On further investigation, I see that the big problem with trying to build
a
board with ADC to PCIe x16 is the lack of a suitable FPGA to do the PCI
end. The
lowest-cost FPGA from Xilinx that will handle x8 PCIe costs $3000.
Methinks that the FPGA makers don't want us building boards that
Hi David,
I agree, this would be very interesting to have in hand. I had previously asked
Steve Ord about sampler cards for PCIe transfer, to mate with our GPU X-engine
and learned the following:
Quote from Steve (option 1):
http://www.edt.com/drx16.html
But it will only give you 2
CASPERites,
I had a crazy idea the other day, and wanted to see if it's crazy enough. Hence,
I post it here.
The idea is to build a spectrometer using off-the-shelf PC hardware, with only a
custom data acquisition board. All the DSP would be done by the PC.
The NVidia Tesla GPU board is no
hi david,
there are a few casper instruments that are similar to what you are
suggesting.
1) some of the VEGAS spectrometer modes use a roach to digitize the data and
send almost raw adc samples to a GPU where the spectroscopy is done.
2) some of the GUPPI pulsar machines use casper hardware to
Hi David,
Its not a crazy idea at all! :) In FY11 I was involved in a project to
identify the right software+hardware for doing something very similar, and
we published some results [1]. Moving further, we have proposed a project
to integrate Simulink, Modelica, and GNU Radio with this
I think it is entirely possible, depending on your need for sample rate
(bandwidth) and the rest of the application. At NRAO, we're using the
FPGA/digitizer as a front end to compute nodes as Dan mentioned. Right
now, we can't do a dual channel 2.5 Gs/s 16k channel spectrometer in a PC.
The
6 matches
Mail list logo