lekernel changed the topic of #m-labs to: Mixxeo, Migen, MiSoC & other M-Labs projects :: fka #milkymist :: Logs http://irclog.whitequark.org/m-labs
aeris has quit [Ping timeout: 264 seconds]
FabM has quit [Ping timeout: 264 seconds]
larsc has quit [Ping timeout: 264 seconds]
aeris has joined #m-labs
FabM has joined #m-labs
larsc has joined #m-labs
mithro has joined #m-labs
cfelton has joined #m-labs
cfelton has quit [Read error: Connection reset by peer]
_whitelogger_ has joined #m-labs
cfelton has joined #m-labs
fengling__ has joined #m-labs
uhhimhere has joined #m-labs
<uhhimhere> so is m-labs associated with sebastien bordeaxducq
sb0 has joined #m-labs
<uhhimhere> ^
<sb0> uhhimhere, yes. why?
<uhhimhere> is he based in hong kong?
<sb0> that's me, and yes
<uhhimhere> oh ok
<uhhimhere> how did you end up in HK
<uhhimhere> anyways better question, how plausible is it for the milkymist board to run as a gfx card on a PC
<sb0> that will be a lot of work, and it'll be slower than current GPUs
<uhhimhere> is the milkymist SoC only a GPU implementation
<sb0> no, there's a cpu, memory controller, ethernet, audio, etc.
<uhhimhere> have you run any benchmarks on it? phoronix test suite comes to mind
<uhhimhere> would be nice to see how it compares to mainstream SoCs
<uhhimhere> would you think of getting a chinese manufacturer to implement them on SoCs to lower the price and sell the boxes at higher volume
<sb0> not for this reason, but cheap ASICs sound interesting. do you know any manufacturer?
xiangfu has joined #m-labs
<uhhimhere> well if there is no demand on the boxes there wont be a market for the ASICs
<uhhimhere> unless you find another application for the SoC
<uhhimhere> you are in HK, im pretty sure theres a bunch of contacts in the phonebook; but its good to know youre interested
<uhhimhere> so is it possible to run phoronix's test suite on the box
<sb0> it'd take a few years of work and hundreds of k€ to get it to run at acceptable speeds, only so that some cheap bastard can point out that the latest raspberry pi is 20% faster. no, thanks.
_whitelogger_ has joined #m-labs
<uhhimhere> well its just to put the machine out there thats all
<uhhimhere> not to compete or anything
<uhhimhere> sooner or later someone else will come and pick it up and make some improvements
<uhhimhere> etc etc
<uhhimhere> plus you dont have to pay licensing and royalties for your SoC do you
<uhhimhere> unlike MIPS/ARM
<uhhimhere> ok well
<uhhimhere> good luck hope to see the box in affordable form in the future and hope that some kind of open SoC (non fpga) comes out of it
uhhimhere has quit [Read error: No route to host]
_whitelogger_ has quit [Excess Flood]
_whitelogger_ has joined #m-labs
<GitHub81> [artiq] sbourdeauducq pushed 3 new commits to master: http://git.io/Di1xhw
<GitHub81> artiq/master 4160d24 Sebastien Bourdeauducq: management/sync_struct: export process_mod function
<GitHub81> artiq/master ebdd92c Sebastien Bourdeauducq: management/sync_struct: always publish with root notifier
<GitHub81> artiq/master c0bdc92 Sebastien Bourdeauducq: master: broadcast realtime results
uhhimhere has joined #m-labs
<uhhimhere> sb0: just wondering by the way, where are the CAD files for the board?
<GitHub191> [artiq] sbourdeauducq pushed 1 new commit to master: http://git.io/DRyhHw
<GitHub191> artiq/master 070788a Sebastien Bourdeauducq: separate master modules
_whitelogger_ has joined #m-labs
<uhhimhere> sb0: so do you plan on addressing more applications other than the ILM scene
xiangfu has quit [Ping timeout: 244 seconds]
xiangfu has joined #m-labs
mumptai has joined #m-labs
mumptai has quit [Remote host closed the connection]
mithro has quit [Read error: Connection reset by peer]
mithro has joined #m-labs
<uhhimhere> sb0: can the fpga on the milky board be reprogrammed
xiangfu has quit [Read error: Connection reset by peer]
xiangfu has joined #m-labs
Bertl is now known as Bertl_zZ
<ysionneau> 09:35 < uhhimhere> sb0: can the fpga on the milky board be reprogrammed < yes, either by programming the flash chip, or via jtag
xiangfu has quit [Remote host closed the connection]
fengling__ has quit [Ping timeout: 244 seconds]
stekern has quit [Ping timeout: 245 seconds]
<uhhimhere> ysionneau: is latticemicro scalable?
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 245 seconds]
<ysionneau> uhhimhere: what do you mean by scalable ?
<larsc> ultra-scalable
<ysionneau> superscalar?
<ysionneau> the pipeline only fetch one instruction at a time
<aeris> ultrascalable : manycore superscalar architecture ? :p
<larsc> ysionneau: that's the implementation ;)
<ysionneau> yes I guess you could implement a dual issue one
<ysionneau> or multi issue
<ysionneau> you could even make an out of order one maybe, but it will be tricky to respect the location of exception raising
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 244 seconds]
_florent_ has joined #m-labs
stekern has joined #m-labs
<GitHub120> [artiq] sbourdeauducq pushed 2 new commits to master: http://git.io/dfWbHw
<GitHub120> artiq/master 33283fe Sebastien Bourdeauducq: sync_struct: pass mod to notify callback
<GitHub120> artiq/master 95ee6a4 Sebastien Bourdeauducq: gui: beginning of realtime plotting
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 264 seconds]
sb0 has quit [Quit: Leaving]
Bertl_zZ is now known as Bertl
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 245 seconds]
mumptai has joined #m-labs
fengling__ has joined #m-labs
Bertl is now known as Bertl_oO
fengling__ has quit [Ping timeout: 272 seconds]
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 265 seconds]
_florent_ has quit [Ping timeout: 252 seconds]
_florent_ has joined #m-labs
fengling__ has joined #m-labs
Bertl_oO is now known as Bertl
fengling__ has quit [Ping timeout: 264 seconds]
Bertl is now known as Bertl_zZ
mumptai has quit [Remote host closed the connection]
fengling__ has joined #m-labs
fengling__ has quit [Ping timeout: 245 seconds]
_florent_ has quit [Quit: Leaving]