| stekern | believe it or not, I've written some documentation: https://github.com/skristiansson/diila/blob/master/README | 00:02 |
|---|---|---|
| stekern | also moved to github and changed the name to diila | 00:03 |
| glowplug | That is amazing! | 00:05 |
| LoneTech | \o/ | 00:10 |
| --- Log closed Thu Mar 21 01:35:30 2013 | ||
| --- Log opened Thu Mar 21 01:35:48 2013 | ||
| -!- Irssi: #openrisc: Total of 24 nicks [0 ops, 0 halfops, 0 voices, 24 normal] | 01:35 | |
| -!- Irssi: Join to #openrisc was synced in 23 secs | 01:36 | |
| GentlemanEnginee | Hello. | 03:45 |
| -!- heroux_ is now known as heroux | 03:55 | |
| glowplug | Whats up? | 04:11 |
| GentlemanEnginee | I am slowly being driven mad by the wind... | 04:26 |
| GentlemanEnginee | Yourself? | 04:26 |
| GentlemanEnginee | What progress have you made in terms of a development board? | 04:30 |
| glowplug | Negative progress. Actually. Haha | 04:30 |
| GentlemanEnginee | Define negative progress. | 04:32 |
| glowplug | It turns out that the motor control that I need to do can be done directly from a parallel port and external powerstages. | 04:32 |
| glowplug | The only reason thats possible is that my system rpm (mechanical bandwidth) is very very low. | 04:33 |
| GentlemanEnginee | I was curious why you were looking at this manner of exotic solution. | 04:34 |
| GentlemanEnginee | I assumed you had a reason. | 04:34 |
| glowplug | I am still going to design the board as a low-cost developer platform. But progress might be slow. | 04:34 |
| glowplug | At least I finally decided on a form factor which is an SO-DIMM module. That will give the greatest flexibility by allowing mainboards to be tailored to a specific person. | 04:35 |
| glowplug | It will also be 2-layer. And on standard fiberglass board. | 04:37 |
| glowplug | So I guess progress wasn't really negative. But decelerated. | 04:37 |
| GentlemanEnginee | I see. | 04:38 |
| GentlemanEnginee | I am making slow progress on Memory Controller. | 04:38 |
| glowplug | I really want to use DDR on the board because I think it will open up a lot of development in Linux to have 512mb. 256mb is extremely limiting. | 04:40 |
| GentlemanEnginee | I concur. | 04:40 |
| GentlemanEnginee | I am simply dealing with dependencies at the moment. | 04:40 |
| GentlemanEnginee | In between bouts of wind-madness, naturally... | 04:41 |
| glowplug | O_O | 04:41 |
| GentlemanEnginee | 60 - 80 km/h. If you did not enjoy it today, you may enjoy it in the morrow! | 04:42 |
| GentlemanEnginee | Makes the eves buzz constantly. | 04:42 |
| glowplug | Where are you located? Thats crazy... | 04:42 |
| GentlemanEnginee | Saskatchewan. | 04:42 |
| GentlemanEnginee | Two years ago, not long after purchasing the property, I was awakened by a buzzing noise. | 04:43 |
| GentlemanEnginee | Finally determined it was the wind vibrating the steel door... | 04:43 |
| glowplug | Crazy! | 04:44 |
| GentlemanEnginee | It would not have been my first guess... | 04:44 |
| glowplug | If the steel is relatively thick no it wouldn't have been mine either. | 04:46 |
| glowplug | Michigan weather is pretty mild for a peninsula. | 04:47 |
| GentlemanEnginee | The best is the snow drifts. 3+ feet deep accross my entire drive. | 04:48 |
| GentlemanEnginee | I need to purchase a larger tractor, as my small one just has not been up to the task. | 04:55 |
| GentlemanEnginee | So, what manner of time-frame are we looking at for the development board? | 04:55 |
| glowplug | Probably 2 months for a prototype realistically. | 05:27 |
| GentlemanEnginee | Alright. | 05:59 |
| GentlemanEnginee | Just found out from the neighbour she could not return with the school bus this afternoon. | 06:00 |
| GentlemanEnginee | She had her husband pick her and the children up with his backhoe. | 06:00 |
| GentlemanEnginee | Took them over five hours to drive five km. Drifts over seven feet tall... | 06:01 |
| GentlemanEnginee | Apparently Milkymist is using a depreciated Verilog Simulator, cver. | 06:01 |
| GentlemanEnginee | Found an older version of it in source. | 06:25 |
| GentlemanEnginee | Edited makefile to compile it. | 06:25 |
| glowplug | You got MilkyMist to compile? Is it possible to use it with Icarus? | 06:38 |
| GentlemanEnginee | I am attempting using Icarus. | 06:40 |
| GentlemanEnginee | The result is a large number of warnings. Attempting to investigate their validity. | 06:46 |
| stekern | GentlemanEnginee: sounds like the climate over where you live is even more of a pain than here :/ | 07:13 |
| GentlemanEnginee | It can be... | 07:18 |
| GentlemanEnginee | I doubt I will make it to the office tomorrow either. | 07:18 |
| GentlemanEnginee | Are you in the south of Finland in the area of Helsinki? | 07:21 |
| stekern | yes | 07:22 |
| stekern | in Espoo | 07:22 |
| stekern | we've got around -10C here now | 07:23 |
| GentlemanEnginee | It is odd. You are approximately eight degrees north of myself. Yet, we experience a far colder winter. | 07:24 |
| GentlemanEnginee | Never underestimate the heatsink quality of an ocean... | 07:24 |
| stekern | but we're close to the gulf stream | 07:24 |
| GentlemanEnginee | That would definitely aid you. | 07:25 |
| stekern | it has been around -20C last week though | 07:27 |
| GentlemanEnginee | In Alberta, especially in the area of Calgary and Lethbridge, there is a phenominon known as a Chinook. | 07:27 |
| GentlemanEnginee | It is an adibiatic heating from traversing the Rocky Mountains. In the winter, it is capable of raising the temperature 20 or more degrees in a matter of an hour. | 07:29 |
| GentlemanEnginee | Thus, one may have a temperature of +15C at midnight and -20 at noon. | 07:29 |
| stekern | "In Pincher Creek, the temperature rose by 41°C (74°F), from -19 to 22°C (-2 to 72°F), in one hour in 1962" | 07:32 |
| stekern | heh | 07:32 |
| GentlemanEnginee | It gave me terrible migraines when I lived in Calgary. | 07:32 |
| GentlemanEnginee | The wind is also positively charged, and can wreak havok on electronics during its duration. | 07:34 |
| GentlemanEnginee | Also, for chemistry experiments, one must read the barometric pressure, and account for it, as it can change dramatically. | 07:35 |
| GentlemanEnginee | I am looking at the ODDR2 Primative being used by the milkymist memory controller. | 07:52 |
| GentlemanEnginee | How available is this manner of primative on other platforms? | 07:52 |
| stekern | it's pretty much spartan 6 specific | 07:53 |
| GentlemanEnginee | Do other FPGAs have similar primatives? | 07:54 |
| GentlemanEnginee | Or is relying on this marrying myself to a specific FPGA from a specific vendor. | 07:55 |
| stekern | I guess this is alteras counterpart: http://www.altera.com/literature/ug/ug_altdq_altdqs.pdf | 07:57 |
| GentlemanEnginee | So, with a little abstraction, it should be possible to deal with this discrepency between platforms. | 07:59 |
| stekern | I haven't really looked at DDR in detail ever, but I believe so | 07:59 |
| stekern | I think the higher layer is completely compatible with single rate SDRAM too, so in theory it should even be possible to modify my SDRAM controller to support DDR without enormous effort | 08:01 |
| GentlemanEnginee | I had not considered it from that point of view... | 08:02 |
| GentlemanEnginee | It might be easier to do so... | 08:02 |
| stekern | ...but it currently only supports 16 bit data interface | 08:02 |
| GentlemanEnginee | Would that require much effort to change? | 08:03 |
| stekern | probably not | 08:03 |
| GentlemanEnginee | I may take a look at it from that perspective as well. | 08:04 |
| GentlemanEnginee | I thank you kindly, stekern. | 08:04 |
| GentlemanEnginee | However, I believe my bed is requesting my presence... | 08:04 |
| stekern | you better satisfy that request then :) | 08:06 |
| GentlemanEnginee | I do believe I shall! | 08:07 |
| * stekern sneaks up on the non suspecting bug, slowly lifts a hammer and... *BAM!* | 09:44 | |
| stekern | left to do is to find the hideout where he came from | 09:45 |
| stekern | so the problem is clearly visible here: http://oompa.chokladfabriken.org/tmp/mor1kx_on_atlys_dump5.png | 09:46 |
| stekern | the icache tagram is not write-first, but read-first | 09:46 |
| stekern | spartan 6 block ram resources user guide (http://www.xilinx.com/support/documentation/user_guides/ug383.pdf) states that write-first is the default, but it does not get inferred as such | 09:49 |
| stekern | I believe quartus ii do infer them as write-first | 09:49 |
| stekern | I bet the simulations simulate them as write-first (I'm going to confirm this) | 09:49 |
| stekern | s/simulations/simulators | 09:50 |
| stekern | yep, simulations show write-first behaviour | 10:09 |
| stekern | I think I understand this now, since we're using seperate read and write addresses the restrictions under Conflict Avoidance - Synchronous Clocking applies, i.e. write-first mode would yield unreliable data when data is written to the same address as is being read. | 10:43 |
| stekern | so, obviously ISE decides that that's not good and infers it as read-first, without a word of warning | 10:43 |
| stekern | while quartus ii infers bypass logic and gives a warning about it | 10:44 |
| _franck_ | http://www.altera.com/literature/hb/qts/qts_qii51007.pdf , Example 13-11 and 13-13 | 12:38 |
| _franck_ | I didn't know that (I alsmost never infers memories) | 12:40 |
| stekern | yeah, we use the "alternative way" under example 13-13 | 12:42 |
| stekern | and altera does that right (as the code says) | 12:43 |
| stekern | xilinx tools does it "wrong" and without a warning about it | 12:45 |
| _franck_ | "Byitself,the code describes new data read-during-writebe havior.However, if theRAMoutput feeds a register in another hierarchy, a read-during-write results in the old data." | 12:48 |
| _franck_ | *"For this reason, avoid using this alternate type of coding style"* | 12:48 |
| stekern | but the other method involves blocking assignments, which also is ugly | 12:53 |
| stekern | anyways, the safest is probably to describe the RAM as read-first and then manually put in bypassing logic | 12:54 |
| stekern | that's what my fix in my working tree does | 12:55 |
| _franck_ | ok great | 12:55 |
| stekern | with that fix, trivial software like dhry and the likes works again | 13:06 |
| stekern | it's not quite booting linux though | 13:06 |
| mor1kx | [mor1kx] skristiansson pushed 2 new commits to master: https://github.com/openrisc/mor1kx/compare/fd14d9e82e60...0014bfa73c6e | 13:32 |
| mor1kx | mor1kx/master 5651742 Stefan Kristiansson: cappuccino/fetch: disallow icache refill when kill_fetch=1... | 13:32 |
| mor1kx | mor1kx/master 0014bfa Stefan Kristiansson: spram: add explicit bypass logic for write-first behaviour... | 13:32 |
| juliusb | stekern: interesting bug w/ the read/write-first thing | 13:39 |
| stekern | what I find most interesting is that ISE turns valid code into something completely different without a word about it. | 13:41 |
| stekern | ok, if it threw hands up in the air and just refused to infer it, or at least warned about it | 13:42 |
| stekern | otoh, if it would have, I might not have spent time on improving diila =P | 13:44 |
| juliusb | diila? | 13:45 |
| stekern | that's what I have dubbed the logic analyzer to | 13:46 |
| juliusb | ahh :) | 13:47 |
| juliusb | very good | 13:47 |
| juliusb | I'm thinking we should use the wiki on github more | 13:47 |
| juliusb | for instance, to record implementation information | 13:47 |
| juliusb | and implementation bugs like that | 13:47 |
| stekern | sounds like a good idea | 13:58 |
| stekern | then we could link to that from opencores.org/or1k | 13:59 |
| stekern | I've planned to update the cappuccino documentation btw | 13:59 |
| stekern | it's grown painfully out of date | 14:00 |
| juliusb | :) | 14:00 |
| juliusb | yeah that whole documentationt hing needs an update before a release | 14:00 |
| stekern | you're never going to get to a release if you're waiting to fix stuff before the release ;) | 14:01 |
| stekern | well, fixing bugs is of course necessary | 14:01 |
| stekern | and correct documentation | 14:14 |
| ams | <3 common lisp <3 | 14:24 |
| stekern | ams: looks like your hatred for sw have been cured! =P | 14:27 |
| ams | stekern: hahahahaha | 14:28 |
| ams | don't get me started ... i've been fighting stupid tools all week | 14:28 |
| ams | my favourite all week was when i had to frob an ELF ph and sh --- manually, using sed. | 14:30 |
| stekern | sounds like fun | 14:31 |
| ams | yes, it was, it was one of those "okie, this is stupid, will you go away if i do it in the most convulted fashion i can think of?" momeents. | 14:34 |
| GentlemanEnginee | Hello. | 19:13 |
| glowplug | Good morning. =) | 19:23 |
| glowplug | I read through the channel. The idea of implimenting the SDRAM controller to work with DDR is interesting. Maybe doing it that way would depend on the existing code quality. Is the milkymist code messy? | 19:24 |
| GentlemanEnginee | Not particularly, as far as I am able to read. | 19:26 |
| GentlemanEnginee | However, it is designed for a differing chain. | 19:27 |
| GentlemanEnginee | Also, it would be better to be able to have an option as to how the memory controller is used. | 19:27 |
| glowplug | The Altera VS Xilinx thing is really messy. | 19:37 |
| stekern | it looks like this project is using the milkymist controller on altera: https://github.com/marmolejo/zet | 19:48 |
| glowplug | That project is extremely interesting. x86 was an interesting choice. | 19:50 |
| juliusb | I believe the point was to build an x86 PC | 19:51 |
| juliusb | I'd like to play with that at some point | 19:51 |
| glowplug | And it runs DOS. Clearly they have a different world-view. Haha | 19:51 |
| juliusb | I'd what I started using when I was young | 19:51 |
| juliusb | 386 | 19:51 |
| juliusb | my goal would be to run a game like duke nukem 3d or redneck rampage on a FPGA :) | 19:51 |
| juliusb | and there's no shortage of x86 tools out there | 19:51 |
| juliusb | :) | 19:51 |
| juliusb | (compilers, software, etc.) | 19:52 |
| glowplug | My first computer was a 486. But I would give anything to go back in time and tell myself about Dennis Ritchie and Richard Stallman when I was 9. Haha | 19:52 |
| juliusb | actually, funnily enough, there may not be any good embedded stuff | 19:52 |
| glowplug | I had Redneck Rampage! No way. What an awesome game. | 19:52 |
| glowplug | The interesting thing about x86 vs RISC (as far as I understand it) is that the physical digital logic of a RISC processor is more simple (although in more modern CPU's I realize there is a convergence). | 19:54 |
| glowplug | If we are going to be succesfull in home-made semiconductor fabrication we need to focus on the most simple physical chips to reach a desired goal. | 19:55 |
| glowplug | Intel doesn't have to worry about such things. =) | 19:55 |
| juliusb | yes, I think x86 is very basic | 19:55 |
| juliusb | sorry | 19:55 |
| juliusb | I didn't finish typing or thinking about that sentence before I pressed enter | 19:56 |
| juliusb | i think the x86 implementation he's got is very basic (in the zet project) but I'm curious to know what sort of performance he's getting, though, for something like coremark | 19:56 |
| juliusb | if he can run it | 19:56 |
| glowplug | The main difference is the "x86 translation" circuitry correct? | 19:57 |
| glowplug | Sort of hardware abstraction to CPU functions. | 19:57 |
| juliusb | but, it'd be sweet to build something emulating a proper 386/486 era machine and just out-of-the-box software work on it (I guess getting DOS going is an indication that he's there | 19:57 |
| juliusb | I believe he had screenshots of command and conquer, or dune ,or something going - that's quite cool :) | 19:57 |
| juliusb | well, translation? you mean decode and execute? | 19:57 |
| glowplug | He was running Dune 2! Yeah it is extremely cool. | 19:57 |
| juliusb | all modern x86s would have epic amounts of decode-x86-to-RISC circuitry inside of them | 19:58 |
| glowplug | I'm not sure. It was my understanding that x86 CPU's have translation circuitry that is inherent to their design that RISC CPU's do not need. | 19:58 |
| juliusb | but you could do a pretty basic one probably | 19:58 |
| glowplug | Ahh ok. That's what I was reffering to. | 19:58 |
| juliusb | with a realtively simple pipeline | 19:58 |
| glowplug | That sort of thing seems like it would be *very* difficult to get right in a DIY-ASIC (although obviously we are 5+ years away from that). | 19:59 |
| glowplug | Where a processor like mor1kx could be replicated onto a chip with much less complexity and probably higher yields. | 20:00 |
| glowplug | mor1kx is 32,000 lines of code right? | 20:00 |
| glowplug | Actually that might be ORPSoc. I can't remember now. | 20:02 |
| juliusb | mor1kx isn't 32k | 20:02 |
| juliusb | I'm not sure SLOC really equates too well to gates or complexity, anyway | 20:03 |
| glowplug | Got it. mor1kx is 15767 lines including documentation. | 20:04 |
| juliusb | really?! | 20:04 |
| glowplug | Yup! | 20:05 |
| glowplug | That includes all RTL files though. And they are not all used simultaniously correct? | 20:05 |
| glowplug | It also includes non source lines like the license header ect. | 20:06 |
| glowplug | If you are only using cappuccini you can drop 4k lines right there. Then probably another 1k lines for documentation + headers. | 20:07 |
| juliusb | https://github.com/openrisc/mor1kx/wiki | 20:07 |
| glowplug | So a running CPU starts at around 10k lines or so. | 20:07 |
| juliusb | I see 10k lines of actual code (if treating it as C-like code) | 20:07 |
| glowplug | Holy shit what a good guess! | 20:08 |
| glowplug | Haha | 20:08 |
| glowplug | Your method for finding source lines is *way* better than mine. | 20:08 |
| glowplug | And your right source lines is probably a bad measure of digital logic complexity. | 20:09 |
| glowplug | Do you think that x86 type cores are worth pursuing for practical purposes given how good your RISC architecture already is? | 20:10 |
| juliusb | I'm not sure or1k is a good architecture versus what else is available nowdays | 20:11 |
| glowplug | It seems to be getting good synthetic performance compared to modern chips. I think if it was fabricated it would perform very comparable. | 20:13 |
| glowplug | Assuming comparable clock speeds and process ect. | 20:13 |
| glowplug | It looks like the x86 core's RTL hasn't been updated for 3 years. =( | 20:13 |
| glowplug | Some updates 2 years ago. | 20:13 |
| juliusb | Maybe it'd be comparable to an ARM M3, but not much more | 20:14 |
| glowplug | What do you think the biggest challenge is for scaling performance/core/mhz? Is that being delayed for the 2k architecture? | 20:17 |
| juliusb | 2k architecture needs to be defined before we can be considering implementation challenges | 20:19 |
| juliusb | but, actually, yes, I'd like to get a basic 2k architecture sorted out (I have a rough ISA drafted) and then basically mod mor1kx to run that | 20:20 |
| juliusb | and then look at doing stuff like multiple-issue pipelines | 20:20 |
| juliusb | could do hat with mor1kx as is I suppose | 20:20 |
| glowplug | I see so you don't plan on abandoning mor1kx but using it as a testbed for 2k functionality (whatever that might be). | 20:21 |
| juliusb | perhaps, yes | 20:22 |
| juliusb | I don't know, maybe start again with lessons learned | 20:22 |
| juliusb | but it's pretty nice to work with | 20:22 |
| juliusb | nice code | 20:23 |
| glowplug | Ahhh one of those types. Complete a massive project learns a few things. Realizes its not "absolutely perfect" so you have to start from scratch again. Haha | 20:23 |
| glowplug | That is a slippery slope! | 20:23 |
| juliusb | :) not from scratch probably | 20:23 |
| juliusb | but if it's an entirely different ISA, you may want to do that | 20:24 |
| glowplug | Really I'm joking because in all honesty if all important projects were handled that way we would have significantly better systems. =) | 20:24 |
| glowplug | That and distributed development and I think we can surpass Intel in not too long. 8) | 20:25 |
| glowplug | Have you popped into the homecmos channel yet? I have been working with those guys over the last week or so. It is very promising stuff! | 20:26 |
| glowplug | Specifically the sub $1,000 1 micron resolution home lithography device. | 20:27 |
| juliusb | no, never look at that | 20:27 |
| juliusb | really!?! | 20:27 |
| juliusb | s/look/looked/ | 20:27 |
| glowplug | Yeah. I'm helping them design an even cheaper version. (I'm much better at hardware than software). Haha | 20:27 |
| glowplug | Of course litho is a very small part of the whole picture. But it shows real promise / progress. | 20:28 |
| stekern | since we're obviously comparing first x86 computers, my first was a Commodore 8086 (yes, you heard right) :) | 20:29 |
| glowplug | Sub-micron resolution with that device is possible in principle as well with closed loop motor control and interferometers for linear encoder feedback. | 20:29 |
| glowplug | I never owned a Commadore myself unfortunately but my father had a C64. I loved that thing! | 20:29 |
| stekern | yeah, I had one of those too, and an amiga 500 at some point | 20:30 |
| glowplug | He had a Karate game, flight sim, all kinds of awesome stuff. I wrote some BASIC programs but I've never excelled at software. O.o | 20:31 |
| glowplug | In fact (asside from CSS/HTML) that was the last time I programmed until I tried to pick up Verilog just recently. 16 year gap! | 20:32 |
| glowplug | If you guys are interested in collaborating with the fabrication side of thise thing you should pop into the channel sometime. You guys can make progress much faster than they can but we need both in the end. =) | 20:34 |
| glowplug | It is #homecmos =) | 20:34 |
| glowplug | Another interesting thing is that although old, there is a complete functional open source toolchain for semiconductor fabrication. Including place and route ect. | 20:35 |
| glowplug | I'm sure at some point in the very near future the two groups will have to collaborate no matter what anyways. Haha | 20:36 |
| stekern | http://www.richardlagendijk.nl/cip/computer/item/pc20iii/en | 20:37 |
| stekern | so it was actually an 8088 | 20:37 |
| stekern | but ours had 720kb DD floppy drive | 20:38 |
| glowplug | Did you ever use cassette tapes for data storage? | 20:38 |
| stekern | on the C64 yes, but this isn't a C64, it's a PC | 20:39 |
| stekern | x86 | 20:39 |
| glowplug | <10mhz one! That is awesome! | 20:39 |
| glowplug | Did you run Unix on this thing? | 20:40 |
| stekern | I've dusted off the old C64 about a year ago and let the kids play some bubble bobble on it ;) | 20:40 |
| stekern | no, just DOS | 20:40 |
| stekern | I remember playing leisure suit larry on it | 20:40 |
| glowplug | I'm still mystified that DOS took over. It is absolutely horrible compared to Unix. | 20:41 |
| glowplug | I may never understand that. | 20:41 |
| stekern | an excellent game, good keyboard and english training for a young boy ;) | 20:41 |
| stekern | "open door" "give apple to man" | 20:41 |
| glowplug | I never thought about it like that. Text RPG's actually would be a great tool for language. | 20:42 |
| stekern | not to mention training in how to handle the ladies (or not!) :) | 20:42 |
| glowplug | Haha | 20:42 |
| GentlemanEnginee | At one point I had at my disposal a barn full of old 8088 clones (result of uncle's failed used computer business). I derived great enjoyment writing assembly "viruses" to push hardware beyond its capabilities (blown tracks, cracked screens, &c). Ah, youth... | 20:44 |
| glowplug | A barn full of 8088's! | 20:45 |
| glowplug | That is pretty much unlimited fun. | 20:45 |
| GentlemanEnginee | It was. | 20:46 |
| GentlemanEnginee | I taught myself assembly for that processor, long before I learned it was not actually designed for hand-assembly. | 20:46 |
| GentlemanEnginee | General Purpose Registers, my left ankle... | 20:46 |
| glowplug | It looks like there is a C compiler for that thing! | 20:50 |
| glowplug | That would have been a lot easier. =D | 20:50 |
| GentlemanEnginee | I did use C. | 20:51 |
| GentlemanEnginee | I also wished to learn assembly. | 20:51 |
| GentlemanEnginee | I was rather young. | 20:51 |
| juliusb | Do you guys mind if I ask what you do at the moment - are you both software engineers or something? | 20:52 |
| GentlemanEnginee | I am an embedded systems developer currently. | 20:54 |
| GentlemanEnginee | Prior to that it has been hardware and some microcontroller. | 20:54 |
| glowplug | <= Insane hobbyist / Linux admin | 20:55 |
| juliusb | Oh cool | 20:55 |
| GentlemanEnginee | My FPGA exposure is rather limited. | 20:55 |
| juliusb | Yes, I would class home CMOS lithography as an insane hobby :) | 20:55 |
| glowplug | I wish I worked more directly with product development with you guys. Maybe some day. =) | 20:56 |
| juliusb | Well, nice. You're in the right place to learn some FPGA/microprocessor stuff I think | 20:56 |
| GentlemanEnginee | However, I did manage to co-design an extremely simplistic processor. | 20:56 |
| glowplug | Also he's being modest! | 20:56 |
| juliusb | product development? me too! not sure we have any products to develop... | 20:56 |
| glowplug | Ahh there it is. Haha | 20:56 |
| juliusb | You guys know each other, then? | 20:57 |
| glowplug | Everybody has products do develop even if they dont realize it yet. =) | 20:57 |
| glowplug | We met in this channel. | 20:57 |
| glowplug | I live in Detroit, MI. | 20:57 |
| juliusb | True - I consider the mor1kx a product. I intend on packaging it up for release sometime soon | 20:57 |
| juliusb | Ah ok, sounded like you were mates from before. | 20:57 |
| GentlemanEnginee | Simply a product of glowplug's bonhomie... | 20:58 |
| glowplug | We are. But before is about 2 weeks ago. Haha | 20:58 |
| glowplug | The design we are working on is based on this. http://bit.ly/11lk0wm | 21:00 |
| glowplug | To anyone interested. =) | 21:00 |
| juliusb | that paper is 16 years old? | 21:01 |
| glowplug | Nope! Wrong link! | 21:01 |
| glowplug | http://bit.ly/10330Kd | 21:01 |
| glowplug | That one is correct. Haha | 21:01 |
| glowplug | Nope. I'm losing it. | 21:02 |
| glowplug | I really need to get these PDF's on the homecmos wiki. | 21:02 |
| glowplug | bit.ly is not very good at this. | 21:02 |
| juliusb | what's the homecmos wiki | 21:04 |
| juliusb | (URL for) | 21:04 |
| glowplug | http://homecmos.drawersteak.com/wiki/Main_Page | 21:04 |
| glowplug | The wiki was put up yesterday so it is severely lacking. | 21:05 |
| glowplug | Andrew in the #homecmos channel is the operator of the wiki. I think him, one other and myself has edit right now. | 21:08 |
| glowplug | Finally found the right PDF. | 21:09 |
| glowplug | bit.ly/Z3uNen | 21:09 |
| stekern | Andrew Zonenberg, right? he's frequently in the #milkymist channel | 21:13 |
| glowplug | Interesting! | 21:20 |
| glowplug | I wonder what he's doing in there and not in here. HAha | 21:20 |
| GentlemanEnginee | juliusb, I am looking at your mo1kx-dev-env, and do not see any test benches, either for the peripherals, or for the mor1kx core. Have I missed something? | 21:22 |
| stekern | GentlemanEnginee: the tests are under sw/tests | 21:24 |
| GentlemanEnginee | I was referring to the Verilog Test Benches. sw/tests appears to be sw tests, in C. | 21:28 |
| stekern | and asm | 21:29 |
| stekern | the cpu testbench is running the sw tests | 21:30 |
| GentlemanEnginee | It is the CPU Testbench that I am having difficulty locating. | 21:32 |
| stekern | https://github.com/juliusbaxter/mor1kx-dev-env/blob/master/boards/generic/mor1kx/bench/verilog/orpsoc_testbench.v | 21:33 |
| stekern | for cappuccino | 21:33 |
| GentlemanEnginee | Thank you stekern. It would have taken me some time to locate that... | 21:36 |
| GentlemanEnginee | BTW, there is no "blob" in the file path... | 21:37 |
| GentlemanEnginee | Or "master" for that matter | 21:37 |
| stekern | boards/generic/mor1kx/bench/verilog/orpsoc_testbench.v | 21:38 |
| GentlemanEnginee | Exactly. | 21:38 |
| stekern | the blob and master is github | 21:39 |
| stekern | master is the branch | 21:39 |
| GentlemanEnginee | I downloaded an archive to look at. | 21:39 |
| stekern | yeah, sure. I just meant that the "blob" and "master" is just part of the github link | 21:41 |
| GentlemanEnginee | Alright. I actually have not used github prior to this. | 21:42 |
| GentlemanEnginee | My humblest apologies for obtuseness... | 21:43 |
| stekern | np :) | 21:43 |
| glowplug | Git can take a little bit to get the hang of. And some of its features are so advanced maybe they will never be used. Haha | 21:47 |
| GentlemanEnginee | You are correct. NP is hard... | 21:48 |
| stekern | humm, what does your NP mean? | 21:50 |
| GentlemanEnginee | A complexity joke. NP = Nondeterministic Polynomial time, ex. the Travelling Salesman Problem. | 21:53 |
| stekern | ah, I see. *My* humblest apologies for obtuseness... =) | 21:58 |
| GentlemanEnginee | Not at all. Not at all. I am overbrimming with obtusosity... | 21:58 |
| stekern | juliusb: I think a lot of modern performance improving techniques could be applied to or1k without changing the architecture | 23:18 |
| stekern | especially with the delay slot made optional | 23:19 |
| stekern | not that there isn't a lot in or1k that could be made better in or2k... | 23:20 |
| glowplug | That's good to hear! Although the performance you guys already have is very good (in my opinion at least!). | 23:26 |
Generated by irclog2html.py 2.15.2 by Marius Gedminas - find it at mg.pov.lt!
