In this paper, we present the design and implementation of a BRAM-based multiported register file with arbitrary number of read and write ports. In order to avoid the conflicts associated with write ports, we present a register renaming technique that is applied between the compi
...
In this paper, we present the design and implementation of a BRAM-based multiported register file with arbitrary number of read and write ports. In order to avoid the conflicts associated with write ports, we present a register renaming technique that is applied between the compiler and the assembler. This technique enables the utilization of a banked-BRAM register file as a true multiported register file. The advantage is that we do not need to modify the compiler nor the assembler and the technique is scalable. A register file with the register renaming technique has the highest performance, requires fewer resources and consumes less power compared to other approaches. As a case study, we applied our technique to the configurable open-source ρ-VEX VLIW processor. We implemented a 64 × 32-bit, 4-write and 8-read ports register file utilizing BRAMs for a 4-issue ρ-VEX processor. This register file with register renaming saves 9109 Xilinx Virtex-4 FPGA slices by just utilizing 32 BRAMs compared to a pure slice-based register file with no effect on the overall frequency of the processor as well as the cycle count for any application.@en
