Yep... you can check the actual temp in linux with lmsensors, or
otherwise remotely through the xport using roach_monitor.py. If
they're in an air-conditioned room, it _should_ be fine.
The PAPER ROACH PPCs have run at 60degC for extended periods without
trouble, but much above that and I've seen them crash or hang. We've
started sticking heatsinks onto some of our PPC boards here at KAT
just to be safe. But the PPC's DIMM makes creating laminar airflow
over the PPC really hard, so cooling is difficult. ROACH-II will not
have a DIMM for the PPC (memory will be onboard) which solves a few
other problems and should significantly help with the cooling of this
part.
Jason
On 29 Apr 2010, at 07:48, Aaron Parsons wrote:
On a semi-related note, I've notice the CPU running pretty hot when I
read data fast from the FPGA and make packets out of it. Do we need
heatsinks for the CPU?
On Wed, Apr 28, 2010 at 10:44 PM, Jason Manley
<[email protected]> wrote:
ROACH bus runs at 66MHz (or 83MHz if you "overclock" it to boot
config H). I
agree that the 3.5MB/s is miserable performance considering what it
should
be capable of achieving. I suspect these bottlenecks are mostly BORPH
related. I also recall an extended bus handshake being mentioned
for every
bus transaction. Dave G, Marc or Shanly might be able to comment
further. I
believe Shanly has been working on some optimisation in BORPH.
Dave, what
speeds can you get through uboot? Is there room for optimisation
here? I
would also welcome a speedup.
Jason
On 28 Apr 2010, at 20:11, David MacMahon wrote:
Hi, Mel,
On Apr 28, 2010, at 9:54 , melvyn wright wrote:
You should be getting around 7MegaBytes/s across that bus.
56 Mb / 16 b < 4 MHz << bus clock frequency
Good suggestion re kernel, but don't understand the significance
of the
56 Mb
I omitted the "/s" in "56 Mb/s". 7 megabytes/s == 56 Megabits/s.
Since
the bus to the FPGA is 16 bits wide, dividing by 16 gives the
number of 16
bit words transferred per second as around 3.5 million. I don't
know the
frequency at which the bus runs, but I suspect it is far greater
than 3.5
MHz hence my comment about room for improvement.
Dave
P.S. I don't know how conventional or official it is, but I use
lowercase
'b' for "bit" and uppercase 'B' for "byte".
--
Aaron Parsons
510-406-4322 (cell)
Campbell Hall 523, UCB
