| lekernel | hmm, if this isn't all bullshit, lm32 should run at 166MHz in kintex | 00:00 |
|---|---|---|
| lekernel | it's faster than v6, so that's rather surprising | 00:00 |
| Fallenou | with the newer ISE you could try to synthetize it | 00:02 |
| lekernel | yeah, that's where the 166MHz figure comes from | 00:03 |
| Fallenou | oh ! | 00:06 |
| Fallenou | nice nice | 00:06 |
| kristianpaul | mwalle: woah, nice scope | 02:02 |
| Action: kristianpaul waiting for xilinx/avnet introduce dirty cheap kintex kit | 02:02 | |
| kristianpaul | funny interactive banner sebastien put on the top right place of milkymist.org ;-) | 02:47 |
| kristianpaul | "Milkymist One can run software written in Ruby and Lua." ah nice ;-) | 02:48 |
| wpwrak | kristianpaul: a better one would be simply "Milkymist can". or maybe "Milkymist can do things your Arduino doesn't even dare to dream of" ;-) | 04:13 |
| Gurty | Happy Birthday Fallenou <3 *\o/* | 07:23 |
| scrts` | congratz :) | 07:26 |
| xiangfu | http://www.milkymist.org/doc/system.pdf | 08:04 |
| xiangfu | Not Found | 08:05 |
| xiangfu | The requested URL /doc/system.pdf was not found on this server. | 08:05 |
| xiangfu | report a issue . :) | 08:05 |
| xiangfu | maybe it should point to : http://www.milkymist.org/socdoc/bios.pdf | 08:12 |
| kristianpaul | Fallenou: Feliz Cumpleaños :-) | 10:43 |
| Fallenou | oh :) | 11:00 |
| Fallenou | thanks ! | 11:00 |
| scrts` | Fallenou: how much? | 11:34 |
| scrts` | :) | 11:34 |
| Fallenou | scrts`: 23 :) | 11:55 |
| Gurty | Fallenou :D | 12:01 |
| Fallenou | Gurty: hey :) thanks for the text message ! | 12:03 |
| scrts` | heh | 12:05 |
| scrts` | same for me tomorrow | 12:05 |
| scrts` | :) | 12:05 |
| Gurty | It's always a pleasure Fallenou ;) | 12:06 |
| Fallenou | oh 23 too tomorrow ? | 12:06 |
| scrts` | yep | 12:10 |
| scrts` | :)) | 12:10 |
| Gurty | Fallenou, A happy birthday fkosmala (kostek) wishes you | 12:12 |
| Fallenou | thanks ! | 12:13 |
| methril_work | hi | 18:02 |
| lekernel | hi | 18:12 |
| methril_work | lekernel, what is missing from the driver side? | 18:20 |
| methril_work | into RTEMS | 18:21 |
| lekernel | ethernet fixes/rewrites | 18:21 |
| Fallenou | file manager | 18:21 |
| lekernel | that's not rtems | 18:21 |
| Fallenou | oh ok | 18:21 |
| lekernel | but yes, gui filemanager | 18:22 |
| methril_work | and in the linux side? | 18:24 |
| methril_work | i know there is no much interest in the Linux side | 18:24 |
| methril_work | but | 18:24 |
| methril_work | i think that Linux word attract developers | 18:25 |
| lekernel | about every driver is missing i'd say | 18:27 |
| lekernel | or at least requires serious cleanup | 18:27 |
| methril_work | if it`s a long term goal, could i start to hack it in qemu? | 18:28 |
| lekernel | sure, go ahead | 18:30 |
| methril_work | thanks | 18:31 |
| lekernel | http://www.xilinx.com/support/answers/39999.htm | 18:52 |
| lekernel | is there anything that works on spartan6? | 18:52 |
| lekernel | ... | 18:52 |
| lekernel | the funny thing is we don't seem to have run into this problem | 18:52 |
| mwalle | Fallenou: happy birthday :) | 19:28 |
| Fallenou | thanks mwalle :) | 19:29 |
| methril_work | Fallenou, today is your birthday? Happy Birthday then!! | 19:29 |
| methril_work | :) | 19:29 |
| methril_work | mine is 13 days left | 19:29 |
| Fallenou | héhé thank you all :) | 19:30 |
| Fallenou | a lot of people are born in march i guess :p | 19:31 |
| lekernel | Fallenou: happy bday :) | 19:32 |
| lekernel | hey, with ise 13.1 we run at 90MHz now | 19:32 |
| Fallenou | hey nice ! | 19:32 |
| lekernel | should check the stability though :) | 19:33 |
| Fallenou | that's the birthday gift :) | 19:33 |
| lekernel | well, let's hope it's not poisoned with heisenbugs | 19:33 |
| Fallenou | it was running at 88 MHz before, right ? and then you switched to 80 | 19:34 |
| Fallenou | or something like that | 19:34 |
| lekernel | 83 and then 80 | 19:34 |
| lekernel | now 90 | 19:34 |
| Fallenou | ok | 19:34 |
| Fallenou | why the drop from 83 to 80 ? | 19:35 |
| Fallenou | to meet timings ? | 19:35 |
| lekernel | because it wasn't possible anymore to meet timing at 83 | 19:35 |
| lekernel | yes | 19:35 |
| Fallenou | oh ok | 19:35 |
| Fallenou | you just gave it a try blindly or ise told you "you can run at 90 MHz" ? | 19:36 |
| lekernel | well I saw that it was easily meeting timing at 80 (it was a total mess before), so I pushed it a bit | 19:36 |
| Fallenou | ok :) | 19:36 |
| Fallenou | at least they improve Xst a little bit each time | 19:36 |
| Fallenou | they don't just change the GUI | 19:36 |
| lekernel | seems too good to be true imo | 19:36 |
| lekernel | i expect a few surprises | 19:37 |
| Fallenou | hehe we'll see | 19:37 |
| lekernel | hmm... there are some slight "dancing pixels" on the screen | 19:37 |
| lekernel | not sure where this comes from | 19:38 |
| mwalle | lekernel: is this with debug enabled? (except the breakpoints?) | 19:53 |
| lekernel | mwalle: no, no debug at all | 20:01 |
| kristianpaul | ha thats probably what larsc pointed time ago in qi http://www.xilinx.com/technology/roadmap/zynq7000/features.htm | 20:14 |
| scrts | I wonder what artix and kintex devices will be :) | 20:28 |
| lekernel | probably even buggier than s6 | 20:46 |
| lekernel | it's amazing how crippled the s6 is... silicon bugs with BRAM asynchronous clocking, silicon bugs with BRAM initialization, and others, and they said they will NOT fix them | 20:47 |
| lekernel | given how rushed up the 7 series seems to be, i expect the worst | 20:48 |
| lekernel | i'd much prefer to see a "s6-stable" device than a freaky "k7" | 20:48 |
| kristianpaul | bram > buffer > fixo rx overflow !! (That hapen just when doing pld load of the milkymist soc bitstream) | 20:49 |
| lekernel | oh, and no characterization of the IODELAY timing too... "let's shift the 45nm process problems to our customers"... that's why I had lots of intermittent DRAM problems on the M1 | 20:50 |
| lekernel | terpstra: don't Altera multiplier blocks have internal pipeline registers? | 21:10 |
| lekernel | it seems weird to me that you have to split the operation manually | 21:10 |
| methril_work | lekernel, when you work in the USB part, do you thinks some usuall mistakes that i could translate to CAN Bus? | 21:14 |
| lekernel | hmm as expected it's unstable at 90M | 22:32 |
| lekernel | i'd have been surprised otherwise | 22:33 |
| lekernel | stupid xilinx crap | 22:35 |
| Fallenou | ^^ | 22:38 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * rf731094 / (5 files in 4 dirs): LM32 GSI patches - http://bit.ly/dEEqtc | 22:41 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * r5fc9102 / boards/milkymist-one/synthesis/common.ucf : ISE 13.1 support - http://bit.ly/ffruCr | 22:41 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * r9679c6d / build_bitstream.sh : Build host tools for bitstream (needs byteswap) - http://bit.ly/fFb81x | 22:41 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * r4c314c5 / (2 files in 2 dirs): Bump SoC version number - http://bit.ly/hnY3Iv | 22:41 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * r5366fec / software/bios/main.c : Use timer for boot timeout - http://bit.ly/houF37 | 22:41 |
| lekernel | seems they can't characterize a 45nm chip (IODELAY data mess + bugs in the timing analyzer) so those 28nm ones will be a disaster | 22:42 |
| Fallenou | is it so difficult to get the IO timing ? | 22:43 |
| lekernel | the I/O thing I'm talking about is: | 22:44 |
| lekernel | in S6 they introduced a new low-cost way to delay all incoming signals on every I/O pin | 22:45 |
| lekernel | on previous fpgas, it was done using a delay chain with a variable tap, and it included some calibration circuitry that worked great | 22:45 |
| lekernel | it was only available in virtex though | 22:46 |
| lekernel | in S6, they replaced that with a multi-GHz ring oscillator that drives programmable counters that generate the delayed signal when they overflow | 22:46 |
| Fallenou | hum ok | 22:47 |
| Fallenou | sounds great too | 22:47 |
| lekernel | the problem is the frequency of said ring oscillator is totally unstable | 22:47 |
| lekernel | and your delays vary by a ridiculous margin, some 1000% (can't remember the exact figure from the datasheet, but it's a total mess) | 22:47 |
| lekernel | and you can't easily calibrate them | 22:48 |
| lekernel | they removed the previously available calibration logic that compared the delays against a reference clock | 22:50 |
| lekernel | and allowed you to have precise delays without much of a mess | 22:50 |
| Fallenou | the | IODELAY thing ? | 22:50 |
| Fallenou | in the ucf | 22:51 |
| lekernel | oh, funny, it has yet more silicon bugs too: http://www.xilinx.com/support/answers/38408.htm | 22:51 |
| lekernel | I think my next FPGA design will have an Altera chip | 22:52 |
| lekernel | Fallenou: it's not in the UCF, IODELAY2 is a logic primitive you instantiate in the signal path to (hopefully) implement the programmable delay | 22:56 |
| Fallenou | oh ok | 22:56 |
| Fallenou | I remembered something about "delay" in the ucf | 22:56 |
| Fallenou | that you can put on the pins of the fpga | 22:57 |
| Fallenou | oh ok it's the SLEW | 23:00 |
| jackgassett | hello, I was just checking out the Softusb project and was wondering what was used for synthesis. | 23:48 |
| jackgassett | I tried with Xilinx ISE and it gives some errors. | 23:48 |
| lekernel | phew, LZMA decompression is slow as hell... boot time went from 9s to 43s | 23:53 |
| lekernel | jackgassett: well right now there aren't that many options. we use ISE too | 23:54 |
| lekernel | softusb cannot be used stand alone | 23:54 |
| lekernel | I don't know what you tried to do... | 23:54 |
| jackgassett | ok, so it probably just needs some love then. | 23:54 |
| jackgassett | I just wanted to see if it should work with ISE. | 23:54 |
| lekernel | if you just take the contents of the softusb/rtl folder and drop that into an ISE project, there's no chance it would work | 23:55 |
| jackgassett | ok, so it looks like memory needs to be added through wishbone bus then? | 23:55 |
| lekernel | memory is integrated | 23:56 |
| jackgassett | and then peripherals can be added with your csr bus? | 23:56 |
| lekernel | well, have a look at the ports on the top level | 23:56 |
| lekernel | (softusb.v) | 23:56 |
| jackgassett | ok, right I see that memory is included, Data and Program. | 23:57 |
| jackgassett | I commented out the sie and hostif modules because I just wanted to check out navre and wishbone controller for now. | 23:57 |
| CIA-94 | milkymist: Sebastien Bourdeauducq master * r5b47999 / (5 files in 2 dirs): Flash boot image LZMA compression support - http://bit.ly/f1MNkB | 23:57 |
| jackgassett | should the softusb core work for that purpose without much modification? | 23:59 |
| --- Fri Mar 4 2011 | 00:00 | |
Generated by irclog2html.py 2.9.2 by Marius Gedminas - find it at mg.pov.lt!