Justin Stoecker

The UMul instruction, in particular, is useful for implementing the [Philox-4x32 ](http://www.thesalmons.org/john/random123/papers/random123sc11.pdf) pseudorandom number generator. This is one of the fastest PRNGs available for GPUs, since it is non-sequential, and...

The UMul instruction, in particular, is useful for implementing the [Philox-4x32 ](http://www.thesalmons.org/john/random123/papers/random123sc11.pdf) pseudorandom number generator. This is one of the fastest PRNGs available for GPUs, since it is non-sequential, and...