Store Buffers : implementing single cycle store instructions in write-through, write-back and set associative caches

Abstract

This thesis proposes a new mechanism, called Store Buffers, for implementing single cycle store instructions in a pipelined processor. Single cycle store instructions are difficult to implement because in most cases the tag check must be performed before the data can be written into the data cache. Store buffers allow a store instruction to read the cache tag as it. passes through the pipe while keeping the store instruction data buffered in a backup register until the data cache is free. This strategy guarantees single cycle store execution without increasing the hit access time or degrading the performance of the data cache for simple direct-mapped caches, as well as for more complex set associative and write-back caches. As larger caches are incorporated on-chip, the speed of store instructions becomes an increasingly important part of the overall performance. The first part of the thesis describes the design and implementation of store buffers in write through, write-back, direct-mapped and set associative caches. The second part describes the implementation and simulation of store buffers in a 6-stage pipeline with a direct mapped write-through pipelined cache. The performance of this method is compared to other cache write techniques. Preliminary results show that store buffers perform better than other store strategies under high IO latencies and cache thrashing. With as few as three buffers, they significantly reduce the number of cycles per instruction.