|
|
本帖最后由 dange66 于 2023-5-19 18:43 编辑
英伟达在RTX4060/60ti发布之际写了一篇文章专门阐释了显存子系统在RTX系列显卡中的背后设计意图以及各方权衡.
其中有个很有意思的点.
原文地址: https://www.nvidia.com/en-us/gef ... o-memory-explained/
NVIDIA engineers tested the RTX 4060 Ti with its 32 MB L2 cache against a special test version of RTX 4060 Ti using only a 2 MB L2.
In testing with a variety of games and synthetic benchmarks, the 32 MB L2 cache reduced memory bus traffic by just over 50% on average compared to the performance of a 2 MB L2 cache.
in this scenario, isolating for memory performance, an Ada GPU with 288 GB/sec of peak memory bandwidth would perform similarly to an Ampere GPU with 554 GB/sec of peak memory bandwidth
32MB的L2相对于2MB版本在测试中平均减少了大约50%的访存需求, 就显存性能而言: Ada 288GB/s vs Ampere 544GB/s的表现相当
(苏妈直拍大腿 .
话说70-class的192bit也为人诟病怎么没有对应的数据出来,还是他们觉得2023年推出一个3000+价格的128bit显卡是真的难为情
|
|
310112100042806
发表于 2023-5-19 18:44
他不是做了两版本吗，8G跟16G 4060TI