asper has quit [Ping timeout: 260 seconds]
asper has joined #m-labs
mumptai has quit [Remote host closed the connection]
xiangfu has quit [Ping timeout: 272 seconds]
JewFro297 has quit [Ping timeout: 272 seconds]
Alarm has quit [Quit: ChatZilla 0.9.90.1 [Firefox 26.0/20131205075310]]
xiangfu has joined #m-labs
xiangfu has quit [Quit: leaving]
xiangfu has joined #m-labs
Alarm has joined #m-labs
sb0 has joined #m-labs
kyak has joined #m-labs
Alarm has quit [Ping timeout: 260 seconds]
mrueg_ has joined #m-labs
gric_ has joined #m-labs
os1r1s_ has joined #m-labs
balrog has quit [Ping timeout: 272 seconds]
gric has quit [Ping timeout: 272 seconds]
mrueg has quit [Ping timeout: 272 seconds]
os1r1s has quit [Ping timeout: 272 seconds]
balrog_ has joined #m-labs
os1r1s_ is now known as os1r1s
balrog_ is now known as balrog
mrueg_ has quit [Changing host]
mrueg_ has joined #m-labs
sb0 has quit [Read error: Connection reset by peer]
sb0 has joined #m-labs
JewFro297 has joined #m-labs
mumptai has joined #m-labs
Alarm has joined #m-labs
Alarm has quit [Remote host closed the connection]
godkiefka has joined #m-labs
paraboloid has joined #m-labs
godkiefka has quit [Read error: Connection reset by peer]
paraboloid has quit [Remote host closed the connection]
windlove has joined #m-labs
windlove has quit [Remote host closed the connection]
<
JewFro297>
So, does Wishbone interconnect allow for data transfer from different clock domains?
sb0 has quit [Ping timeout: 246 seconds]
sb0 has joined #m-labs
<
sb0>
JewFro297, wishbone itself no; but you can have two wishbone buses, one in each clock domain, and have some bridge core between the two
larsc has quit [Remote host closed the connection]
larsc has joined #m-labs
<
mumptai>
is there actually a bus with built-in clock-domain crossing?
<
larsc>
depends on what you mean by built-in
<
larsc>
AXI works fine if you add a fifo on the bus for domain crossing
<
larsc>
or whatever else
<
larsc>
you want to use for domain crossing
<
larsc>
it's basically message based and the messages only ever travel in one direction
<
larsc>
so when you want to cross clock domains you can use your faviourite clock-domain crossing method
<
larsc>
so in a sense there is no built-in support for it, since it doesn't require anything special
<
mumptai>
mhmm, arbittration gotta be more tricky with it ;)
<
larsc>
it's super easy ;)
<
mumptai>
wasn't it capable of out-of-order transfers?
* mumptai
has to read overview & introduction again
<
larsc>
axi3 was, but this was dropped for axi4
azonenberg has quit [Read error: Connection reset by peer]
azonenberg has joined #m-labs
<
mumptai>
so, the default implementation is buffered cross-bar, with optional cd-crossing in the buffers?
<
larsc>
I don't think there is a default implementation
<
larsc>
but yea, that sounds about right for a typical implementation
<
larsc>
you don't need the buffers though if you don't care about throughput
<
mumptai>
you can always choose the buffer implementation, per port ;)
xiangfu has quit [Ping timeout: 260 seconds]
xiangfu has joined #m-labs
<
kristianpaul>
ahmm, axi is amba, tought was something from opencores :|
<
larsc>
well it's royalty free and the specification is available
<
mumptai>
but no bfm and references?
sb0 has quit [Quit: Leaving]
mumptai has quit [Quit: Verlassend]