Parallel computers processor interconnection

Symmetric multiprocessor A parallel computer with multiple, similar, interconnected processors controlled by a single operating system, and with each processor having equal access to all I/O devices. 

In the distributed memory case, each processor has its own local memory. This collection of independent computers communicates via messages, and is the clearest digital analog of nature s parallel computers discussed in Section III. Each processor-memory pairs forms the basis of a node of the parallel computer. Much computer science research has been done into the appropriate way to interconnect the nodes. Examples include the following ... 

The complexity analysis shows that the load is evenly balanced among processors and therefore we should expect speedup close to P and efficiency close to 100%. There are however few extra terms in the expression of the time complexity (first order terms in TV), that exist because of the need to compute the next available row in the force matrix. These row allocations can be computed ahead of time and this overhead can be minimized. This is done in the next algorithm. Note that, the communication complexity is the worst case for all interconnection topologies, since simple broadcast and gather on distributed memory parallel systems are assumed. 

Hardware. Computers built to work like neural nets are called "parallel processors". A parallel processor uses a large number of small, interconnected processing units rather than a single CPU. Prominent among these is Thinking Machines Corporation s "Connection Machine", which can realize a variety of neural net models. It is programmable in LISP, and is well-suited to database tasks. Hecht-Nielsen produces the ANZA board, a co-processor which allows the PC/AT to emulate a parallel processor. 

The computations were done in parallel on a cheap Beowulf cluster consisting of 8 PCs with the processors AMD Athlon 1.4 GHz, 768 MB RAM. The PCs are interconnected by Fast Ethernet LAN. The results in Table 2 correspond to computations on 3 and 8 PC s from the cluster. 

---