MMX is a new technology to accelerate multimedia applications on Pentium processors. We report an implementation of IDEA on a Pentium MMX that is $1.65$ times faster than any previously known implementation on the Pentium. By parallelizing four IDEA's we reach an unprecedented $78$ Mbits/s throughput per output block on a 166MHz MMX. In the light of rapidly increasing popularity of multimedia applications, causing more dedicated hardware to be built, and observing that most of the current block ciphers do not benefit from MMX, we raise the problem of designing block ciphers (and encryption modes) fully utilizing the basic operations of multimedia.

. We present a cross-table of almost all publicly known implementations of AES candidates, including the ones done by the authors. A short overview of our own implementations of Rijndael is given. The relative easiness of doing "the world best" implementations and a lot of gaps in the table force us to ask if there is enough information known to really decide which ciphers are fast and which are not. (This paper only compares the encryption speed in the case of the 128-bit keys.) In the conclusions we present a very brief survey of the known attacks to the candidates, stressing the fact that other aspects of the candidates are still less known (at least to the public). We finish this paper with apparent conclusions that the first round of the AES process has been too short, but we still give recommendations which candidates should be elected to the second round basing on the knowledge known to the public at the moment of writing this paper. 1 Introduction The author of th...