吴虎成, 刘洋徐瑞, 刘建平. 高性能SIMD乘法阵列体系结构[J]. 微电子学与计算机, 2014, 31(3): 9-13.
引用本文: 吴虎成, 刘洋徐瑞, 刘建平. 高性能SIMD乘法阵列体系结构[J]. 微电子学与计算机, 2014, 31(3): 9-13.
WU Hu-cheng, LIU Yang-xu-rui, LIU Jian-ping. Architecture of a High Performance SIMD Multiplication Array[J]. Microelectronics & Computer, 2014, 31(3): 9-13.
Citation: WU Hu-cheng, LIU Yang-xu-rui, LIU Jian-ping. Architecture of a High Performance SIMD Multiplication Array[J]. Microelectronics & Computer, 2014, 31(3): 9-13.

高性能SIMD乘法阵列体系结构

Architecture of a High Performance SIMD Multiplication Array

  • 摘要: 描述了一种新型的高性能高能效SIMD乘法阵列的结构.该乘法阵列支持同时执行1个64位乘法,4个32位乘法或16个16位有符号/无符号乘法.通过修改乘法算法实现结构,提高了乘加单元的面积复用度,在较小的面积和性能开销下实现了上述功能.并引入了“溢出补偿技术”解决了复数矩阵乘法运算的判溢出问题.通过牺牲非关键路径上短位宽乘法性能,提高关键路径上高位宽乘法性能.所述结构与文献1中乘法簇结构相比,64位乘法延时减少3.65%,面积降低3.92%,功耗提高5.71%.

     

    Abstract: This paper presents a 64-bit fixed-point SIMD multiplication array.This array has capable of supporting one 64 × 64,four 32 × 32 or sixteen 16 × 16 bit signed/unsigned.The component is used more efficient with multiplication cell array.Implement all above function with a small increase in delay and area.An algorithmof"overflow compensate" is introduced,which solve the overflow judgment in fixed-point complex multiplication.The synthesize result shows that the multiplication reduces the 64 bit multiplication's critical path by 3.65%,reduces the area by 3.92% and increases the power consumption by 5.71%.

     

/

返回文章
返回