CN108037953A - 一种基于流水线的块浮点模式下的dsp内部架构 - Google Patents

一种基于流水线的块浮点模式下的dsp内部架构 Download PDF

Info

Publication number
CN108037953A
CN108037953A CN201711303004.7A CN201711303004A CN108037953A CN 108037953 A CN108037953 A CN 108037953A CN 201711303004 A CN201711303004 A CN 201711303004A CN 108037953 A CN108037953 A CN 108037953A
Authority
CN
China
Prior art keywords
assembly line
floating point
block floating
pattern based
register group
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711303004.7A
Other languages
English (en)
Inventor
张军
赵汀
方勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Qi Network Network Technology Co Ltd
Original Assignee
Shanghai Qi Network Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Qi Network Network Technology Co Ltd filed Critical Shanghai Qi Network Network Technology Co Ltd
Priority to CN201711303004.7A priority Critical patent/CN108037953A/zh
Publication of CN108037953A publication Critical patent/CN108037953A/zh
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30098Register arrangements
    • G06F9/3012Organisation of register space, e.g. banked or distributed register file
    • G06F9/3013Organisation of register space, e.g. banked or distributed register file according to data content, e.g. floating-point registers, address registers
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline or look ahead

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

本发明公开一种基于流水线的块浮点模式下的DSP内部架构。架构的特征为,先从存储器中读取数据;输入寄存器组,加上控制逻辑;通过流水线移位寄存器组,再加上控制逻辑;输出寄存器组,最后写回到存储器。

Description

一种基于流水线的块浮点模式下的DSP内部架构
技术领域
本发明涉及一种基于流水线的块浮点模式下的DSP内部架构
背景技术
时序电路的速度由任意两个寄存器间、或一个输入与一个寄存器间、或一个寄存器与输出间的路径中最长的路径限定。这个最长的路径可以通过在电路结构中适当插入流水线寄存器来减短。流水线设计是使用寄存器对复杂组合逻辑电路根据期望的关键路径延迟时间进行分割,设计后关键路径延迟缩减,时钟频率提高,吞吐率增加。
作为一种能够提高电路性能的可选方法,可以将流水线型寄存器插入到组合逻辑的关键位置上,将逻辑分割成具有更短路径的群组。这些寄存器的布局是由数据通路的前馈割集所决定的,以保证数据依然是相关的。流水线技术减少了组合逻辑中的级数,缩短了存储元件间的数据通路。
流水线技术是有成本前提的。但对于高端的FPGA的来说,它们具有丰富的寄存器,所以很容易实现流水线结构。流水线技术通过在短时间内计算更小的函数,用空间的复杂度来换取时间的复杂度。这种技术是通过将在一个时间周期完成全部功能所需的逻辑宽度分配到多个短时钟周期上的方法实现的。
采用块浮点算法是将数据分成组,组内的数据相对彼此按比例缩放,但是不能与其他组的成员按相同的比例缩放,即使诸如乘法这样简单的数学运算。在比较复杂的矩阵求逆情况中,分组之间需要比较复杂的数学运算,就必须采用块浮点处理器。
块浮点量化算法基于的事实是在一个小的时间间隔上,数据的熵要低于整个数据集的熵。块浮点量化器是一个接收模数转换器的输出数据流,并将采样数据统一量化为原始数据的一种有效表示形式的设备,在量化过程中只要求比特数小于样本数。
FPGA中最重要的资源就是DSP。FPGA对传统的通信、图像信号处理做了非常多的适配,早期的硬件架构已经能够完美配合这类算法。设计人员只需要简单研究DSP的结构就很容易发现:DSP与算法是完全匹配的。
本发明提供了一种基于流水线的块浮点模式下的DSP内部架构。架构的特征为,先从存储器中读取数据;输入寄存器组,加上控制逻辑;通过流水线移位寄存器组,再加上控制逻辑;输出寄存器组,最后写回到存储器。
发明内容
本发明的目的在于提供一种基于流水线的块浮点模式下的DSP内部架构。本发明包括以下特征:
发明技术方案
1.一种基于流水线的块浮点模式下的DSP内部架构,架构的特征:
1)先从存储器中读取数据;
2)输入寄存器组,加上控制逻辑;
3)通过流水线移位寄存器组,再加上控制逻辑;
4)输出寄存器组,最后写回到存储器。
附图说明
附图1是基于流水线的块浮点模式下的DSP内部架构图。
具体实施方式
这种基于流水线的块浮点模式下的DSP内部架构,包括如下步骤特征:
1)先从存储器中读取数据;
2)输入寄存器组,加上控制逻辑;
3)通过流水线移位寄存器组,再加上控制逻辑;
4)输出寄存器组,最后写回到存储器。

Claims (1)

1.一种基于流水线的块浮点模式下的DSP内部架构,架构的特征:
1)先从存储器中读取数据;
2)输入寄存器组,加上控制逻辑;
3)通过流水线移位寄存器组,再加上控制逻辑;
4)输出寄存器组,最后写回到存储器。
CN201711303004.7A 2017-12-11 2017-12-11 一种基于流水线的块浮点模式下的dsp内部架构 Pending CN108037953A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711303004.7A CN108037953A (zh) 2017-12-11 2017-12-11 一种基于流水线的块浮点模式下的dsp内部架构

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711303004.7A CN108037953A (zh) 2017-12-11 2017-12-11 一种基于流水线的块浮点模式下的dsp内部架构

Publications (1)

Publication Number Publication Date
CN108037953A true CN108037953A (zh) 2018-05-15

Family

ID=62102113

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711303004.7A Pending CN108037953A (zh) 2017-12-11 2017-12-11 一种基于流水线的块浮点模式下的dsp内部架构

Country Status (1)

Country Link
CN (1) CN108037953A (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107894966A (zh) * 2017-12-11 2018-04-10 上海齐网网络科技有限公司 一种基于流水线的块浮点模式下的fft处理器引擎原型

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101720025A (zh) * 2009-12-07 2010-06-02 上海电器科学研究所(集团)有限公司 高性能水上无人巡查装置的水域无线图传系统
CN101776752A (zh) * 2010-01-29 2010-07-14 中国科学院空间科学与应用研究中心 机群链路高动态信号的精密跟踪与测量方法
CN101908134A (zh) * 2010-06-01 2010-12-08 福建新大陆电脑股份有限公司 一种串行总线式条码解码芯片以及条码解码装置
CN102629191A (zh) * 2011-04-25 2012-08-08 中国电子科技集团公司第三十八研究所 数字信号处理器寻址方法
CN105718242A (zh) * 2016-01-15 2016-06-29 中国人民解放军国防科学技术大学 多核dsp中支持软硬件数据一致性的处理方法及系统
CN107894966A (zh) * 2017-12-11 2018-04-10 上海齐网网络科技有限公司 一种基于流水线的块浮点模式下的fft处理器引擎原型

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101720025A (zh) * 2009-12-07 2010-06-02 上海电器科学研究所(集团)有限公司 高性能水上无人巡查装置的水域无线图传系统
CN101776752A (zh) * 2010-01-29 2010-07-14 中国科学院空间科学与应用研究中心 机群链路高动态信号的精密跟踪与测量方法
CN101908134A (zh) * 2010-06-01 2010-12-08 福建新大陆电脑股份有限公司 一种串行总线式条码解码芯片以及条码解码装置
CN102629191A (zh) * 2011-04-25 2012-08-08 中国电子科技集团公司第三十八研究所 数字信号处理器寻址方法
CN105718242A (zh) * 2016-01-15 2016-06-29 中国人民解放军国防科学技术大学 多核dsp中支持软硬件数据一致性的处理方法及系统
CN107894966A (zh) * 2017-12-11 2018-04-10 上海齐网网络科技有限公司 一种基于流水线的块浮点模式下的fft处理器引擎原型

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107894966A (zh) * 2017-12-11 2018-04-10 上海齐网网络科技有限公司 一种基于流水线的块浮点模式下的fft处理器引擎原型

Similar Documents

Publication Publication Date Title
Garrido et al. Optimum circuits for bit reversal
US10275219B2 (en) Bit-serial multiplier for FPGA applications
Wang et al. Design, evaluation and fault-tolerance analysis of stochastic FIR filters
Choi et al. Energy-efficient design of processing element for convolutional neural network
Chen et al. A low-power architecture for the design of a one-dimensional median filter
WO2006109240A2 (en) Fast fourier transform architecture
Turaka Low power VLSI implementation of real fast Fourier transform with DRAM-VM-CLA
Dixit et al. IIR filters using Xilinx System Generator for FPGA implementation
CN108037953A (zh) 一种基于流水线的块浮点模式下的dsp内部架构
Roncella et al. 70-MHz 2-mu m CMOS bit-level systolic array median filter
CN107894966A (zh) 一种基于流水线的块浮点模式下的fft处理器引擎原型
US9787290B2 (en) Resource-saving circuit structures for deeply pipelined systolic finite impulse response filters
García et al. FPGA realization of a Split Radix FFT processor
Mukherjee et al. A novel architecture of area efficient FFT algorithm for FPGA implementation
Subathradevi et al. Delay optimized novel architecture of FIR filter using clustered-retimed MAC unit Cell for DSP applications
Shinde et al. High‐throughput and compact reconfigurable architectures for recursive filters
Hazarika et al. Energy efficient VLSI architecture of real‐valued serial pipelined FFT
US7007059B1 (en) Fast pipelined adder/subtractor using increment/decrement function with reduced register utilization
US10410700B1 (en) Systems and method for a low-power correlator architecture using shifting coefficients
Sato et al. A Logic Block for Wave-Pipelining
Le Thanh et al. Power consumption improvements in aes decryption based on null convention logic
Savich et al. A Low‐Power Scalable Stream Compute Accelerator for General Matrix Multiply (GEMM)
Roy Digital System Design Examples
Saranya et al. FPGA synthesis of reconfigurable modules for FIR filter
Pritha et al. Enhancing the Efficiency of Wallace Tree Multipliers Through Optimized ECSLA Design

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20180515

WD01 Invention patent application deemed withdrawn after publication