Vector access and storage device supporting SIMT in vector processor and control method

Abstract

The invention discloses a vector access and storage device supporting SIMT in a vector processor and a control method. The device comprises a base address vector register unit, an offset vector register unit and a vector address calculation unit; each of the base address vector register unit and the offset vector register unit comprises a plurality of groups of vector registers; each group of vector registers is composed of a plurality of vector registers; the vector address calculation unit comprises a plurality of address calculation subunits; each address calculation subunit is connected with each memory bank in the vector processor correspondingly one to one; each of the base address and the offset address of each thread is obtained by use of one group of the vector registers, and then the base address and the offset address are output to the address calculation subunits for calculation, and the obtained access and storage address of each thread is output to the corresponding memory bank; the method is the control method of the vector access and storage device. The vector access and storage device has the advantages of high vector access and storage flexibility, high parallel access and storage efficiency and low power consumption, and is capable of supporting SIMT thread level parallelism.

Description

technical field [0001] The invention relates to the technical field of microprocessor architecture design, in particular to a vector memory access device and control method supporting SIMT in a vector processor. Background technique [0002] The development of streaming media applications such as wireless communication and image processing requires microprocessors to provide higher real-time computing capabilities under a limited power budget. Single Instruction Multiple Data (SIMD) technology can share hardware because of its Features such as control structures, the ability to exploit massive amounts of data-level parallelism, and computing power that can achieve high data throughput at relatively low power consumption quickly became important extensions of all types of microprocessors. The vector processor integrates a vector processing unit (Vector Processing Units, VPU) and a vector memory access unit VMU. The vector processing unit VPU integrates multiple parallel compu...

AI Technical Summary

Problems solved by technology

However, the current vector memory access operation only provides access to a set of vector data with specific address change rules such as continuous address or equal address stride, which cannot meet the needs of multi-threaded parallel execution of the vector memory unit VPU, so it cannot support SIMT single Instruction stream multiple data stream (Single Instruction Multiple Data, SIMT) vector memory access

Images