your theory would be fine except for the slight problem that without ARM Inc the massive global low power smartphone market wouldn't exist today, in fact its only since the ARM cortex A8 that most average users finally realized that ARM existed, but they have been around a very long time and all the many ARM vendor licencee's have sown up the Mass low power world markets a very long time ago now.
sure there always was a small contingent of superH, MIPS etc vendors in phones to also contribute a small % and perhaps finally Intel will also find a place and help fill that small sub section of the world markets sometime soon, but remember this is not your old school x86 market place and the masses of long time ARM licencee's will not give up their low power top spot without a fight even for that small NON ARM corner.
as for "dozens of variations that are all incomparable with each other. So the market is flexible" you also have to remember and realize that's exactly what all these many ARM licencee's today are in the "Linaro" initiative to have all their ARM engineers actually write the new Cortex ARM/NEON SIMD optimized code and integrate or throw out all their old disparate ARM code bases into a single binary and submit it upstream in to the Kernel for all ARM/NEON vendors to simply load and use, and yet still remain flexible.
they are in effect providing a new standard base ARM platform infrastructure with ARM cortex at the core , again see Charbax's 32 videos at the Linaro Connect show to get a flavor of whats what http://slashdot.org/submission/2097239/videos-linaro-engineers-talk-about-the-status-of-linux-on-arm
as you say Tough Love, i too cant see Intel matching $ for $ the likes in bulk of for instance Freescale and their £22ish per 1.2ghz i.MX6 Quad core SOC with any of their intel offerings today or any time soon and that's just one single ARM white box vendor never mind any of the other vendors with faster ARM A15 and better SOC on the table this year.
TSMC skips 22-nm, rolls 20-nm process.... (TSMC) is putting a new spin on its strategy: After the 28-nm node, it plans to skip the 22-nm ''full node'' and will move directly to the 20-nm ''half node.''
At its technology conference here, the world's largest silicon foundry also provided details about its 20-nm CMOS process, which will be the company's main technology platform after the 28-nm node. TSMC will also not offer an 18-nm process.
TSMC's 20-nm process is a 10-level metal technology based on a planar technology. It will feature a high-k/metal gate scheme, strained silicon and newfangled ''low-resistance'' copper ultra-low-k interconnects--or what it calls ''low-r.
'' For the 20-nm node, it will only offer a high-k/metal-gate scheme for the gate stack--and not a silicon dioxide option. TSMC (Hsinchu) will continue to use 193-nm immersion lithography at 20-nm, but it will also deploy a double-patterning and source-mask optimization schemes.
Unlike its previous processes in recent times--which focused on low power first--TSMC's initial 20-nm process will be a high-performance technology. Following that process, it will roll out a low-power technology.
With the announcement, TSMC is seeking to gain an edge over its leading-edge rivals, such a GlobalFoundries, Samsung and UMC....."
thats what TSMC is for and why ARM inc have them and IBM etc as core partners for their tape out implementation program as in http://www.eetimes.com/electronics-news/4229820/ARM-TSMC-design-20-nm-A15-processor from way back in 10/18/2011
ARM said it would now optimize its physical IP to the TSMC 20-nm process for power, performance and area and produce a specification for a Cortex-A15 processor optimization pack (POP). It did not say how soon this would be completed.
"This first 20-nm ARM Cortex-A15 tape out paves the way for the next generation of SoC integration and performance," said Mike Inglis, general manager of ARM's processor division, in a statement. These SoCs will be suitable for smartphones, tablet computers, digital home systems, servers and wireless infrastructure, ARM said.
sure you could do that , or you could finally do it right and read and actually implement in several prototype current patches for popular app's , video,audio,streaming,encoding etc from Brinch Hansen's paper's back when paper's really did solve practical problem's http://brinch-hansen.net/papers/
did you miss the part where ARM cortex A9 + NEON SIMD have HDMI output these days or the fact these also have The new Mali T400 platform, and the next one The new Mali T604 platform will have http://www.rethink-wireless.com/print.asp?article_id=3942 "Samsung backs ARM's souped-up graphics platform Mali T604 will support HD and 3D in low power devices, says ARM CAROLINE GABRIEL Published: 11 November, 2010... he new Mali T604 platform, unveiled at ARM's developer conference this week, aims to bring high performance applications like 3D imaging and gaming to smartphones, without sacrificing battery life. The upgraded graphics processor will accelerate video applications while drawing less power, said marketing director Ian Smythe, and will handle 3D imaging and full HD video. Performance is up fivefold on the previous Mali, and when included in a chip, the core consumes less than 850 milliwatts. Mali is designed to work with ARM's latest CPU core, the Cortex-A15, which targets smartphones, tablets and even servers. Up to 16 2.5GHz cores can work together for these larger systems.
Mali T604 will be compatible with Microsoft's DirectX 11 and with OpenCL 1.1, both programming frameworks for parallel processing over multiple cores. The inclusion of DirectX 11 aroused speculation that this programming technology would soon be supported fully in Windows Phone 7. Currently, full compatibility with DirectX 11 is only seen in Windows 7..."
you may also find these interesting too http://liliputing.com/2011/01/freescale-introduces-new-single-dual-and-quad-core-chips.html "... the 6Quad the most expensive, the price difference isn’t expected to be all that great. Freescale tells me the single core chip will be available to device makers for under $10, while the quad core will cost more than $20, with the dual core model falling somewhere in between. Sure, that means the quad-core chip will cost more than twice as much as the single core chip, but we’re still not talking about a lot of money here...."
"Freescale will be among the first companies to make quad core ARM-based chips available. All three new chips will begin sampling in the second quarter of 2011, and the company expects devices using the new chips to hit the market before the end of the year...."
http://www.linuxfordevices.com/c/a/News/Freescale-iMX-6/ ".... The i.MX 6 series is Freescale's first ARM-based multicore SoC and first Cortex-A9 model. The processor advances the i.MX family with dual-stream 1080p video playback at 60 frames per second (fps), 3D video playback at 50Mbps, desktop-quality gaming, augmented reality applications, and novel content creation capabilities, says Freescale.
The SoC is also touted for being one of the first applications processors to offer hardware support for the open source VP8 codec. VP8 drives the related WebM open container format, both of which are supported in the most recent Android 2.3 release.
The i.MX 6 series uses 40nm fabrication and provides low power draw and advanced power management capabilities, says Freescale. The SoC is claimed to enable 1080p video (single stream) with only 350mW consumption. As a result, the i.MX 6 series can deliver up to 24 hours of HD video playback and 30-plus days of device standby time, claims the company....."
"The video coprocessor, meanwhile, is said in the dual or quad versions to support 1080p60 H.264 video decode. It also provides for 720p60 encode of H.264, with "1080p planned," says Freescale. Separately, Freescale refers to a 1080p30 encode feature, but it is unclear whether this will be available in the initial release or is the aforementioned "planned" feature.
The i.MX 6's image processing unit (IPU) supports a whopping four displays via HDMI 1.4, and offers stereoscopic image sensor support for 3D imaging, says the company. Other IPU features are said to include color adjustments, gamut mapping, gamma correction, contrast stretching, as well as compensation
" I'm interested to hear what smartphone apps/features/functions — if any — Slashdot readers reckon quad-core chips would enable"
that's totally missing the real long term point of cortex , its not the smart phone , nit rather the form factor and far lower power for at full load on your desk that matters most
for instance the http://armdevices.net/2011/03/03/trim-slice-tegra2-arm-cortex-a9-dual-core-desktop/ or even making the so dimm form factor instant plug in and power on popular http://armdevices.net/2011/03/04/toradex-shows-tegra2-computer-on-so-dimm-form-factor/
and OC dont forget the lower power of your server http://armdevices.net/2011/03/14/arm-powered-servers-designed-by-calxeda-could-be-10x-more-efficient-than-intel ARM Powered servers designed by Calxeda could be 10x more efficient than Intel Posted by Charbax – March 14, 2011... The SOC, as Calxeda will demonstrate with one of its reference designs, will enable OEMs to design servers as dense as 120 ARM quad-core nodes (480 cores) in a 2U enclosure, with an average consumption of about 5 watts per node (1.25 watts per core) including DRAM....
its not always a case that its low quality encoding though.
you are aware that the BBC is as far as i know the only broadcasters that do multicasting test AVC/H.264 broadcasting,assuming your ISP (alas Virgin Media dont ) allows and activates multicasting on their network.
true now you do have to ask to be included in the trials by email but their there if your able to use multicasting over the net,shame theres no simple tunneling app.... http://www.bbc.co.uk/multicast/
And as I pointed out, 20% is pretty much in the BEST of circumstances. Don't expect to get that with most encodings. There are some cases where h.264 does worse than codecs like lavc and xvid... That's mainly because the latter are simply more mature.
Right now, h.264 just doesn't come out as a plus. Sticking to <b>MPEG-4 is a better idea</b> for at least a few years into the future."</blockquote>
(again with the generic MPEG-4 were you know it should be ASP or AVC but lets progress) im sorry but thats just plain wrong.
its 2007 not 2004/5 were your assumptions for the AVC MIGHT have been valid.
i assume your in the US in which case you might not be aware, but today in the much of the EU and beyond its perfectly possible to get Hi-Def AVC down to SD Mpeg2 biterates and currently its standard for commercial realtime HD AVC encoding to be around the 6mbit/s bitrate and getting smaller.
heres a cut and paste of a post i made a few months back to give you an idea of how things actually are today. "yea that seems cool, but lets hope some Exec with a brain and an eye on the long term future picks the AVC (aka H.264/MPEG-4 Part 10) codec rather than some accountant messing with the short term books.......
the link is 3 pages long, so heres an overview http://www.newvideobusiness.com/content/view/74/26/
" 'Bookmarks' in this feature (just follow the section headings): VC-1 IS SIDELINED FOR REAL-TIME BROADCASTING DUAL-CODEC APPROACH AT TIER-1 TELCOS CONTINUING ROLE FOR MPEG-2 -- EVEN ON IPTV IPTV MPEG-2/AVC MIGRATIONS SATELLITE ADOPTS AVC FOR HDTV CABLE HAS LESS NEED FOR ADVANCED CODING ADVANCED COMPRESSION ON DIGITAL TERRESTRIAL DTT REMAINS LARGELY MPEG-2 AVC HALVING BIT RATES SWEET SPOT FOR HDTV IS 6-7.5Mbps IPTV NEEDS TWO SIMULTANEOUS HD STREAMS SATELLITE PUTS A PREMIUM ON PICTURE QUALITY HDTV COULD BE POSSIBLE "IN 3-3.5Mbps" HDTV BECOMING THE NEW STANDARD-DEFINITION? TANDBERG TELEVISION'S NEW COMPRESSION ENGINE TIER-1 QUALITY HDTV ONTO DENSE TELCO PLATFORMS FOUR HD, FOUR SD AND FOUR PIP FROM 1RU HARMONIC'S NEW SD AND HD ENCODING PLATFORMS FOUR CHANNELS OF HDTV FROM 1RU HARMONIC MOVES AWAY FROM MPEG-2/AVC PLATFORMS "STILL A NEED FOR MPEG-2/AVC PLATFORMS" DEBATE ABOUT IMPORTANCE OF DENSITY BUT NEAR-CONSENSUS ABOUT VC-1 KEY DEPLOYMENTS: WHO USES WHO? SCOPUS FINALISING HD PLATFORM"
NTL:tw accountant said *| LOL "A spokesman says, "We are using MPEG-2 because we can."
" AVC HALVING BIT RATES The good news for operators on all platforms is that AVC is living up to its hype and halving bit rates compared to MPEG-2.
The fastest gains appear to be for high-definition, where the world's leading encoder vendors have set their sights over the last 24 months.
So, from bit rates of up to 20Mbps for HDTV on MPEG-2 a couple of years ago, like-for-like HD services plummeted to around 8Mbps on leading-edge advanced encoders this time last year.
By IBC (Amsterdam exhibition) this September, the figures will be 6-8Mbps depending on content, with the most bullish predictions being for sub-6Mbps for hard-to-encode content like sports."
" Depending on who you talk to, the so-called 'sweet spot' for HDTV is between 6Mbps and 7.5Mbps.
Carl Furgusson, VP product management at TANDBERG Television, comments: "We are getting to the point where we can get to around 6Mbps for HDTV with top quality pictures and with statistical multiplexing you can get between 6-8 satellite services onto a 36Mbps transponder."
In fact, TANDBERG claims that with its latest encoder it can deliver more than eight channels of full-resolution HDTV on a 36MHz transponder using DVB-S2 (the latest satellite transmission standard) and 8PSK."
notice thats Mpeg-2 NOT HD Mpeg-2 "HDTV COULD BE POSSIBLE "IN 3-3.5Mbps" Harmonic is also pushing the boundaries of bit rate reduction, claiming sub-6Mbps for
sorry that should be.
after all AVC/AAC makes it clear and common sense, rather than H.264/AAC and MPeg-4/AAC makes no sense at all, as is it the old codec ASP or the far better and newer AVC (with lossless options, that ASP does NOT) your average user is refering to ?.
ofcourse people keep using the MPEG-4 term to refer to a single codec when in fact its a general term that in the case of the video, YOU should be using eather ASP (aka Mpeg-4 Part2) OR AVC (aka Mpeg-4 part 10) to qualify the codec.
why is it everyone even here were you should know better, are still using generic MPEG-4 instead of the right terms.
after all AVC/AAC makes it clear and common sense, rather than H.264/ACC and MPeg-4/AAC makes no sense at all as is it the old codec _ASP_ or the far better and newer _AVC_ (with lossless options, that ASP doe NOT)your average user is refering to ?.
btw , AVI isnt a file, its a container.
Re:The Amiga Could Run THREE OS's at Once!
on
AmigaOS 4
·
· Score: 1
"throwing x86 cards into an a3000 is no more special than buying a small pc and running it under your desk.. vmware IS special - throw vmware server onto a fast multi-core linux box and be amazed. (1.6ghz quad core xeons are less than 350 USD afterall)
Sun had x86 cards since the supersparc days, and HP supported this on the PA-RISC arch natively!"
ohh come on, you apparently know a few things about the older tech, but you have to admit that the 286/386/486 bridgeboards for the old amiga were rather more than your average £1000/$2000 home PC today has...
why is it your lumping the home Amiga PC in with these industrial strength server boxs and kit, hardly seems fair to compare unless your trying to say that even the way back x86 cards inside the A3000UX with its offical Unix port/support can still compare rather well to these massivly more expensive server grade boxs?...
if you have never owned or used these tricked out Amiga boxs and kit and are willing to listen, it seems this thread (well done btw for keeping it civil/helpful/informative etc) is full of the old helpful amiga crew that can try and give advice and info to help you understand.
i always liked the (forgive me if i get it slighty wrong syntax been a while LOL) ---------------- makedir s:web assign web: s:web add mount tcpweb: assign www.big-arse-super----------------duper-long-url web: 1 ----------------
i forget if thats the right syntax but you get the picture, web: is infact the added s:web dir made earlyer and you can add as many assigns as you like and have the system search each one as though it were one dir etc.
i also liked requestchoice "this-window" "quit" "Ok" "1" "2" "3" for makign quick and easy GUi scripts, shame these request* cli/shell commands and kingcon: shell were never ported to windows and linux as then anyone could use something aproaching a super small quick cli/GUI amiga script.
"YttriumOxide said:
I've said it before (and will therefore probably get my first ever "redundant" mod) but if he's wanting OS4, then AROS is *NOT* the answer. Unless you consider Win95 the answer to someone looking for Windows Vista!"
sure , you have said it but it seems your under the impression that AROS being at its original base a 1.3 clone is in some way restricting it to that old version as its limit.
take a look at some of the current AROS screenshots http://aros.sourceforge.net/pictures/screenshots/ and tell me thats your idea of a restricted 1.3 AOS clone....
the fact is AROS can become anything you want it to become (within the Amiga realm/idea's etc) all it takes is your time to code it up and submit it.
btw Dammy, you should also tell them your the AROS bounty treasery guy, and that CURRENTLY the PPC port hasnt started yet, as it appears the current devs are all x86 based and favour that atm.
unless its changed in the last few days perhaps?, is there any new or old amiga devs now hacking on PPC AROS perhaps ready to load/run a usable AROS PPC compile on the coming UK/EU PS3 soon!.
perhaps someones now cross-compiling to the http://www.powerdeveloper.org/8641d.php but you have not seen fit to make it known yet ?, or perhaps non of the above as i note you said elsewere your finding it hard to get new PPC based OSS devs involved?.
so are there any OSS PPC devs here or infact x86 devs that are thinking of getting and playing with PPC linux/AROS/whatever on the PS3 once it arrives ?, will you consider taking one or more of the bountys or would you work on somthing else that interests you and ask that a bounty be put up for it as your reqard for your efforts in PPC AROS perhaps...?
apparently a new-age fanboy there; but ignoring most of what you said its interesting to note
for reference
"emulated mac better than a mac shame linux was not out it probably ould have dusted a pc at running it..."
true the 3rd party mac emulators and the hardware 68k mac add-ins etc were faster...
many of these were 3rd party amiga hardware/software devs btw.
as for Linux , well we had to make do with official payed for ports of AT&T Unix System V Release 4 at that time...
http://en.wikipedia.org/wiki/Amiga_Unix
did anyone try loading that into one of the emulators BTW?, that might be interesting to see.
"rufty_tufty said: the other trick is to use Knoppix, create a ram drive (the size of the CD), copy the cd into the ram drive, and boot from there - now that is a fast system!"
sure, that so call 'trick' might work rather well, infact it the same concept of the old Amiga RAD disk (Recoverable rAm Disk) but to this day AFAIK, there is no other OS/machine/app that can infact keep that ram copy in a recoverable ram and boot from it after a warmboot?, is there infact such a thing for linux or windows today?.
the RAD IS/was rather cool keeping in mind you can mearly copy any file/dir, assign it as whatever you like and boot it , so it was trivial to make a RAD, fill it with your boot assigns options/apps then copy it to a dir somewere, then you had an enarc mount a RAD,copy that disk dir to the rad and reboot after that every reset would auto boot the RAD as it was still available in ram so no need to keep copying that HD dir on reset... now thats cool and way faster than booting/copying from harddrive every time...
average first (HD)boot time 20 seconds, after that , RAD boot times,between 4 and 15 seconds depending on what your usual booting stuff is/was/
Slashdot Mirror
your theory would be fine except for the slight problem that without ARM Inc the massive global low power smartphone market wouldn't exist today, in fact its only since the ARM cortex A8 that most average users finally realized that ARM existed, but they have been around a very long time and all the many ARM vendor licencee's have sown up the Mass low power world markets a very long time ago now.
sure there always was a small contingent of superH, MIPS etc vendors in phones to also contribute a small % and perhaps finally Intel will also find a place and help fill that small sub section of the world markets sometime soon, but remember this is not your old school x86 market place and the masses of long time ARM licencee's will not give up their low power top spot without a fight even for that small NON ARM corner.
as for "dozens of variations that are all incomparable with each other. So the market is flexible" you also have to remember and realize that's exactly what all these many ARM licencee's today are in the "Linaro" initiative to have all their ARM engineers actually write the new Cortex ARM/NEON SIMD optimized code and integrate or throw out all their old disparate ARM code bases into a single binary and submit it upstream in to the Kernel for all ARM/NEON vendors to simply load and use, and yet still remain flexible.
they are in effect providing a new standard base ARM platform infrastructure with ARM cortex at the core , again see Charbax's 32 videos at the Linaro Connect show to get a flavor of whats what http://slashdot.org/submission/2097239/videos-linaro-engineers-talk-about-the-status-of-linux-on-arm
as you say Tough Love, i too cant see Intel matching $ for $ the likes in bulk of for instance Freescale and their £22ish per 1.2ghz i.MX6 Quad core SOC with any of their intel offerings today or any time soon and that's just one single ARM white box vendor never mind any of the other vendors with faster ARM A15 and better SOC on the table this year.
LOL true, but no one cares as long as ARM Inc provides a Processor Optimization Pack (POP) for a given provider process and they do.
Guspaz, they skipped 22nm and went directly to 20nm as per their original 2010 plan
....
...."
http://www.eetimes.com/electronics-news/4088580/TSMC-skips-22-nm-rolls-20-nm-process
"Mark LaPedus
4/13/2010 1:30 PM EDT
TSMC skips 22-nm, rolls 20-nm process
(TSMC) is putting a new spin on its strategy: After the 28-nm node, it plans to skip the 22-nm ''full node'' and will move directly to the 20-nm ''half node.''
At its technology conference here, the world's largest silicon foundry also provided details about its 20-nm CMOS process, which will be the company's main technology platform after the 28-nm node. TSMC will also not offer an 18-nm process.
TSMC's 20-nm process is a 10-level metal technology based on a planar technology. It will feature a high-k/metal gate scheme, strained silicon and newfangled ''low-resistance'' copper ultra-low-k interconnects--or what it calls ''low-r.
'' For the 20-nm node, it will only offer a high-k/metal-gate scheme for the gate stack--and not a silicon dioxide option.
TSMC (Hsinchu) will continue to use 193-nm immersion lithography at 20-nm, but it will also deploy a double-patterning and source-mask optimization schemes.
Unlike its previous processes in recent times--which focused on low power first--TSMC's initial 20-nm process will be a high-performance technology. Following that process, it will roll out a low-power technology.
With the announcement, TSMC is seeking to gain an edge over its leading-edge rivals, such a GlobalFoundries, Samsung and UMC.
thats what TSMC is for and why ARM inc have them and IBM etc as core partners for their tape out implementation program as in
http://www.eetimes.com/electronics-news/4229820/ARM-TSMC-design-20-nm-A15-processor
from way back in 10/18/2011
ARM said it would now optimize its physical IP to the TSMC 20-nm process for power, performance and area and produce a specification for a Cortex-A15 processor optimization pack (POP). It did not say how soon this would be completed.
"This first 20-nm ARM Cortex-A15 tape out paves the way for the next generation of SoC integration and performance," said Mike Inglis, general manager of ARM's processor division, in a statement. These SoCs will be suitable for smartphones, tablet computers, digital home systems, servers and wireless infrastructure, ARM said.
sure you could do that , or you could finally do it right and read and actually implement in several prototype current patches for popular app's , video,audio,streaming,encoding etc from Brinch Hansen's paper's back when paper's really did solve practical problem's http://brinch-hansen.net/papers/
https://docs.google.com/viewer?url=http%3A%2F%2Fbrinch-hansen.net%2Fpapers%2F1995d.pdf
https://docs.google.com/viewer?url=http%3A%2F%2Fbrinch-hansen.net%2Fpapers%2F1995e.pdf
https://docs.google.com/viewer?url=http%3A%2F%2Fbrinch-hansen.net%2Fpapers%2F1978a.pdf
etc....
did you miss the part where ARM cortex A9 + NEON SIMD have HDMI output these days or the fact these also have The new Mali T400 platform, and the next one The new Mali T604 platform will have http://www.rethink-wireless.com/print.asp?article_id=3942 ...
"Samsung backs ARM's souped-up graphics platform
Mali T604 will support HD and 3D in low power devices, says ARM
CAROLINE GABRIEL
Published: 11 November, 2010
he new Mali T604 platform, unveiled at ARM's developer conference this week, aims to bring high performance applications like 3D imaging and gaming to smartphones, without sacrificing battery life. The upgraded graphics processor will accelerate video applications while drawing less power, said marketing director Ian Smythe, and will handle 3D imaging and full HD video. Performance is up fivefold on the previous Mali, and when included in a chip, the core consumes less than 850 milliwatts.
Mali is designed to work with ARM's latest CPU core, the Cortex-A15, which targets smartphones, tablets and even servers. Up to 16 2.5GHz cores can work together for these larger systems.
Mali T604 will be compatible with Microsoft's DirectX 11 and with OpenCL 1.1, both programming frameworks for parallel processing over multiple cores. The inclusion of DirectX 11 aroused speculation that this programming technology would soon be supported fully in Windows Phone 7. Currently, full compatibility with DirectX 11 is only seen in Windows 7..."
you may also find these interesting too
http://liliputing.com/2011/01/freescale-introduces-new-single-dual-and-quad-core-chips.html
"...
the 6Quad the most expensive, the price difference isn’t expected to be all that great. Freescale tells me the single core chip will be available to device makers for under $10, while the quad core will cost more than $20, with the dual core model falling somewhere in between. Sure, that means the quad-core chip will cost more than twice as much as the single core chip, but we’re still not talking about a lot of money here...."
"Freescale will be among the first companies to make quad core ARM-based chips available. All three new chips will begin sampling in the second quarter of 2011, and the company expects devices using the new chips to hit the market before the end of the year...."
http://www.linuxfordevices.com/c/a/News/Freescale-iMX-6/
"....
The i.MX 6 series is Freescale's first ARM-based multicore SoC and first Cortex-A9 model. The processor advances the i.MX family with dual-stream 1080p video playback at 60 frames per second (fps), 3D video playback at 50Mbps, desktop-quality gaming, augmented reality applications, and novel content creation capabilities, says Freescale.
The SoC is also touted for being one of the first applications processors to offer hardware support for the open source VP8 codec. VP8 drives the related WebM open container format, both of which are supported in the most recent Android 2.3 release.
The i.MX 6 series uses 40nm fabrication and provides low power draw and advanced power management capabilities, says Freescale. The SoC is claimed to enable 1080p video (single stream) with only 350mW consumption. As a result, the i.MX 6 series can deliver up to 24 hours of HD video playback and 30-plus days of device standby time, claims the company....."
"The video coprocessor, meanwhile, is said in the dual or quad versions to support 1080p60 H.264 video decode. It also provides for 720p60 encode of H.264, with "1080p planned," says Freescale. Separately, Freescale refers to a 1080p30 encode feature, but it is unclear whether this will be available in the initial release or is the aforementioned "planned" feature.
The i.MX 6's image processing unit (IPU) supports a whopping four displays via HDMI 1.4, and offers stereoscopic image sensor support for 3D imaging, says the company. Other IPU features are said to include color adjustments, gamut mapping, gamma correction, contrast stretching, as well as compensation
" I'm interested to hear what smartphone apps/features/functions — if any — Slashdot readers reckon quad-core chips would enable"
...
that's totally missing the real long term point of cortex , its not the smart phone , nit rather the form factor and far lower power for at full load on your desk that matters most
for instance the
http://armdevices.net/2011/03/03/trim-slice-tegra2-arm-cortex-a9-dual-core-desktop/
or even making the so dimm form factor instant plug in and power on popular
http://armdevices.net/2011/03/04/toradex-shows-tegra2-computer-on-so-dimm-form-factor/
and OC dont forget the lower power of your server
http://armdevices.net/2011/03/14/arm-powered-servers-designed-by-calxeda-could-be-10x-more-efficient-than-intel
ARM Powered servers designed by Calxeda could be 10x more efficient than Intel
Posted by Charbax – March 14, 2011
The SOC, as Calxeda will demonstrate with one of its reference designs, will enable OEMs to design servers as dense as 120 ARM quad-core nodes (480 cores) in a 2U enclosure, with an average consumption of about 5 watts per node (1.25 watts per core) including DRAM....
its not always a case that its low quality encoding though.
,assuming your ISP (alas Virgin Media dont ) allows and activates multicasting on their network.
you are aware that the BBC is as far as i know the only broadcasters that do multicasting test AVC/H.264
broadcasting
http://support.bbc.co.uk/multicast/streams.html
true now you do have to ask to be included in the trials by email but their there if your able to use multicasting over the net,shame theres no simple tunneling app....
http://www.bbc.co.uk/multicast/
sorry that should be. after all AVC/AAC makes it clear and common sense, rather than H.264/AAC and MPeg-4/AAC makes no sense at all, as is it the old codec ASP or the far better and newer AVC (with lossless options, that ASP does NOT) your average user is refering to ?.
ofcourse people keep using the MPEG-4 term to refer to a single codec when in fact its a general term that in the case of the video, YOU should be using eather ASP (aka Mpeg-4 Part2) OR AVC (aka Mpeg-4 part 10) to qualify the codec.
why is it everyone even here were you should know better, are still using generic MPEG-4 instead of the right terms.
after all AVC/AAC makes it clear and common sense, rather than H.264/ACC and MPeg-4/AAC makes no sense at all as is it the old codec _ASP_ or the far better and newer _AVC_ (with lossless options, that ASP doe NOT)your average user is refering to ?.
btw , AVI isnt a file, its a container.
"throwing x86 cards into an a3000 is no more special than buying a small pc and running it under your desk.. vmware IS special - throw vmware server onto a fast multi-core linux box and be amazed. (1.6ghz quad core xeons are less than 350 USD afterall)
Sun had x86 cards since the supersparc days, and HP supported this on the PA-RISC arch natively!"
ohh come on, you apparently know a few things about the older tech, but you have to admit that the 286/386/486 bridgeboards for the old amiga were rather more than your average £1000/$2000 home PC today has...
why is it your lumping the home Amiga PC in with these industrial strength server boxs and kit, hardly seems fair to compare unless your trying to say that even the way back x86 cards inside the A3000UX with its offical Unix port/support can still compare rather well to these massivly more expensive server grade boxs?...
if you have never owned or used these tricked out Amiga boxs and kit and are willing to listen, it seems this thread (well done btw for keeping it civil/helpful/informative etc) is full of the old helpful amiga crew that can try and give advice and info to help you understand.
i always liked the (forgive me if i get it slighty wrong syntax been a while LOL)
----------------
makedir s:web
assign web: s:web add
mount tcpweb:
assign www.big-arse-super----------------duper-long-url web: 1
----------------
i forget if thats the right syntax but you get the picture, web: is infact the added s:web dir made earlyer
and you can add as many assigns as you like and have the system search each one as though it were one dir etc.
i also liked requestchoice "this-window" "quit" "Ok" "1" "2" "3"
for makign quick and easy GUi scripts, shame these request* cli/shell commands and kingcon: shell
were never ported to windows and linux as then anyone could use something aproaching a super small quick cli/GUI amiga script.
mount speak: say "this is amiga speaking" LOL.
"YttriumOxide said: I've said it before (and will therefore probably get my first ever "redundant" mod) but if he's wanting OS4, then AROS is *NOT* the answer. Unless you consider Win95 the answer to someone looking for Windows Vista!" sure , you have said it but it seems your under the impression that AROS being at its original base a 1.3 clone is in some way restricting it to that old version as its limit. take a look at some of the current AROS screenshots http://aros.sourceforge.net/pictures/screenshots/ and tell me thats your idea of a restricted 1.3 AOS clone.... the fact is AROS can become anything you want it to become (within the Amiga realm/idea's etc) all it takes is your time to code it up and submit it. btw Dammy, you should also tell them your the AROS bounty treasery guy, and that CURRENTLY the PPC port hasnt started yet, as it appears the current devs are all x86 based and favour that atm. unless its changed in the last few days perhaps?, is there any new or old amiga devs now hacking on PPC AROS perhaps ready to load/run a usable AROS PPC compile on the coming UK/EU PS3 soon!. perhaps someones now cross-compiling to the http://www.powerdeveloper.org/8641d.php but you have not seen fit to make it known yet ?, or perhaps non of the above as i note you said elsewere your finding it hard to get new PPC based OSS devs involved?. so are there any OSS PPC devs here or infact x86 devs that are thinking of getting and playing with PPC linux/AROS/whatever on the PS3 once it arrives ?, will you consider taking one or more of the bountys or would you work on somthing else that interests you and ask that a bounty be put up for it as your reqard for your efforts in PPC AROS perhaps...?
apparently a new-age fanboy there; but ignoring most of what you said its interesting to note for reference "emulated mac better than a mac shame linux was not out it probably ould have dusted a pc at running it ..."
true the 3rd party mac emulators and the hardware 68k mac add-ins etc were faster...
many of these were 3rd party amiga hardware/software devs btw.
as for Linux , well we had to make do with official payed for ports of AT&T Unix System V Release 4 at that time...
http://en.wikipedia.org/wiki/Amiga_Unix
did anyone try loading that into one of the emulators BTW?, that might be interesting to see.
"rufty_tufty said:
,between 4 and 15 seconds depending on what your usual booting stuff is/was/
the other trick is to use Knoppix, create a ram drive (the size of the CD), copy the cd into the ram drive, and boot from there - now that is a fast system!"
sure, that so call 'trick' might work rather well, infact it the same concept of the old Amiga RAD disk (Recoverable rAm Disk) but to this day AFAIK, there is no other OS/machine/app that can infact keep that ram copy in a recoverable ram and boot from it after a warmboot?, is there infact such a thing for linux or windows today?.
the RAD IS/was rather cool keeping in mind you can mearly copy any file/dir, assign it as whatever you like and boot it , so it was trivial to make a RAD, fill it with your boot assigns options/apps then copy it to a dir somewere, then you had an enarc mount a RAD,copy that disk dir to the rad and reboot after that every reset would auto boot the RAD as it was still available in ram so no need to keep copying that HD dir on reset... now thats cool and way faster than booting/copying from harddrive every time...
average first (HD)boot time 20 seconds, after that , RAD boot times