GPU上的整数计算 [英] Integer calculations on GPU

问题描述

对于我的工作，进行整数计算特别有趣，显然不是GPU的制作方法。我的问题是：现代GPU是否支持高效的整数运算？我意识到这应该很容易为自己弄清楚，但我发现相互矛盾的答案（例如是 vs no ），所以我认为最好问。

For my work it's particularly interesting to do integer calculations, which obviously are not what GPUs were made for. My question is: Do modern GPUs support efficient integer operations? I realize this should be easy to figure out for myself, but I find conflicting answers (for example yes vs no), so I thought it best to ask.

此外，GPU上有任意精度整数的库/技术吗？

Also, are there any libraries/techniques for arbitrary precision integers on GPUs?

推荐答案

首先，您需要考虑您正在使用的硬件：GPU设备的性能在构造函数之间差异很大。

其次，它还取决于所考虑的操作：例如，添加可能是快于倍增。

First, you need to consider the hardware you're using: GPU devices performance widely differs from a constructor to another.
Second, it also depends on the operations considered: for example adds might be faster than multiplies.

在我的情况下，我只使用NVIDIA设备。对于这种硬件：官方文档宣布了使用新架构（Fermi）的32位整数和32位单精度浮点数的等效性能。以前的架构（Tesla）曾经为32位整数和浮点数提供相同的性能，但只有在考虑增加和逻辑运算时才会提供。

In my case, I'm only using NVIDIA devices. For this kind of hardware: the official documentation announces equivalent performance for both 32-bit integers and 32-bit single precision floats with the new architecture (Fermi). Previous architecture (Tesla) used to offer equivalent performance for 32-bit integers and floats but only when considering adds and logical operations.

但是再一次，这可能不是真的取决于您使用的设备和说明。

But once again, this may not be true depending on the device and instructions you use.

这篇关于GPU上的整数计算的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！