Pragmatic approach to systolic design

Limitations of current systolic designs are pointed out and new constraints are imposed to make systolic solutions practical. Matrix multiplication is used as an illustration, and a simple but very high performance systolic architecture, the supercoprocessor for matrix problems (S-MP), which satisfies these constraints is presented. Implementation alternatives for the linear systolic array for matrix-vector multiplication, which forms the core of the S-MP, are also described.