是否有可能投花车直接__m128，如果他们是16字节的神韵？ [英] Is it possible to cast floats directly to __m128 if they are 16 byte alligned?

问题描述

它是安全/可能/最好直接投花车以 __ M128 如果他们是16字节对齐？

Is it safe/possible/advisable to cast floats directly to __m128 if they are 16 byte aligned?

我注意到使用 _mm_load_ps 和 _mm_store_ps 来包装原始阵列增加了一个显著的开销。

I noticed using _mm_load_ps and _mm_store_ps to "wrap" a raw array adds a significant overhead.

什么是潜在的陷阱我应该知道的？

What are potential pitfalls I should be aware of?

编辑：

目前实际上是在使用加载和存储指令没有开销，我得到了混合一些数字，这就是为什么我得到了更好的性能。即便是你我能够做一些可怕的mangling与原始内存地址的 __ M128 例如，当我跑测试花了两倍的时间来完成，而不 _mm_load_ps 指令，可能回落到一些故障安全code路径。

There is actually no overhead in using the load and store instructions, I got some numbers mixed and that is why I got better performance. Even thou I was able to do some HORRENDOUS mangling with raw memory addresses in a __m128 instance, when I ran the test it took TWICE AS LONG to complete without the _mm_load_ps instruction, probably falling back to some fail safe code path.

推荐答案

是什么让你认为 _mm_load_ps 和 _mm_store_ps 添加显著的开销？这是正常的方式来加载/存储浮点数据从/ SSE寄存器假设源/目的就是内存（以及任何其他方法，最终归结为是这样）。

What makes you think that _mm_load_ps and _mm_store_ps "add a significant overhead" ? This is the normal way to load/store float data to/from SSE registers assuming source/destination is memory (and any other method eventually boils down to this anyway).

这篇关于是否有可能投花车直接__m128，如果他们是16字节的神韵？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！