2014-06-18 00:23 <nicksydney> wpwrak: https://www.kickstarter.com/projects/1973729481/aurbee
2014-06-18 00:27 <wpwrak> must be an interesting definition of "compatible' :)
2014-06-18 00:46 Textmode has joined #qi-hardware
2014-06-18 01:03 nicksydney has quit [Remote host closed the connection]
2014-06-18 01:03 nicksydney has joined #qi-hardware
2014-06-18 02:00 <DocScrutinizer05> x86 dma been slower than CPU sw mem-move since 80186 iirc
2014-06-18 02:02 <DocScrutinizer05> unless CPU does other stuff while DMA completes, it's way more overhead to set up DMA than to do same stuff in software. Even when both in the end reach same transfer rate. And nowadays DMA often is a relic like A20 gate, with CPU copying 10 words in the time where DMA moves one byte
2014-06-18 02:35 <wpwrak> well, x86 dma is kinda special :)
2014-06-18 04:38 valhalla has joined #qi-hardware
2014-06-18 04:42 valhalla_ has quit [Ping timeout: 255 seconds]
2014-06-18 05:49 nicksydney has quit [Remote host closed the connection]
2014-06-18 05:50 nicksydney has joined #qi-hardware
2014-06-18 05:56 jekhor__ has joined #qi-hardware
2014-06-18 06:19 Textmode has quit [*.net *.split]
2014-06-18 06:23 Textmode has joined #qi-hardware
2014-06-18 07:05 luke-jr has quit [Ping timeout: 245 seconds]
2014-06-18 07:11 luke-jr has joined #qi-hardware
2014-06-18 07:11 pcercuei has joined #qi-hardware
2014-06-18 07:27 pcercuei has quit [Ping timeout: 272 seconds]
2014-06-18 07:37 pcercuei has joined #qi-hardware
2014-06-18 08:21 jekhor__ has quit [Ping timeout: 240 seconds]
2014-06-18 08:58 astr has quit [Ping timeout: 245 seconds]
2014-06-18 09:12 astr has joined #qi-hardware
2014-06-18 10:29 <nicksydney> i don't read German but after translating it sounds interesting http://www.mikrocontroller.net/topic/331876
2014-06-18 10:37 <nicksydney> https://www.kickstarter.com/projects/903107259/scio-your-sixth-sense-a-pocket-molecular-sensor-fo
2014-06-18 10:37 <whitequark> oh, that spectrophotometer thing again
2014-06-18 10:37 <whitequark> it's practically useless
2014-06-18 10:39 <nicksydney> why useless ?
2014-06-18 10:39 <nicksydney> $2Million dollar is not useless :)
2014-06-18 10:39 <whitequark> well, it's useful to the ones producing it, sure
2014-06-18 10:40 <nicksydney> time will tell whether they deliver or not..if they do deliver and backers are happy than it's worth the $2Million
2014-06-18 10:40 <nicksydney> wpwrak: it's using BLE too :)
2014-06-18 10:41 <whitequark> nicksydney: they probably will. it doesn't matter. it's a very expensive toy that you can't really use for anything interesting except "omg an apple"
2014-06-18 10:41 <larsc> I don't think you need your smartphone to tell an apple and a banna appart ;)
2014-06-18 10:42 <larsc> banana
2014-06-18 11:08 freespace has quit [Ping timeout: 252 seconds]
2014-06-18 11:10 freespace has joined #qi-hardware
2014-06-18 11:20 Textmode has quit [Ping timeout: 255 seconds]
2014-06-18 11:33 Textmode has joined #qi-hardware
2014-06-18 11:46 Textmode has quit [Ping timeout: 255 seconds]
2014-06-18 11:54 <larsc> apelete: try to find out why and where the DMA based transfers spend there time compared to the PIO method
2014-06-18 11:54 <larsc> maybe that will tell you why it takes longer
2014-06-18 11:55 <pcercuei> DMA is working now?
2014-06-18 11:57 <larsc> 00:36 < apelete> larsc: boot time with mmc dma mode + debug logs = 120s -> http://paste.debian.net/105528/
2014-06-18 11:57 <larsc> 00:36 < apelete> larsc: boot time with mmc dma mode = 70s -> http://paste.debian.net/105545/
2014-06-18 11:57 <larsc> 00:36 < apelete> larsc boot time with mmc pio mode = 34s -> http://paste.debian.net/105548/
2014-06-18 11:57 <larsc> 00:37 < whitequark> wow, pio faster than dma
2014-06-18 11:57 <larsc> 00:37 < apelete> larsc: it takes twice as long to boot with dma enabled, shouldn't dma be faster than pio ?
2014-06-18 12:02 Textmode has joined #qi-hardware
2014-06-18 12:07 <pcercuei> apelete: good job!
2014-06-18 12:10 wolfspraul has joined #qi-hardware
2014-06-18 12:42 jekhor__ has joined #qi-hardware
2014-06-18 12:50 <apelete> pcercuei: thanks :)
2014-06-18 12:51 <apelete> larsc: I was thinking about using something like bootchart, but I guess it won't be detailed enough to spot dma transfers
2014-06-18 12:52 <larsc> yes
2014-06-18 12:53 <apelete> larsc: do you think ftrace could help ?
2014-06-18 12:54 <pcercuei> apelete: what CPU usage do you have during transfers? Ingenic's MMC driver for jz4770 uses DMA, is slow, and uses a lot the CPU
2014-06-18 12:55 <apelete> pcercuei: don't know yet, I only looked at the boot log timing
2014-06-18 12:56 <apelete> I'm going to try a "zcat file >/dev/null" with PIO vs. DMA like wpwrak was suggesting last night
2014-06-18 13:06 <larsc> apelete: Use something like getrawmonotonic() in the driver and messure the time it takes to transfer one block
2014-06-18 13:23 jekhor__ has quit [Read error: Connection reset by peer]
2014-06-18 13:26 jekhor has joined #qi-hardware
2014-06-18 13:44 * DocScrutinizer05 wonders if they really got a proper mass spectrometer in that SCiO thing. If they do (I seen an early prototype of a sugar cube sized mass spectro several years ago at embedded fair in Nuernberg) then this could become a damn lot more than just "tell apat apples from banana" - it would be Abby's wet dream: Major Mass-Spectrometer in your pocket
2014-06-18 13:47 <whitequark> DocScrutinizer05: it's NOT a mass spectrometer
2014-06-18 13:48 <whitequark> you can't have a mass spectrometer without at least a turbomolecular pump, and even if you have, it's more or less useless without a chromatograph
2014-06-18 13:48 <whitequark> they quite plainly explain that what they have is a simple spectrophotometer
2014-06-18 13:48 <DocScrutinizer05> the sugar-cube-mass-spectro was a damn smart ting: thanks to micro size they didn't need to evacuate the "chamber" where molecules get "sorted" in an electric field. And also thanks to the tiny size of the thing, really low voltages were sufficient to create the field to accelerate and deviate the molecules
2014-06-18 13:49 <whitequark> DocScrutinizer05: your sugar-cube thing is NOT a mass-spectrometer
2014-06-18 13:49 <whitequark> http://www.photonics.com/Article.aspx?AID=50898
2014-06-18 13:49 <DocScrutinizer05> oooh, spectrophot is boring useless
2014-06-18 13:49 <whitequark> it's also a NIR spectrophotometer
2014-06-18 13:49 <whitequark> exactly
2014-06-18 13:50 <DocScrutinizer05> *my* sugar cube thing is https://en.wikipedia.org/wiki/File:Mass_Spectrometer_Schematic.svg
2014-06-18 13:50 <whitequark> link?
2014-06-18 13:50 <DocScrutinizer05> BZZZZ you're out
2014-06-18 13:51 <DocScrutinizer05> you may have a few buzzwords, maybe you find a link by yourself: mass spectrometer; fraunhofer; embedded Nuernberg
2014-06-18 13:52 <DocScrutinizer05> and a time frame: maybe 6 to 12 years ago
2014-06-18 13:52 <whitequark> was the first thing I did
2014-06-18 13:52 <whitequark> no relevant results
2014-06-18 13:52 <whitequark> link above is the closest one I found
2014-06-18 13:53 <whitequark> there's some interesting results from DARPA, but what they have is supposed to work on Mars
2014-06-18 13:53 <whitequark> which means you don't even need to have a rough pump. considerably simpler
2014-06-18 13:53 <DocScrutinizer05> I talked with the guy and asked him "but how do you evacuate the thing?". He answered "we don't need to, the gap is so small only a few molecules come in anyway, no matter if it's air or the test substance"
2014-06-18 13:53 <whitequark> interesting
2014-06-18 13:54 <whitequark> did he publish the result in a journal or something?
2014-06-18 13:54 <DocScrutinizer05> *shrug*
2014-06-18 13:54 <whitequark> (that'd make it easier to find)
2014-06-18 13:57 <whitequark> said DARPA thing, btw: http://www.gizmag.com/darpa-mems-smallest-vacuum-pumps/27883/
2014-06-18 14:02 <DocScrutinizer05> I asked him "but you need high voltages to accelerate and do the deviating field, no?"  he answered: " look at this tiny cube. Now figure we have hundreds of electrodes in there, each powered from normal 5V digital logic. We create fields of kV to MV per meter, thanks to the tiny structures"
2014-06-18 14:04 <whitequark> since it's not evacuated, wouldn't such high potential gradient just cause a discharge?
2014-06-18 14:04 <whitequark> and even if it would be
2014-06-18 14:04 <DocScrutinizer05> the gap is so small, there are only a few "dozen" molecules of anything in there at all
2014-06-18 14:05 <DocScrutinizer05> the space is too narrow to contain anything other than a pretty good vacuum
2014-06-18 14:06 <DocScrutinizer05> check out the gradients you have in CPU chips
2014-06-18 14:06 <DocScrutinizer05> horrid
2014-06-18 14:07 <DocScrutinizer05> when you power a modern chip with 5V instead of 1.2V, it probably has sparks all over the complete die ;-)
2014-06-18 14:08 <DocScrutinizer05> a trace with high potential and a ground level trace my be separated only a few dozen nanometers
2014-06-18 14:08 <DocScrutinizer05> may*
2014-06-18 14:08 <whitequark> hm, you're right
2014-06-18 14:09 <DocScrutinizer05> 1V difference makes for a gradient of 10E6 to 10E8V/m
2014-06-18 14:32 FDCX has quit [Remote host closed the connection]
2014-06-18 14:33 FDCX has joined #qi-hardware
2014-06-18 14:38 jekhor_ has joined #qi-hardware
2014-06-18 14:41 jekhor has quit [Ping timeout: 255 seconds]
2014-06-18 15:10 Textmode has quit [Ping timeout: 255 seconds]
2014-06-18 15:43 wolfspra1l has joined #qi-hardware
2014-06-18 15:43 wolfspraul has quit [Quit: leaving]
2014-06-18 15:43 wolfspra1l has quit [Client Quit]
2014-06-18 15:44 wolfspraul has joined #qi-hardware
2014-06-18 16:01 kilae has joined #qi-hardware
2014-06-18 16:04 pcercuei has quit [Ping timeout: 244 seconds]
2014-06-18 17:14 jekhor__ has joined #qi-hardware
2014-06-18 17:18 jekhor_ has quit [Ping timeout: 245 seconds]
2014-06-18 17:35 jekhor__ has quit [Ping timeout: 240 seconds]
2014-06-18 17:36 jekhor has joined #qi-hardware
2014-06-18 17:41 jekhor has quit [Read error: Connection reset by peer]
2014-06-18 17:42 jekhor has joined #qi-hardware
2014-06-18 17:43 jekhor has quit [Read error: Connection reset by peer]
2014-06-18 17:43 jekhor has joined #qi-hardware
2014-06-18 17:48 jekhor has quit [Read error: Connection reset by peer]
2014-06-18 17:51 jekhor has joined #qi-hardware
2014-06-18 18:36 jekhor has quit [Ping timeout: 240 seconds]
2014-06-18 19:35 kilae has quit [Quit: ChatZilla 0.9.90.1 [Firefox 29.0.1/20140506152807]]
2014-06-18 20:56 wolfspraul has quit [Quit: leaving]
2014-06-18 23:30 Textmode has joined #qi-hardware