Very long instruction work architectures and the ELI-512
Joseph A. Fisher · 1998
By compiling ordinary scientific applications programs with a radical technique called trace scheduling, we are generating code for a parallel machine that will run these programs faster than an equivalent sequential machine -we expect 10 to 30 times faster.Trace scheduling generates code for machines called Very Long Instruction Word architectures.In Very Long Instruction Word machines, many statically scheduled, tightly coupled, fintgrained operations execute in parallel within a single instruction stream.VUWs are more parallel extensions of several current architectures.