Which Processor is faster & better - JASJAR, XDA Exec, MDA Pro ROM Development

"Intel Bulverde 520 MHz"
The one in the Universal
OR
"Qualcomm MSM7201A 528 Mhz"
in the new HTC HD unit
I feel they are the same. Am I right?

qualcomm is much better
Its similar the difference between a 2.5ghz Pentium 4 and a 2.5ghz Core2Solo

i don't think that core2solo and pentium4 with ht much differ

l2tp said:
i don't think that core2solo and pentium4 with ht much differ
Click to expand...
Click to collapse
Google up "Instructions per second" and you'll understand.
The Netburst architec of P4 is one of the worst example in history of it. A failure by engineering standard.

The PXA270 Processor in the Universal actually runs at 624mhz and is underclocked. The HTC X7500 uses the same CPU running at 624mhz. It is clearly the better CPU.

genetik_freak said:
The PXA270 Processor in the Universal actually runs at 624mhz and is underclocked. The HTC X7500 uses the same CPU running at 624mhz. It is clearly the better CPU.
Click to expand...
Click to collapse
Very, very wrong.
I wouldn't say that the Intel two processors are exactly the same, with one just being underclocked via software. Notice how intel puts out multiple pentiums of a given generation at different speeds? Would you venture to say that all those chips are the same too?
Also, clock speed is a poor metric when comparing chips from different companies. PDADB.Net says that the Intel chip has a ARMv5TE instruction set and the Qualcom chip has a ARMv6 instruction set. The Intel is a generation behind.
Comparing
Wikipedia says
Main article: Megahertz myth
The clock rate of a computer is only useful for providing comparisons between computer chips in the same processor family. An IBM PC with an Intel 486 CPU running at 50 MHz will be about twice as fast as one with the same CPU, memory and display running at 25 MHz, while the same will not be true for MIPS R4000 running at the same clock rate as the two are different processors with different functionality. Furthermore, there are many other factors to consider when comparing the speeds of entire computers, like the clock rate of the computer's front side bus (FSB), the clock rate of the RAM, the width in bits of the CPU's bus and the amount of Level 1, Level 2 and Level 3 cache.
Clock rates should not be used when comparing different computers or different processor families. Rather, some software benchmark should be used. Clock rates can be very misleading since the amount of work different computer chips can do in one cycle varies. For example, RISC CPUs tend to have simpler instructions than CISC CPUs (but higher clock rates), and superscalar processors can execute more than one instruction per cycle (on average), yet it is not uncommon for them to do "less" in a clock cycle. In addition, subscalar CPUs or use of parallelism can also affect the quality of the computer regardless of clock rate.
Click to expand...
Click to collapse

Sonus you are correct about the Mhz comparison. However, the PXA270 in the Universal can be safely "overclocked" to 624Mhz because the chip is designed to max out at that speed.
I would still like to see some benchmark tests between the 624Mhz PXA270, and the 528Mhz Qualcomm MSM7201A.
Generations aside, I can't see the Qualcomm chip outperforming the Intel Chip by much, if any. Also, it should be noted that the PXA270 can be scaled, not sure if that is true for the MSM7201A.

The other catch phrase is "Performance per watt". I bet the MSM7201A has a huge advantage over PXA27x in that, mainly due to newer manufacturing process.

That may be true wuzy, but considering the PXA270 is almost 5 years old and still being used in new devices should tell you plenty about its capabilities and performance.

Not really... It does, however tell a lot about the stinginess of device manufacturers.
As for the overclocking, not every Universal can run 624 MHz without crashing because the CPUs are going through a selection process after manufacturing and there is simply no reason to use the best ones for a device that doesn't need them running at full speed.

The crashes are usually the result of the type of program used to overclock and also the rom. For the most part, people have found that 624mhz is pretty stable, inlcuding myself. Some have even pushed it beyond that speed, but that's another story...
Also take this into consideration:
The Universal has been on the market since 2005, almost 4 years now. By industry standards, it should be obsolete. Why is it not then? Simply, it is quite inexpensive compared to the newer devices having similar features, sometimes less. When it comes to performance vs. price vs. features, you just cannot beat the value of the Universal and its blistering fast 520/624mhz PXA270 CPU! The PXA270's performance is only rivaled by its bigger brother, the 800Mhz PXA320 which has made its way into some newer devices already.

genetik_freak said:
That may be true wuzy, but considering the PXA270 is almost 5 years old and still being used in new devices should tell you plenty about its capabilities and performance.
Click to expand...
Click to collapse
Try out a Diamond/Touch Pro with Opera9.5 the next time you see one and notice the speed difference.
On MSM7201A compared to our PXA27x it's a lot more smoother.
The lack of driver for MSM7200 on a lot of devices released last year tainted our perception on the new generation chips I think.
Touch HD vs. ASUS Galaxy7 at end of the year... hmmm

I think you're missing the point wuzy.
I know there are newer devices out now that can deliver slightly better performance in some areas than the Universal, but considering how old our device is, it is to be expected. All I'm saying is that given the age of the Universal compared to what's out there now, The Universal has held up well. Furthermore, with all the new cooked roms popping up, you can expect the Uni to live even longer!

Take a look at H.264 decompression and real high performance tasks and the PXA270 looses so badly against the PXA320 that it is not even funny anymore...
Why does the Uni keep up with most software? Because most programs are written for the old ARMv4 instruction set, thus wasting a lot of CPU cycles on newer processors that have already moved on. Apart from that the average application simply does not need that much CPU power to begin with.
The Uni held out well in a market that is very slow to adapt new technologies to begin with. The Axim x50v had a dedicated graphics chip at the end of 2004 - how many applications make use of that today? Only some games (ports, emulators) and media players. For those alone the Axim has held out better than the Uni though as it is still one of the best performing PPCs on the market.
Our little one will be around for quite a while, but it is far, far away from what nowadays devices can offer and it shows if you run anything beyond mail and office apps on it.

Which Processor is faster & better
I feel from your input above that "Qualcomm MSM7201A 528 Mhz" has higher performance, clock rete, Instructions per second, & Performance per watt when compared to the "Intel Bulverde 520 MHz" about 2:1 am I right ?
Another Question:
What is the highest speed Processor available for the PDA industry today?
Best Regards.

IMHO the ARM Cortex processors are very far up the ladder when it comes to performance and energy consumption. The Pandora makers claim 10 hours of runtime for their device. Together with its media chip this little bugger is capable of decoding 720p HD video streams (take a look at the Archos 5)
I am not sure if the MSM7201A chipset's CPU alone reaches twice the performance of the Uni, but you will see a huge difference in apps that support and need the latest in CPU architecture (media players & games). If (one way or the other) the 3D capabilities can be put to use you will probably see more than a 2:1 performance boost.

The sad truth is the Universal is one of the slowest VGA devices around. Especially considering lack of the graphical accelerator (which was even present in prototypes).

Too bad the dedicated 3D chip didn't make it into the final design. But it's still better than having a 3D accelerator without drivers! I have a Sharp EM-ONE here with a GoForce 5500 that could theoretically accelerate many video formats. The sad truth is that because there are no drivers no media player can make use of the chip. Even worse: Because the graphics chip still controls the display video is even slower because the optimized X-Scale drivers can't be used. It's like Sharp and NVidia wanted to punish users double So, as bad as it is, the Uni is not the worst device out there!

x86
I wonder why there´re no x86 cpu´s placed in mobile devices yet. maybe because of the high power consumption? x86 cpu´s running at 528mhz would be more powerful than arm cpu´s. furthermore the device could run x86 os like xp embedded with more features and capabilities...

x86 CPU enabled systems are still too much power hungry and too much complicated to be used in such a small device (sounds weird when talking abut HTC Universal, doesn't it).

Related

CPU Benchmarks

Hello everyone,
I was wondering if there are any benchmarks/comparisons for mobile platform chipsets/CPUs. For example, I'd like to know how does the Qualcomm MSM7200 perform versus Samsung SC32442, since they're both marketed as "400 MHz".
For example my Trinity's Samsung 400MHz performace doesn't really feel as "double the MHz" of my old TI OMAP 850 CPU (200MHz).
I'm not interested in features that each chipset offers, what I'd like to see is raw performance of the above mentioned chipsets/CPUs, such as the good ol' Intel vs. AMD benchmarks.
Hi, I guess the simpliest would be to post benchmark results here. One can do it with SPB Benchmark, which is free for personnal use.
I'll start with my ti-omap ~200Mhz cpu from HTC Prophet:
Stock:
Spb Benchmark index 269.28
CPU index 954.15
File system index 112.2
Graphics index 2917.14
Synched + loaded with apps:
Spb Benchmark index 240.33
CPU index 910.67
File system index 110.25
Graphics index 2800.08
Maybe there are already some comparison charts ?
++, niko
Benchmark Charmer here http://forum.xda-developers.com/showpost.php?p=969086&postcount=115
Same cpu, same results.
Intel Vs AMD
Performance -Intel vs AMD Ryzen
If we peek into the past Intel had better technology and overall better performance whereas AMD provided more affordable solutions that relied solely on power to compete with Intel.
It worked fine until 2013 but after this phase, things took a turn for AMD to get worse. Although AMD came with the FX series, things were not in support of AMD. Their technology stabilized and Intel, on the other hand, continued to try to get better.
After the AMD Ryzen series came to market in March 2017, it stood as a strong competitor to Intel’s i7 model. If your primary focus is to do basic tasks like gaming, internet surfing, typing documents, then there’s nothing wrong with AMD.
Whereas if you’re a person who works on 3d rendering, stuff like Photoshop, intense math calculations, and all such kinds of operations then definitely you have to go with an Intel-based system.
I mean there is a reason why Mac only chooses to use intel in their systems and not AMD. When it comes to high tech stuff, Intel is just better.
In a nutshell, if you need a performance-oriented you definitely need to go with Intel. AMD Zen might change this but I really doubt it. I don’t have super high hopes for AMD processors so, an Intel i7 is definitely the play if you need lots of gaming performance.
Multi-threaded tasks such as video editing or transcoding, or heavy multitasking activities with tens of browser tabs, are more efficient at AMD’s CPU and more cost-effective across the entire price & performance spectrum.
.
Performance is not the only factor to judge a processor. There are even other factors such as Heating, Core count, Clock Speed, etc. I cannot mention all these stuffs. Read this article- AMD Ryzen vs Intel

Over Clock

Is there a way to over clock the TC? I have had WM devices before and was able to over clock it with OMAP. Went to N95-3 for a wile (S60) and am now back to WM. Didn't know if this method still worked or if there was a new method.
Thanks
Anyone have an idea?
AFAIK there is no overclocking tool for the Qualcomm. Maybe that's because it's a dual core design. But I'm still hoping that I'm wrong.
TI Omap is also Dualcore. It's just because nobody has written a program to overclock so far.
I agree. It's just a new processor with different architecture and developers haven't made any overclocking tool for that yet. But... it's a matter of time.
If you are right, then it should really be only a matter of time. Due to the fact that HTC uses the Qualcomm for all their new products chances are high. Overclocking to 500MHz could resolve most performance issues. Maybe we should ask HTC for delivering an overclocking tool.
It's almost sure that in the near future we will have the tools to overclock easily our devices, while this processor (32bit Qualcomm MSM7200), is capable to run at much higher speed. For example future devices such as HTC Omni and Toshiba Portege G910 & G920 will run with this processor at 528MHz!!!
athanaso77 said:
It's almost sure that in the near future we will have the tools to overclock easily our devices, while this processor (32bit Qualcomm MSM7200), is capable to run at much higher speed. For example future devices such as HTC Omni and Toshiba Portege G910 & G920 will run with this processor at 528MHz!!!
Click to expand...
Click to collapse
Man that would be great!
"is capable to run at much higher speed. For example future devices such as HTC Omni and Toshiba Portege G910 & G920 will run with this processor at 528MHz!!! "
there seem to be a common misconception that the same family of cpus running on various Mhz's are under and overclocks that is sadly not the case not on pc's and not on pda's
Well I hope that even if this is not the 528MHz prosessor in the TC that it can still be over clocked.... I've run my Blue Angel, Hermes, and StarTrek all over clocked.
yeah most overclock at least a bit
though some cpu's never got oc programs i believe
like samsungs hope for your sake that this cpu will get a tool
personaly i'd go with the longer batt life though
and a good driver will prob do alot more for general speed
Don't know why there's so little rumor about this - but there is actually an app that could possibly let us overclock the TC:
http://forum.ppcgeeks.com/showthread.php?t=11573&page=2
It's called HTC Performance and it has already been included in some HTC Kaiser ROMs. I fit works with the Kaiser, why not with the TC?
I will test this! I just wonder why "nobody" knows about this app.
Found some more info on the forum: http://forum.xda-developers.com/showthread.php?t=347546&highlight=htc+performance
Looks like it doesn't work... Or does it? I'm still about to test.
What the f---?! I can't believe this. I set it to 520MHz and PointUI became soo slow. Then I started the camera app and it ran perfectly smooth. PointUI also runs good now after closing th camera app. Don't know what to think about this but: Try it!
@Rudegar
Hm, I would like to have both (more or less ). More power when I need it and less power when battery life is much more important. Maybe a little more speed would provide the performance to play my files encoded in H264 smoothly. But I don't want to watch my files every day so there is no need to overclock my device all the time.
@maati
The people in that forum are talking about an HTC Apache. AFAIK the Apache has an Intel XScale processor. So I would be really surprised if it works with the TC or Kaiser. Maybe there are another tweaks within this package?
Either way, there is at least one company which tries to find a solution: http://www.wizcode.com/devblog/comments/pocket_hack_master_v5_feature_requests/
(Unfortunately they are trying it for just a while and it seems that they still haven't made real efforts)
Guess we'll wait and see.
Rudegar said:
there seem to be a common misconception that the same family of cpus running on various Mhz's are under and overclocks that is sadly not the case not on pc's and not on pda's
Click to expand...
Click to collapse
What are you talking about????
You must have forgotten that 32bit Intel XScale PXA270 processor runs in most devices (such as Gigabyte i350, ASUS P535 and many many other) at 520MHz BUT in XDA Atom life at 624MHZ!!! And we are talking for exactly the same processor!!!
One more example for you because you talked about Samsung processors... 32bit Samsung SC32442 runs in HTC P3600 and ETEN X600 at 400MHz but in ETEN X650, ETEN X800, MWg Zinc II and HTC P3600i runs at 500MHz.
So... who has made the misconception?
Have a nice day!
Still no ideas?
Overclock TC
Kick the subject:
Anyone found a tool to overclock the TC or any suggestions how to write an overclock application?
"You must have forgotten that 32bit Intel XScale PXA270 processor runs in most devices (such as Gigabyte i350, ASUS P535 and many many other) at 520MHz BUT in XDA Atom life at 624MHZ!!! And we are talking for exactly the same processor!!!"
no it's not the same processor at all sure it's the same processor family but
you are dead wrong if you believe that all p4's are the same or all athlons no matter
the mhz
nanometer mean alot and verious silicon dices provide various cabebilites speedwise
2 devices with the same cpu one running 520Mhz and one running 300 dont mean that they took 1 cpu and over or underclocked it
just like the first p4 of the northwind series was 1.6Ghz and the last one was 3.06Ghz this was not! the same chip they just changed the mhz of
apart from just that then just cpu speed is not everything flash storage speed and sd interface speed or wifi or usb speed and lack of gpu driver in tc and kaisers case
are much bigger bottlenecks then cpu speed in current devices

msm7200 520mhz vs. xscale 800mhz?

Is there much of difference beside clock speed. from the msm7200 in the touch pro 2 and the xscale running at 800mhz in the omnia II in terms of performance? ANy help would be appreciated.
If you ask me it (should) make quite a difference. The msm7200 is quite notorious for it's quite allright clockspeed but slow performance.
I used to have a Diamond (with 528 mhz) and then got a Omnia (Marvell 624 mhz) which was already quite a difference. I guess the 800 mhz will make even more of a difference.
Do note that there is a big difference in resolution between the Diamond and the Omnia, so that will also give some speed increase. The Omnia II has a Samsung 800 mhz chip (as far as I know) and I don't know what kind of performance that will give.
Both cpu's are a ARMv6 (afaik), so in that perspective you could say the 800 mhz is faster than the 528 mhz.
See this:
Samsung chip: http://pdadb.net/index.php?m=cpu&id=a6410&c=samsung_s3c6410
Qualcomm chip: http://pdadb.net/index.php?m=cpu&id=a7200a&c=qualcomm_msm7200a
My old diamond was much slower than my current ipaq 211. The ipaq has a 624mhz marvell and is much faster and more responsive than the diamond. It can also play videos back much better. 800mhz would just increase the performance gap.
The Omnia II is Arm11 which is slightly faster than the iphone 3G(both get blown out of the water by the 3Gs), and should support OpenGL ES 2.0.
Here's Samsungs Data sheet on it: http://www.samsung.com/global/syste.../2008/5/30/785500s3c6410_datasheet_200804.pdf
The msm7200, i BELIEVE(dont quote me), would be faster than the SC36410, if it had proper drivers.. however, thats not the case.
numbers are an indicator and nothing more. They give you a clue but clues can be very misleading. If they were usefull, why would you need benchmarking?
http://en.wikipedia.org/wiki/Megahertz_myth
(yeah i know wiki is sometimes full of BS but it certainly backs up what I learned in Uni and during my assembler cracking/virus writing days)
The ONLY way to compare CPU's is to run the same application and then run the SAME task in that application. Once you have done so ALL you can say is "For performing task X in application Y, processor ZXY running operating system ABC is faster on the BLAHBLAH platform" and nothing more. It does not mean its faster at everything or indeed, you cannot say its faster than ANYTHING else until you have tested it.
At the end of the day, the processor is affected by drivers, processor design and the operating system and its installaition.
and Software.. if theres no apps that incorporates acceleration, then its wasted.
what about qualcomm 1G snapdragon cpu?
how fast is that compares to current 528mzh? haha
i'm waiting for Acer S200 with 1G cpu.
netnerd said:
what about qualcomm 1G snapdragon cpu?
how fast is that compares to current 528mzh? haha
i'm waiting for Acer S200 with 1G cpu.
Click to expand...
Click to collapse
please re-read and if you still don't understand, i'll try and explain again.
clearly, marvell is better, even the mhz is lesser than what qualcomm offers!
having better decoders also like video playback & multitasking when video is playing!
waiting for devices with marvell cpu pxa168 series.
they use qualcomm chip becoz its cheaper & provide hsdpa to network & GPS module while the rest does not come with it. so individual chip must be used. but its better like GPSone VS SiRF III

A good OMAP 3640 vs snapdragon vs humming bird article

CPU performance from the new TI OMAP 3640 (yes, they’re wrong again, its 3640 for the 1 GHz SoC, 3630 is the 720 MHz one) is surprisingly good on Quadrant, the benchmarking tool that Taylor is using. In fact, as you can see from the Shadow benchmarks in the first article, it is shown outperforming the Galaxy S, which initially led me to believe that it was running Android 2.2 (which you may know can easily triple CPU performance). However, I’ve been assured that this is not the case, and the 3rd article seems to indicate as such, given that those benchmarks were obtained using a Droid 2 running 2.1.
Now, the OMAP 3600 series is simply a 45 nm version of the 3400 series we see in the original Droid, upclocked accordingly due to the reduced heat and improved efficiency of the smaller feature size.
If you need convincing, see TI’s own documentation: http://focus.ti.com/pdfs/wtbu/omap3_pb_swpt024b.pdf
So essentially the OMAP 3640 is the same CPU as what is contained in the original Droid but clocked up to 1 GHz. Why then is it benchmarking nearly twice as fast clock-for-clock (resulting in a nearly 4x improvement), even when still running 2.1? My guess is that the answer lies in memory bandwidth, and that evidence exists within some of the results from the graphics benchmarks.
We can see from the 3rd article that the Droid 2’s GPU performs almost twice as fast as the one in the original Droid. We know that the GPU in both devices are the same model, a PowerVR SGX 530, except that the Droid 2’s SGX 530 is, as is the rest of the SoC, on the 45 nm feature size. This means that it can be clocked considerably faster. It would be easy to assume that this is reason for the doubled performance, but that’s not necessarily the case. The original Droid’s SGX 530 runs at 110 MHz, substantially less than its standard clock speed of 200 MHz. This downclocking is likely due to the memory bandwidth limitations I discussed in my Hummingbird vs Snapdragon article, where the Droid original was running LPDDR1 memory at a fairly low bandwidth that didn’t allow for the GPU to function at stock speed. If those limitations were removed by adding LPDDR2 memory, the GPU could then be upclocked again (likely to around 200 MHz) to draw even with the new memory bandwidth limit, which is probably just about twice what it was with LPDDR1.
So what does this have to do with CPU performance? Well, it’s possible that the CPU was also being limited by LPDDR1 memory, and that the 65 nm Snapdragons that are also tied down to LPDDR1 memory share the same problem. The faster LPDDR2 memory could allow for much faster performance.
Lastly, since we know from the second article at the top that the Galaxy S performs so well with its GPU, why is it lacking in CPU performance, only barely edging past the 1 GHz Snapdragon?
It could be that the answer lies in the secret that Samsung is using to achieve those ridiculously fast GPU speeds. Even with LPDDR2 memory, I can’t see any way that the GPU could achieve 90 Mtps; the required memory bandwidth is too high. One possibility is the addition of a dedicated high-speed GPU memory cache, allowing the GPU access to memory tailored to handle its high-bandwidth needs. With this solution to memory bandwidth issues, Samsung may have decided that higher speed memory was unnecessary, and stuck with a slower solution that remains limited in the same manner as the current-gen Snapdragon.
Lets recap: TI probably dealt with the limitations to its GPU by dropping in higher speed system RAM, thus boosting overall system bandwidth to nearly double GPU and CPU performance together.
Samsung may have dealt with limitations to the GPU by adding dedicated video memory that boosted GPU performance several times, but leaving CPU performance unaffected.
This, I think, is the best explanation to what I’ve seen so far. It’s very possible that I’m entirely wrong and something else is at play here, but that’s what I’ve got.
Click to expand...
Click to collapse
CPU Performance
Before I go into details on the Cortex-A8, Snapdragon, Hummingbird, and Cortex-A9, I should probably briefly explain how some ARM SoC manufacturers take different paths when developing their own products. ARM is the company that owns licenses for the technology behind all of these SoCs. They offer manufacturers a license to an ARM instruction set that a processor can use, and they also offer a license to a specific CPU architecture.
Most manufacturers will purchase the CPU architecture license, design a SoC around it, and modify it to fit their own needs or goals. T.I. and Samsung are examples of these; the S5PC100 (in the iPhone 3GS) as well as the OMAP3430 (in the Droid) and even the Hummingbird S5PC110 in the Samsung Galaxy S are all SoCs with Cortex-A8 cores that have been tweaked (or “hardened”) for performance gains to be competitive in one way or another. Companies like Qualcomm however will build their own custom processor architecture around a license to an instruction set that they’ve chosen to purchase from ARM. This is what the Snapdragon’s Scorpion processor is, a completely custom implementation that shares some similarities with Cortex-A8 and uses the same ARMv7 instruction set, but breaks away from some of the limitations that the Cortex-A8 may impose.
Qualcomm’s approach is significantly more costly and time consuming, but has the potential to create a processor that outperforms the competition. Through its own custom architecture configuration, (which Qualcomm understandably does not go into much detail regarding), the Scorpion CPU inside the Snapdragon SoC gains an approximate 5% improvement in instructions per clock cycle over an ARM Cortex-A8. Qualcomm appeals to manufacturers as well by integrating features such as GPS and cell network support into the SoC to reduce the need of a cell phone manufacturer having to add additional hardware onto the phone. This allows for a more compact phone design, or room for additional features, which is always an attractive option. Upcoming Snapdragon SoCs such as the QSD8672 will allow for dual-core processors (not supported by Cortex-A8 architecture) to boost processing power as well as providing further ability to scale performance appropriately to meet power needs. Qualcomm claims that we’ll see these chips in the latter half of 2010, and rumor has it that we’ll begin seeing them show up first in Windows Mobile 7 Series phones in the Fall. Before then, we may see a 45 nm version of the QSD8650 dubbed “QSD8650A” released in the Summer, running at 1.3 GHz.
You might think that the Hummingbird doesn’t stand a chance against Qualcomm’s custom-built monster, but Samsung isn’t prepared to throw in the towel. In response to Snapdragon, they hired Intrinsity, a semiconductor company specializing in tweaking processor logic design, to customize the Cortex-A8 in the Hummingbird to perform certain binary functions using significantly less instructions than normal. Samsung estimates that 20% of the Hummingbird’s functions are affected, and of those, on average 25-50% less instructions are needed to complete each task. Overall, the processor can perform tasks 5-10% more quickly while handling the same 2 instructions per clock cycle as an unmodified ARM Cortex-A8 processor, and Samsung states it outperforms all other processors on the market (a statement seemingly aimed at Qualcomm). Many speculate that it’s likely that the S5PC110 CPU in the Hummingbird will be in the iPhone HD, and that its sister chip, the S5PV210, is inside the Apple A4 that powers the iPad. (UPDATE: Indications are that the model # of the SoC in the Apple iPad’s A4 is “S5L8930”, a Samsung part # that is very likely closely related to the S5PV210 and Hummingbird. I report and speculate upon this here.)
Lastly, we really should touch upon Cortex-A9. It is ARM’s next-generation processor architecture that continues to work on top of the tried-and-true ARMv7 instruction set. Cortex-A9 stresses production on the 45 nm scale as well as supporting multiple processing cores for processing power and efficiency. Changes in core architecture also allow a 25% improvement in instructions that can be handled per clock cycle, meaning a 1 GHz Cortex-A9 will perform considerably quicker than a 1 GHz Cortex-A8 (or even Snapdragon) equivalent. Other architecture improvements such as support for out-of-order instruction handling (which, it should be pointed out, the Snapdragon partially supports) will allow the processor to have significant gains in performance per clock cycle by allowing the processor to prioritize calculations based upon the availability of data. T.I. has predicted its Cortex-A9 OMAP4440 to hit the market in late 2010 or early 2011, and promises us that their OMAP4 series will offer dramatic improvements over any Cortex-A8-based designs available today.
GPU performance
There are a couple problems with comparing GPU performance that some recent popular articles have neglected to address. (Yes, that’s you, AndroidAndMe.com, and I won’t even go into a rant about bad data). The drivers running the GPU, the OS platform it’s running on, memory bandwidth limitations as well as the software itself can all play into how well a GPU runs on a device. In short: you could take identical GPUs, place them in different phones, clock them at the same speeds, and see significantly different performance between them.
For example, let’s take a look at the iPhone 3GS. It’s commonly rumored to contain a PowerVR SGX 535, which is capable of processing 28 million triangles per second (Mt/s). There’s a driver file on the phone that contains “SGX535” in the filename, but that shouldn’t be taken as proof as to what it actually contains. In fact, GLBenchmark.com shows the iPhone 3GS putting out approximately 7 Mt/s in its graphics benchmarks. This initially led me to believe that the iPhone 3GS actually contained a PowerVR SGX 520 @ 200 MHz (which incidentally can output 7 Mt/s) or alternatively a PowerVR SGX 530 @ 100 MHz because the SGX 530 has 2 rendering pipelines instead of the 1 in the SGX 520, and tends to perform about twice as well. Now, interestingly enough, Samsung S5PC100 documentation shows the 3D engine as being able to put out 10 Mt/s, which seemed to support my theory that the device does not contain an SGX 535.
However, the GPU model and clock speed aren’t the only limiting factors when it comes to GPU performance. The SGX 535 for example can only put out its 28 Mt/s when used in conjunction with a device that supports the full 4.2 GB per second of memory bandwidth it needs to operate at this speed. Assume that the iPhone 3GS uses single-channel LPDDR1 memory operating at 200 MHz on a 32-bit bus (which is fairly likely). This allows for 1.6 GB/s of memory bandwidth, which is approximately 38% of what the SGX 535 needs to operate at its peak speed. Interestingly enough, 38% of 28 Mt/s equals just over 10 Mt/s… supporting Samsung’s claim (with real-world performance at 7 Mt/s being quite reasonable). While it still isn’t proof that the iPhone 3GS uses an SGX 535, it does demonstrate just how limiting single-channel memory (particularly slower memory like LPDDR1) can be and shows that the GPU in the iPhone 3GS is likely a powerful device that cannot be used to its full potential. The GPU in the Droid likely has the same memory bandwidth issues, and the SGX 530 in the OMAP3430 appears to be down-clocked to stay within those limitations.
But let’s move on to what’s really important; the graphics processing power of the Hummingbird in the Samsung Galaxy S versus the Snapdragon in the EVO 4G. It’s quickly apparent that Samsung is claiming performance approximately 4x greater than the 22 Mt/s the Snapdragon QSD8650’s can manage. It’s been rumored that the Hummingbird contains a PowerVR SGX 540, but at 200 MHz the SGX 540 puts out 28 Mt/s, approximately 1/3 of the 90 Mt/s that Samsung is claiming. Either Samsung has decided to clock an SGX 540 at 600 MHz, which seems rather high given reports that the chip is capable of speeds of “400 MHz+” or they’ve chosen to include a multi-core PowerVR SGX XT solution. Essentially this would allow 3 PowerVR cores (or 2 up-clocked ones) to hit the 90 Mt/s mark without having to push the GPU past 400 MHz.
Unfortunately however, this brings us right back to the memory bandwidth limitation argument again, because while the Hummingbird likely uses LPDDR2 memory, it still only appears to have single-channel memory controller support (capping memory bandwidth off at 4.2 GB/s), and the question is raised as to how the PowerVR GPU obtains the large amount of memory bandwidth it needs to draw and texture polygons at those high speeds. If the PowerVR SGX 540 (which, like the SGX 535 performs at 28 Mt/s at 200 MHz) requires 4.2 GB/s of memory bandwidth, drawing 90 Mt/s would require over 12.6 GB/s of memory bandwidth, 3 times what is available. Samsung may be citing purely theoretical numbers or using another solution such as possibly increasing GPU cache sizes. This would allow for higher peak speeds, but it’s questionable if it could achieve sustainable 90 Mt/s performance.
Qualcomm differentiates itself from most of the competition (once again) by using its own graphics processing solution. The company bought AMD’s Imageon mobile-graphics division in 2008, and used AMD’s Imageon Z430 (now rebranded Adreno 200) to power the graphics in the 65 nm Snapdragons. The 45 nm QSD8650A will include an Adreno 205, which will provide some performance enhancements to 2D graphics processing as well as hardware support for Adobe Flash. It is speculated that the dual-core Snapdragons will utilize the significantly more powerful Imageon Z460 (or Adreno 220), which apparently rivals the graphics processing performance of high-end mobile gaming systems such as the Sony PlayStation Portable. Qualcomm is claiming nearly the same performance (80 Mt/s) as the Samsung Hummingbird in its upcoming 45 nm dual-core QSD8672, and while LPDDR2 support and a dual-channel memory controller are likely, it seems pretty apparent that, like Samsung, something else must be at play for them to achieve those claims.
While Samsung and Qualcomm tend to stay relatively quiet about how they achieve their graphics performance, T.I. has come out and specifically stated that its upcoming OMAP4440 SoC supports both LPDDR2 and a dual-channel memory controller paired with a PowerVR SGX 540 chip to provide “up to 2x” the performance of its OMAP3 line. This is a reasonable claim assuming the SGX 540 is clocked to 400 MHz and requires a bandwidth of 8.5 GB/s which can be achieved using LPDDR2 at 533 MHz in conjunction with the dual-channel controller. This comparatively docile graphics performance may be due to T.I’s rather straightforward approach to the ARM Cortex-A9 configuration.
Power Efficiency
Moving onward, it’s also easily noticeable that the next generation chipsets on the 45 nm scale are going to be a significant improvement in terms of performance and power efficiency. The Hummingbird in the Samsung Galaxy S demonstrates this potential, but unfortunately we still lack the power consumption numbers we really need to understand how well it stacks up against the 65 nm Snapdragon in the EVO 4G. It can be safely assumed that the Galaxy S will have overall better battery life than the EVO 4G given the lower power requirements of the 45 nm chip, the more power-efficient Super AMOLED display, as well as the fact that both phones sport equal-capacity 1500mA batteries. However it should be noted that the upcoming 45 nm dual-core Snapdragon is claimed to be coming with a 30% decrease in power needs, which would allow the 1.5 GHz SoC to run at nearly the same power draw of the current 1 GHz Snapdragon. Cortex-A9 also boasts numerous improvements in efficiency, claiming power consumption numbers nearly half that of the Cortex-A8, as well as the ability to use multiple-core technology to scale processing power in accordance with energy limitations.
While it’s almost universally agreed that power efficiency is a priority for these processors, many criticize the amount of processing power these new chips are bringing to mobile devices, and ask why so much performance is necessary. Whether or not mobile applications actually need this much power is not really the concern however; improved processing and graphics performance with little to no additional increase in energy needs will allow future phones to actually be much more efficient in terms of power. This is because ultimately, power efficiency relies in a big part on the ability of the hardware in the phone to complete a task quickly and return to an idle state where it consumes very little power. This “burst” processing, while consuming fairly high amounts of power for very short periods of time, tends to be more economical than prolonged, slower processing. So as long as ARM chipset manufacturers can continue to crank up the performance while keeping power requirements low, there’s nothing but gains to be had.
Click to expand...
Click to collapse
http://alienbabeltech.com/main/?p=19309
http://alienbabeltech.com/main/?p=17125
its a good read for noobs like me, also read the comments as there is lots of constructive criticism [that actually adds to the information in the article]
Kind of wild to come across people quoting me when I'm just Googling the web for more info.
I'd just like to point out that I was probably wrong on the entire first part about the 3640. I can't post links yet, but Google "Android phones benchmarked; it's official, the Galaxy S is the fastest." for my blog article on why.
And the reason I'm out here poking around for more information is because AnandTech.com (well known for their accurate and detailed articles) just repeatedly described the SoC in the Droid X as a OMAP 3630 instead of the 3640.
EDIT - I've just found a blog on TI's website that calls it a 3630. I guess that's that! I need to find a TI engineer to make friends with for some inside info.
Anyhow, thanks for linking my work!
Make no mistake, OMAP 3xxx series get left in the dust by the Hummingbird.
Also, I wouldn't really say that Samsung hired Intrinsity to make the CPU - they worked together. Intrinsity is owned by Apple, the Hummingbird is the same core as the A4, but with a faster graphics processor - the PowerVR SGX 540.
There was a bug in the Galaxy S unit they tested, which was later confirmed in the authors own comments later on.

Dual core processor?

Why would a phone need it? Wouldn't battery life just suck?
Sent from the key to my world.
Sure, if you want a portable console lol.
The response speed would be great thought, and camera will be able to record in full HD without trouble. But, the software will need to be programmed to take advantage of the dual-core processor.
As for the battery, not necessary. The cpu will throttle back its speed a lot, and a dual-core might be able to drop really low and remain fully operational which will require less battery. Also the new dual-core cpu nanometer architecture would most probably be lower which means better battery consumption but at full load (like when playing graphically intensive games) battery probably won't last long. Still thought, new battery technology will need to be manufactured soon to keep up with this new phone technology. Next you'll see are dual-gpu phones lol
I'm waiting for the 2011 CES to see if anything dual-core will be announced before dropping $800 on a phone as I would love such a device, just for fun.
CES is just next week right?
They've already announced one phone to run it, I just think technology is getting crazy with portability. My computer still has a 1.6ghz processor, these new phones will undoubtedly surpass my poor system. Ha.
Sent from the key to my world.
One thing that the makers of the chips take into consideration, is power usage. And it's easy to see that too. I'll use desktop cpus and laptop cpus for example. Intel and AMD's 6 core designed both have a TDP of under 125W. Old single core pentiums had a TDP higher than that, and were much bigger in nm range. Laptop cpus now only use at the most, 1/4 the tdp of a desktop cpu.(Not as fast though)
Other than that, right now I can bet that there is no multi-threaded apps available, and is Android really able to take advantage of a multi-core system? Probably not on it's own.
HAPPY NEW YEAR people!!
Yeah, CES is just next week. I know they announced some phone but I would like to know when they are coming so I know if I should buy the best thing right now or not.
I wouldn't have a clue if Android can handle multicore processors but maybe the new Honeycomb version of Android will enable this? If this is the case then maybe this phones will come March/April....sigh
And yeah, TDP of this chips will be lower then current chips. I bet they are working hard to make the best use of the battery.
ceg1792 said:
Why would a phone need it? Wouldn't battery life just suck?
Sent from the key to my world.
Click to expand...
Click to collapse
A multi core cpu does not necessarily use more power than a single core cpu; it's mostly dependent on the architecture.
NVIDIA talks about benefits of dual core:
http://www.engadget.com/2010/12/08/nvidia-touts-the-benefits-of-multi-core-processors-for-smartphon/
I think there is a definite need for Dual-Core Processors in phones. Gaming is making a mainstream shift from dedicated handheld gaming consoles to Smartphones. In order for developers to make more robust and graphically appealing games, they are going to need more processing power. Another point is that Dual-Core Processors will help browser rendering speeds. With HSPA+, WiMax, and LTE we are getting some serious downlink on our devices. But if you notice, a smartphone getting 3mbps down and one getting 10 mbps down renders a webpage at the same speed. Right now the processor bottlenecks webpage rendering, not our data connection. With these faster processors it helps eliminate the bottleneck to provide a gratifying web experience to the end-user.
It'll help if the application has multi-thread support. But if the app can only use 1 core/thread, then that's where dual core is useless. Also gaming isn't the main focus of Smartphones, there's probably a huge minority of people using their Smartphones as a serious gaming machine compared to people who are using their smartphone for work, talk, text, or other multimedia.

Categories

Resources