| kristianpaul | k | 00:03 |
|---|---|---|
| kristianpaul | lekernel: you made this crossbar swich and conbus motifications because navre? if, yes why? | 00:04 |
| Action: kristianpaul install gitg in order to do a better browsing of changes | 00:06 | |
| Fallenou | hehe gitg is great | 00:07 |
| Fallenou | gitk too | 00:07 |
| Fallenou | something funny is gource | 00:12 |
| kristianpaul | wow | 00:15 |
| kristianpaul | gource is awesome | 00:15 |
| kristianpaul | (not saying how usefull) | 00:15 |
| kristianpaul | the little human moving and jumping around is sebastien? :_) | 00:16 |
| Fallenou | its not written "lekernel" on it ? :p | 00:16 |
| kristianpaul | oh yes | 00:17 |
| kristianpaul | finally clicked on it | 00:17 |
| kristianpaul | is moving fast | 00:17 |
| Fallenou | oh my gource is broken | 00:17 |
| Fallenou | gsoc organization applications are now closed | 00:18 |
| Fallenou | I hope we submitted | 00:18 |
| kristianpaul | lets wait rejon | 00:22 |
| kristianpaul | ok xbar is the new conbus | 00:45 |
| lekernel | Fallenou: rejon submitted it, yeah | 04:45 |
| lekernel | kristianpaul: what jumpy person? | 04:45 |
| kristianpaul | jumpy? | 04:53 |
| kristianpaul | i used word jump for when some one will join something | 04:54 |
| kristianpaul | may be is not well miss undernstoof for the enlgish concept | 04:54 |
| Action: kristianpaul zzz | 04:56 | |
| kristianpaul | Fallenou: remenber MLEN it was defined in ./cpukit/libnetworking/sys/mbuf.h but it you already knew it.. | 11:37 |
| kristianpaul | Fallenou:About ethernet driver, where are defined DMA "parameters" wich point the right address from system memory to read? | 11:45 |
| kristianpaul | Is that the procedure isnt? | 11:48 |
| kristianpaul | or wait, question is how to you read the the rx slots | 12:00 |
| kristianpaul | ? | 12:00 |
| Action: kristianpaul thinks that have a misscopnception about DMA | 12:01 | |
| kristianpaul | ah i fount somethin.. | 12:03 |
| kristianpaul | found* | 12:03 |
| kristianpaul | 0x0C 0x18 0x24 0x30 are slots DMA adress | 12:03 |
| Action: kristianpaul rtfm | 12:04 | |
| kristianpaul | hmm but thosre are adress at the CSR bridge.. | 12:08 |
| kristianpaul | let see | 12:08 |
| kristianpaul | acording to system_conf.h MM_MINIMAC_ADDR0 0xe000800C | 12:09 |
| kristianpaul | Peripheral WB base (L1 cached/uncached) | 12:15 |
| kristianpaul | FML bridge (SDRAM) 0x40000000 / 0xc0000000 | 12:15 |
| kristianpaul | ah ! | 12:15 |
| kristianpaul | ergg no | 12:15 |
| kristianpaul | CSR bridge 0x60000000 / 0xe0000000 | 12:15 |
| kristianpaul | but from xbar | 12:20 |
| kristianpaul | // SDRAM 0x40000000 (shadow @0xc0000000) | 12:20 |
| kristianpaul | argg again | 12:20 |
| kristianpaul | // CSR bridge 0x60000000 (shadow @0xe0000000) | 12:20 |
| kristianpaul | Fallenou: when you read MM_MINIMAC_ADDR0, this reg store an adress not actually data? | 13:32 |
| kristianpaul | lekernel: resuming, can you explain me a bit how is implemented the DMA Controller in the mm1 soc? | 14:05 |
| kristianpaul | if there is one.. | 14:09 |
| lekernel | well just send wishbone or fml master cycles? | 14:10 |
| lekernel | cores supporting dma are simply additional bus masters, whose requests get routed to the peripherals through the arbiters | 14:11 |
| lekernel | there's no special DMA infrastructure (yet) | 14:11 |
| kristianpaul | ah | 14:12 |
| kristianpaul | hmm, so potentially devices like the ethernet core can create bottle neck in for busy env on wich the ethernet handle big amount of data.. | 14:14 |
| kristianpaul | of course not the case for a VJ ;-) | 14:14 |
| lekernel | you have this problem with any centralized shared memory system | 14:16 |
| kristianpaul | is the case also of fml? (note i dint read too much about this yet) | 14:17 |
| kristianpaul | s(¿/of/for | 14:17 |
| kristianpaul | oops | 14:17 |
| lekernel | yes, of course | 14:17 |
| lekernel | but fml has higher throughput than the wishbone bus | 14:18 |
| kristianpaul | so, the swich code you added with the cross bar will help on this shared bus problem, isnt? but is working right now? | 14:22 |
| lekernel | all the crossbar allows is simultaneous processor<->flash (which uses the bus inefficiently due to the flash's slowness) and ethernet<->ram communications | 14:26 |
| lekernel | this way the processor<->flash communication, e.g. when running the bios, doesn't suck all the memory bandwidth from the ethernet core | 14:27 |
| kristianpaul | if the pfpu is not in the fml, it means the caculations it have are no so troughtput demanding? or.. | 14:28 |
| kristianpaul | (ethernet<->ram communications) ah. nice hint ! less fifo overflow issues ;-) | 14:28 |
| kristianpaul | s/fifo/buffer | 14:28 |
| lekernel | well, I'll leave it as an exercise for you to compute how much memory bandwidth the pfpu is using | 14:29 |
| kristianpaul | ;-) | 14:29 |
| kristianpaul | If you're are teacher i wish the best for your students | 14:30 |
| lekernel | oh come on, it's not hard | 14:31 |
| kristianpaul | But if remenber well you compile the pach before run it.. | 14:32 |
| lekernel | two 32-bit integers on each vertex of a 128x128 grid, 30 times per second, how much bandwidth is that? | 14:32 |
| kristianpaul | 1 megabyte per second i think | 14:33 |
| kristianpaul | but i may wrong i dont know what the vertex part is about in the rendering process | 14:34 |
| kristianpaul | but i guess (128*128*30)*2 | 14:36 |
| lekernel | *32 | 14:36 |
| kristianpaul | oh, yes i asumed data word byte but is a integer, true | 14:42 |
| Fallenou | kristianpaul: yes the reg stores address | 15:57 |
| kristianpaul | Fallenou: yeah ;-) oh well i still learning :-) | 16:00 |
| kristianpaul | lekernel: Fallenou mwalle wpwrak What you think about http://sphinx.pocoo.org/ in order to create a central base for milkymist soc documentation | 16:00 |
| kristianpaul | That could be esilly update rather than individuals pdf.. latex... | 16:01 |
| kristianpaul | of course that, project is not a wiki, and should be friendly for programmers | 16:01 |
| lekernel | personally, even though I recognize the value of documentation (and I think milkymist has second-best documentation for open source SoCs after GRLIB), I have little time to take care of it... | 16:02 |
| lekernel | note that this doesn't mean i'm against switching to sphinx, just that it's not high on my priority list | 16:08 |
| kristianpaul | oh, sure, i just asking if you like this platform or have suguestions for other? | 16:10 |
| kristianpaul | migration could be done even slowly, but wiki could be a good point for decent manuals, also pdf is not easilly updated within the time | 16:11 |
| kristianpaul | wiki could not* | 16:11 |
| lekernel | well, at first sight it looks better than doxygen | 16:12 |
| Fallenou | kristianpaul: it seems great | 16:17 |
| Fallenou | for the moment we have a wiki, which is good too | 16:18 |
| Fallenou | I think we can first focus on writing some valuable documentation on the wiki | 16:18 |
| Fallenou | before thinking about migrating stuff to another plateform | 16:18 |
| Fallenou | but yes it looks nice :) | 16:18 |
| Fallenou | wiki pages looks nice too imo | 16:18 |
| kristianpaul | lekernel: Are you aware of a way/program to convert verilog to a DOT graphiz output? | 16:28 |
| lekernel | no | 16:29 |
| wpwrak | kristianpaul: (doc) dunno. i find post-processing-friendly comments in source code hard to read. | 16:32 |
| lekernel | kristianpaul: also, DOT would be a mess with large and complex verilog files | 16:42 |
| lekernel | and maybe not even relevant | 16:42 |
| lekernel | it works great for LLHDL to show the tree like structures (which e.g. can help explaining/understanding how libmapkit plug-ins work) but for verilog... | 16:44 |
| kristianpaul | lekernel: yeah in llhdl looks awesome | 16:57 |
| kristianpaul | (relevant) indeed, actually as the DOT ouput should be done after the sintesis process i think | 16:58 |
| lekernel | kristianpaul: sure, we can do that. that's what it does: http://milkymist.org/fpgatools/blinker.pdf | 17:44 |
| lekernel | as you can see, it doesn't work so well except for designs of trivial complexity | 17:45 |
| kristianpaul | puff, what a mess | 17:46 |
| Action: kristianpaul remenber when trying to undesrstand some self generated networks maps by ntop + graphiz | 17:47 | |
| kristianpaul | now i read with care sebastien tesis i'm please to read how a FFT process done by software on a PC is replaced by an accumulator :-). So the new zelands were not so crazy after all when they tought that for the gold code tracking | 18:12 |
| kristianpaul | Fallenou: how big a ethernet frame is? | 20:50 |
| kristianpaul | #define ETHERNET_FRAME_LENGTH 1532 | 20:50 |
| Fallenou | something like that | 20:57 |
| Fallenou | 1500+ | 20:57 |
| Fallenou | it's the max size btw | 20:58 |
| Fallenou | it can be less | 20:58 |
| Fallenou | maybe 1518 | 20:59 |
| Fallenou | http://fr.wikipedia.org/wiki/Fichier:Ethernet_Type_II_Frame_format.svg | 20:59 |
| Fallenou | anyone here is richard sharpe ? | 22:10 |
| kristianpaul | Fallenou: is he, from the oshg? | 22:24 |
| kristianpaul | the question about ddr2 should be in the FAW | 22:24 |
| kristianpaul | FAQ* | 22:24 |
| Fallenou | don't think so | 22:25 |
| Fallenou | it's just to ask him if he is porting milkymist on genesys | 22:25 |
| Fallenou | or what he' gonna do | 22:25 |
| kristianpaul | i see | 22:25 |
| kristianpaul | Fallenou: you made the driver for the softcore usb, or whatever that is, or was sebastien? | 22:33 |
| Fallenou | sebastien did | 22:33 |
| kristianpaul | i dont remenber well, in that time your logs were unknow for me | 22:33 |
| kristianpaul | k | 22:33 |
| kristianpaul | And is all in flicernoise repo? that was you're talking about last time? | 22:34 |
| Fallenou | i'm sorry what ? | 22:34 |
| kristianpaul | ergg yes sorry | 22:35 |
| kristianpaul | where is that driver? | 22:35 |
| Fallenou | the usb driver ? | 22:51 |
| kristianpaul | softub core.. | 22:52 |
| kristianpaul | i can dig np.. | 22:52 |
| kristianpaul | just i dont used yet to rtem directory structure | 22:52 |
| Fallenou | c/src/lib/libbsp/lm32/shared/milkymist_usbinput | 22:52 |
| Fallenou | all milkymist drivers are in the same directory | 22:52 |
| Fallenou | in "shared" | 22:52 |
| kristianpaul | ah ok | 22:52 |
| Action: kristianpaul blind | 22:52 | |
| kristianpaul | // TODO: move softusb firmware to the filesystem | 22:53 |
| kristianpaul | Fallenou: what that means? | 22:53 |
| Fallenou | dunno | 22:53 |
| kristianpaul | ah, i guess he mean the microcode | 22:54 |
| Fallenou | yes | 22:54 |
| Fallenou | the code that runs on navre | 22:54 |
| kristianpaul | wich actually es load by cpu | 22:54 |
| kristianpaul | and using some xilinx libraries i think.. | 22:54 |
| kristianpaul | yeah TOOD | 22:54 |
| --- Sun Mar 13 2011 | 00:00 | |
Generated by irclog2html.py 2.9.2 by Marius Gedminas - find it at mg.pov.lt!
