PCMark05
Source: Tom's Guide US | Keywords: system, builder, marathon
9. PCMark05
PCMark05 is a set of synthetic benchmarks that simulate various kinds of workloads for PCs to tackle. Though these ratings do not necessarily reflect real-life performance, they do provide a useful basis for comparing across multiple systems, such as the four builds we put together for this story.
In the table that follows, we report the measurement for overall performance (called PCMarks, a common mechanism for comparing and one-upping systems on the Web), CPU, Memory, Graphics, HDD, audio compression and video encoding, all of which have some bearing on media PC behavior.
The table first shows PCMark05 scores for today's AMD 6000+ build and yesterday's AMD 4600+ build. Then follow the PCMark05 scores for the four Media PCs we built in the previously mentioned DIY article.
| CPU | PCMarks | CPU | Memory | Graphics | HDD | AudioC | VideoE |
|---|---|---|---|---|---|---|---|
| AMD 6000+ | 6594 | 6098 | 5112 | 9323 | 4809 | 2910.1 kB/s | 441.1kB/s |
| AMD 4600+ | 3460 | 4891 | 3879 | 1345 | 4772 | 2269.1 kB/s | 357.5kB/s |
| AMD 4800+ | 5215 | 5001 | 4010 | 5323 | 4821 | 2823.8 kB/s | 374.4kB/s |
| AMD 6000+ | 5605 | 6107 | 5016 | 5516 | 4937 | 2875.8 kB/s | 447.3kB/s |
| Intel T7200 | 5213 | 5021 | 4556 | 5361 | 4751 | 2226.2 kB/s | 367.5kB/s |
| Intel T7600 | 5767 | 6945 | 5899 | 5474 | 4780 | 2546.6 kB/s | 424.8kB/s |
As you'd expect, much faster graphics and somewhat faster memory add up to better overall results (what modest improvements we see in other areas - or not - are probably due to these influences as well). Certainly, the move to an 8800 offers a profound improvement in overall graphics quality and capability as the ensuing benchmarks also demonstrate.
3DMark05
3DMark05 runs a series of video source materials through the system and measures its graphics performance at two different settings: first, with anti-aliasing (No AA) and anisotropic filtering (No AF) turned off, then with 4x anti-aliasing (4xAA) and 8x anisotropic filtering (8xAF) turned on. These results show how the graphics subsystem performs with (4xAA 8xAF) and without (No AA No AF) complex shading and edge filtering mechanisms enabled.
Without these visual enhancements turned on scores go up, but the video is less attractive. With these visual enhancements enabled scores go down, but the video looks better. This matters much more for gaming than for DVD video, but does provide a useful metric for graphic subsystem performance.
| Today's System: 8800 GTX GPU | ||
|---|---|---|
| Resolution | NoAA, NoAF | 4xAA,8xAF |
| 1024x768 | 14690 3DMarks | 13292 3DMarks |
| 1280x1024 | 13625 3DMarks | 11687 3DMarks |
| Yesterday's System: Radeon X1250 GPU (built-in) | ||
|---|---|---|
| Resolution | NoAA, NoAF | 4xAA,4xAF |
| 1024x768 | 937 3DMarks | 514 3DMarks |
| 1280x1024 | 716 3DMarks | 357 3DMarks |
It's interesting to observe how single, new Nvidia graphics cards routinely outperform pairs of older cards from the previous generation. These are some of the best graphics numbers we've ever seen on any PC we've benchmarked, and certainly far above anything we've benchmarked with 66xx or 76xx passively cooled cards. This increases our anticipation for the new generation of 86xx passively cooled cards that should make its way to market soon.
- Previous page How And What We Tested
- Next page The HQV Benchmark