Published on *freevec.org* (http://www.freevec.org)

Submitted by markos on Mon, 28/10/2013 - 01:48

This paper is hosted here actually! First version was using drutex-rendered of LaTeX excerpts of the original paper, today I'm using MathJax, much better. I wrote this paper when I was attempting to optimize MySQL with Altivec as part of a Genesi project, unfortunately it didn't amount to much in terms of accelerating MySQL, but I did invent an algorithm to vectorize a whole certain family of hashing functions.

The result was this paper [2]

Tags:

Submitted by markos on Mon, 25/06/2007 - 21:26

Hashing a piece of data is one of the most time consuming process in a a database. Basically, the process builds a unique integer (aka 'hash key') from a series of operations on the objects bytes. Usually these algorithms are not parallelizable, or at least not easily parallelizable, due to the dependency to previous calculations involved. Taking a single family of hashing algorithms, we will provide (with mathematical proof) a second deterministic way of calculating the Nth hash, using easily parallelizable tecniques and also provide the Altivec equivalent of this algorithm.

Tags:

**Links**

[1] http://www.freevec.org/content/paper_altivec_vectorization_hashing_algorithms_2007

[2] http://www.freevec.org/node/78

[3] http://www.freevec.org/category/simd/architecture/altivec

[4] http://www.freevec.org/category/simd/algorithms/hashing

[5] http://www.freevec.org/category/simd/algorithms

[6] http://www.freevec.org/content/altivec_vectorization_hashing_algorithms