system's CPU, FPU, and memory systems.

Th e Access test, an application-based benchmark that uses Microsoft's Test 4.0 compiler, measures how well a system can generate multiple business database transactions.

We also used Bapco's Sysmark 4.0 for NT, which measures NT client PC performance across a spectrum of business-application mixes, such as Word for Windows 6.0 (native 32-bit), Excel 5.0 (native 32-bit), Texim Project 2.0e (native 32-bit), Orcad MaxEDA 6.0 (native 32-bit), and PowerPoint 4.0 (16-bit emulation).

Finally, the InterMark video test measures primitive Graphical Device Interface (GDI) operations and displays entire pictures generated by applications such as Excel, Word, CorelDraw, PowerPoint, Freelance Graphics, and others.

Usability and Features

We examined each of the eight machines for usability by focusing on two areas: system design and documentation. We rate how easy it is to remove and reinstall the cover, for example. Ease of upgradability (for adding RAM and mass-storage devices) adds points to the usability score. We look for accessible memory slots and drive bays that offer room for cabling.

We give top honors to systems with vendor-specific manuals that are comprehensive, include easy-to-use diagrams, and offer up-to-date technical information. Those that lack specifications for the motherboard, hard drive, and graphics subsystem are rated lower.

Each vendor completes a lengthy questionnaire and provides a detailed description of each system's features and support options. We weigh each feature and calculate an overall features score. Features related to performance include the size and write policy of the secondary cache. The use of hard drive controllers, network adapters, and graphics adapters on the motherboard frees up expansion slots and earns a system extra points. Finally, it's important to note that warranty and support policies are what frequently separate major vendors from second- and third-tier vendors.


The evaluations in t


Best Bang for the Buck

illustration_link (18 Kbytes)

At $2999, Xi's 600 MTower DP offers the most bang for the buck.


Up to the BYTE Hardware Lab Report section contentsGo to previous article: Go to next article: 300-MHz Workstations FeaturesSearchSend a comment on this articleSubscribe to BYTE or BYTE on CD-ROM  
Flexible C++
Matthew Wilson
My approach to software engineering is far more pragmatic than it is theoretical--and no language better exemplifies this than C++.

more...

BYTE Digest

BYTE Digest editors every month analyze and evaluate the best articles from Information Week, EE Times, Dr. Dobb's Journal, Network Computing, Sys Admin, and dozens of other CMP publications—bringing you critical news and information about wireless communication, computer security, software development, embedded systems, and more!

Find out more

BYTE.com Store

BYTE CD-ROM
NOW, on one CD-ROM, you can instantly access more than 8 years of BYTE.
 
The Best of BYTE Volume 1: Programming Languages
The Best of BYTE
Volume 1: Programming Languages
In this issue of Best of BYTE, we bring together some of the leading programming language designers and implementors...

Copyright © 2005 CMP Media LLC, Privacy Policy, Your California Privacy rights, Terms of Service
Site comments: webmaster@byte.com
SDMG Web Sites: BYTE.com, C/C++ Users Journal, Dr. Dobb's Journal, MSDN Magazine, New Architect, SD Expo, SD Magazine, Sys Admin, The Perl Journal, UnixReview.com, Windows Developer Network