可重构视频阵列处理器测试平台设计与实现

针对可重构视频阵列处理器的设计要求及传统测试方法测试视频编解码系统时速度慢、精度低和可观测性不强的问题。开发了基于Qt的用户界面,设计实现了以现场可编程门阵列(Field programmable gate-array,FPGA)为核心的软硬件协同测试平台。在PC端实现以软件仿真为基础的数据传输与图像重现,在FPGA端实现以可重构视频阵列处理器为基础的视频编解码算法并行映射。实验结果表明,在工作频率为100 MHz时,FPGA与PC之间可正确传输数据并满足算法测试时不同测试用例的更换需求,具有较好的可观测性。     

阵列处理器分布式存储的簇内全访问结构设计

采用分布式存储结构来解决阵列处理器片内访问延迟等"存储墙"问题已经成为研究主流。针对阵列处理器中分布式存储簇内互连问题,设计了一种电路结构简单、使用效率高和延迟低的簇内全访问电路结构,实现了簇内16个处理单元对存储单元的并行访问。实验结果表明,在无冲突情况下,最高频率达223 MHz,访问峰值带宽可达7.42 GB/S.测试结果表明,相比于行列交叉互连结构,全访问结构具有更小的访问延迟。通过对256×256和512×512边缘检测canny算法在该结构上进行并行化实现和性能比较发现,相比于CPU+GPU结构的处理时间,加速比分别提升了2.84倍和2.91倍。     

Design and implementation of instruction-driven and data-driven self-reconfigurable cell array

The reconfigurable chip, which integrates the advantages of high performance, high flexibility,high parallelism, low power consumption, and low cost, has achieved rapid development and wide application. Generally, the control part and the computing part of algorithm is accelerated based on different reconfigurable architectures, but it is difficult to obtain overall performance improvement.For improving efficiency of reconfigurable structure both for the control part and the computing part,a hyb...