有关GF114核心的问题

为什么GF114核心(GTX560)每个SM单元上有48个SP(而GF100(GTX480等)和GF110(GTX580)每个SM单元中只有32个SP),一直没有找到相关的介绍,按照NVIDIA发布的GF100核心白皮书,其上面有一段这样的描述:
Dual Warp Scheduler
The SM schedules threads in groups of 32 parallel threads called warps. Each SM features two warp
schedulers and two instruction dispatch units, allowing two warps to be issued and executed
concurrently. GF100’s dual warp scheduler selects two warps, and issues one instruction from each
warp to a group of sixteen cores, sixteen load/store units, or four SFUs.
Because warps execute
independently, GF100’s scheduler does not need to check for dependencies from within the instruction
stream. Using this elegant model of dual-issue, GF100 achieves near peak hardware performance.

按照它上面的解释,其每个时钟周期最大只能占用32个SP单元执行程序,所以我觉得每个SM单元安排32个SP时最合理的。如果GF114也是只有两个Warp Scheduler会不会导致其中的16个SP单元空闲?或者我的理解有误? 我想用GTX560做高性能计算,但GTX580和480都太贵了,烦请大侠指点,非常感谢

顶一下,求指教

继 续 求 教

继 续 求 教

[

GF104的构架就已经是每个SM 48个SP了。指令的分发执行与GF100一样,但不会出现你所说的16个SP单元空闲。因为GF104中一个SM有4个Instruction Dispatch Unit,而GF100只有2个,4个Buffer slot保证了即便GF104的SM中有48个SP,8个SFU(GF100是32个SP,4个SFU),同样不会有空周期。