Since the 1960s, the general-purpose processor (also known as the central processing unit or CPU) has served as the brains in computing instruments. For example, each of the 1,100 compute nodes in Virginia Tech's System X supercomputer has a pair of homogeneous brains, i.e., two 2.3-GHz PowerPC 970FX CPUs. Recent trends, however, have exposed the CPU as a "jack of all (computing) trades, master of none." To address this, heterogeneous computing systems with multiple types of brains have emerged to herald a new age in supercomputing. Building on our expertise in this area at Virginia Tech, we seek to tackle all aspects of accelerator-based parallel computing from systems software to middleware and libraries to applications.