kiwichris has quit [Quit: This computer has gone to sleep]
kiwichris has joined #milkymist
kiwichris has quit [Quit: This computer has gone to sleep]
kiwichris has joined #milkymist
aeris has joined #milkymist
mumptai has joined #milkymist
Martoni has joined #milkymist
xiangfu has quit [Ping timeout: 246 seconds]
xiangfu has joined #milkymist
bhamilton has joined #milkymist
fsk has joined #milkymist
lekernel has joined #milkymist
Thorn has quit [Read error: No route to host]
Thorn has joined #milkymist
Thorn has quit [Changing host]
Thorn has joined #milkymist
mumptai has quit [Ping timeout: 258 seconds]
<lekernel>
sh4rm4, hum, that's a 2010 article. they weren't shipping by then.
<lekernel>
but this looks surprisingly cheap
xiangfu has quit [Ping timeout: 240 seconds]
fsk has quit [Quit: fsk]
xiangfu has joined #milkymist
xiangfu has quit [Ping timeout: 258 seconds]
xiangfu has joined #milkymist
jaeckel_ has joined #milkymist
davidc___ has joined #milkymist
davidc__ has quit [Ping timeout: 255 seconds]
stekern has quit [Ping timeout: 255 seconds]
jaeckel has quit [Ping timeout: 255 seconds]
zumbi has quit [Ping timeout: 255 seconds]
balrog has quit [Ping timeout: 260 seconds]
froggyto1d has quit [Ping timeout: 260 seconds]
froggyto2d has joined #milkymist
jaeckel_ has quit [Changing host]
jaeckel_ has joined #milkymist
xiangfu has quit [Ping timeout: 246 seconds]
stekern_ has joined #milkymist
horon has joined #milkymist
balrog has joined #milkymist
jaeckel_ is now known as jaeckel
xiangfu has joined #milkymist
azonenberg has quit [*.net *.split]
jevin has quit [*.net *.split]
ximian_ has quit [*.net *.split]
azonenberg has joined #milkymist
ximian_ has joined #milkymist
jevin has joined #milkymist
lekernel has quit [Quit: Leaving]
stekern_ is now known as stekern
bhamilton has quit [Quit: Leaving.]
sh4rm4 has quit [Ping timeout: 276 seconds]
sh4rm4 has joined #milkymist
wpwrak has quit [Quit: Leaving]
wpwrak has joined #milkymist
lekernel has joined #milkymist
bhamilton has joined #milkymist
bhamilton has left #milkymist [#milkymist]
Padawan- has quit [Ping timeout: 248 seconds]
Padawan- has joined #milkymist
Padawan- is now known as Guest89446
fsk has joined #milkymist
Guest89446 is now known as Padawan-
Padawan- has quit [Changing host]
Padawan- has joined #milkymist
bhamilton has joined #milkymist
bhamilton has left #milkymist [#milkymist]
Martoni has quit [Quit: ChatZilla 0.9.90 [Firefox 19.0.2/20130307164200]]
bhamilton1 has joined #milkymist
bhamilton1 has quit [Read error: No route to host]
bhamilton has joined #milkymist
bhamilton has quit [Client Quit]
<lekernel>
hehe, running at 1024*768 32bpp with only 256 pixels buffered on-chip
<lekernel>
the old soc required thousands for doing the same at 16bpp
<lekernel>
I'm sure we can do 1080p if the 140MHz DAC accepts being overclocked to 148.5
<lekernel>
let me try tha
<lekernel>
t
<lekernel>
yeh, the old soc has 1024 pixels buffered for coping with half the bandwidth milkymist-ng does with a 256-deep buffer
jimmythehorn has joined #milkymist
<wpwrak>
the buffering is for the burstiness of the transfer from RAM ?
<lekernel>
yes
<lekernel>
and when DRAM has to deal with other requests (CPU etc.)
<lekernel>
milkymist-ng lets you queue several commands into the DRAM controller with dedicated slots (not just one and with arbitration like the old SoC), so it handles better the loads
<lekernel>
it reorders the pending requests to improve page hit rate and reduce read/write turnaround, too
<wpwrak>
so you're now in the < 7 us delay range
<lekernel>
and DRAM is run at 2x the system clock rate
<wpwrak>
ah no, < 2 us even
<lekernel>
the controller can issue both a precharge/activate and a read/write command to another bank in the same cycle
<lekernel>
(system cycle)
<wpwrak>
so this is not only higher bandwidth for linear transfers but also faster switching between banks ?
<lekernel>
so you can have up to 133 million DRAM commands per second on a slowtan6 that can only meet system timing at 83MHz
<lekernel>
yes
<lekernel>
later I'll want to do the same thing with a more serious FPGA and DDR3-1600 or so. it's just multiplying numbers, keeping the same arch.
<wpwrak>
how is stability ? have you done any long-running torture-testing yet ?
<lekernel>
not as much testing as the old controller... actually I want to at least try 1080p as a test before sending the bug-ridden HDMI data to DRAM
<lekernel>
I wrote a traffic generator for the old controller and tested it with dozens of terabytes of data, but I have not ported it
<wpwrak>
yeah, the old one was good. i think it never gave us any trouble. so your methodology appears to work :)
<GitHub63>
[milkymist-ng] sbourdeauducq pushed 1 new commit to master: http://git.io/9u706Q