Fastest way to do horizontal SSE vector sum (or other reduction)

Question

Given a vector of three (or four) floats. What is the fastest way to sum them?

Is SSE (movaps, shuffle, add, movd) always faster than x87? Are the horizontal-add ins

Answer 1

I would definitely give SSE 4.2 a try. If you are doing this multiple times (I assume you are if performance is an issue), you can pre-load a register with (1,1,1,1), and then do several dot4(my_vec(s), one_vec) on it. Yes, it does a superfluous multiply, but those are fairly cheap these days and such an op is likely to be dominated by the horizontal dependencies, which may be more optimized in the new SSE dot product function. You should test to see if it outperforms the double horizontal add Paul R posted.

I also suggest comparing it to straight scalar (or scalar SSE) code - strangely enough it is often faster (usually because internally it is serialized but tightly pipelined using register bypass, where special horizontal instructions may not be fast pathed (yet)) unless you are running SIMT-like code, which it sounds like you are not (otherwise you would do four dot products).