VMETRO MFC700 Board Features Xilinx Virtex-5 FPGAs

Posted by Ken Cheung in FPGA-based Product on Wednesday, September 24, 2008

The VMETRO MFC700 is a 6U VPX-REDI buffer memory node with support for up to 16GB of memory on the baseboard, dual XMC mezzanine sites and support for Serial RapidIO[tm] (sRIO) fabric. It is industry's largest capacity 6U VPX buffer memory board. Designed for applications that buffer large amount of high-speed data, the MFC700 is ideal for signal and image processing applications and data recording subsystems. Uses of buffer memory include high-speed temporary storage, interleaving, data aggregation and warehousing or the need for additional system memory through a fabric.

VMETRO MFC700 6U VPX Buffer Memory Board Block Diagram

VMETRO MFC700 Features

  • Up to 32GB DDR2 memory in a single slot (4-16GB baseboard, with two 2-8GB XMC Mezzanine sites)
  • Four x4 high-speed Serial RapidIO]TM] links to the P1 VPX connector and low-speed I/Os to the backplane
  • On-board 8 port Serial RapidIO switch
  • Dual Xilinx® Virtex®-5 FPGA memory controllers
  • DDR2 SDRAM with ECC
  • Additional RocketIO connections between FPGAs and the backplane
  • System Control Node FPGA
  • Air and conduction cooled options

The MFC700 supports up to 32GB DDR2 SDRAM memory in a single slot with 4-16GB on the MFC700 and two 2-8GB on VMETRO MM-6171 buffer memory node XMC modules. The board supports four x4 high-speed Serial RapidIO links to the VPX P1 connector via an 8-port Serial RapidIO switch and additional I/Os to the backplane. Dual Xilinx® Virtex®-5 FPGAs serve as the memory controllers for the DDR2 SDRAM with ECC memory. The MFC700 provides additional RocketIO[tm] connections between FPGAs and the backplane to give developers flexibility and performance in their data movement. The MPC700 also includes advanced, corner-turning DMA engines which are especially useful in matrix transposition, where converting from columns to rows can eliminate significant processor overhead.

In addition to supporting high-throughput backplane I/O, data may be brought into the MFC700 via onboard XMC sites. With dual XMC sites, the MFC700 enables I/O to be tightly coupled with a large system memory resource. This is useful for what is referred to as rate buffering of high throughput data (i.e., controlling the rate of flow of data through a system). incoming data from an XMC can be temporarily stored on the MFC700 and then passed to processing or recording nodes at a rate that does not overrun their capabilities.

The MFC700 supports VxWorks and Linux. An API is provided for integration with other boards. The MFC700 is a VPX-REDI compliant with 1" pitch and is available in both air and conduction cooled versions. Boards are available 8-12 weeks ARO.

More information: MFC700

If you found this page useful, bookmark and share it on:

Possibly of Interest

 
FPGA Blog Newsletter
Don't have time to visit FPGA Blog everyday? Then sign up for our free newsletter. We'll send you an email when we have something to share with you. Your email address will be kept confidential and we will not share, sell, or rent it to anyone. You can unsubscribe at any time by clicking a link in the email.

Enter your email address to sign up for our free newsletter:   

If you are familiar with RSS feeds, you can also sign up for our free blog feed. Our RSS feed is updated in real-time while our newsletter is updated daily.