Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

PandaBoard ES Benchmarked

Unknown Lamer posted more than 2 years ago | from the entering-calendar-entries-was-never-so-fast dept.

Intel 77

An anonymous reader writes "Phoronix has benchmarked the Texas Instruments PandaBoard ES and compared its performance against Intel Atom N270, Atom Z530, Pentium M, and Core Duo T2400 processors. The OMAP4660 dual-core 1.2GHz ARM Cortex-A9 development board generally loses out to Intel's older competition, but does manage to win in ray-tracing and other tests, and is advantageous on a per-Watt basis."

cancel ×

77 comments

ARM is coming along (1)

Anonymous Coward | more than 2 years ago | (#38514734)

Still not as fast as it's power hogging competition, but pretty decent.

I do a lot of work with Gumstix Overo's, and at home on the original Pandaboard. I am constantly amazed at how powerful those little systems are.

To be sure my Quad Core Xeon that I cross compile on will eat them for lunch... but at 5x the cost and 50x the power consumption.

Re:ARM is coming along BADLY! (0)

Anonymous Coward | more than 2 years ago | (#38516286)

I already feel badly for the people who will make the mistake of buy a computer in the near future with an ARM processor in it. The latest ARM processors performance is comparable to a 1996 Pentium class processor. In embedded device which require low wattage and high performance the natural choice is PowerPC. And sense next year being the year of GNU/Linux, and Lenovo's rights to use the THINKPAD name will expire. So if IBM can make the PowerEN a 18-core 64-bit processor all under 60-watts using a 45nm process, then surely IBM could make a dual-core 64-bit PowerPC processor using a 32nm process which would be under 5-watts for the NEW ThinkPads.

Re:ARM is coming along BADLY! (1)

Lumpy (12016) | more than 2 years ago | (#38516614)

I dont.

They will have a mini computer that will go 12 hours on a charge and do everything you need for web surfing except for crap designed flash websites.

I want one, I want a laptop that will go all day long and will recharge with a solar panel.

Hell I would buy a laptop that had a e paper display and could not play video. A backpacking computer / tablet that is durable as hell, goes a week on a charge, and cna let me record my thoughts or inspect maps at camp at the end of the day would be a god send. the craptastic kindle cant do any of those, except for the last a week. I carry one for a book to read at night, just wish it had the resolution to display topo maps decently and a flip out keyboard for journal entries.

Re:ARM is coming along BADLY! (1)

shams93 (2510370) | more than 2 years ago | (#38516878)

The panasonic toughpad with ics android http://www.panasonic.com/business/toughpad/us/best-android-rugged-tablet-overview.asp [panasonic.com]

Re:ARM is coming along BADLY! (1)

Lumpy (12016) | more than 2 years ago | (#38518422)

Ok, let me add one more requirement.

Must not cost as much as a car.

Panasonic Toughpad $2,995.00

If I cant use it as a shovel in gravel or as a oar in the water taped to a stick and it will take ZERO damage.... It's not worth it.

and the battery life of the toughpad is not at 12 hours with fast recharge like E-paper devices.

Re:ARM is coming along BADLY! (1)

shams93 (2510370) | more than 2 years ago | (#38519114)

Yeah sort of makes the ipad look frugal LOL.

Re:ARM is coming along BADLY! (1)

badkarmadayaccount (1346167) | more than 2 years ago | (#38536464)

Make that two orders, and it better have a a metal chassis.

Re:ARM is coming along BADLY! (1)

Trashman (3003) | more than 2 years ago | (#38516650)

And What OS & Applications would these PowerPC based Thinkpads run? Certainly not Windows 8 This sounds like a solution looking for a problem....

Re:ARM is coming along BADLY! (1)

Osgeld (1900440) | more than 2 years ago | (#38516710)

Mac os 9 and windows NT 4.0 (nah there are plenty of nix choices with power pc support)

Re:ARM is coming along BADLY! (0)

Anonymous Coward | more than 2 years ago | (#38516874)

In the year of GNU/Linux you wouldn't wont to run Windows or Windows 8. Yet, Microsoft has licensed the Power architecture from IBM for the X-box360, and they have been coding PowerPC builds of windows for over 5 years now. So if your one of those who still uses windows, Microsoft could easily build "windows 8" for the NEW Thinkpads which would also be easer than building for ARM.

Re:ARM is coming along BADLY! (1)

an_orphan (1918548) | more than 2 years ago | (#38521770)

that's totally silly, a non-x86 cpu has no benefit for running windows. You can't run x86 software on it, and that's why anyone uses windows in the first place. Windows without backwards compatibility will not sell.

Re:ARM is coming along BADLY! (0)

Anonymous Coward | more than 2 years ago | (#38523416)

That argument it so old, yet it keep people from migrating in the 80-90's from x84 to the superior architectures of Mipps, Motorola's 68000, Digital's Alpha, IBM's PowerPC, or MOS 6502. Microsoft NT was initially designed to operate on a broad set of architectures, so your implying that windows NT for Itanium doesn't support most of Microsoft tools. Even Apple with OSX is minimizing cpu architecture dependencies as much a possible. Furthermore, we no longer care about windows backwards compatibility just us windows in a virtual machine until you find or port the application to Unix. We use Unix and Unix-like systems. Have you seen the road maps for Intel's future processors at 22nm?( http://www.tested.com/news/intels-ivy-bridge-mobile-processor-roadmap-leaked/3255/ ) The TDP are all above 16 watts that abysmal for a 22nm process, and a two-core design.

Re:ARM is coming along BADLY! (1)

an_orphan (1918548) | more than 2 years ago | (#38655324)

Ugh... It's not MY argument, it's the reality of history. A software translation layer (VM) will be less efficient than microcode, which is what intel processors use anyway to decode x86 into a RISC ISA. You really don't know what you're talking about here.

Re:ARM is coming along BADLY! (1)

gatkinso (15975) | more than 2 years ago | (#38516750)

PPC?

1997 called and wants it's next big thing back.

Re:ARM is coming along BADLY! (2)

White Flame (1074973) | more than 2 years ago | (#38518922)

You do know that all 3 current gen game consoles are driven by PPC CPUs, right?

Re:ARM is coming along BADLY! (1)

LordLimecat (1103839) | more than 2 years ago | (#38516752)

1996 Pentiums didnt run at 1ghz. And theyre stacking this up against Core2s, which are hardly Pentium class.

Re:ARM is coming along BADLY! (1)

wed128 (722152) | more than 2 years ago | (#38518366)

Performance != Clock Speed.

Re:ARM is coming along BADLY! (1)

the linux geek (799780) | more than 2 years ago | (#38519710)

Performance is, however, strongly affected by clock speed. Cortex-A8 isn't too far off microarchitecturally from the Pentium (two-issue, in-order), so they're probably not too far off in performance-per-cycle. Current-gen A9 cores are (I would say) around a fast Pentium II or a low-clocked Pentium III.

Re:ARM is coming along BADLY! (1)

wagnerrp (1305589) | more than 2 years ago | (#38519226)

No, they're stacking this up against Pentium Ms and Cores. The Core architecture was a short-lived 32-bit mobile architecture in 2006, derived from the older P6 family. They are the final generation of actual Pentium (discounting the rebranding of new low end chips). The Core2 architecture was a completely new design, based off the same paradigms as the P6 family. Both mainstream systems detailed in this review were over five years old.

Re:ARM is coming along BADLY! (1)

hattig (47930) | more than 2 years ago | (#38517232)

The latest ARM processors performance is comparable to a 1996 Pentium class processor.

Troll much?

These SoCs can devote a dozen or so mm^2 for the CPU cores, yet they still achieve performance comparable to a 1GHz Atom but at far far lower power consumption levels. In addition the rest of the SoC contains application specific accelerators (graphics, video, security are the most common) for the difficult tasks. The Phoronix benchmarks sadly didn't test the SoC as a whole, just the CPU cores. It's also up in the air whether ARM Neon was actually utilised in all the tests.

Just an ARM is coming along (1)

Anonymous Coward | more than 2 years ago | (#38520116)

I think the limitations of boards like the Panda force programmers and designers to be more efficient instead of brute-forcing like the competition.

What about power and cost? (4, Insightful)

GreatBunzinni (642500) | more than 2 years ago | (#38514766)

The benchmarks provided by Phoronix focus on computational power, which is a relevant criteria. Yet, ARM-based systems aren't targeted at the high performance computing field. In their domain of application, criteria such as power usage and price tends to be much more relevant than how fast it compresses files, encodes MP3s or runs synthetic benchmarks. In fact, if it is fast enough to play media then it's fast enough to do anything at all.

So, how about comparing them where they need to be compared: power output and price?

Re:What about power and cost? (2, Insightful)

tsahil (921519) | more than 2 years ago | (#38514820)

There's even more to it... In these benchmarks the accelerators of the OMAP4 were totally ignored. These would have improved things like x264 encoding to being a lot faster even than a Core i7 chip. The OMAP4 as do other ARM Cortex A9 chipsets, have a lot of accelerators to deal specifically with highly computational tasks - and when you develop you actually use them...

Re:What about power and cost? (1)

pinkeen (1804300) | more than 2 years ago | (#38515124)

I haven't heard the term 'accelerator' in a long time. I belive the more appriopriate one would be 'DSP'.

Re:What about power and cost? (1)

savuporo (658486) | more than 2 years ago | (#38515310)

DSP is generally meant to be a programmable array. Most video compression and decompression accelerators in such systems are in large part fixed function ASICs, and not programmable down to macroblock processing level. Even some audio codecs are fixed function.

Fixed function ASIC will always beat DSPs and CPUs in MIPS/watt domain, and often in $/MIPS as well.

Re:What about power and cost? (2)

hattig (47930) | more than 2 years ago | (#38517354)

The TI OMAP 4460 actually does use a full programmable DSP, and can decode and encode 1080p30 apparently.
http://www.ti.com/general/docs/wtbu/wtbuproductcontent.tsp?templateId=6123&navigationId=12843&contentId=53243 [ti.com]

The 1.8GHz OMAP 4470 should be out soon as well - that will surely perform even more comparably to the Intel Medfield offering coming in the same timeframe.
http://www.ti.com/general/docs/wtbu/wtbuproductcontent.tsp?templateId=6123&navigationId=12869&contentId=123362 [ti.com]

Re:What about power and cost? (1)

wagnerrp (1305589) | more than 2 years ago | (#38519258)

The OMAP 4460 has a full programmable DSP, as well as independent ASICs for video encoding and encoding. You can have both. They are not mutually exclusive.

Re:What about power and cost? (3, Insightful)

Desler (1608317) | more than 2 years ago | (#38515780)

These would have improved things like x264 encoding to being a lot faster even than a Core i7 chip.

And yet you provide no actual evidence of this beyond an assertion. Please show your x.264 settings, which corei7 you used (there is more than one model), link to your source material, etc. so that you're results can be duplicated and verified.

Re:What about power and cost? (1)

RightSaidFred99 (874576) | more than 2 years ago | (#38516840)

These would have improved things like x264 encoding to being a lot faster even than a Core i7 chip

Lol. No, they wouldn't have. Now you're just making stuff up.

Re:What about power and cost? (1)

wagnerrp (1305589) | more than 2 years ago | (#38519414)

In these benchmarks the accelerators of the OMAP4 were totally ignored. These would have improved things like x264 encoding to being a lot faster even than a Core i7 chip.

And with just one misplaced letter, you show that you have no idea what you're talking about. The embedded platforms have ASICs dedicated to H 264 encoding, which can run much faster than comparable quality settings in x 264 running on a high end i7. If you actually tried running the software x 264 encoder on an ARM, you would be looking at days for a single TV show, and that's assuming x86-optimized x264 will even compile and run on the ARM architecture. If you want to compare apples to apples, you would have to test it against QuickSync on modern Intel chips.

Re:What about power and cost? (1)

tsahil (921519) | more than 2 years ago | (#38523678)

That was what I meant. Trying to compare Intel Atom to TI OMAP4 by checking the performance of a software video codec is plain wrong. Both chips are headed towards mobility and consumer electronic devices, where things like power consumption (which was already mentioned) is a lot more important than number crunching. The TI OMAP4 was designed with multimedia in mind, and as such it includes hardware accelerators for things like H.264 encoding/decoding and a lot of other things (3D graphics comes to mind). This being the case, you wouldn't be using an x264 software codec on it - you'd simply use its hardware acceleration. And there - the numbers we have from work are 20% CPU usage on the ARM for 720p30fps encoding/decoding + sending that media over the network using RTP (running over UDP). As far as I know, the Intel Atom has no such accelerators, which requires it to do H.264 using software codecs such as x264. The two are not comparable. Intel Atom has its uses. OMAP4 has its uses. The comparison mentioned is simply irrelevant, as for the uses the OMAP4 will be taken they simply make no sense.

ARM Cortex A8 vs Atom N450 power consumption (1)

IYagami (136831) | more than 2 years ago | (#38515118)

You can find an ARM vs x86 power consumption at:

http://www.brightsideofnews.com/news/2011/5/19/the-coming-war-arm-versus-x86.aspx?pageid=6 [brightsideofnews.com]

"The chart below contrasts power consumption between the Intel Atom N450 and the ARM Cortex-A8 while running miniBench. The power curves were generated from system power usage adjusted downwards so that idle system power was discarded. For the Atom, idle power was 13.7W with the Gateway netbook’s integrated panel disabled while the idle power for the Pegatron system (ARM Cortex-A8) was only 5.4W."

Re:ARM Cortex A8 vs Atom N450 power consumption (1)

jones_supa (887896) | more than 2 years ago | (#38516250)

Looking at the numbers very roughly, one could say that the ARM is about half slower than the Atom, but uses only one third of the power. So if we normalize either the processing speed or power consumption to the same level, it can be concluded that ARM is 50% more energy efficient while making the same amount of work than Atom.

Re:ARM Cortex A8 vs Atom N450 power consumption (0)

Anonymous Coward | more than 2 years ago | (#38519324)

Yes, Great Observations. When compared whilst doing nothing the ARM is 50% more efficient than the Atom, yet when the need comes to encrypt your data to protect it from the Neocons, you would loose patience waiting for the ARM processor to encrypt a few giga-bytes of data. So when the Neocons come to kick in your door, and your computer being such a miracle of efficiency you never bother to encrypt your data. So off to jail for you.

Re:ARM Cortex A8 vs Atom N450 power consumption (0)

Anonymous Coward | more than 2 years ago | (#38520650)

Parallel processing is where the future has been for all computing for a few years now... meaning you can take advantage of the efficiency.

These tests are irrelevant at best (1, Interesting)

Anonymous Coward | more than 2 years ago | (#38514772)

A lot of the tests are irrelevant when done between Atom and OMAP4.
The OMAP4 has internal accelerators for voice and video coding - stuff like VP8 and x264 can be done a lot faster on the OMAP4 if you ditch the software itself and use the OMAP4's accelerators instead.
We've been able to use OMAP4660 for encoding 720p at 30fps into H.264 while using only ~20% of the CPU. Try doing that in software on a Core i7 and see where it gets you.

When doing benchmarking on ARM Cortex chipsets, there needs to be more care taken in how you treat the accelerators of the SoC in question and if you use them at all. By the results of these benchmarking trial it seems that the accelerators were ignored altogether - not something I'd do if I were to actually use the OMAP4 for any real development.

Re:These tests are irrelevant at best (-1)

Anonymous Coward | more than 2 years ago | (#38514834)

A lot of the tests are irrelevant when done between Atom and OMAP4. The OMAP4 has internal accelerators for voice and video coding - stuff like VP8

VP8 ... here we go again! Nobody cares. Use h.264 or be irrelevant.

Re:These tests are irrelevant at best (0)

Anonymous Coward | more than 2 years ago | (#38515002)

Way to nitpick at a totally insignificant detail. When you're building something embedded you of course check if the exact codecs you use are indeed accelerated. The point is that the test was largely irrelevant.

And yeah, of course IMAP video accelerator supports H264.

Re:These tests are irrelevant at best (0)

Anonymous Coward | more than 2 years ago | (#38514938)

This dude posted in http://linux.slashdot.org/comments.pl?sid=2594422&cid=38514820 non-anonymously.

Keep fappin' to this OMAP garbage.

Re:These tests are irrelevant at best (2)

Desler (1608317) | more than 2 years ago | (#38515664)

We've been able to use OMAP4660 for encoding 720p at 30fps into H.264 while using only ~20% of the CPU. Try doing that in software on a Core i7 and see where it gets you.

It gets you doing multiple 720p streams at once. 720@30p is child's play.

Re:These tests are irrelevant at best (1)

tsahil (921519) | more than 2 years ago | (#38515834)

True. For us 720p means both encoding and decoding at the same time.

Re:These tests are irrelevant at best (1)

Desler (1608317) | more than 2 years ago | (#38515866)

And for me too. I can do 3-4 streams at realtime with ease. With faster settings even more.

Re:These tests are irrelevant at best (1)

hattig (47930) | more than 2 years ago | (#38517418)

To be fair, Sandy Bridge does include a video encoding accelerator/transcoder as well. However Atom doesn't at the moment, although Medfield will presumably include one.

The thing about OMAP 44xx is that the accelerator is a programmable DSP, not fixed function hardware. The specs say it can do 1080p30 (at 30fps). That means it could do VP8, or presumably even your own custom DSP code.

We should also be considering the quality of the output though.

Phoronix (0)

Anonymous Coward | more than 2 years ago | (#38514794)

after so many years, the constant Phoronix crap on the front page is like parody

TI (4, Interesting)

Kagetsuki (1620613) | more than 2 years ago | (#38514870)

As someone with experience doing embedded development on ARM I can tell you I found the OMAP architecture to be awful. I'll admit the only time I ever used it was on a demo board (the Beagle) vs a board with essentially identical specs from FreeScale, Renesas and a few others. TI was awful with support, their documents were awful, the hardware was flaky (overheating!?) and the sample sources and module sources they provided were absolute crap. On top of that when we did get the boards running and started comparing them the OMAP board was slow as tar on anything that involved a lot of memory operations in a small timeframe. Apparently the GLES subsystem was fantastic or something but after a few attempts we couldn't get the modules built correctly against the kernel we were using and just gave up. In the end we went with the FreeScale (not my choice) which was easily superior to the TI OMAP garbage.

Sorry TI, I'm not even touching this one.

Re:TI (1)

gatkinso (15975) | more than 2 years ago | (#38515596)

I am doing a lot of development on Gumstix Overos and am finding that platform to be pretty sweet. I think many of the problems you are encountering might be an artifact of the Beagle (who incidentally flat out state not to base an actual product on their hardware).

Re:TI (1)

tsahil (921519) | more than 2 years ago | (#38515852)

Same here. We've used the TI Blaze tablet platform with the OMAP4660 chip. No such issues. And their support in Israel at least is top notch.

Re:TI (0)

Anonymous Coward | more than 2 years ago | (#38517470)

We are using some TI chips in our company, and i found OMAP architecture to be awful :
- the hardware is very complex (they include stuff for compatibility with previous version, ...)
- the kernel driver are developed for demo board (with hard-coded stuff).
- the software is very complex (count the line of code in the linux kernel for Omap and freescale) and buggy.
- the support is really bad : lot's of time we spend so much time to explain what's the problem, how to reproduce it, that we ended in solving it ourself...

PS : I seems that TI out-source some of their software to India and Bulgaria

Re:TI (0)

Anonymous Coward | more than 2 years ago | (#38522252)

Complete opposite of my experience with TI and Freescale.

When we need to support Freescale parts, we take our estimate, and triple it.

Re:TI (1)

badkarmadayaccount (1346167) | more than 2 years ago | (#38536482)

Could you give me some advice on building a standalone mixing pult/equalizer? I was considering a cheap dev board with plenty o' DSP and linux, but I don't know how to pick it up from there. I'm kinda on a shoestring budget (<$800).

Re:TI (1)

Kagetsuki (1620613) | more than 2 years ago | (#38536724)

Well even on the project where the OMAP was evaluated I wasn't the one making the final decisions and I haven't been doing much device development lately either, so at the moment I don't think I could give you much good advice. You're lucky looking for something like that now though, because with all the tablets and smart phones out now everyone seems to be offering really complete and capable ARM dev boards with well done reference designs. You may also want to check out the communities around those manufacturers. Also, just some personal advice but if you are doing a non-commercial project I'd recommend putting together some design documents and promise to release open source/open hardware - companies like Atmel and Renesas love that kind of stuff and may give you free samples/dev hardware/other goodies.

How about OpenCL for POWERVR?? (1)

gatkinso (15975) | more than 2 years ago | (#38514896)

Where are the drivers and SDK for this?

MIPS/FLOPS per $... (1)

lobiusmoop (305328) | more than 2 years ago | (#38515094)

A more interesting benchmark for me at the moment is performance per $, which is where Raspberry Pi is going to have a big impact soon I think.

Re:MIPS/FLOPS per $... (1)

drinkypoo (153816) | more than 2 years ago | (#38516216)

Amen. If you need the latest greatest fastest it's not a fit, but it solves very many problems. My first RISC machine had, I believe, a 16 MHz CPU, it had a ~500MB SCSI-fast-narrow disk on a very poky VME controller, and an 8 bit, fairly stupid frame buffer... a Sun 4/260. And I ran a browser on it...

Re:MIPS/FLOPS per $... (1)

jones_supa (887896) | more than 2 years ago | (#38516436)

Very true.

Benchmark seems to be missing lots (0)

Anonymous Coward | more than 2 years ago | (#38515374)

Reading the article I'm left with a number of what I feel are important questions.

Firstly, which distro was this run on? I don't believe the 11.12 linaro release was (www.linaro.org) used which would be the most optimized for arm choice that currently exists. I looked at the phoronix source code and it seems to have no concept of linaro at all tho it does know ubuntu and debian of which linaro is a varient.

GFX Hardware acceleration for the Pandaboard ES is a bit of a work in progress, it's hard to know if the lastest work was included.

The article does not state which version of the compilers is in use. gcc 4.4 ? 4.6? flags? It can make a bit of a difference.

There is no statement if the intel comparisons are running the same level of software or not? This is another important data point.

Others have mentioned but I will too, it does appear that software decode/encoders were uses instead of the hardware versions. This would substantially change the numbers.

All that said, for someone obtaining a board, pulling software from anywhere without direction as to how to get the best performing code for arm, this would seem to be a good sample. If the goal of the article was to see the Pandaboard ES running with the best performance as compared to intel atom running at it's best, this article misses the mark completely.

Era of absurdly overpriced ARM boards is ending (3, Interesting)

Roman Mamedov (793802) | more than 2 years ago | (#38515714)

I will ENJOY seeing this absolutely DESTROYED, BEAT INTO THE ASPHALT in terms of price to performance by the Raspberry Pi very soon. Days of $100-200 ARM boards are coming to an end, now dear Pandawhatever please set the sane price of $50 for your board, or die out of existence.

Re:Era of absurdly overpriced ARM boards is ending (0)

Anonymous Coward | more than 2 years ago | (#38515942)

While the PI board looks nice, you are comparing apples to oranges. There is a lot more on that Panda board. The PI board is ancient ARM11..... That and at this point it is Vapor ware until they are actually selling product.

Re:Era of absurdly overpriced ARM boards is ending (1)

imroy (755) | more than 2 years ago | (#38516276)

The PI board is ancient ARM11...

Oh, that's right. Hasn't Broadcom licensed any of the Cortex cores yet? No wonder they're able to make them so cheap; they're several generations behind and ARM Holdings mustn't be charging much in royalties.

How far behind? Well each of the Cortex-A9 cores in this OMAP 4-based SoC perform about 2.5 times better than ARM11 at the same clock speed. So each one could get about the same amount of work done as the 700 MHz ARM11 while puttering along at only 280 MHz. The dual-core OMAP 4460 running at 1.2 GHz has about 1200 * 2 * 2.5 / 700 = 8.57 times the processing power of the Raspberry Pi. Hmm... $25 * 8.57 = $214.29. So the $187 price of the PandaBoard ES (subsidised by TI) may be worth it!

Re:Era of absurdly overpriced ARM boards is ending (0)

Anonymous Coward | more than 2 years ago | (#38517372)

As the Nokia N8 has shown (It uses a SOC that is slower than the one used by RaspberryPI), there's more to a SOC than just a fast CPU. Sure an A9 is faster (broadcom does offer a chip similar to the one used in PI where the ARM11 is replaced by an A9), but is it that much more important for most low-end needs?

RaspberryPI has three basic interest groups. The first is education; CPU power isn't critical here, but cost is. The second is HTPC; CPU power isn't critical here, but GPU power and cost are (note: Roku 2 uses the same SOC). The third is hobbyists; this group would often be content with a 20 year old pocket-calculator or some old, hackable piece of tech, an ARM11 is definitely okay as long as it's cheap and hackable.

As far as power per dollar, things change when you account for the dual-videocore IV GPU. According to the official RaspberryPI wiki page, the GPU offers 24GFLOPS of compute power. The SGX543MP2 in the ipad only offers 12.8GFLOPS of power. With the pandaboard SGX540 (3.2GFLOPS according to anandtech) being 1/7 the power of the Broadcom GPU, suddenly things look different. RaspberryPI offers the best GPUs available with one of the worst CPUs available (resulting in what is technically the most powerful silicon around) while still undercutting boards like Panda or Beagle by 2.5 - 5.5x in pricing.

For people wanting more CPU power, I think that modding and using several RaspberryPI,s in a small cluster could be an entertaining project.

Re:Era of absurdly overpriced ARM boards is ending (1)

wagnerrp (1305589) | more than 2 years ago | (#38519568)

Apples to oranges. The ARM architecture provides a lot of integer performance, with little to no floating point performance. GPUs provide a lot of floating point performance, with little to no integer performance. The question then becomes which is more important for your specific application.

Re:Era of absurdly overpriced ARM boards is ending (1)

imroy (755) | more than 2 years ago | (#38523488)

The ARM architecture provides a lot of integer performance, with little to no floating point performance.

That hasn't been true for a while now. Floating point support (in various versions of "VFP") have been standard since ARMv6 (e.g ARM11) and were optional in ARMv5 (e.g ARM9, ARM10, XScale). ARMv7 (e.g Cortex-A8/A9/A15...) has NEON ("advanced SIMD") as an option that most licensees also include. So ARM cores now have pretty good floating point performance too.

Re:Era of absurdly overpriced ARM boards is ending (1)

wagnerrp (1305589) | about 2 years ago | (#38527238)

They have much better floating point performance than they used to. They still don't come close to x86 systems in terms of performance per clock.

Re:Era of absurdly overpriced ARM boards is ending (1)

bWareiWare.co.uk (660144) | more than 2 years ago | (#38516074)

Why the hate? This has 4 times the memory, twice the clock speed and twice the cores of the Pi, of course it isn't going to be less then twice the price.
Everything else being equal you might expect nearly 4 times the price (i.e. ~$130) but not only is this already actually available (and we don't know what it will cost once we can actually buy a Pi), but the Raspberry Pi is hoping to operate without profit and to short-cut the economies of scale with large government orders for education. If they achieve that, and it is a big if, then they may well out compete Panda et al. but even then I will be very grateful the higher-end boards are still available.

Re:Era of absurdly overpriced ARM boards is ending (2)

Roman Mamedov (793802) | more than 2 years ago | (#38516590)

This has 4 times the memory, twice the clock speed and twice the cores of the Pi, of course it isn't going to be less then twice the price. Everything else being equal you might expect nearly 4 times the price (i.e. ~$130)

So, $130 for a bare board with CPU and RAM?
Yeah that would sound great, except when anyone can build a whole PC for $191, http://www.pcmag.com/article2/0,2817,2392163,00.asp [pcmag.com]
With 2x the RAM and a CPU that rips the ARM on PandaBoard into a thousand of tiny teddy bears in terms of performance.
And a frigging 500 GB HDD (ok, pre-HDD-crisis).

You could say, "yeah but it's not ARM and low-power etc". Okay. There are now Chinese tablets with comparable specs, http://www.aliexpress.com/product-gs/509457480-CPAM-Free-shipping-10-1-superpad-3-android-2-3-tablet-pc-flytouch-3-GPS-512MB-wholesalers.html [aliexpress.com]
that cost $125 shipped. Including stuff like 10" touch screen, camera, internal flash, battery, casing, etc, etc. There's no way a bare board should cost $130. It's just vendors up until now felt just fine with hiking up the price as much as they desire, because those who need it (for development etc) would buy it anyway, or even buy on their company's funds. But hopefully the Raspberry Pi will beat some sense into competitors in this area, and this will move an ARM PC from the ranks of a too-expensive-to-be-practical dream, to reality.

Re:Era of absurdly overpriced ARM boards is ending (1)

Nadaka (224565) | more than 2 years ago | (#38517242)

Economies of scale. The price is relatively high due to the low volume of production. These are hobby boards. The only reason you can build a $200 PC right now is because the hardware gets production runs in the millions or more.

Re:Era of absurdly overpriced ARM boards is ending (1)

Roman Mamedov (793802) | more than 2 years ago | (#38517440)

Economies of scale. The price is relatively high due to the low volume of production. These are hobby boards. The only reason you can build a $200 PC right now is because the hardware gets production runs in the millions or more.

Sure, and also maybe the chicken-and-egg problem?
There won't be any scale until there's significant demand, and there won't be any demand while those boards cost so much, that even most ARM enthusiasts would find it difficult to justify the purchase.
It's okay that the performance of those boards would not be stellar, but with them being so overpriced, the result is that the price/performance absolutely BLOWS -- and that's a big problem.

Re:Era of absurdly overpriced ARM boards is ending (1)

goarilla (908067) | about 2 years ago | (#38527984)

I don't consider 130 $ to be much if you are a ARM enthusiast !
Development boards used to cost a LOT more.

Re:Era of absurdly overpriced ARM boards is ending (1)

Osgeld (1900440) | more than 2 years ago | (#38516776)

I think he is more refering to the current selection of arm dev boards, like TI's offering which starts at 130$ for a 96k 75Mhz M3 and then wants another 100 bucks for a book, and god knows how much for a compiler that if you install it you get some douche salesman calling you once a month wanting to know if you need more software.

Re:Era of absurdly overpriced ARM boards is ending (0)

Anonymous Coward | more than 2 years ago | (#38516912)

100-200$ for a decent ARM EVM is a good price. I recall buying quite a few for 1.5-2k about 2 years ago. That was absurdly overpriced, wasn't it ?

Panaboard - Tests not done with Hard Float (1)

thatkid_2002 (1529917) | more than 2 years ago | (#38521718)

A lot of the tests that were done would have benefited from having Hard Float. Ubuntu ARM port does not have Hard Float. They should have used the Debian HardFloat port to get more accurate performance metrics of what the hardware can do.

I'm not arguing over semantics or fractions of percentages - Hard Float would have given an easy 20% increase in performance for some tests! For example here's an engineer from Genesi showing off the Debain Hard-Float work a few months back... 300% increase in some places? [armdevices.net]

Would you benchmark cars giving all the others high-octane fuel except one?

Please let it Soft-float fucking die already. It's horrible.

By weight or volume (1)

niftymitch (1625721) | more than 2 years ago | (#38522180)

I would like to see a 12 hour benchmark that reported normalized results
in terms of Kg of battery. All these processors are in the ball park for
operations per second but many can NOT do it all day long.

Twelve and 24 hour results are needed to be sure. But a smart phone with a three hour
battery life is not a smart design. Simply from the safety point of view this is important.

Re:By weight or volume (1)

qualityassurancedept (2469696) | more than 2 years ago | (#38522790)

Yes, but then the issue is that the device is only for people who need more than three hours at full operating capacity without access to any kind of powersource... and in reality that is not necessarily very many people... especially if you consider that a $100 device can compete with a $600 iPad for most people's needs. My laptop only gets about 4 hours on battery with dimmed screen and wifi and blue tooth off and I have never really found that to be a major limitation of its portability or usefulness.

Re:By weight or volume (1)

niftymitch (1625721) | more than 2 years ago | (#38534206)

Yes, but then the issue is that the device is only for people who need more than three hours at full operating capacity without access to any kind of powersource... and in reality that is not necessarily very many people... especially if you consider that a $100 device can compete with a $600 iPad for most people's needs. My laptop only gets about 4 hours on battery with dimmed screen and wifi and blue tooth off and I have never really found that to be a major limitation of its portability or usefulness.

BUT a phone is a critical safety device. Dialing 911 or 999 for emergency services
when stuck in a snow drift or calling to tell your safe and sound kids to stay put after a tornado has
passed ... but wait the kids phone battery is exhausted because they were playing
Angry Birds now you do not know....

Re:By weight or volume (1)

qualityassurancedept (2469696) | more than 2 years ago | (#38536956)

In that case, I don't think it really makes sense to let children play Angry Birds on battery with your critical safety device. The problem seems to be that people expect a critical safety device to be useful as a toy, phone, computer, car battery and who knows what else.... which is of course rather a lot to ask from a retail device that you are literally risking your life on hoping it functions correctly in critical situations.

Re:By weight or volume (1)

niftymitch (1625721) | more than 2 years ago | (#38554548)

In that case, I don't think it really makes sense to let children play Angry Birds on battery with your critical safety device. The problem seems to be that people expect a critical safety device to be useful as a toy, phone, computer, car battery and who knows what else.... which is of course rather a lot to ask from a retail device that you are literally risking your life on hoping it functions correctly in critical situations.

I am with you -- yet the parents that give their kids "smart" phones are not thinking
about a quake or a regional power outage. My guess is they are thinking -- is
my kid home yet, has he stopped at his GF house to neck blow smoke.

It starts with the very young kids, too young to exercise personal restraint
especially where Angry Birds is considered safe and blowing smoke and having
sex at age 11 is not.

Yank my tool chain. (1)

niftymitch (1625721) | about 2 years ago | (#38532340)

The compilers, libs and more for x86 and friends
are so much more mature this is hardly a fair game.
The best high school players paired against the
winner of the superbowl....

And it is not just the processor the comparison
seemed to depend a lot on graphics drivers that are
just now using graphics hardware.

Check for New Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...