ROACH2's PHY is different. It's now Marvel (as opposed to a National Semi on
ROACH1). It works reliably at 1Gbps.
I bank on 10Mb/s on ROACH1, which is achievable using the normal katcp and
tcpborphserver2 without any trickery. You can get better if you write your own
PPC code.
ROACH2 should
Hi, Jason,
Why only a factor of 2 faster instead of a factor of 10? What is the limiting
factor other than ethernet speed?
10 Mbps throughput over a 100 Mbps link (10% efficiency) seems not so great but
understandable/acceptable.
20 Mbps throughput over a 1,000 Mbps link (2% efficiency)
hi dave,
the PPC ethernet bottleneck is in the PPC code needed
to read data from the FPGA, format the data,
and write it to the ethernet port
.
if you spend work at optimizing your code,
you can get a higher data rate.
dan
On Mon, Apr 29, 2013 at 8:35 AM, David MacMahon
casper workshop info from Ben Stappers:
Dear Colleagues,
It is a pleasure to inform you that registration is now open for the
CASPER collaboration workshop in Manchester which will take place from
September 2nd-6th 2013 at Jodrell Bank Observatory.
To register for the meeting please follow the
4 matches
Mail list logo
