Instruction Format Based Selective Execution for Register Port Complexity Reduction in High-Performance Processors

Abstract

As the width of the processor grows, complexity of a register file (RF) with multiple ports grows more than linearly and leads to larger register access time and higher power consumption. Analysis of characteristics of the Spec2000 benchmark programs when run in an 8-wide processor reveals that only two or less two-source instructions (that require both source registers) are executed in a cycle for a significant portion of total execution time (more than 98% time for Spec2000 integer and 93% time for Spec2000 floating-point). Thus the analysis observes that the register port bandwidth is highly underutilized for a significant portion of time in general purpose computing. In this paper, we propose a novel technique to significantly reduce the number of register ports with a very minor modification in the select logic to issue only a limited number of two-source instructions. This is achieved with no significant impact on processor’s performance. The novelty of the technique is that it is easy to implement and succeeds in reducing the access time, power, and area of the register file, without shifting burden, in terms of these factors, to any other logic on the chip. With this technique in an 8-wide processor, as compared to a conventional 128-entry RF with 16 read ports, for Spec2000 integer programs a register file can be designed with 11 or 10 read ports as these configurations result in instructions per cycle (IPC) degradation of only 0.929% and 3.38%, respectively. This significantly low degradation in IPC is achieved while reducing the register access time by 9% and 12%, respectively, and reducing power by 35% and 50%, respectively. For Spec2000 floating-point programs, a register file can be designed with 12 read ports (1.16% IPC loss, 8% less access time, and 28% less power) or with 11 read ports (3.5% IPC loss, 9% less access time, and 35%less power). The paper analyzes the performance of all the possible flavors of the proposed technique for register file in both 4- wide and 8-wide processors, and presents a choice of the performance and register port complexity combination to the designer.