2010-12-11 05:33 xiangfu: http://qt-apps.org/content/show.php/kinyin?content=95926 2010-12-11 05:34 xiangfu: might be interesting for you :) 2010-12-11 06:16 kristianpaul: trabajas en Loongson2f ahora? :) 2010-12-11 06:17 xiangfu: did you commit that 'nerase' change? 2010-12-11 06:17 xiangfu: (I'm lazy to erase the flash... Do you know how should I backup my ubifs for a later nprog ? 2010-12-11 06:17 ) 2010-12-11 06:21 xiangfu: ni hao ma? 2010-12-11 06:28 viric: mount the root to another folder. then use mkfs.ubifs to create an ubi file base on this folder. :) 2010-12-11 06:28 hmmm is it 'the way'? :) 2010-12-11 06:29 viric: that is come out first in my mind. :) 2010-12-11 06:29 ah ok 2010-12-11 06:30 viric: I am not commit that change. 2010-12-11 06:31 xiangfu: why don't you commit it? 2010-12-11 06:31 xiangfu: don't you think it is better than now? 2010-12-11 06:31 viric: I am not well test that change. 2010-12-11 06:31 viric: recently I always working on the openwrt image. 2010-12-11 06:32 viric: and u-boot, a little slow on nerase. :( 2010-12-11 06:32 ok 2010-12-11 07:09 viric: hace un tiempo tengo uno 2010-12-11 07:09 viric: y ciertas cosas no ejecutan bien, por falta del SIMD :S 2010-12-11 07:12 viric: tambien queria comparar el simd del loonsoon con el del xbusrt a ver que puedo esperar de ambos 2010-12-11 07:13 kristianpaul: yo tengo un par de minipc 2010-12-11 07:14 kristianpaul: quÃ© no "ejecuta bien"? 2010-12-11 07:14 viric: gps-sdr.com 2010-12-11 07:16 no carga 2010-12-11 07:17 no :( 2010-12-11 07:17 me hace falta, no se que paso no se a quien contactar para preguntas 2010-12-11 07:17 almenos tengo el codigo 2010-12-11 07:17 hmm espera 2010-12-11 07:18 viric: http://www.ctae.org/sdr/ (mirror del codigo) 2010-12-11 07:21 hey the USRP gnu radio is super expensive :) 2010-12-11 07:22 yes , but i plan get one any time next year i hope 2010-12-11 07:22 is relly usefull for debugging 2010-12-11 07:22 rellay* 2010-12-11 07:23 it looks very ogod 2010-12-11 07:23 good 2010-12-11 07:23 a radio laboratory should have one 2010-12-11 07:24 viric: less espensive that buying separate radio stuff 2010-12-11 07:24 I agre 2010-12-11 07:24 e 2010-12-11 07:24 also you add it a ITX board and you're done 2010-12-11 07:24 i saw openBTS shop and they sell it with on, is good idea 2010-12-11 07:24 can it do CDMA? 2010-12-11 07:25 i dont know 2010-12-11 07:26 kristianpaul: how you test the speed on the minipc for the gps code' 2010-12-11 07:27 correlation time, but first i need pass the simd-like self testÂ Â :) 2010-12-11 07:30 kristianpaul: cÃ³mo lo pruebas? 2010-12-11 07:31 can't you test it without simd? 2010-12-11 07:32 hehe , no i think , simd is heart for acquisition step 2010-12-11 07:36 does the loongson2f have simd instructions for floating point? 2010-12-11 07:36 or your calculations don't involve floating point? 2010-12-11 07:37 i dont know yet, i need read manual first 2010-12-11 07:37 float point dont know either, is just FFT from data-like -1,0,1 2010-12-11 07:40 for what I read... 2010-12-11 07:40 it only has integer SIMD instructions 2010-12-11 07:40 so, they can work as fixed point. 2010-12-11 08:25 damn mocp dint fit on nanonote screen :/ 2010-12-11 08:27 kristianpaul: (simd) you mean the correlation ? 2010-12-11 08:28 nope 2010-12-11 08:28 MMX like instructions 2010-12-11 08:28 kristianpaul: yes, but for what kind of operation ? 2010-12-11 08:29 wpwrak_: fft 2010-12-11 08:29 ah yes, fft should be happier with that 2010-12-11 08:45 are you using fftw3? 2010-12-11 08:47 i will for first test, but i want to try re-use gps-sdr code later 2010-12-11 09:07 [commit] Cristian Paul PeÃ±aranda Rojas: Sync signal to mcu is taken from SiGE as result removed non needed code and fixed identation http://qi-hw.com/p/ben-gps-sdr/f7203fa 2010-12-11 09:07 [commit] Cristian Paul PeÃ±aranda Rojas: Updated simulation, reset trigger removed http://qi-hw.com/p/ben-gps-sdr/f0ae342 2010-12-11 09:07 [commit] Cristian Paul PeÃ±aranda Rojas: Pin asigment is completed http://qi-hw.com/p/ben-gps-sdr/c379297 2010-12-11 09:12 [commit] Cristian Paul PeÃ±aranda Rojas: Added README with basic description and spected behavior http://qi-hw.com/p/ben-gps-sdr/31ad2b4 2010-12-11 09:21 [commit] Cristian Paul PeÃ±aranda Rojas: Updated makefile to be more friendly and removed non required features http://qi-hw.com/p/ben-gps-sdr/4e57bf8 2010-12-11 15:03 he 2010-12-11 15:03 something really weird happen after load bistream to fpga, screen just got crazy :/ and i lost ssh conection 2010-12-11 15:04 on sie? 2010-12-11 15:04 yes 2010-12-11 15:11 hmm is my bitstream 2010-12-11 15:12 what's wrong with port A :/ 2010-12-11 15:16 In theory i just send a 4bits data plus a clock signal at 2.048Mhz 2010-12-11 16:51 hi 2010-12-11 16:52 please anybody could recommend the best book to learn about gpu's? basics 2010-12-11 17:06 I would like to learn the typical GPU's architectures, theorical things 2010-12-11 17:07 not interested in programming GL and such 2010-12-11 17:07 everybody's sleeping? 2010-12-11 17:08 are you more interested in the power supply and clock of the GPU? 2010-12-11 17:11 Madridman: if you're interested in how GPUs are made, have a look at my thesis (on milkymist), and specifically the chapter on the texture mapping unit (tmu) 2010-12-11 17:11 the tmu implements several fundamental features of GPUs 2010-12-11 17:11 but if you have no prior experience with opengl, I'd recommend playing around a bit with it for starters 2010-12-11 17:11 it will really help you understand what is going on 2010-12-11 17:12 lekernel I would like to check your thesis, where is milymist? 2010-12-11 17:12 not interested in opengl, just electronic architecture theorics 2010-12-11 17:12 milkymist.org 2010-12-11 17:12 i do not pretend to program 2010-12-11 17:12 well, opengl understanding will really come handy 2010-12-11 17:13 and opengl is already pretty low-level itself 2010-12-11 17:13 sure but before it could be good to know how the memory etc. are placed 2010-12-11 17:14 all the buses and rest of components 2010-12-11 17:14 lekernel: is the milkymist source available? 2010-12-11 17:14 yes, of course 2010-12-11 17:14 (to me, I mean, for example :) 2010-12-11 17:14 I know plastation and xbox have nothing to do one each other 2010-12-11 17:14 lekernel: is it in vhdl? 2010-12-11 17:14 no, verilog 2010-12-11 17:14 ouch. Bad luck I had. :) 2010-12-11 17:15 verilog is little more than a less verbose vhdl, so if you already know VHDL well enough you'll have little trouble with verilog 2010-12-11 17:15 lekernel sorry, I accessed the web page http://milkymist.org/ but I don't know where is the theorical part of your thesis 2010-12-11 17:15 I never tried verilog. 2010-12-11 17:15 there is a part about architecture? 2010-12-11 17:15 (teoric= 2010-12-11 17:15 ) 2010-12-11 17:16 is it so hard to find that link? http://www.milkymist.org/thesis/thesis.pdf 2010-12-11 17:17 I'll steal it too 2010-12-11 17:18 lekernel that fpga can compete with a commercial architecture? 2010-12-11 17:18 I mean is slower? 2010-12-11 17:18 having seen a demo of ARM Mali on a FPGA, I think it does :) 2010-12-11 17:18 at least performance-wise 2010-12-11 17:19 but it lacks some features (that I didn't need for my application) to make a complete GPU that supports all OpenGL application 2010-12-11 17:19 lekernel: do you use any floating point there? 2010-12-11 17:20 a fpga can be as fast as a commercial video card as ati or nvidia? 2010-12-11 17:20 the texturing unit is fixed point, but the pfpu (roughly, a vertex shader) uses 32-bit ieee 754 2010-12-11 17:20 floating point 2010-12-11 17:20 Madridman: generally no 2010-12-11 17:21 at least for GPU operations 2010-12-11 17:21 so fpga's are not as useful as they say 2010-12-11 17:21 they has limitations 2010-12-11 17:21 (it) 2010-12-11 17:22 everything has limitations 2010-12-11 17:22 the fpga is however a lot more flexible than a gpu 2010-12-11 17:22 ok, do you know a book or web or resource which speaks about fpga's so I could know better them? 2010-12-11 17:22 lekernel: aren't Floating Point operations taking lots of logic in the fpga? 2010-12-11 17:23 just general theory 2010-12-11 17:23 so if your particular application doesn't map nicely to, say, CUDA code, the FPGA can still deliver there 2010-12-11 17:23 viric: no, I'm not using the Opencores FPU ;) 2010-12-11 17:24 lekernel: where did you get the FPU operations from then? 2010-12-11 17:25 I wrote some code... 2010-12-11 17:25 ah 2010-12-11 17:25 lekernel do you know a book or web or resource which speaks about fpga's so I could learn and know better them? 2010-12-11 17:25 it's not 100% IEEE 754 compliant btw 2010-12-11 17:25 ahh. 2010-12-11 17:26 the number format and a lot of things are the same 2010-12-11 17:26 Madridman: get a manual from an FPGA seller 2010-12-11 17:26 but I don't totally respect details of the standard such as the way of rounding numbers 2010-12-11 17:26 Madridman: get the manual for the spartan3 fpga for example. 2010-12-11 17:26 or how to deal with numbers like NaN or infinites 2010-12-11 17:26 viric but I want to know the general common basics, not a concrete seller 2010-12-11 17:26 again - I don't need those for graphics processing 2010-12-11 17:26 clear. 2010-12-11 17:27 Eg. which kind of transistors or biestables are used generically, etc 2010-12-11 17:27 Madridman: that thing you call "generic fpga" does not exist. There are only concrete FPGAs :) 2010-12-11 17:28 ok, imagine I'm new (what is absolutelly true), I never heard about a thing called FPGA. You can't give a manual of a concrete implementation because I don't know even what technology we are speaking about 2010-12-11 17:28 Madridman: look for the "Spartan 3 User Guide" 2010-12-11 17:29 ok 2010-12-11 17:30 that looks as a board to do circuits 2010-12-11 17:30 Madridman: http://lekernel.net/presentations/FPGA_Workshops/ 2010-12-11 17:31 http://lekernel.net/presentations/FPGA_Workshops/091108_tmplab/scenes_draft.pdf will generally explain you how they work internally, but you may want to have some practical experience before 2010-12-11 17:32 Madridman: I call FPGA a chip that can be programmed *by software* to mimic a logic circuit. Software allows you to rearrange whatever is there inside to get as if you had made a circuit concerning whatever FPGA pins you want. 2010-12-11 17:33 ok, but later what you get is a physical circuit isn't it? 2010-12-11 17:33 i mean, logical gates interconnected 2010-12-11 17:34 yes. 2010-12-11 17:35 ok, that pdf's seems to have theorical information too, that's what I need for starters 2010-12-11 17:35 The circuits there come at some limitations, of maximum clock frequency, maximum number of clock signals, maximum number of flip flops... 2010-12-11 17:35 the more you pay, higher the limits 2010-12-11 17:36 I understand 2010-12-11 17:37 the scenes draft looks nice 2010-12-11 17:37 there are hardware description languages, and most FPGA sellers offer 'compilers' for those common languages to whatever their FPGA needs. 2010-12-11 17:37 yes, as vhdl which I hates 2010-12-11 17:37 So you can describe your circuit in a common way, and expect it to work among different FPGA vendors. 2010-12-11 17:37 Madridman: there is also verilog 2010-12-11 17:38 for sure is much better 2010-12-11 17:38 no idea. 2010-12-11 17:38 and how you have such an opinion about that? Some minutes ago you did not know anything about FPGA 2010-12-11 17:38 sure 2010-12-11 17:39 that's because I need theorical resources, to avoid bugging you 2010-12-11 17:39 is reallistic to pretend have a fpga's hardware which competes against commercial circuits (performance, fabrication costs)? 2010-12-11 17:40 no 2010-12-11 17:40 so it'sr just experimental things oriented? 2010-12-11 17:40 by "commercial circuit", you mean full customs ICs? 2010-12-11 17:40 well, a microprocessor yes 2010-12-11 17:40 FPGAs can compete only in the sense that they can be 'reprogrammed' 2010-12-11 17:40 in a typical design 90% of the FPGA transistors are wasted 2010-12-11 17:41 lekernel: hey, talk for your designs 2010-12-11 17:41 ;) 2010-12-11 17:41 my university research for multiexecution architectures specific for some tasks, so there are just experiments 2010-12-11 17:41 but if you compare that to the NRE of spinning an ASIC, sometimes it makes economic sense to keep an FPGA in a product where the FPGA design remains static 2010-12-11 17:42 FPGA over ASICs may have advantages on a) reprogrammability and b) cheaper for small productions 2010-12-11 17:53 http://en.qi-hardware.com/wiki/ASIC_production_notes 2010-12-11 17:59 thank you so much, you both provided me a lot of information 2010-12-11 18:25 hi 2010-12-11 18:27 Hello 2010-12-11 18:35 [commit] David KÃ¼hling: First shot at an Emacs package.Â Â Experimental! http://qi-hw.com/p/openwrt-packages/bea9c01 2010-12-11 18:40 Emacs?? 2010-12-11 18:40 wow 2010-12-11 18:40 :) 2010-12-11 18:48 kristianpaul: using that will require more than thumbs 2010-12-11 19:53 wpwrak: do you have a signal generator at home? 2010-12-11 20:02 yup 2010-12-11 20:02 a Picotest G5100A 2010-12-11 20:03 I'm testing fpga bistream for the serial to parallel stuff on SIE 2010-12-11 20:03 as soon i get loaded the bitstream the LCM got odd interfereance and i lost ssh link 2010-12-11 20:04 i'm not sure if is mestastabillity or something ii'm forgoting to set in port A 2010-12-11 20:04 hmm. so the FPGA is crashing the CPU ? 2010-12-11 20:04 seems 2010-12-11 20:05 i need dig more, i'll do try and error as i lack scopemeter and signal generators at home 2010-12-11 20:05 maybe you're mis-initializing some of the pins ? 2010-12-11 20:05 i think 2010-12-11 20:06 checking that righ now 2010-12-11 20:06 do you have any other program for the fpga that works ? 2010-12-11 20:06 sure 2010-12-11 20:06 and it worked as usual 2010-12-11 20:07 odd then 2010-12-11 20:08 well, you can try translating the one that works step by step to the one that doesn't :) 2010-12-11 20:08 hehe 2010-12-11 20:08 well i could i just wanted do do it before this ;= 2010-12-11 20:08 is just too elaborated for what i wanted to do 2010-12-11 20:09 what is too elaborated ? the debugging process ? 2010-12-11 20:09 no 2010-12-11 20:09 or the "good" one ? 2010-12-11 20:09 yup 2010-12-11 20:10 well is NOT so much, it just was intended to drive FPGA as a memory 2010-12-11 20:11 so you have a buffer to write and read, thats the general idea 2010-12-11 20:11 ah. a bit complex indeed. probably more complex than the serial to parallel converter 2010-12-11 20:12 yup