Altera Home Page
文档资料 许可
在线购买 下载

  主页   |   产品   |   支持   |   最终市场   |   技术中心   |   教育与活动   |   公司介绍   |   在线购买  
  器件   |   设计软件   |   IP   |   设计服务   |   开发套件及配件   |   资料  

 IP产品
   嵌入式处理器
   接口与外设
   DSP
          Filtering
          Modulation/Demodulation
          Transforms
          Encryption/Decryption
          Correlation
          Error Detection/Correction
          Video & Image Processing
          Audio Processing
          Arithmetic
          Signal Generation
          Additional Functions
          Consortiums
          资料
   通信
  
 About IP
      运用IP进行设计
      IP认证
      系统设计
      申请IP
  
 IP界合作伙伴
      AMPP计划
      AMPP核合作伙伴
  

Bidimensional DCT/IDCT

from Barco Silex

Request Free Evaluation



AMPP Approved
OpenCore Support
DSP Builder Ready



Features

  • Optimized for APEX 20KC and APEX II architectures
  • Combined fixed-point 2D DCT/IDCT core
  • Row column decomposition method (RCM)
  • Compatible with JPEG, H.263, and MPEG standards
  • IDCT compliant to IEEE 1180-1990 number precision standard
  • 9-bit signed (2's complement) pixel interface
  • 12-bit signed (2's complement) transformed coefficient interface
  • Deeply optimized architecture with small LE count
  • One pixel per clock cycle throughput
  • Continuous pipeline decoding across multiple consecutive blocks until end-of-data signaling
  • Fully synchronous design with single clock
  • Integrated dual-port 64 x 22 synchronous SRAM for block transposition
  • Fully RTL design
  • Simple synchronous strobe-acknowledge pixel and transformed coefficient interfaces
  • End-of-image and end-of-scan support for easy integration in JPEG chains

Block Diagram

Figure 1 shows a block diagram of the megafunction.

Figure 1. Block Diagram

Figure 1. Block Diagram

Description

The bidirectional DCT/IDCT IP core performs high-speed 2D discrete cosine transform and inverse discrete cosine transform, dealing with 9-bit signed pixels and 12-bit signed transformed coefficients. This IP core efficiently decomposes 2D transforms into two consecutive 1D transforms with an effective 1-pixel per clock cycle throughput.

This IP core's internal arithmetic architecture has been tuned to meet the requirements of the IEEE 1180-1990 number precision standard with the smallest core area, allowing you to use this IP core for JPEG, H.263, and MPEG applications. This IP core features 12-bit unsigned cosine coefficients and 22-bit transpose memory.

With its simple synchronous interfaces and 100% synchronous structure, you can integrate this IP core in a complex system with little effort.

Contact Barco Silex for more information.

Device Utilization and Performance

Table 1 lists the typical device utilization results for the megafunction.

Table 1. Typical Device Utilization
Target Device Speed Grade Utilization Performance
(fMAX)
Parameter Setting
Logic Cells ESBs I/O Pins
EP20K200CQ208 -7 3372 2 37 85 MHz Contact Barco Silex
EP2A15F672C -7 3371 2 37 97 MHz Contact Barco Silex
EP1M120F484C -5 3203 2 37 103 MHz Contact Barco Silex

Deliverables

  • Design encrypted files
  • VHDL testbenches
  • Bit-level precise C models for DCT/IDCT functionalities
  • VHDL/Verilog instantiation templates
  • User guide documentation

Contact Information

For additional information, contact Barco Silex at:

Barco Silex
Scientific Park
Rue du Bosquet 7
B-1348 Louvain-la-Neuve
Belgium
Tel: +32 10 486 403
Fax: +32 10 454 636
E-mail: barco-selix@barco.com
URL: www.barco-silex.com

  请填写反馈意见