Architecture of SIMD Type Vector Processor

Abstract

Throughput and performance are the major constraints in designing system level models. As vector processor used deeply pipelined functional unit, the operation on elements of vector was performed concurrently. It means the elements were processed one by one. Improvement can be made in vector processing by incorporating parallelism in execution of these concurrent operations so that these operations can be performed simultaneously. This paper presents a design and implementation of SIMD-Vector processor that implements this parallelism on short vectors having 4 words. The operation on these words is performed simultaneously i.e. the operation on these words is performed in one cycle. This reduces the clock cycles per instruction (CPI). To implement parallelism in vector processing requires parallel issue and execution of vector instructions. Vector processor operates on a vector and superscalar processor issues multiple instructions at a time. This means parallel pipelines are implemented and then made these to support vector data. SIMD-Vector processor will operate on short vector say 4 words vector in a superscalar fashion i.e. 4 words will be fetched at a time and then executed in parallel. This requires redundant functional units e.g. if addition is to be performed on two vectors multiple adders are needed. We have designed the architecture of SIMD type Vector processor. All the designing parameters are explained. KeywordsSIMD type Vector processor, vertical and horizontal parallelism, ILP.

Implementation and Evaluation of SIMD Instructions using RISC-V

“…Additionally, it discusses the drawbacks and advantages of different SIMD processing architectures and provides an overview of the SIMD help framework for off loading multimedia applications. Mohammad Suaib et.al [2] proposed the design and architecture of a SIMD type vector processor, which aims to improve system-level model performance by exploiting data level parallelism (DLP) and instruction level parallelism (ILP). The processor operates on short vectors with 4 words, allowing for concurrent processing of elements in one clock cycle.…”