|
Page 5 of 8 Benchmarks
Benchmarks can be divided into two kinds, component and system. Component benchmarks measure the performance of specific parts of a computer system, such as a microprocessor or hard disk, while system benchmarks typically measure the performance of the entire computer system. In either case, the performance you see in day-to-day use will almost certainly vary from benchmark performance, for a number of reasons. First, individual components must usually be tested in a complete computer system, and it is not always possible to eliminate the considerable effects that differences in a system design and configuration will have on a benchmark result. For instance, system vendors sell systems with a wide variety of disk capabilities and speeds, system memory, system bus features and video and graphics capabilities, all of which influence how the system components (such as the processor) and the computer system perform in actual use and can dramatically affect benchmark results. Also, you may not actually purchase the exact components we use in your benchmark system. This is just a reference you can base your purchase decisions on. Also, differences in software, including operating systems and compilers, will affect component and system performance. Finally, benchmark tests are typically written to be exemplary of only a certain type of computer application, which may or may not be similar to your applications.
Benchmarks are, at most, only one kind of information that you may use during the purchasing process. To get a true picture of the performance of a component or system you are considering purchasing, you must consult other sources of information (such as performance information on the exact system you are considering purchasing). You may also want to try actually sitting down and using the system if possible. There’s now better way to get a feel of a system than actually using it.
BAPCo SYSMark 2000 - Win2K
SYSMark is great for testing memory bandwidth. We’ll see how the Pentium 4 stacks up with its RDRAM compared to the Athlon with its PC133 SDRAM.
The Pentium 4 leads a bit with its RDRAM but it’s also clocked 400MHz faster than our comparing Athlon system. This might not be a good thing since RDRAM is more expensive and isn’t as widely available as PC133. It would be interesting to see how the Athlon at 1.5GHz would compare to the Pentium 4. However, the Athlon core may not be able to scale as high as the Pentium 4 -- able to reach beyond 2GHz. By that time, things may change significantly. ZD Benchmarks
ZD Content Creation Winstone 2000
On the ZD side, the Pentium 4 gains a little more momentum and is able to lead by 4.2 points. Content Creation tests stressful situations in business and creation apps such as Word, Photoshop, Netscape, Dreamweaver and more while multitasking between all of them at the same time. Like SYSMark, we still have to wonder how a 1.5GHz Athlon will compare. We guess it should close the gap significantly or possibly outperform the Pentium 4. Keep in mind though that Intel is positioning the Pentium 4 as power for the future. When optimized software appears, it may put the Pentium 4 in a totally new class all by itself. With programs such as Office with repetitive information, the processor’s Advanced Transfer Cache comes into play and pushes it forward.
ZD High-End Winstone 99
Here you see the Athlon not very far away at all. While the Pentium 4 does hold the lead (although a small one), keep in mind that it is clocked 400MHz faster. Intel needs to start pushing out really fast Pentium 4’s to be able to compete successfully with AMD’s coming and current processors.
Leads like the ones shown above aren’t impressive and do not show the Pentium 4’s new capabilities. We’ll wait until things have been recompiled. With newer applications coming out, we should definitely start to see the Pentium 4 pull away. SiSoft Sandra 2001
Above you see the Processor Information screen for SiSoft Sandra. Notice it says Pentium 4 CPU 1600MHz @ 1.5GHz? Interesting. We did not overclock our processor, but this is what SiSoft displays.
Here we see the Pentium 4’s FPU strengths come into play. It is significantly higher than a 1GHz Athlon. This is due to the double pumped ALU units. The Pentium 4 does have strong FPU performance but it also helps that it is clocked so high -- double the speed of the processor core -- 3GHz! As Intel scales the processor to higher speeds, we’ll be able to witness more significant increases and gaps between the Athlon and the Pentium 4.
What does the scores mean for you as a user? It means your games fly higher and drive faster. It means you have an advantage above other players in tournaments. It means your calculations come through faster.
|
