Even though the HTC desire HD and Galaxy s have the processor with 1Ghz clock speed their linpack scores vary. SGS has about 12-14 and HTC Desire HD has 35-38. Also the same case with Nexus One. Can someone help me with this dilema?
vivekrk44 said:
Even though the HTC desire HD and Galaxy s have the processor with 1Ghz clock speed their linpack scores vary. SGS has about 12-14 and HTC Desire HD has 35-38. Also the same case with Nexus One. Can someone help me with this dilema?
Click to expand...
Click to collapse
Simple. Linpack is optimised for snapdragon processors. I'm sure if you searched you could have solved this by yourself.
Sent from my GT-I9000 using XDA App
And it's a synthetic benchmark anyway. Benchmarks are only useful if you know what exactly they are testing, they produce verbose outputs and if they test similar workloads to what you normally perform. Linpack is only somewhat useful if you only care about the speed floating point operations.
By the way, please stop saying it's optimised for snapdragon! To the best of what I've heard, that isn't the case. Snapdragons simply handle floating points better apparently. So yes, it might run better on snapdragon, but the developer probably didn't shift through the Dalvik code finding ways to speed it up on snapdragon.
We still don't really have enough information to understand if Snapdragon or hummingbird are faster in most applications, because we don't have an application similar to PCmark
Auzy said:
We still don't really have enough information to understand if Snapdragon or hummingbird are faster in most applications, because we don't have an application similar to PCmark
Click to expand...
Click to collapse
I know for a fact that in the "real world" the Desire HD $hits all over the SGS... I have both devices, and its very clear that the lag kills the SGS experience.
Its also worth noting, the Desire HD has the more optimised rev II Snapdragon processor. Clock for clock vs original Snapdragon, rev II is about 25% quicker...
PS - It is a shame tho, the Desire HD does not have native DIVX player support. You have to download Rockplayer for $10 to get that..
cheetah2k said:
I know for a fact that in the "real world" the Desire HD $hits all over the SGS... I have both devices, and its very clear that the lag kills the SGS experience.:
Click to expand...
Click to collapse
The lag is caused by the internal memory and file system though, not the Hummingbird.
cheetah2k said:
You have to download Rockplayer for $10 to get that..
Click to expand...
Click to collapse
eum. Rockplayer is free.
cheetah2k said:
I know for a fact that in the "real world" the Desire HD $hits all over the SGS... I have both devices, and its very clear that the lag kills the SGS experience.
Its also worth noting, the Desire HD has the more optimised rev II Snapdragon processor. Clock for clock vs original Snapdragon, rev II is about 25% quicker...
PS - It is a shame tho, the Desire HD does not have native DIVX player support. You have to download Rockplayer for $10 to get that..
Click to expand...
Click to collapse
How does the desire HD handle 3D games? When i went to the HTC event in London, it wasnt really very impressive when it came to the 3D games, the SGS was clearly superior thanks to its PowerVR 540 GPU.
cheetah2k said:
I know for a fact that in the "real world" the Desire HD $hits all over the SGS... I have both devices, and its very clear that the lag kills the SGS experience.
Its also worth noting, the Desire HD has the more optimised rev II Snapdragon processor. Clock for clock vs original Snapdragon, rev II is about 25% quicker...
PS - It is a shame tho, the Desire HD does not have native DIVX player support. You have to download Rockplayer for $10 to get that..
Click to expand...
Click to collapse
For starters, the question was based on linpack, but you are comparing the overall device. The software has already been shown to have a large impact on the devices. Furthermore, it's running bytecode, so it depends on the dalvik implementation.Your "facts" are actually non-conclusive, and seem to be based on observations.
Secondly, 25% faster isn't enough info when you don't know how hummingbird is in comparison. And even that is total crock, because 25% under which workload? It's like saying that a mechanical harddisk is half as fast as an SSD. However, under which conditions? We KNOW that mechanical HDD's operate horribly with random access. Well, what conditions have been improved on the scorpion CPU?
The harsh reality is, we don't know how exactly they compare, and benchmarks like Linpack or Quadrant only provide a tiny picture. It's more important to identify what kind of operations you need, and test those operations specifically. What we should ask is why you care about linpack?
I'm interested in finding out how the CPU's perform exactly though honestly (even against snapdragon).
What I've seen on quadrant is that it tests all aspects of a cpu. Arithmetic of int, short, long, xml parsing, audio and video decoding and the nexus one still has a better score only in cpu. Nexus one has about 4500 and my sgs has a max of 1992. Dosent this provide the big picture?
Sent from my GT-I9000 using XDA App
get CyanogenMod in SGS and try again
vivekrk44 said:
What I've seen on quadrant is that it tests all aspects of a cpu. Arithmetic of int, short, long, xml parsing, audio and video decoding and the nexus one still has a better score only in cpu. Nexus one has about 4500 and my sgs has a max of 1992. Dosent this provide the big picture?
Sent from my GT-I9000 using XDA App
Click to expand...
Click to collapse
The big picture of what exactly? That quadrant doesn't give accurate results when comparing phones? This thread is a waste of time
There's been a topic about this before. To get a proper comparison of actual MFLOPS performance of both devices, we'd need to make a comparison that is not hampered by different versions of Android software, different Linux kernels or different levels of JIT optimization.
To properly compare them, you could load Ubuntu (same version) on both devices, and have them run a properly optimized version of native UNIX Linpack. That'd actually be testing the hardware capabilities. Native UNIX Linpack runs 62+ on the iPad's 1 GHz Apple A4 (of which the execution core is said to be identical to the Hummingbird) which is over four times as much as we're getting on Android Linpack on the Hummingbird.
I'd be happy to volunteer my Galaxy S, but we'd need someone with a Snapdragon phone to do the same.
vivekrk44 said:
What I've seen on quadrant is that it tests all aspects of a cpu. Arithmetic of int, short, long, xml parsing, audio and video decoding and the nexus one still has a better score only in cpu. Nexus one has about 4500 and my sgs has a max of 1992. Dosent this provide the big picture?
Sent from my GT-I9000 using XDA App
Click to expand...
Click to collapse
Nope.. Because as mentioned, it still goes through the VM, and you are looking at a weighted score or does it show every component individually? Also, when you say "all aspects of the CPU", how do you know it's all aspects. The fact you mention XML parsing as a proper test is silly, because it's basic string operations (array of numbers generally).
You also forget that Android is a timesharing OS, so background processes can have an effect. When I say the overall view, I mean a total breakdown of the CPU, cache, average cycles taken for specific instructions, etc.
You can't test the CPU with Dalvik, or even the NDK. And in the case of Linpack as mentioned, it's a very specific workload. There might be CPU specific workloads which hummingbird performs significantly faster than the other processors (we don't know). All that should matter to you, is how well your apps run.
As all the smart people have said, don't trust benchmarks and also Froyo's JIT compiler isn't yet optimized for hummingbird, That will change once google plays around with the nexus s.
Related
Hi guys..
I sad Google developed 2.2 to improve snapdragon cpu and becuase of that the benchmarks shows 3X faster cpu on nexus,
will work 2.2 on galaxy like nexus ? or not for SGS cpu!
at all what you think about power of CPU/GPU in SGS on 2.2 ?
Is nexus cpu better than galaxy on Android 2.2 ?
The Galaxy's CPU/GPU is the best on the market right now and with 2.2 it should fix a lot of software problems with the SGS.
Actually can't wait for 2.2, and it's released around about my birthday!
When is your birthday
22nd September mate. You can buy me a Galaxy S as a spare if you want
well I have to see it first.
Guess Samsung finds a way to **** up the phone again i'm sure of that.
matty___ said:
well I have to see it first.
Guess Samsung finds a way to **** up the phone again i'm sure of that.
Click to expand...
Click to collapse
If it has rfs file format and TouchWiz, consider it ****ed up.
kgk888 said:
If it has rfs file format and TouchWiz, consider it ****ed up.
Click to expand...
Click to collapse
If froyo on the SGS sucks, then the chefs in here will cut it open and make it run properly and it won't matter what the FW was like when samsung sent it out. Also, TouchWiz is fine, even if it does have a dumb name.
I have been worried about this. The sgs line and droid line do not get over 15 in linpack with 2.2. I dont see the same increase in speed as I do with snapdragon based phones. I have read this is due to the snapdragon having 128 bit vs 64 bit something but cant find the forum post about this. The sgs line with 2.1 is still faster then a 2.2 snapdragon based phone but it must have the lag fix installed. Without the lag fix it is slower for sure. I will try to find the forum post about 128bit vs 64bit.
http://www.youtube.com/watch?v=gKsAUR61ByM
http://www.youtube.com/watch?v=ji49qFNxC4c
Edit: found the forum post
Originally Posted by Gimic26
Your question was answered already...it comes down to processor architecture. Qualcomm's Snapdragon platform and more specifically the Scorpion application processor, while being related to TI's Omap Arm series, has enhancements made by Qualcomm. The part of the cpu that handles the SIMD instructions has a wider pipeline, 128 bits vs 64 bits in TI's Omap. Scorpion also has a deeper pipeline to better handle all that data which I'd assume offsets some of the performance benefits a little bit.
As far as the difference between the two benchmarks, they are written to benchmark two different things. Linpack can run almost entirely within the SIMD/NEON portion of the cpu thereby showing off the enhancements made by Qualcomm. Quadrant stresses the entire core showing off total system performance showing that only in certain situations will Snapdragon outperform any other Arm based core.
shep211 said:
I have been worried about this. The sgs line and droid line do not get over 15 in linpack with 2.2. I dont see the same increase in speed as I do with snapdragon based phones. I have read this is due to the snapdragon having 128 bit vs 64 bit something but cant find the forum post about this. The sgs line with 2.1 is still faster then a 2.2 snapdragon based phone but it must have the lag fix installed. Without the lag fix it is slower for sure. I will try to find the forum post about 128bit vs 64bit.
http://www.youtube.com/watch?v=gKsAUR61ByM
http://www.youtube.com/watch?v=ji49qFNxC4c
Edit: found the forum post
Originally Posted by Gimic26
Your question was answered already...it comes down to processor architecture. Qualcomm's Snapdragon platform and more specifically the Scorpion application processor, while being related to TI's Omap Arm series, has enhancements made by Qualcomm. The part of the cpu that handles the SIMD instructions has a wider pipeline, 128 bits vs 64 bits in TI's Omap. Scorpion also has a deeper pipeline to better handle all that data which I'd assume offsets some of the performance benefits a little bit.
As far as the difference between the two benchmarks, they are written to benchmark two different things. Linpack can run almost entirely within the SIMD/NEON portion of the cpu thereby showing off the enhancements made by Qualcomm. Quadrant stresses the entire core showing off total system performance showing that only in certain situations will Snapdragon outperform any other Arm based core.
Click to expand...
Click to collapse
From what I've seen and read, the 2.2 builds for the Galaxy S do NOT have a JIT compiler enabled which explains the lower scores. The N1 got the huge CPU boost from having JIT enabled. That doesn't explain the Droid X's scores, but then again I haven't read enough about 2.2 running on the DX to see if it has JIT installed.
What're you think? I'll buy SGS 2.1 or wait for SGS 2.2 ?
It's very important to buy most powerfull phone.
I like Nexuse cus it's tested sucssasfuly in Android 2.2 and I'm gono love SGS if it will be better than nexus in 2.2.
Help me to choose better path )
Vogie said:
What're you think? I'll buy SGS 2.1 or wait for SGS 2.2 ?
It's very important to buy most powerfull phone.
I like Nexuse cus it's tested sucssasfuly in Android 2.2 and I'm gono love SGS if it will be better than nexus in 2.2.
Help me to choose better path )
Click to expand...
Click to collapse
I would wait at this time before purchasing an SGS if that's your concern.
Out of the box, the current phone/software is laggy and disappointing. If you're willing to hack it with some of the various fixes found here (I prefer samset with mimocan kernel), then you won't be unhappy with the phone, but there's no guarantee that Samsung will get FroYo right, and that if they do get it wrong that the devs here will be able to bring you a hot, non-laggy, super FroYo ROM before there's better, or at least comparable hardware done right by the manufacturer available.
That's no reflection on the devs here at all, I'm just thinking that Samsung won't release the firmware until the end of September, the devs will need a couple of weeks to make magic at least, and so now we're well into October. By October, the SGS will be a six month old phone. Six months is a very long time in the Android hardware world, and we'll likely see a landslide of new phones with faster CPU, maybe even dual-cores in the fall for the holiday season. The only thing the SGS will have over other phones at that point is the Super AMOLED screen by Samsung, since they're holding it all to themselves. I wouldn't be surprised if Moto or HTC try to kang the iPhone display tech for newer models if they can't get Super AMOLED for themselves.
In the android world it is nearly impossible to but a device that won't be out of date within at most a year and sometimes within 6 months.
Having said that, I don't see anything that will topple the sgs quite that soon. Although there is talk of dual core snap dragons, there has been nothing announced yet, and indeed the two new Desire handsets are still on the same chip.
I wouldn't expect to see anything that will have more raw power than the sgs until at least mid 2011. If there was anything closer than that it'd already be getting hyped.
If you keep looking at what is just over the horizon then you won't end up ever getting one, because there always seems to be something new out in a few months time. The sgs isn't prefect, but it beats the hell it of most anything that you'll be able to buy this year.
My humble opinion of course, but I think that if you want top end hardware, the sgs will serve you very well.
Sent from my GT-I9000 using XDA App
Based on your responses so far, I'd just get an iPhone 4 and be done with it.
There are a lot of people here and elsewhere who are perfectly happy with the device. I for one haven't installed the lag fix and I don't experience any lags, except for the situations below:
1. I'm trying to do something while there are several apps being installed/downloaded from the marketplace in the background. I think this will be resolved with the dualcore next gen CPU's.
2. Using LauncherPro, for all that is good and nice on this earth, I do not know why it took me 3 months before the option to change the shortcut on its drawer was shown to me. Imagine that, 3 months just to show the option to add a shortcut. Jeezus. I click on add shortcut and it took 3 months. Someone shoot me. I'm using ADW now and am very happy.
Out of sheer curiosity, why is it that you need "THE MOST POWERFUL PHONE"?
shep211 said:
As far as the difference between the two benchmarks, they are written to benchmark two different things. Linpack can run almost entirely within the SIMD/NEON portion of the cpu thereby showing off the enhancements made by Qualcomm. Quadrant stresses the entire core showing off total system performance showing that only in certain situations will Snapdragon outperform any other Arm based core.
Click to expand...
Click to collapse
The hummingbird core is widely recognized to be faster than the snapdragon core. Benchmarks do not tell you everything. Reference:
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).
Click to expand...
Click to collapse
Here is a GPU comparison for some of the leading smartphones:
Motorola Droid: TI OMAP3430 with PowerVR SGX530 = 7-14 million(?) triangles/sec
Nexus One: Qualcomm QSD8x50 with Adreno 200 = 22 million triangles/sec
iPhone 3G S: 600 MHz Cortex-A8 with PowerVR SGX535 = 28 7 million triangles/sec
Samsung Galaxy S: S5PC110 with PowerVR SGX540 = 90 million triangles/sec
Click to expand...
Click to collapse
Wait for G2 as nexus one is old news and i think they are winding down production. Frankly i love my sgs. Get it now cos frankly froyo is way over hyped compared to what sgs can do now with a lagfix
Sent from my GT-I9000 using XDA App
ickyboo said:
Wait for G2 as nexus one is old news and i think they are winding down production. Frankly i love my sgs. Get it now cos frankly froyo is way over hyped compared to what sgs can do now with a lagfix
Sent from my GT-I9000 using XDA App
Click to expand...
Click to collapse
You can't really say froyo is over hyped, I mean its free, and beyond that its an incremental upgrade.
I don't see why anyone would be staying on eclair once official froyo drops, and you can't deny that it will bring a performance boost.
Now I doubt it will bring quite as much of a boost as it gave to the N1 until we get a few months of development to really get it running sweetly, but all the same its still not over hyped if I ask me.
With optimized ROMs and whatever fixes we need (cuz samsung WILL break something) I figure the sgs will shred the N1's new scores. I recon we'll see around 3k in quadrant.
Considering how far ahead of almost everything a lag fixed non-stock-rom sgs is now, we'll see something really special once froyo starts rocking our crotches.
Sent from my GT-I9000 using XDA App
The.Opethian said:
Based on your responses so far, I'd just get an iPhone 4 and be done with it.
There are a lot of people here and elsewhere who are perfectly happy with the device. I for one haven't installed the lag fix and I don't experience any lags, except for the situations below:
1. I'm trying to do something while there are several apps being installed/downloaded from the marketplace in the background. I think this will be resolved with the dualcore next gen CPU's.
2. Using LauncherPro, for all that is good and nice on this earth, I do not know why it took me 3 months before the option to change the shortcut on its drawer was shown to me. Imagine that, 3 months just to show the option to add a shortcut. Jeezus. I click on add shortcut and it took 3 months. Someone shoot me. I'm using ADW now and am very happy.
Out of sheer curiosity, why is it that you need "THE MOST POWERFUL PHONE"?
Click to expand...
Click to collapse
Why powerfull phone? ok i'll tell u:
Because I don't like to buy an expensive phone (like SGS) that power is lesser than a chipper phone (like N1) !
Because I'd rather a phone without stalling (lagging) to play games and running big applications. I will very gray if i'll se lagging/stalling...
Because I need a phone with a good support (it's enough, don't need mazing support). a phone with a clear (alive or nice) Future
JIT for Hummingbird should be promising.
High Mem
anyone got any idea on the high mem issue?... when i was browsing the Gmarket.com, i realize 305 total available memory is not enough for me... and the web page just closed....
I've been reading a lot of discussion on this and would love to hear some opinions and see some benchmarks.
I currently own a Nexus One & where I live they are priced about $150 dollars more for a Nexus than a Galaxy S (It's my understanding Nexus are regarded as cheaper phones in America?) So basically I can sell my 4 month old Nexus One & buy a brand new 16GB Galaxy S for no extra cost. Here is what I am wondering...
I know the Galaxy S has an amazing GPU, it facerolls the Nexus One & even seems to stomp the Droid X with its improved GPU so that is great.
The CPU however seems to under perform in every benchmark I can find versus the Nexus/Droid2 & many more current high end Androids.
I realise these devices are running Android 2.2 with JIT. I've seen Linpacks of 2.2 running Galaxy S devices and JIT enabled ROMs that still don't compare with these other devices.
Question 1
What I'm wondering is the difference we can see in CPU benchmarks going to be surpassed with the addition of a proper 2.2 JIT rom on our devices or is simply that the Snapdragons & other Qualcomm CPU are actually better than our Hummingbird.
Question 2
My Nexus One is Linkpacking 30 MFlops atm, I think with OC etc I can get it higher too. Does anyone have any evidence of a Galaxy S phone (running 2.2, JIT, lagfix or anything) that competes (or even comes close to competing) with this? I have been unable to find anything.
Question 3
Is the current Quadrant scores that I'm seeing people reporting in the Lag Fix threads (2000+) actually representative of speed or are these (as Cyanogen & others seem to be claiming) distorted?
(I realise a lot of people are reporting lag fixed.. what I'm asking is the number represented there (x2 N1 Froyo's score) actually accurate. I don't understand the mechanics behind the I/O benchmark so I don't understand if the lagfix is distoring the reported results from it.)
1. Hummingbird is apparently faster.
2. We don't have JIT yet.. Compare Nexus One 2.1/Eclair with Galaxy S 2.1, and I remember seeing we are faster.. JIT has a massive impact on mflops (because the benchmark uses bytecode, not compiled code).
3. No benchmark is really representative of speeds (no matter what people tell you). Because different apps have different workloads. You might get 50mflops in a CPU test, but for 3D games, the number of triangles matters more. It has recently been shown the I/O test for quadrant can be tricked too.
Benchmarks aren't really comprehensive enough for anything more than getting an idea of the performance.. But don't rely on them.
The reason why we get crappy benchmarks is due to having ****ty filesystem (rfs) which don't let us have multi writes. That's what lag fixes help. Cpu wise we eat snapdragons for breakfast, lunch and tea.
Sent from my GT-I9000 using Tapatalk
andrewluecke said:
1. Hummingbird is apparently faster.
2. We don't have JIT yet.. Compare Nexus One 2.1/Eclair with Galaxy S 2.1, and I remember seeing we are faster.. JIT has a massive impact on mflops (because the benchmark uses bytecode, not compiled code).
3. No benchmark is really representative of speeds (no matter what people tell you). Because different apps have different workloads. You might get 50mflops in a CPU test, but for 3D games, the number of triangles matters more. It has recently been shown the I/O test for quadrant can be tricked too.
Benchmarks aren't really comprehensive enough for anything more than getting an idea of the performance.. But don't rely on them.
Click to expand...
Click to collapse
what he said ^^^
regards
ickyboo said:
The reason why we get crappy benchmarks is due to having ****ty filesystem (rfs) which don't let us have multi writes.
Sent from my GT-I9000 using Tapatalk
Click to expand...
Click to collapse
Source please.. I never have actually seen anyone prove this here, but I hear it being thrown around increasingly. How was this proven? I'm becoming increasingly concerned that this conclusion was made by playing chinese whispers
andrewluecke said:
Source please.. I never have actually seen anyone prove this here, but I hear it being thrown around increasingly. How was this proven? I'm becoming increasingly concerned that this conclusion was made by playing chinese whispers
Click to expand...
Click to collapse
Well, if you look at pre-Froyo benchmarks of Snapdragon devices, they generally get around 6.1 in Linpack, vs ~8.4 for a Galaxy S. That's a pretty big delta, and carriers through most other synthetic and real world benchmarks, roughly 20% faster at the same clock speed. Same thing can be seen with the TI processors in the Droid line, at 1Ghz, they score in the 8's with 2.1.
Froyo benchmarks are suspect for a number of reasons, mainly because most of the benchmarks were designed with 1.6-2.1 in mind, and partly because Google spent a lot of time optimizing the base Froyo build for a Snapdragon processor. HTC, Sony, Dell, etc can piggyback off this work with their version, whereas Samsung and Motorola have to start much closer to scratch. Which is also why the HTC devices got Froyo sooner.
Believe it or not (and despite the marketing hype) the Snapdragon chipset is a budget solution, with less complex/expensive memory subsystem, and a far less costly integrated graphics solution than what is found on the Galaxy S.
It's cheap to produce, it has almost everything in a nice tidy package that makes it cheaper to engineer handsets (when I say everything, I mean CPU/GPU/Radio/WiFi/GPS/USB).
It's a pretty good package for companies like HTC, who don't do any real hardware engineering, and try to keep costs low. They do software (very very well, I should add), industrial design, and mass manufacturing, but they've NEVER designed a chipset (or display), they always source those from a third party, in this case Qualcom for the chipset, Samsung/Sony for the displays, etc.
However, they were the first to market with 1Ghz speed and it's a solid and stable hardware setup. Just keep in mind that clock speeds don't tell the whole tale.
The Galaxy S, (and to a lesser extent the Droid series) use a better stand-alone CPU solution and a far superior non-integrated (has its own chip) GPU. Samsung does do their own in-house chipset engineering, and they didn't cut corners on the CPU design, and they learned a lot about how to squeeze a lot of performance out of the ARM instruction set from their own products and the work they did for the iPhone processors. In brute-force, they smack the Snapdragon chipset around like a *****, but they get slapped around in turn by HTC's superior software engineering.
HTC has a real advantage in lots and lots of PDA/Smartphone software experience. They know how to make the most of the hardware they purchase, and seem to spend a great deal of time optimizing the software, be it Windows Mobile or Android, and lessons learned from a decade of making PDAs, under their name and for others.
If HTC used a Hummingbird or TI OMAP chipset with PowerVR GPU, I have no doubt they'd be able to more quickly wring more performance and stability out of it than Samsung or Motorola can.
Croak said:
Well, if you look at pre-Froyo benchmarks of Snapdragon devices, they generally get around 6.1 in Linpack, vs ~8.4 for a Galaxy S. That's a pretty big delta, and carriers through most other synthetic and real world benchmarks, roughly 20% faster at the same clock speed. Same thing can be seen with the TI processors in the Droid line, at 1Ghz, they score in the 8's with 2.1.
Froyo benchmarks are suspect for a number of reasons, mainly because most of the benchmarks were designed with 1.6-2.1 in mind, and partly because Google spent a lot of time optimizing the base Froyo build for a Snapdragon processor. HTC, Sony, Dell, etc can piggyback off this work with their version, whereas Samsung and Motorola have to start much closer to scratch. Which is also why the HTC devices got Froyo sooner.
Believe it or not (and despite the marketing hype) the Snapdragon chipset is a budget solution, with less complex/expensive memory subsystem, and a far less costly integrated graphics solution than what is found on the Galaxy S.
It's cheap to produce, it has almost everything in a nice tidy package that makes it cheaper to engineer handsets (when I say everything, I mean CPU/GPU/Radio/WiFi/GPS/USB).
It's a pretty good package for companies like HTC, who don't do any real hardware engineering, and try to keep costs low. They do software (very very well, I should add), industrial design, and mass manufacturing, but they've NEVER designed a chipset (or display), they always source those from a third party, in this case Qualcom for the chipset, Samsung/Sony for the displays, etc.
However, they were the first to market with 1Ghz speed and it's a solid and stable hardware setup. Just keep in mind that clock speeds don't tell the whole tale.
The Galaxy S, (and to a lesser extent the Droid series) use a better stand-alone CPU solution and a far superior non-integrated (has its own chip) GPU. Samsung does do their own in-house chipset engineering, and they didn't cut corners on the CPU design, and they learned a lot about how to squeeze a lot of performance out of the ARM instruction set from their own products and the work they did for the iPhone processors. In brute-force, they smack the Snapdragon chipset around like a *****, but they get slapped around in turn by HTC's superior software engineering.
HTC has a real advantage in lots and lots of PDA/Smartphone software experience. They know how to make the most of the hardware they purchase, and seem to spend a great deal of time optimizing the software, be it Windows Mobile or Android, and lessons learned from a decade of making PDAs, under their name and for others.
If HTC used a Hummingbird or TI OMAP chipset with PowerVR GPU, I have no doubt they'd be able to more quickly wring more performance and stability out of it than Samsung or Motorola can.
Click to expand...
Click to collapse
Thanks, that was a really insightful post.
So basically even though our processor should outperform or ATLEAST match the snapdragons. Due to the mass optimization of 2.2 JIT for Snapdragon devices it's likely we'll never see the same performance. Unless Samsung gets really keen to do some optimization themselves.
I searched all over the internet to see why the CPU scores in Quadrant and other benchmarks are waaaay lower then the Nexus ones, but still I can't find anything.
Does Samsung disable the JIT in their Froyo ROMs? Because both Snapdragon and Hummingbird are still based on the same Cortex A8 cores
"It's clear that FroYo's JIT compiler currently only delivers significant performance gains for Snapdragon CPUs with the Scorpion core. This in turn explains why, so far, only a beta version of Android 2.2 is available for the Cortex-A8-based Samsung Galaxy S — the JIT compiler is the outstanding feature of FroYo. For the widespread Cortex-A8 cores, used in many high-end Android smartphones, the JIT compiler needs to be optimised. A Cortex-A8 core will still be slower than a Scorpion core at the same clock speed, but the Scorpion's advantage may not be as much 260 percent."
Click to expand...
Click to collapse
http://androidforums.com/samsung-ca...ant-scores-why-humming-bird-doing-so-bad.html
There are multiple reasons, not optimised jit, slow memory for caching and more. Most of them are solved in the CM roms (it performs on par with the N1), and i can tell you that when Gingerbread comes it will blow the snapdragons away.
Which custom ROM provides CPU performance close to Snapdragon?
[ignore this post please]
Still the 1Ghz humming bird out performs the 1Ghz snap in real world performance
Even the LG Optimus One ARM11 600MHz Core scores better than Galaxy S. I still believe it's a software problem.
http://lgoptimusonep500.blogspot.com/2011/01/custom-rom-for-lg-optimus-one-p500.html#more
Another benchmark:
http://www.anandtech.com/show/4126/nokia-http://www.anandtech.com/show/4126/nokia-n8-review-/7
...where the Nexus S proves that the Hummingbird can do more than it currrently does in Galaxy S.
The Droid2/X use the same graphic processor as Droid 1, which is PowerVR SGX 530. According to the datasheet, this core is designed to run at 200Mhz with power of rendering 14M triangles/sec. But our Droid/Milestone runs underclocked at 110Mhz(7M tri/s) while D2/X at 200Mhz. That leads to major UI responsiveness&gaming difference between D2&D1.
I wonder if there's any possibility to overclock the GPU as well?
Thanks in advance.
Sent from my Milestone using XDA App
TeroZ said:
The Droid2/X use the same graphic processor as Droid 1, which is PowerVR SGX 530. According to the datasheet, this core is designed to run at 200Mhz with power of rendering 14M triangles/sec. But our Droid/Milestone runs underclocked at 110Mhz(7M tri/s) while D2/X at 200Mhz. That leads to major UI responsiveness&gaming difference between D2&D1.
I wonder if there's any possibility to overclock the GPU as well?
Thanks in advance.
Sent from my Milestone using XDA App
Click to expand...
Click to collapse
As far as I know this has been tried (overclocking), but with no results (constant reboots)
Imagination Technologies (PowerVR) defines the GPU internals and sells the "plans" for the part, to be included in SOCs like TI's OMAP.
But PowerVR does not, however, define the exact clocks at which the parts should run, nor other things like number of memory channels, memory speed, etc.
Texas Instruments are the ones who defined the GPU clocks. The OMAP 34xx chips (Droid 1, Milestone, XT720, Flipout, etc) are made using 65nm process, and that determines a certain power consumption using certain clocks, hence why they defined a ~100MHz clock for the GPU and ~600-800MHz for the CPU.
The OMAP 36xx (Droid X, Droid 2, Defy, etc) are made using a newer, smaller 45nm process, which allows them to run at higher speeds while spending approx. the same power, which is why Texas Instruments decided to clock the GPU at ~200MHz and the CPU at ~1-1.2GHz.
So it's not like the Milestones and Droids have their GPUs underclocked, those are just their factory clocks.
Of course, overclocking the GPU would be nice and it could be possible. If someone found out how to change the GPU's voltage and clocks, I'm sure it could come in handy in future games.
However, right now, the 1st gen Milestones/Droids are running every high-end HD game from gameloft at full speed, and I bet it'll even do Infinity Blade and other UE3 games when they're out for Android.
Every "HD" Android game has to be compatible with the 1st-gen Snapdragon's GPU, the Adreno 200, which is a lot slower than the SGX530 @ 100MHz, so we're sitting confortably above the base spec for now. And with all the Windows Mobile 7 phones coming with a 1st-gen Snapdragon (mandatory requirement), it'll be like this for a while.
So there's really not a big need for overclocking the GPU right now, except for getting higher scores in mobile benchmarks (some of them terribly unoptimized, like GLBenchmark 1.1 and 2.0).
Furthermore, I it seems the first factor to limit the 1st-gen Droids in games will be the RAM amount.
The first UE3-based game for Android is already out, and it requires 512MB of RAM.
So the game runs on Nexus One and not on a Droid/Milestone, which has far superior graphics performance.
(I'm pretty sure this has something to do with the fact that Android doesn't allow graphics buffering in the main memory, though, which could be resolved in future firmware revisions).
Then again, overclocking the GPU would be cool, and I'm pretty sure getting our SGX530 to work @ ~200MHz would significantly increase the gaming longevity of our phones for quite a while.
Thanks for your useful and important reply.
"The Manhattan Project" on Galaxy S Series just made me curious about Droid's gpu oc, because SGS also use a PowerVR gpu. But things isn't easy due to a fact that one is made by TI while another is made by samsung, the structure inside both SoCs may be completely different.
But I still hope someone capable would try something on this.
That's really cool and significantly lengthen the lifetime of our Droid and Milestone.
Thx again for your reply!
PS: I also felt strange why the UI(not games) on N1 is faster than an OCed droid, could it be the optimization problem?
Sent from my Milestone using XDA App
TeroZ said:
PS: I also felt strange why the UI(not games) on N1 is faster than an OCed droid, could it be the optimization problem?
Sent from my Milestone using XDA App
Click to expand...
Click to collapse
Definitely part of the optimization --a fast ROM with a good theme like the Droid X theme on the GOT 2.2.1 ROM has as fast a GUI as I've encountered on Android, even without overclock.
Also take in consideration that all the current 2.1 and 2.2 roms have a cap of 30fps in 2D, perhaps when the final 2.2 update arrives there will be some perfomance gain
Sent from my Milestone using Tapatalk
Let me start off by saying that I know that all benchmarks should be taken with a grain of salt, and that Quadrant is a poor and outdated benchmark. But, that does not matter. I'm sure we've all ran at least one Quadrant before. Well, there is an issue with the planets test. The D3 only gets 12fps on it, and there is artifacting throughout the test.
It has been this way for every OMAP based Moto phone. The OG Droid, Droid 2, Droid 2 Global, Droid X, and so on. They ALL run the planets test at 12fps with the same exact artifacts. No matter the GPU or clock speed. I feel like I'm the only one who has noticed this. Go and perform a Quadrant on your D3 and observe the planet test. If you have any other phones, benchmark them too. Compare a D3, D2, and Inc.
The OMAP 4430 has the PowerVR SGX 540 gpu. This was the GPU in the previous gen Hummingbird. On the planets test, it would constantly be at the framerate cap of 56 with no artifacts. The Droid Incredible, even with the pathetic Adreno 200 GPU, would run the planets test well above 30fps. It is not an intense graphics test and nearly any mobile GPU can run it above 30fps.
The only Moto phones that run the planet test without issue are those with the Tegra 2. Keep in mind that Tegra 2 based devices all use nvidia's own proprietary drivers. Sure, the Droid 3 is qHD, and it won't score as well as a Galaxy s or Optimus 3D with the same GPU pushing less pixels. The X2 is also qHD and the Droid 3 typically gets a higher framerate on other GPU benchmarks-except for the planets test. In theory, the Droid 3 should score the same, if not, slightly better, on the planets test.
All of the evidence leads me to believe that it is an issue with Moto's drivers. It isn't TI, since the Optimus 3D has the exact same CPU, but runs the test without a hitch. Is anyone able to provide any insight on this, perhaps someone who can speak with someone at Moto that would know? Will this affect games, or other benchmarks? Can it be fixed in an update? Something is obviously not right here, and I'd like to find out why.
EDIT: I'm on my phone and I was in general when I hit new thread. I don't know how this ended up in development, but I apologize. Will a mod please move this?
Games and emulators on the Droid 3 don't have the FPS problem as compared to other devices. I think it's a coding issue in Quadrant, not a problem in the drivers. It would be like running 3DMark 2000 on today's hardware and having it crash out or run slower than a P3 with a 3DFX card (which it actually does in many cases).
elkay said:
Games and emulators on the Droid 3 don't have the FPS problem as compared to other devices. I think it's a coding issue in Quadrant, not a problem in the drivers. It would be like running 3DMark 2000 on today's hardware and having it crash out or run slower than a P3 with a 3DFX card (which it actually does in many cases).
Click to expand...
Click to collapse
A coding issue IS possible, but if it was a coding issue, then how is it that only specific phones from one manufacturer with CPU's and GPU's from the same manufacturers are the only ones with issues? The only Moto phones that don't have the issue are those with the Tegra 2, which uses proprietary coding and drivers from NVIDIA. There are phones from other manufacturers with the same SoC, and very similar hardware otherwise, that don't have the issue. It seems extremely likely that it is an issue with Motorola's software and coding.
GoogleAndroid said:
A coding issue IS possible, but if it was a coding issue, then how is it that only specific phones from one manufacturer with CPU's and GPU's from the same manufacturers are the only ones with issues? The only Moto phones that don't have the issue are those with the Tegra 2, which uses proprietary coding and drivers from NVIDIA. There are phones from other manufacturers with the same SoC, and very similar hardware otherwise, that don't have the issue. It seems extremely likely that it is an issue with Motorola's software and coding.
Click to expand...
Click to collapse
I'll respectfully disagree. If the same FPS problem exhibited itself in any games on the market, then I would lean toward agreeing with you. However, I have pretty much every emulator on the market and about 75-80 games on my phone, and not one has shown any performance problems and all outperform my original Droid X by a very noticeable margin.
Or perhaps it's both? Quadrant could use something in OpenGL that isn't supported very well by Motorola's drivers, and it could be a feature that isn't widely used in other apps, so it's why you're not seeing any issues in them.
Pokelover980 said:
Or perhaps it's both? Quadrant could use something in OpenGL that isn't supported very well by Motorola's drivers, and it could be a feature that isn't widely used in other apps, so it's why you're not seeing any issues in them.
Click to expand...
Click to collapse
By all means, continue to investigate. I think the problem will end up lying in how Quadrant makes its OGL ES calls. The only one that would help right now is the developer of Quadrant, which if you can get to answer the question, would be great. Not stone hard fact, but a step toward solving this.
Quadrant is not optimised for dual core processors let alone any device that has recently come out in the last year including Tegra devices, the tests are not that complicated in the bench mark yet devices are scoring sub 30 fps values.
Use a different bench mark as Quad is old hat and in need of an update or 3.
-smc
I thought I should note that the PowerVR SGX 540 in our Droid 3's are not the same as the SGX 540 in Samsung's Hummingbird SOC. It's quite a bit faster!
The SGX 540 in the OMAP 4430 is clocked 100MHz higher and gets 4.8GFLOPS vs the Hummingbird's 3.2GFLOPS.
snowblind64 said:
I thought I should note that the PowerVR SGX 540 in our Droid 3's are not the same as the SGX 540 in Samsung's Hummingbird SOC. It's quite a bit faster!
The SGX 540 in the OMAP 4430 is clocked 100MHz higher and gets 4.8GFLOPS vs the Hummingbird's 3.2GFLOPS.
Click to expand...
Click to collapse
Yes, but the higher resolution screen counterbalances that.
GoogleAndroid said:
Yes, but the higher resolution screen counterbalances that.
Click to expand...
Click to collapse
Well, not quite. The screen resolution only increased by 35% while the GPU is 50% more powerful than the SGX 540 in the Hummingbird SOC. In theory the OMAP4 should still perform better than the Hummingbird even at the higher resolution.
I would have to say that Quadrant is at least partly responsible for the low FPS. It seems likely that Quadrant is using an odd method of method of rendering for the planets test that in combination with Motorola/OMAP drivers causes a massive performance drop. Fortunately this performance issue has not been seen in other apps/games.
My main reason for posting was just to point out that the SGX 540 in our D3's is much faster. I would hate to think our GPU is no better than the Galaxy S'
this is a problem with quadrant, all motorola devices(since the mb200 aka dext/cliq we have this issue, always got the same results in 2d test and the planet) give the same score in the tests. but the new sgx 540 for dual core have a dedicated gpu for 2d graphics, i spent 3 days searching about that. so, the problem is with the app, not the phone.
can somebody send me a benchmark from D3 of smartbench, Mandrobench, linpack, antutu and cfbench. im thinkin in getting one =p
Too many variables in synthetic tests to come to a conclusion with Quadrant. One parameter can be off and that will bias the weighted result. Speaking of weight, the dev still has yet to quantify the weighting in the app for each parameter.
D3 plays N64 and PSX games equal for most and better for some (if already 60fps, will inherently be equal) than the Tegra 2 devices I had or have now. In a way, the D3 is the device the Sony Play should have been (except the control pad is better than the keyboard, of course).
guidoido004 said:
can somebody send me a benchmark from D3 of smartbench, Mandrobench, linpack, antutu and cfbench. im thinkin in getting one =p
Click to expand...
Click to collapse
On stock I got ~70mflops on average on multi-threaded Linpack test. With some of the modifications I can do with root, Antutu gets me 5112, and on stock I got somewhere around 4700 I believe. I don't have any of the other benchmarks you listed, so I couldn't tell you for them.
guidoido004 said:
this is a problem with quadrant, all motorola devices(since the mb200 aka dext/cliq we have this issue, always got the same results in 2d test and the planet) give the same score in the tests. but the new sgx 540 for dual core have a dedicated gpu for 2d graphics, i spent 3 days searching about that. so, the problem is with the app, not the phone.
can somebody send me a benchmark from D3 of smartbench, Mandrobench, linpack, antutu and cfbench. im thinkin in getting one =p
Click to expand...
Click to collapse
Antutu- 4967
Smartbench 2010-1263, 2849
Smartbench 2011- 3612, 2586
Linpack- 42, 66
CF-Bench-9397, 2636, 5340
Quadrant- 2000-2500
I couldn't find Mandrobench.
hello guys..i heard that galaxy note and other samsung device are using an outdated GPU (Mali-400MP GPU)...so is it a little "fail" for our note to have an outdated GPU?plss give ur opinion.. thanks guys
..u can read the review about the GPU--> Here
It's so much faster than the sgx540 in the nexus it's ridiculous and since my choice was between those two I'm very happy with it.
Sent from my superior GT-N7000 using Tapatalk
Check out the real world performances. Mali 400 outclasses Adreno 220 easily.
The weakpoint of Mali is geometry performance, but it does not matter much with mobiles until now as mobile games are not geometry heavy.
On the other hand, the OpenGL ES 2.x performance and real world performance of Mali is excellent.
With the clock speed of exynos in Note which actually gives much better real world performance with Mali 400 than even SGS2, it runs circles around Adreno 220 powered devices like sensation and even SGX540 powered devices.
http://www.anandtech.com/show/4686/samsung-galaxy-s-2-international-review-the-best-redefined/17
The above review is of SGS2. And mind you the performance of note is much better than SGS2. It is one of the most balanced GPUs on market with great gaming as well as multimedia performance (which actually matters more to someone like me.)
Funkym0nkey said:
Check out the real world performances. Mali 400 outclasses Adreno 220 easily.
The weakpoint of Mali is geometry performance, but it does not matter much with mobiles until now as mobile games are not geometry heavy.
On the other hand, the OpenGL ES 2.x performance and real world performance of Mali is excellent.
With the clock speed of exynos in Note which actually gives much better real world performance with Mali 400 than even SGS2, it runs circles around Adreno 220 powered devices like sensation and even SGX540 powered devices.
http://www.anandtech.com/show/4686/samsung-galaxy-s-2-international-review-the-best-redefined/17
The above review is of SGS2. And mind you the performance of note is much better than SGS2. It is one of the most balanced GPUs on market with great gaming as well as multimedia performance (which actually matters more to someone like me.)
Click to expand...
Click to collapse
thanks for this info sir
although mali has been here for a very long time, it was well ahead of its time. and it still is i guess
anjath said:
although mali has been here for a very long time, it was well ahead of its time. and it still is i guess
Click to expand...
Click to collapse
Yeah well Scott Adams is wayyyyyyy past his heyday (heck, even being relevant).... haven't read him since 2007 or so, when he started dabbling in intelligent design woo and sexist claptrap...
for being a heavy mobile gamer
i can assure you that the mali 400 on the note does very well with the latest games (asphalt7, dead trigger to name a few) despite having to compute for a much higher resolution display than other phones...
and with a little overclocking (tegrak app or gl notecore kernel) gpu performance can get sky high.
best phone i ever got :victory:
GAME ON said:
hello guys..i heard that galaxy note and other samsung device are using an outdated GPU (Mali-400MP GPU)...so is it a little "fail" for our note to have an outdated GPU?plss give ur opinion.. thanks guys
..u can read the review about the GPU--> Here
Click to expand...
Click to collapse
The note was released ten months ago but still its gpu is better than all the others except sgs3 and and maybe one x..
Btw do you even own a note?? Did you every notice any lag in any game??
Whiskeyjack4855 said:
The note was released ten months ago but still its gpu is better than all the others except sgs3 and and maybe one x..
Btw do you even own a note?? Did you every notice any lag in any game??
Click to expand...
Click to collapse
The NOTE's and SGS3's GPU are the same.
However, the S3 is built on a smaller 32nm die-size, so it means it uses less space and less power for same performance. Samsung uses this advantage to clock the frequency much higher than the NOTE (which is built on a 45nm die).
Also, the S3 implements a new, updated driver for the gpu and squeezes more performance out. This was a same move Samsung made with the SGX540, which is also a very fast gpu. The original SGS was clocked real-low and had outdated drivers... after stealing the driver sources from the LG with OMAP 4440 SoC, the SGS (with 4.0.3) was performing in the same league as the 2011/2012 devices.
Kangal said:
The NOTE's and SGS3's GPU are the same.
However, the S3 is built on a smaller 32nm die-size, so it means it uses less space and less power for same performance. Samsung uses this advantage to clock the frequency much higher than the NOTE (which is built on a 45nm die).
Also, the S3 implements a new, updated driver for the gpu and squeezes more performance out. This was a same move Samsung made with the SGX540, which is also a very fast gpu. The original SGS was clocked real-low and had outdated drivers... after stealing the driver sources from the LG with OMAP 4440 SoC, the SGS (with 4.0.3) was performing in the same league as the 2011/2012 devices.
Click to expand...
Click to collapse
I know that that both the note and sgs3 has same gpu.. But the one in sgs3 its more powerful cause you said it's overclocked and has better drivers..
Btw do you know why the mali in sgs3 gets so high benchmark scores even wih the 720p screen? I mean is it all due to oc and better drivers?
Whiskeyjack4855 said:
I know that that both the note and sgs3 has same gpu.. But the one in sgs3 its more powerful cause you said it's overclocked and has better drivers..
Btw do you know why the mali in sgs3 gets so high benchmark scores even wih the 720p screen? I mean is it all due to oc and better drivers?
Click to expand...
Click to collapse
Better drivers + a little O'C makes the overwhelming difference.
I mean the NOTE comes with *only* 2 cores and *slow* gpu... after I customized it, its running toe-to-toe with the HTC One X (Tegra3).
An easier way to understand is to look at the new RIM PlayBook.
It's got the same processor as the Gnex (Galaxy Nexus) however its much much faster, especially in browsing. It decimates it. It even decimates the ASUS Transformer Prime Infinity (O'C Tegra3 + ICS).... or the Nexus7 (U'C Tegra3 + JBean).
You are only as fast as your slowest component. In the case of Android, its the high-level (slow) implemented software.
= Getting a faster soc with more cores and more ram doesn't really increase performance that much.
Some serious thread necromancy going on here!
Regards,
Dave
Sent from my GT-N7000 using Tapatalk 2
Kangal said:
Better drivers + a little O'C makes the overwhelming difference.
I mean the NOTE comes with *only* 2 cores and *slow* gpu... after I customized it, its running toe-to-toe with the HTC One X (Tegra3).
Click to expand...
Click to collapse
By toe to toe with the one x do you mean benchmarks or real life perfomance..
Hey one thing more..aren't you a engadget reader?
Whiskeyjack4855 said:
By toe to toe with the one x do you mean benchmarks or real life perfomance..
Hey one thing more..aren't you a engadget reader?
Click to expand...
Click to collapse
Both.
But I don't live by the benchmarks. I mean have you tried some of the HD Apps from TegraZone. On stock TouchWizz, the NOTE really struggles. With a custom setup, I don't get much/any problems.
Yeah, I do frequent engadget... also on heaps of other sites.
Kangal said:
Both.
But I don't live by the benchmarks. I mean have you tried some of the HD Apps from TegraZone. On stock TouchWizz, the NOTE really struggles. With a custom setup, I don't get much/any problems.
Yeah, I do frequent engadget... also on heaps of other sites.
Click to expand...
Click to collapse
Would you be kind enough to educate me about your setup?
Kangal said:
Better drivers + a little O'C makes the overwhelming difference.
I mean the NOTE comes with *only* 2 cores and *slow* gpu... after I customized it, its running toe-to-toe with the HTC One X (Tegra3).
An easier way to understand is to look at the new RIM PlayBook.
It's got the same processor as the Gnex (Galaxy Nexus) however its much much faster, especially in browsing. It decimates it. It even decimates the ASUS Transformer Prime Infinity (O'C Tegra3 + ICS).... or the Nexus7 (U'C Tegra3 + JBean).
You are only as fast as your slowest component. In the case of Android, its the high-level (slow) implemented software.
= Getting a faster soc with more cores and more ram doesn't really increase performance that much.
Click to expand...
Click to collapse
Exactly. Even though the Playbook has its many flaws (owned two both with screen/USB issues) it was a powerhouse. Multimedia was outstanding and web surfing was by far the fastest.
But the OS, QNX, is to thank for that. If the Playbook was running android it would be nothing out of the ordinary. As much as I love Android it really is not as efficiant as QNX
Sent from my GT-N7000 using xda app-developers app
anything on market today is outdated tommorow
Sent from my GT-N7000 using Tapatalk 2
Recently I had a doubt about if it's possible to unlock the 2 locked remaining cores in the Galaxy Note N7000? Because I realize that the Note only uses 2 of the 4 GPU cores... It's there a possibility to do this? How?
i think mali 400 is a good GPU because Note1 and Note2 using it. and really nice GPU for gaming