游戏狂人
![Rank: 6](static/image/common/star_level3.gif) ![Rank: 6](static/image/common/star_level2.gif)
- 贡献度
- 193
- 金元
- 11299
- 积分
- 1902
- 精华
- 0
- 注册时间
- 2008-11-26
|
12962662 发表于 2012-8-18 18:02 ![](static/image/common/back.gif)
虽然两张卡SLI后显存不能共享,但SLI下每张卡只处理一半画面,SLI 时候单卡处理整个画面时用的显存少很多
...
沒有...還是一樣,不多也不會少
In all SLI-rendering modes, local memory is duplicated across all GPUs. This means that on an SLI system with two 256MB video cards, there is still only 256MB of video memory available to applications. Additionally, any change to local memory on one GPU (for example, dynamic texture updates) will often require a data broadcast to other GPUs. This can introduce a performance penalty depending on the size and characteristics of the data.
這可以解釋為什麼兩個顯存不一樣的顯卡組sli的時候實際顯存去兩個裡面較小的。根據官方的說法,實際顯存甚至沒有一倍。
鏈接地址是「http://developer.nvidia.com/object/sli_best_practices.html」
|
|
|