Performance in gamesTestbed configuration
Benchmarks
Note that performance charts are located on a dedicated page, because they don't fit a reasonable resolution. S.T.A.L.K.E.R.Performance charts: S.T.A.L.K.E.R. (AA doesn't work in this game; AF only). This game uses relatively old technologies. However, there are still many such games in the market, so its results are very interesting. Performance is apparently limited by system resources, by CPU, in low resolutions. So there are almost no differences there. As game resolution grows, we can see the total fill rate in the 9800 GX2 start to affect results. So the GTX 280 card is outperformed. However, the new card has an apparent advantage over the 9800 GTX. It's not outperformed by the 3870 X2 either (although it's because of the CrossFire problems in this game). World In ConflictPerformance charts: World In Conflict This game supports all latest innovations, including DX10. Firstly, the new card shoots forward on all fronts. Secondly, 512-bit bus provides really high bandwidth, and performance gains in AA+AF modes are fantastic. Especially relative to the 9800 GX2, which suffers from SLI problems in this game. ATI cards are apparently left far behind. CRYSIS, Rescue, DX10, Very HighPerformance charts: CRYSIS, Rescue, DX10, Very High Something strange happens here. The GTX 280 card is almost in between the 9800 GTX and the GX2. The new product leads in the 2560x1600 mode, where SLI fails (we already wrote about it). However, the game is too slow to play. It's either the fill rate has a strong effect in this game (GX2 is much faster in this respect than the new product), or it's a problem with the drivers. You should also keep in mind that the average FPS of a SLI system may fail to reflect the real low instant FPS. That is the average FPS will be high, but it will be difficult to play because of lags. CRYSIS, Harbor, DX10, Very HighPerformance charts: CRYSIS, Harbor, DX10, Very High The other scene in this game demonstrates the same layout of forces, so we have the same conclusions. Call Of JuarezThis game was written for DX9. It has high requirements to multitexturing speed, so the GTX 280 cannot outperform a more powerful card (from the point of view of fill rate). Or DX9 technologies and SLI are finetuned better and demonstrate much higher results than in DX10. The last conclusion seems right. That's why the 3870 X2 is faster here. Company Of HeroesAs soon as we run into a DX10 application, the new product shoots forward again. Especially with AA+AF. What concerns the 3870 Х2, CrossFire fails here, and the card demonstrates low results. 3DMark Vantage: Graphics MARKSPerformance charts: 3DMark Vantage: Graphics MARKS That's another DX10 application, plus optimizations for the new benchmark (groups of programmers always work on 3DMark optimizations both in NVIDIA and AMD), so the GTX 280 demonstrates phenomenal results. 3DMark06: SHADER 2.0 MARKSPerformance charts: 3DMark06 SM2.0 MARKS That's an opposite example. As soon as shaders of the previous generation come into action, the new card slips up. So, the previous-generation cards shoot forward. 3DMark06: SHADER 3.0 MARKSPerformance charts: 3DMark06 SM3.0 MARKS Ditto. Write a comment below. No registration needed!
|
Platform · Video · Multimedia · Mobile · Other || About us & Privacy policy · Twitter · Facebook Copyright © Byrds Research & Publishing, Ltd., 1997–2011. All rights reserved. |