Author : Aishwarya P. Mhaisekar 1
Date of Publication :7th December 2016
Abstract: As the processor community is trying to approach high performance gain from memory. One approach is to add more memory either cache or primary memory to the chip. Another approach is to increase the level of systems integration. Although integration lowers system costs and communication latency,the overall performance gain to application is again marginal.In general the only way to significantly improve performance is to enhance the processors computational capabilities, this means to increase parallelism. At present only certain forms of parallelisms are being exploited .for ex .can execute four or more instructions per cycle; but in practice, they achieved only one or two because, in addition to the low instruction level parallelism performance suffers when there is little thread level parallelism so, the better solution is to design a processor that can exploit all types of parallelism. Simultaneous multi-threading is processor design that meets these goals. Because it consumes both threads level & instruction level parallelism.
Reference :