简体繁体 English

特斯拉双精度

[英]Tesla double precision

原文 2010-08-11 14:14:12 9 3 double/ cuda/ opencl

I am looking for the information, how double precision is hardware implemented in the tesla gpu . 我正在寻找信息，如何在tesla gpu中实现硬件的双精度。 I have read, that two stream processors are working on the single double value, but i didn't found any official paper from nvidia. 我已经读过，两个流处理器正在处理单个double值，但我没有找到任何来自nvidia的官方文件。

Thanks in advance. 提前致谢。 PPS Why most GPU are computing with only single precision (because colors can be stored as RR.GG.BB.TT, where each character is a 8-Bit value)? PPS为什么大多数GPU只用单精度计算（因为颜色可以存储为RR.GG.BB.TT，其中每个字符是8位值）？

PS google it for me didn't help PS 谷歌它对我来说没有帮助

3 个解决方案

Not supporting double is not a matter of storage format like you said (RR.GG.BB.TT) but having native intrinsics (and so dedicated hardware) for handling operations on double (add, mul, madd, etc). 不支持double不是像你说的那样存储格式（RR.GG.BB.TT），而是使用本机内部函数（以及专用硬件）来处理double（add，mul，madd等）上的操作。

Anyway, most GPU supports only single precision because where most of the GPU market lies is in the gaming market and gamers don't need double precision. 无论如何，大多数GPU仅支持单精度，因为大多数GPU市场都在于游戏市场，游戏玩家不需要双精度。 Also most of gamers are looking for good performance/price ratios. 此外，大多数游戏玩家都在寻找良好的性价比。 Implementing DP is costful in term of transistor budget (and TDP), and if games don't use double precision this is meaningless. 在晶体管预算（和TDP）方面实施DP是成本很高的，如果游戏不使用双精度，这是没有意义的。

This is why you see high-end ATI GPUs supporting double (HD 59xx and HD 58xx, but not mid and entry-level GPUs such as HD 57xx and less). 这就是为什么你看到高端ATI GPU支持双倍（HD 59xx和HD 58xx，但不是中端和入门级GPU，如HD 57xx及更低）。

@karlphillip: Yes you're right, IEEE754 (kind of) for GPUs like GTX 260, but current ATI and NVIDIA generation is supporting IEEE 754-2008 on high-end parts. @karlphillip：是的，对于像GTX 260这样的GPU，IEEE754（有点），但目前的ATI和NVIDIA一代支持高端部件的IEEE 754-2008 。

About hardware implementation, this are secrets IHVs usually don't tell :) 关于硬件实现，这是IHV通常不会告诉的秘密:)

Tesla is not a GPU, it's a line of coprocessors featuring various high-end GPUs. 特斯拉不是GPU，它是一系列具有各种高端GPU的协处理器。 If your Tesla has a Fermi GPU inside, it should have good double precision performance. 如果您的特斯拉内置Fermi GPU，它应具有良好的双精度性能。

See the Fermi white paper , page 9. 参见费米白皮书，第9页。

Single precision is more important for regular GPU computing because it is sufficient for such applications. 单精度对于常规GPU计算更为重要，因为它对于此类应用程序已足够。

According to Wiki : 根据维基：

For double precision (only supported in newer GPUs like GTX 260[12]) there are some deviations from the IEEE 754 standard: round-to-nearest-even is the only supported rounding mode for reciprocal, division, and square root. 对于双精度（仅在GTX 260 [12]等较新的GPU中支持），与IEEE 754标准存在一些偏差：舍入到最近偶数是唯一支持的倒数，除法和平方根的舍入模式。 In single precision, denormals and signalling NaNs are not supported; 在单精度中，不支持非正规和信令NaN; only two IEEE rounding modes are supported (chop and round-to-nearest even), and those are specified on a per-instruction basis rather than in a control word; 只支持两种IEEE舍入模式（斩波和舍入到最近的偶数），并且这些模式是在每个指令而不是在控制字中指定的; and the precision of division/square root is slightly lower than single precision. 并且除法/平方根的精度略低于单精度。

There you go, they implement most of the spec of IEEE 754 , but the actual implementation is probably private and secret. 你去了，他们实现了IEEE 754的大部分规范，但实际的实现可能是私密的和秘密的。