Database Users

"FAIL"-phone slower than other phones? Despite Snapdragon?

Looks like HTC has done it again and delivered a phone that should run crazy fast on paper BUT the actual performance is sub-par compared to other phones:
HTC Nexus One (FAILphone):
http://www.youtube.com/watch?v=hvzxZ8tOBcQ
HTC Magic and HTC Liquid Benchmark:
http://www.youtube.com/watch?v=O36LA6EhZg4

I don't think that Neocore benchmarks the entire system, maybe more on the graphics chip. I don't know any specifics on the N1's graphics capabilities, but the 1 ghz snapdragon cpu is a definite boost from its predecessors.

Do you work for Apple?

How does it do on PiBenchmark? That would provide more relevant results with its Snapdragon processor.

andythefan said:
I don't think that Neocore benchmarks the entire system, maybe more on the graphics chip. I don't know any specifics on the N1's graphics capabilities, but the 1 ghz snapdragon cpu is a definite boost from its predecessors.
Click to expand...
Click to collapse
doesn't the liquid come with an underclocked snapdragon?

I have a Magic that is rooted and tweaked to all hell and have played with the nexus. There is no doubt that the Google phone out performs any other phone that HTC has released. Ive seen it first hand. Its very fast and can handle so many things going on at the same time it makes my tummy tickle.

You are an idiot. Get your panties out of a bunch because you are pissed at the price and that it has no AT&T 3G. Should we all be pissed that the Droid only works on Verizon? Should we all be pissed that the iPhone only has AT&T 3G? The Nexus One is designed to be on T-Mobile. Sure, it will technically work on any GSM provider, but that isn't what it was intended to do. Google must have some deal with T-Mobile since they offers the most android phones.
And about the performance, that only shows video performance, and we dont know for sure what the N1 and A1 have in terms of a GPU

staulkor said:
And about the performance, that only shows video performance, and we dont know for sure what the N1 and A1 have in terms of a GPU
Click to expand...
Click to collapse
I thought neocore tested the graphics chip with 3d benchamarking?

andythefan said:
I don't think that Neocore benchmarks the entire system, maybe more on the graphics chip. I don't know any specifics on the N1's graphics capabilities, but the 1 ghz snapdragon cpu is a definite boost from its predecessors.
Click to expand...
Click to collapse
It's called system on a chip.
and the telling comparison is the Acer Liquid with its ~750MHz Snapdragon CPU (underclocked) vs. the Nexus One with its 1GHz Snapdragon CPU.
Looks like HTC screwed up again.
Ohhh. The other posters are pissed because their Messiah phone is a big FAIL?

What are you, 15 years old? Get off of mommy's computer and stop *****ing because you can't use the N1 on your network and get 3G.

Im guessing the benchmark isnt accurate. It goes beyond common senese that the fps are the same as the magic.

Maedhros said:
Im guessing the benchmark isnt accurate. It goes beyond common senese that the fps are the same as the magic.
Click to expand...
Click to collapse
Actually ... it goes nicely with HTC's track record of under-performing hardware.

We have too many variables that makes comparing these results difficult. The HTC Magic and Liquid are running 1.6, while the Nexus is running 2.1. There are dramatically different levels of overhead on different Android system versions. There could be way more overhead on Android 2.1 than on 1.6. Additionally, you forgot to mention that the Nexus One is running at a resolution 2.5 times that of the HTC Magic.
Just because you're not going to buy the Nexus (because you recently purchased another handset and are trying to justify your purchase, or because it doesn't support your carrier's 3G frequencies, or otherwise) doesn't mean you are obliged to spam these forums with "OMG THIS PHONE IS FAIL"

the resolution used on the n1 is far higher than on the older devices remember

coolVariable said:
It's called system on a chip.
and the telling comparison is the Acer Liquid with its ~750MHz Snapdragon CPU (underclocked) vs. the Nexus One with its 1GHz Snapdragon CPU.
Looks like HTC screwed up again.
Ohhh. The other posters are pissed because their Messiah phone is a big FAIL?
Click to expand...
Click to collapse
The only FAIL here are your posts. You sound like a Droid owner, pissed that your phone is about to lose top dog status. Just crawl back into your parents basement, fire up your xbox, and shoot some 12 year olds. It will help you get over the fact that you are a huge FAIL.

lol @semantics now thats funny man

I have had this phone for three weeks now and one thing its not is SLOW. Its way faster than my 3GS and my Mytouch.

I got 27.4 FPS on my G1.
I'm pretty sure the N1 isn't slower then the G1. That would be stupid.

I don't give a damn, I'm buying this joint day 1!! LOL

my theory:
1. Neocore is designed to work with android 1.6 and Open GL ES 1.1
2. The Liquid A1 has the same processor (albeit underclocked) and the same screen resolution as the N1 so you would expect them to perform similarliy. They dont perfrom the same so you must look at the differences between the phones. The biggest to me is the fact that the Liquid A1 has Android 1.6 and Open GL ES 1.1, the sweet spot for Neocore.
3. The N1 had Android 2.1 and Open GL ES 2.0, specs that are not supported by Neocore. How can Neocore accurately test the N1 when it does not support its specifications? The slowness is not due to poor hardware, rather it is due to old software trying to run on the latest hardware.

Quadrant benchmark for Android on HD2 compared to SGS (What's in a score)

Look at this (from 1:44 on):
It's a quadrant benchmark run on a android port on the HD2. Graphics are really bad, but in the end it has approximately the same score as the benchmarking score of the Galaxy with the original firmware. I mean what is in a score? If I look at the beginning of the movie, the UI is very slow and not as responsive as the Galaxy
(BTW i got 55.7 FPS with the neocore benchmark on JM2)
This is not to say that I don't have deep respect for what the HD2-android development team is doing. Really amazing job. I just can't wait to get my HD2 back from repair.

appelflap said:
Look at this (from 1:44 on):
It's a quadrant benchmark run on a android port on the HD2. Graphics are really bad, but in the end it has approximately the same score as the benchmarking score of the Galaxy with the original firmware. I mean what is in a score? If I look at the beginning of the movie, the UI is very slow and not as responsive as the Galaxy
(BTW i got 55.7 FPS with the neocore benchmark on JM2)
This is not to say that I don't have deep respect for what the HD2-android development team is doing. Really amazing job. I just can't wait to get my HD2 back from repair.
Click to expand...
Click to collapse
Quadrant scores have been criticized for their non-descript breakdowns, at least on their free suite. Also, the fact that they chose the weighting of the scores, so should they chose 2D is equal to 3D weight, I don't know their formula (and for all I know, they give equal weighting to all or they give equal weighting to all test where the CPU has 12 tests and the 3D graphics has 4), but the fact that we, as users don't have access to their formula on their website is a bit unnerving.
Add to that the fact that many reviews and videos rely on it so heavily leaves users a bit misinformed. In reality, and thorough review should definitely run a custom test suite to give individual scores to:
CPU
Memory
I/O
2D graphics
3D graphics
That way users can compare what's important to them. The Galaxy S suffers from terrible I/O and the hacks that have given the fixes typically boost Galaxy scores to nearly double their rates, and it's majorly attributed to improving a bunk I/O score.

Totally agree. In addition, it would be really nice to know which benchmarked factors are responsible for which functions. For example it is really interesting to see how the hd2 performs before the user is running the tests. When the user is scrolling through the setting menu there is a very noticible lag. Given the fact that the total score is nearly the same as the scrore for the SGS, and thar the graphic score of the hd2 is bad in comparisson to the SGS, I would conclude that graphic performance is very important for the way the ui responds.
Sent from my GT-I9000 using XDA App

appelflap said:
Totally agree. In addition, it would be really nice to know which benchmarked factors are responsible for which functions. For example it is really interesting to see how the hd2 performs before the user is running the tests. When the user is scrolling through the setting menu there is a very noticible lag. Given the fact that the total score is nearly the same as the scrore for the SGS, and thar the graphic score of the hd2 is bad in comparisson to the SGS, I would conclude that graphic performance is very important for the way the ui responds.
Sent from my GT-I9000 using XDA App
Click to expand...
Click to collapse
From what I can tell, the HD2 got a decent score 'cos it was running Froyo. When we get bumped up to an official froyo build with JIT fully optimized, We should be top of the pile.

don't forget, android isn't working 100% on the HD2.
I personally think it's pointless comparing to a not complete port.

woops dbl post

alovell83 said:
Quadrant scores have been criticized for their non-descript breakdowns, at least on their free suite. Also, the fact that they chose the weighting of the scores, so should they chose 2D is equal to 3D weight, I don't know their formula (and for all I know, they give equal weighting to all or they give equal weighting to all test where the CPU has 12 tests and the 3D graphics has 4), but the fact that we, as users don't have access to their formula on their website is a bit unnerving.
Add to that the fact that many reviews and videos rely on it so heavily leaves users a bit misinformed. In reality, and thorough review should definitely run a custom test suite to give individual scores to:
CPU
Memory
I/O
2D graphics
3D graphics
That way users can compare what's important to them. The Galaxy S suffers from terrible I/O and the hacks that have given the fixes typically boost Galaxy scores to nearly double their rates, and it's majorly attributed to improving a bunk I/O score.
Click to expand...
Click to collapse
Even then though, it's possible to write a benchmark which wins constantly for any phone.
In regards to "terrible I/O", that might even be due to a bug in the FAT32 drivers. Yes you can benchmark it, but it wont mean much. The best way is to actually TEST the applications you need, rather than select a phone based on benchmarks. However, you are possibly best off looking at the component specs, because they ignore software bugs.

scrizz said:
don't forget, android isn't working 100% on the HD2.
I personally think it's pointless comparing to a not complete port.
Click to expand...
Click to collapse
But the topic is about "what's in a score". Maybe one can generally say that is pointless to compare devices this way. I think that such benchmark scores are only (a bit) relevant at the two poles of the benchmark score spectrum. Everything in between can be neglected due to the uninformed way sub-scores are evaluated.

You got 55.7 FPS on Neocore as the sgs has vertical sync enabled, the refresh rate on the sgs'es screen is 56 fps and thus you can only go up to 56 fps as the v-sync is on. This proves that the sgs is indeed a much more powerful device that is actually being held back. If you can disable the v-sync then you can get a higher fps score

appelflap said:
But the topic is about "what's in a score". Maybe one can generally say that is pointless to compare devices this way. I think that such benchmark scores are only (a bit) relevant at the two poles of the benchmark score spectrum. Everything in between can be neglected due to the uninformed way sub-scores are evaluated.
Click to expand...
Click to collapse
I just read in a post that the Galaxy S gets a 0 on the 2D score:
"JIT isn't fully enabled in the current froyo versions, and quadrant, frankly, is bull**** (for exmple, 2d acceleration gets the same weight in the final result as 3D. Due to the fact that the SGS doesn't have a dedicated 2D accelerator, quadrant doesn't try to use the cpu- it just gives a round zero in that part)"
I can't confirm this, but that definitely seems like a terrible set-up, seeing as how I'm pretty sure I have games run in 2D, so to say that it can't do it just seems wrong regardless of if the SGS has a dedicated 2D accelerator or not (so if you aren't testing the way it performs in real-world, why are you testing?)
http://forum.xda-developers.com/showthread.php?t=737787&page=3

Qazz~ said:
You got 55.7 FPS on Neocore as the sgs has vertical sync enabled, the refresh rate on the sgs'es screen is 56 fps and thus you can only go up to 56 fps as the v-sync is on. This proves that the sgs is indeed a much more powerful device that is actually being held back. If you can disable the v-sync then you can get a higher fps score
Click to expand...
Click to collapse
It isn't really being held back - the screen can't display more than 56 fps as you say, and it wouldn't really be visible even if it could. Disabling v-sync isn't really that important, we need a benchmark that can actually use the advanced features in the SGS GPU (Neocore just pushes a fairly small amount of polygons with no real extras.) Using current 3D benchmarks to benchmark the SGS is like using quake 1 to benchmark the brand new ATI/nVidia cards.
The benchmark is what is at fault here, not the device

RyanZA said:
It isn't really being held back - the screen can't display more than 56 fps as you say, and it wouldn't really be visible even if it could. Disabling v-sync isn't really that important, we need a benchmark that can actually use the advanced features in the SGS GPU (Neocore just pushes a fairly small amount of polygons with no real extras.) Using current 3D benchmarks to benchmark the SGS is like using quake 1 to benchmark the brand new ATI/nVidia cards.
The benchmark is what is at fault here, not the device
Click to expand...
Click to collapse
I don't want to speak for the other poster, and I agree with your premise, however, it isn't actually solving the issue at hand. Better FPS wouldn't be noticed, however, it would give a better score and, more importantly, indicate it's potential. So, getting 56FPS isn't doing the phone any justice within the score, which is what reviews are using, giving it an artificially low score, and putting it more in line with units that can't compete on higher end games. So, when a site like anand pushes 150FPS on a game, I know that means that their rig is entirely too powerful for the game in question, but it still means something when you compare it to the lower end graphics card that only gets 90...then when they run Crisis you see these results play out more with differences that we can notice with the eye.

I think the HD2 gets that score because, as I can see in the video, the CPU tests run faster compared to my SGS, probably because of Froyo, and I know, from the time I had the Diamond and the HD2, that the internal memory and RAM are very fast. Sadly SGS has a slow internal memory, atleast when used by the phone`s software, when copying from PC is faster than my class 6 microSD. Luckily, we have mimocan`s fix. Hope this will be fixed in future FW`s.

NexusHD2 with-FRG83D V1.7 with hastarin r8.5.1 On my HD2 got 1920 in quadrant,31.5 on neocore, and 37 on linmark.

The lag might be because you are using launcher pro, I use launcher pro and sometimes it makes the the lock lag on my phone but it doesn't happen when I use the default lock also if you have alot of Widgets on your screen it will cause lag also

appelflap said:
Look at this (from 1:44 on):
It's a quadrant benchmark run on a android port on the HD2. Graphics are really bad, but in the end it has approximately the same score as the benchmarking score of the Galaxy with the original firmware. I mean what is in a score? If I look at the beginning of the movie, the UI is very slow and not as responsive as the Galaxy
(BTW i got 55.7 FPS with the neocore benchmark on JM2)
This is not to say that I don't have deep respect for what the HD2-android development team is doing. Really amazing job. I just can't wait to get my HD2 back from repair.
Click to expand...
Click to collapse
same galaxy s scores 6000+ in quadrant with custem roms

The HD 2 is a better fit for quadrent then the sgs as quadrent was made for the snapdragon processor which the hd2 has and the sgs does not. Comparing apples to orenges in an apple juice contest doesn't really prove much. Use real life feel. If you care about the scores a rom can be made to get you over 3000 quad score but is laggy as hell. Don't believe me? Look at my sig

interesting... I was using quadrant to see how a stock xxjvo and gingerreal compared. Surely that would indicate a real speed difference and not just be some kind of "hack" ?

zelendel said:
The HD 2 is a better fit for quadrent then the sgs as quadrent was made for the snapdragon processor which the hd2 has and the sgs does not.
Click to expand...
Click to collapse
That's right.
HD2 uses two android OS :
- Cyanogenmod, that is faster than our samsung os..
- Nexus one's port to HD2, greatly optimized by google...
It's really fast. I upgraded my father's HD2 last month, replacing windows in the NAND with CM7. It really makes a big change, the phone is like brand new ^^

http://forum.xda-developers.com/showthread.php?t=1012556
Quadrant is pretty flawed. And I say that being someone who had a phone (before modifications) that was mid-range in Quadrant (Galaxy S), and having a phone that's right top of the heap (Galaxy S II)

Vibrant vs G2: The Real Stats

For those that may be wondering about the G2 and especially its 800MHz CPU, these stats are for you.
The only benchmark app I could find that would put the processors on an even playing field (due to the JIT compiler that 2.2 has on the G2) was SetCPU. SetCPU has a "Native Bench" that is (as the app says) "not affected by JIT or other VM optimizations". Lower numbers are faster.
Vibrant @ 1GHz:
C: 848.37
NEON: 333.35
Vibrant @ 1.2GHz:
C: 686.71
NEON: 278.26
G2 @ 800MHz:
C: 701.26
NEON: 351.68
G2 @ 1GHz:
C: 554.26
NEON: 273.83
G2 @ 1.2GHz:
C: 497.41
NEON: 232.69
So what does this mean? Even at the stock 800MHz it blows away the Vibrant in CPU operational speed.
BUT - and this is a big one for me - the GPU on the Vibrant is just so much better! Using Quadrant Advanced and pulling just the 2D and 3D scores, I got this (higher numbers are better):
Vibrant @ 1GHz:
2D: 320
3D: 906
Vibrant @ 1.2GHZ:
2D: 363
3D: 988
G2 @ 800MHz:
2D: 241
3D: 506
G2 @ 1GHz:
2D: 285
3D: 525
G2 @ 1.2GHz:
2D: 312
3D: 603
And just in case people wanted to know the I/O scores (once again, higher numbers are better):
Vibrant (RFS) @ 1GHz:
782
Vibrant (RFS) @ 1,2GHz:
846
Vibrant (Voodoo) @ 1GHz:
4030
Vibrant (Voodoo) @ 1.2GHZ:
4938
G2 @ 800MHz:
2389
G2 @ 1GHz:
3197
G2 @ 1.2GHz:
3963
You guys can interpret this however you want. But for me, the Vibrant with Voodoo feels so much smoother than the G2, even though the G2's CPU is superior, and it even has JIT on top of that. Just something about the Vibrant's GPU that makes the overall experience seem much more fluid. Now I know why iPhone owners think their phones are so fast. Their GPU makes things seem fast, just by looking smooth.
It's hard to walk away from the Vibrant and it's beautiful screen, but I just can't resist the keyboard on the G2...

gravis86 said:
For those that may be wondering about the G2 and especially its 800MHz CPU, these stats are for you.
The only benchmark app I could find that would put the processors on an even playing field (due to the JIT compiler that 2.2 has on the G2) was SetCPU. SetCPU has a "Native Bench" that is (as the app says) "not affected by JIT or other VM optimizations". Lower numbers are faster.
Vibrant @ 1GHz:
C: 848.37
NEON: 333.35
Vibrant @ 1.2GHz:
C: 686.71
NEON: 278.26
G2 @ 800MHz:
C: 701.26
NEON: 351.68
G2 @ 1GHz:
C: 554.26
NEON: 273.83
G2 @ 1.2GHz:
C: 497.41
NEON: 232.69
So what does this mean? Even at the stock 800MHz it blows away the Vibrant in CPU operational speed.
BUT - and this is a big one for me - the GPU on the Vibrant is just so much better! Using Quadrant Advanced and pulling just the 2D and 3D scores, I got this (higher numbers are better):
Vibrant @ 1GHz:
2D: 320
3D: 906
Vibrant @ 1.2GHZ:
2D: 363
3D: 988
G2 @ 800MHz:
2D: 241
3D: 506
G2 @ 1GHz:
2D: 285
3D: 525
G2 @ 1.2GHz:
2D: 312
3D: 603
And just in case people wanted to know the I/O scores (once again, higher numbers are better):
Vibrant (RFS) @ 1GHz:
782
Vibrant (RFS) @ 1,2GHz:
846
Vibrant (Voodoo) @ 1GHz:
4030
Vibrant (Voodoo) @ 1.2GHZ:
4938
G2 @ 800MHz:
2389
G2 @ 1GHz:
3197
G2 @ 1.2GHz:
3963
You guys can interpret this however you want. But for me, the Vibrant with Voodoo feels so much smoother than the G2, even though the G2's CPU is superior, and it even has JIT on top of that. Just something about the Vibrant's GPU that makes the overall experience seem much more fluid. Now I know why iPhone owners think their phones are so fast. Their GPU makes things seem fast, just by looking smooth.
It's hard to walk away from the Vibrant and it's beautiful screen, but I just can't resist the keyboard on the G2...
Click to expand...
Click to collapse
I don't see how G2 processor is superior to that in Vibrant... Enlighten please.
As far as the overall speed of G2 comparing to Vibrant in stock forms, don't forget the fact that Samsung decided to saw off the branch they are seating on by going with an RFS filesystem - this is alone is the major hindering point of the Vibrant performance, it's like fitting a supercar with tires that rated at 50 mph - good for the scenery rides in the school zones.

lqaddict said:
I don't see how G2 processor is superior to that in Vibrant... Enlighten please.
As far as the overall speed of G2 comparing to Vibrant in stock forms, don't forget the fact that Samsung decided to saw off the branch they are seating on by going with an RFS filesystem - this is alone is the major hindering point of the Vibrant performance, it's like fitting a supercar with tires that rated at 50 mph - good for the scenery rides in the school zones.
Click to expand...
Click to collapse
Did you read the whole post?
The CPU is superior because it takes less time to perform the same operations. Which makes it faster. Usually faster=better.
And yes I know that Samsung crippled the Vibrant by giving it RFS. It's like God creating the fastest man in the world and then having him be born with only one leg... But that's not the point.
Using your analogy with the car, I was only talking about the engine. I was comparing the engine of a Ferrari to the engine of a Lamborghini. No need to bring wheels into it.

I will give you a hint: NEON is the ARM Cortex™-A series processors specific instruction set. G2, for your information, is not a ARM Cortex™-A series processor equipped, the Hummingbird in Vibrant is. That benchmark is an illusion.
it's like a competition who will faster answer a question:
Q: What is PI?
Adult: Hmm, let me think is it 3.14... - answer in 5 secs
2 year old kid: I don't know - under one second WINNER!!!!
Source http://www.arm.com/products/processors/technologies/neon.php

I will give you a hint, look at the c score and disregard the neon score.
lqaddict said:
I will give you a hint: NEON is the ARM Cortex™-A series processors specific instruction set. G2, for your information, is not a ARM Cortex™-A series processor equipped, the Hummingbird in Vibrant is. That benchmark is an illusion.
it's like a competition who will faster answer a question:
Q: What is PI?
Adult: Hmm, let me think is it 3.14... - answer in 5 secs
2 year old kid: I don't know - under one second WINNER!!!!
Source http://www.arm.com/products/processors/technologies/neon.php
Click to expand...
Click to collapse
Sent from my GT-I9000 using XDA App

lqaddict said:
I will give you a hint: NEON is the ARM Cortex™-A series processors specific instruction set. G2, for your information, is not a ARM Cortex™-A series processor equipped, the Hummingbird in Vibrant is. That benchmark is an illusion.
it's like a competition who will faster answer a question:
Q: What is PI?
Adult: Hmm, let me think is it 3.14... - answer in 5 secs
2 year old kid: I don't know - under one second WINNER!!!!
Source http://www.arm.com/products/processors/technologies/neon.php
Click to expand...
Click to collapse
The Qualcomm MSM7230 (the CPU in the G2) supports the ARMv7 instruction set. So NEON is relevant. If you are going to talk about something you don't know about, at least do your research.
Also, you should stay away from analogies. That one was worse than your first.

gravis86 said:
The Qualcomm MSM7230 (the CPU in the G2) supports the ARMv7 instruction set. So NEON is relevant. If you are going to talk about something you don't know about, at least do your research.
Also, you should stay away from analogies. That one was worse than your first.
Click to expand...
Click to collapse
damn he **** on you!

Also, this.
Underneath the diagram, click "Connected Community" and read "Silicon Vendors". See Qualcomm on that list? Okay then.
I figured since you posted the site it was only fair.

Well if you read the arm website it states there that cortex is based on armv7 and neon is cortex specific.
Armv7 is a base for cortex not the way around. If you read you will learn a bit.
And while you are at it G2 processor is armv7 the baseline for cortex
Sent from my bionix powered Vibrant

Yeah, but the vibrants flux capacitor is better.
Sent from my SGH-T959 using XDA App

SeanFloyd said:
Yeah, but the vibrants flux capacitor is better.
Click to expand...
Click to collapse
Yeah, it may be better, but with the lag and GPS problems on the Samsung you will definitely be late or in the wrong time and hopelessly lost.

If the G2 didn't support NEON, SetCPU would not have given you a score for NEON.

Numbers Numbers do tell the story
I ve looked at alot of the comparisons for the G2 vs Vibrant
So I tried with my buddy who manages a cell store a real life comparison between the two.
What we found Apps and data access was a little faster on the G2 not much.
The Vibrant was Way smoother and WAY faster on graphics even though its bench tests did not reflect that.
The screen way better on the Vibrant (duh)
Other than that, there were not real big differences That I thought were note worthy.
We used Linpack , Quadrant, neocore, Apps to QR, Google Earth
The Vibrant was rooted The G2 was out of the box.
Considering just the look and feel of the G2 The Vibrant is just a nicer all around phone. For those who have to have everything just the Best Good Luck ...and keep trying, but all these phones ALL have some shortcoming, and my opinion........ The Vibrant is still the best as of today.........

too bad it's still a G2 and I highly doubt it can do over 70 FPS in Neocore. Now that is a benchmark. Whatsup now.

Hmmm, are these scores relevant? Were they done using the same android OS version? 2.2 in the G2 will have an advantage over 2.1 in the Vibrant. Can we really consider these scores "truthful"?
Just curious, The OS itself runs better with JIT, so its not just the apps, no matter how you look at it JIT will effect the score somewhere.
If you are effected by everthing around you, and a stimulus added to the group, just because you are not directly effected doesn't mean you're not effected at all.
I would like to see some stats from both devices under android 2.2 then tell me that JIT has no "effect".

Vibrant won't gain much from 2.2.
Vibrant with RFS is like Windows 7 running off a FAT32 3200 RPM IDE Drive.
No matter how great you make the software, the file system sucks and will make anything that runs off of it suck.
The lag becomes borderline unbrearable towards the end of the day. This is the first time I've had to make sure I reboot my phone 2-3 times a day, lest it become borderline unusable.
Of course, I've heard some Blackberries were just as bad, if not worse.

N8ter said:
Vibrant won't gain much from 2.2.
Vibrant with RFS is like Windows 7 running off a FAT32 3200 RPM IDE Drive.
No matter how great you make the software, the file system sucks and will make anything that runs off of it suck.
The lag becomes borderline unbrearable towards the end of the day. This is the first time I've had to make sure I reboot my phone 2-3 times a day, lest it become borderline unusable.
Of course, I've heard some Blackberries were just as bad, if not worse.
Click to expand...
Click to collapse
Whoa, wait. This was done without the voodoo lagfix?! Wouldn't that also produce improper results? I mean, if we are checking raw power vs raw power we kinda need to have similar environments for both devices.
I understand FAT/RFS sucks, but we have the option to change that. We aren't locked to it so why not benchmark using similar environments. I'm sure the G2 is at least using EXT3. Thats almost like trying to compare a stock honda with the Acura Integra GSR! stock car vs. Stock RACE car. not really a fair comparison. If the honda were modded and tuned to similar equipment as the Integra then I could see the benefit of comparing, but only under similar conditions and tunings.
I'm not saying the vibrant should stomp the G2, but I do believe that it should be a little more capable than what we are seeing. We use almost the same exact hardware as the Iphone4 and Ipad (except GPU ) and those little dudes cook! (NOTE: i'm not a apple fan, so it pains me to admit this much)
I would still like to see the marks from similar environments for each phone.

Actually with the exception of the RFS I/O scores, all tests were run on a Vibrant with Voodoo installed. Not that Voodoo affects the CPU scores anyway. Just thought you guys should know
Sent from my T-Mobile G2 using XDA App

Darksurf said:
Hmmm, are these scores relevant? Were they done using the same android OS version? 2.2 in the G2 will have an advantage over 2.1 in the Vibrant. Can we really consider these scores "truthful"?
Just curious, The OS itself runs better with JIT, so its not just the apps, no matter how you look at it JIT will effect the score somewhere.
If you are effected by everthing around you, and a stimulus added to the group, just because you are not directly effected doesn't mean you're not effected at all.
I would like to see some stats from both devices under android 2.2 then tell me that JIT has no "effect".
Click to expand...
Click to collapse
Read my replies, even though the troll who started the thread called me uneducated, it takes just a little bit of research to conclude that these numbers are completely irrelevant:
1. NEON is a Cortex-A instruction set. G2 is not a Cortex-A processor, so what it does with NEON instructions? It ignores them yielding quicker time (ignoring is much quicker than executing )
2. C number (the gentleman who told me to get a hint from it) - is a condition set on the instruction set, in this case C is carry on condition that tells the processor to continue with the next instruction if the previous resulted in a NOP (no operation), so you feed a bunch of instructions to a processor that has no idea how to process, and ignores them, and you tell the processor to continue ignoring them until the instruction set is empty.
Woohoo that declares a WINNER!!!
LINPACK scores are a little bit more relevant but still not an accurate benchmark for the CPU performance in non-ideal conditions.

The benchmark is shows off the qualcomm CPU strengths. Going by linpacks, they're nearly identical. But they're all synthetic benchmarks anyways, and the difference is negligible in the OS / Real use.

Hummingbird VS Snapdragon

I cannot understand why everyone is saying that hummingbird processor is better than snapdragon and that's why I started this thread.
I own an HD2 (snapdragon) and SGS (hummingbird).
I've run linpack and quadrant in both phones and here are the results showing that snapdragon is 4 to 5 times faster.
Hummingbird: linpack 13,864 quadrant CPU 1456
Snapdragon: linpack 63,122 quadrant CPU 4122
I'm only talking for the CPU cause if you go to 3D I'll agree that hummingbird is better (but I don't care about 3D cause I don't use my device for games)
Both phones have android 2,2 installed and I have voodoo lagfix installed in SGS

johcos said:
I cannot understand why everyone is saying that hummingbird processor is better than snapdragon and that's why I started this thread.
I own an HD2 (snapdragon) and SGS (hummingbird).
I've run linpack and quadrant in both phones and here are the results showing that snapdragon is 4 to 5 times faster.
Hummingbird: linpack 13,864 quadrant CPU 1456
Snapdragon: linpack 63,122 quadrant CPU 4122
I'm only talking for the CPU cause if you go to 3D I'll agree that hummingbird is better (but I don't care about 3D cause I don't use my device for games)
Both phones have android 2,2 installed and I have voodoo lagfix installed in SGS
Click to expand...
Click to collapse
After looking into it for a while, I was focusing on what makes the Nexus One so much better than the other phones. On the chip level, I didn’t see it. Then it dawned on me to look at what Google had to say on the matter. Well, it was there in black and white. In their 20 May 2010 Developer’s Blog entry (http://android-developers.blogspot.com/2010/05/android-22-and-developers-goodies.html) they say that people could see a 2-5x speed increase. I think it is pointed out in an entry later in the blog dealing with NDK, which I initially missed: “ARM Advanced SIMD (a.k.a. NEON) instruction support The NEON instruction set extension can be used to perform scalar computations on integers and floating points. However, it is an optional CPU feature and will not be supported by all Android ARMv7-A based devices. The NDK includes a tiny library named “cpufeatures” that can be used by native code to test at runtime the features supported by the device’s target CPU.”
So, I guess this means that NEON is the difference. If your phone’s CPU has it and it’s enabled for JIT, you can expect higher Linpack numbers.
Click to expand...
Click to collapse
http://www.greenecomputing.com/2010...ack-scores-so-mucher-higher-than-on-my-phone/
Now stop making topics like this.

the difference you notice is software related

If you want a real test, run a hd video on both phones, or a psx emulator and see if the nexus one is 5x faster... it is the same if not slower then the sgs

Well, SGS got hardware h264 decoding acceleration. Also, maybe you forget, but:
he Hummingbird comes with 32KB each of data and instruction caches, an L2 cache, the size of which can be customized, and an ARM® NEON™ multi-media extension.
Click to expand...
Click to collapse
SAMSUNG and Intrinsity Jointly Develop the World's Fastest ARM® Cortex™-A8 Processor Based Mobile Core in 45 Nanometer Low Power Process
Advanced SIMD (NEON)
The Advanced SIMD extension, marketed as NEON technology, is a combined 64- and 128-bit single instruction multiple data (SIMD) instruction set that provides standardized acceleration for media and signal processing applications. NEON can execute MP3 audio decoding on CPUs running at 10 MHz and can run the GSM AMR (Adaptive Multi-Rate) speech codec at no more than 13 MHz. It features a comprehensive instruction set, separate register files and independent execution hardware. NEON supports 8-, 16-, 32- and 64-bit integer and single-precision (32-bit) floating-point data and operates in SIMD operations for handling audio and video processing as well as graphics and gaming processing. In NEON, the SIMD supports up to 16 operations at the same time. The NEON hardware shares the same floating-point registers as used in VFP.
Click to expand...
Click to collapse
source: wiki
This means Hummingbirds are equipped with NEON. Why its not so effective/used in Quadrant/Linpack? My guess they (these benchmarks) are not compiled/optimised for Hummingbirds, just for Snapdragons.

I came from owning an iPhone and playing lots of games on it. I bought the SGS purely for the gaming performance of the Hummingbird processor.
Having seen the difference in game quality between the HTC Desire and the SGS, I know I made the right decision. Benchmarks don't mean anything.

As long as the device can run apps, games, multimedia smoothly, I dont care much about those benchmarkers, maybe they were designed and/or optimized for snapdragon prior to hummingbird.
Sent from my GT-I9000 using XDA App

i bet you anything he actually doesn't have a sgs...lol
jealousy maybe just a troll, ignore

In terms of overall smoothness (everything, not just games) the SGS is vastly superior to any other android phone I've seen (Desire included).

Darkimmortal said:
everything
Click to expand...
Click to collapse
Really? You have to go all out and use the word "everything" when the phone can get major lockups?
"most things" sounds like a more reasonable and believable choice of words...
Sent from my GT-I9000 using XDA App

My friends I do own an SGS (not happy with it thought) and the tests that I posted were run from me.
I wasn't talking about the gaming performance (I know that SGS is the best out there)
This thread was started so that we can find an answer why is this happening?
I see some answers that cover it but I believe not completely because in everyday use of the phones I see that HD2 is snappier (not much but it is) than SGS (with lagfix).
The best test I believe would be to put the phones to encode something (like a video) but I don't know any software that could do that. (If anyone knows some please point them to me and I'll be happy to post the results here)
The tests you mention with psx and multimedia won't show as what we're looking because the SGS will clearly win because of the GPU.

johcos said:
My friends I do own an SGS (not happy with it thought) and the tests that I posted were run from me.
I wasn't talking about the gaming performance (I know that SGS is the best out there)
This thread was started so that we can find an answer why is this happening?
I see some answers that cover it but I believe not completely because in everyday use of the phones I see that HD2 is snappier (not much but it is) than SGS (with lagfix).
The best test I believe would be to put the phones to encode something (like a video) but I don't know any software that could do that. (If anyone knows some please point them to me and I'll be happy to post the results here)
The tests you mention with psx and multimedia won't show as what we're looking because the SGS will clearly win because of the GPU.
Click to expand...
Click to collapse
man. if you are not happy, then i think you should sell it. no one here will give you a satisfying answer that warm your heart. look for desire hd or something.
to answer ur questions. i get a 2100+ on quadrant. using voodoo fix and oclf on my eclaire. lag free and smooth as butter.
but either way, these test scores mean nothing. they were not designed for samusng hardware. it was designed based on htc and the snapdragon processor.
even people who use neocore for gpu are wrong. if you wana test the gpu performance, use nenamark1. the sgs gives u 49+ fps while the desire HD struggle to give u 35. while if you use neocore. the sgs gives u 56 while desire hd 58
my point is most of those software were designed with htc hardware in mind. so you cant really compare them.
just test your device for your self. apply whatever best roms you find here. if it doesnt lag and smooth for you. then ^^^^ everyone else.
the display alone is worth keepin the sgs for me. sure people might like i phone 4 display more. but nothing in my eyes come close to the contrast and colors of the super amoled. watching a movie or playing a game is a joy in this device.
hell yesterday evening a local htc store had a demo of desire hd. and the guy was nice enough to me play with it for like 1 hour.
device as a hardware look. its friggin sexy as hell. screen ? beauitful large 4.3 screen. quality colors compared to sgs ? fail. a lil slow and laggy " i am sure its because of the firmware. once roms are out, it will be faster "
i was thinking to change to desire hd honestly. but i wake away from the store kissing my sgs.
i love the desire hf look and feel. but as of now its not as smooth as my sgs. and the screen isnt as vibrant.

Psx emulator does not use the gpu...yet
Sent from my GT-I9000 using XDA App

android53 said:
Psx emulator does not use the gpu...yet
Sent from my GT-I9000 using XDA App
Click to expand...
Click to collapse
this. i played king of fighters on my hd2 and it was laggy as hell
smooth as butter on my galaxy s
to be honest. the day psx4droid use gpu. galaxy owners are in heaven.

Its unlikely it ever will though, even modern pc emulators barely use the gpu, only for anti aliasing
Sent from my GT-I9000 using XDA App

johcos said:
My friends I do own an SGS (not happy with it thought) and the tests that I posted were run from me.
I wasn't talking about the gaming performance (I know that SGS is the best out there)
This thread was started so that we can find an answer why is this happening?
I see some answers that cover it but I believe not completely because in everyday use of the phones I see that HD2 is snappier (not much but it is) than SGS (with lagfix).
The best test I believe would be to put the phones to encode something (like a video) but I don't know any software that could do that. (If anyone knows some please point them to me and I'll be happy to post the results here)
The tests you mention with psx and multimedia won't show as what we're looking because the SGS will clearly win because of the GPU.
Click to expand...
Click to collapse
Why in hell woul you want to incodea video using a smartPHONE...?
It's like trying to fit your family and grocery in a sport car... not made for this bro!
stop trying to find reason to "not like" the SGS, if you don't like it, sell it and be done...

Snapdragon/Hummingbird scores in glbenchmark (nexus one/galaxy s):
integer: 20661/27624
float: 11173/7968
I guess glbenchmark uses native C code (hopefully with armv7 optimization), so the JIT compiler has no effect. From the scores it seems that the floating point unit in Snapdragon is faster - but most of the time it is not used (except video & games).
Anyway, a benchmark to measure the same algorithm in both native & java code with scalar & vector instructions would be great...

t1mman said:
Why in hell woul you want to incodea video using a smartPHONE...?
It's like trying to fit your family and grocery in a sport car... not made for this bro!
stop trying to find reason to "not like" the SGS, if you don't like it, sell it and be done...
Click to expand...
Click to collapse
he's not whining, well, not in the first place and i don't see any harm on that i think he's trying to UNDERSTAND reasons behind numbers and daily use with help of other people, so am i. if i had to sell phones for every problem i encounter i will problaby be without (smart)phone at this time
i don't care about benchmarks, but if you think that sgs is smoother than hd2 xda optimized (with wm 6.5 or android 2.2) you obviously never owned an hd2 i'm not talking about games, like johcos says galaxy s performance is not questionable. but android is not all about game. anyway, i don't think hardware is the problem here, sure sgs is superior in many aspects, we know that, regardless benchmarks (even if it seems here that only benchmarks where sgs win are trustworthy, others are not good, not optimized, not realistic, meaningless for real life performance etc.). with a little help from samsung and this community sgs will soon outperform (in real usage) all snapdragon phones. i hope

...when average men talk about the high tech w/o knowledge, boo

ll_l_x_l_ll said:
man. if you are not happy, then i think you should sell it. no one here will give you a satisfying answer that warm your heart. look for desire hd or something.
to answer ur questions. i get a 2100+ on quadrant. using voodoo fix and oclf on my eclaire. lag free and smooth as butter.
but either way, these test scores mean nothing. they were not designed for samusng hardware. it was designed based on htc and the snapdragon processor.
even people who use neocore for gpu are wrong. if you wana test the gpu performance, use nenamark1. the sgs gives u 49+ fps while the desire HD struggle to give u 35. while if you use neocore. the sgs gives u 56 while desire hd 58
my point is most of those software were designed with htc hardware in mind. so you cant really compare them.
just test your device for your self. apply whatever best roms you find here. if it doesnt lag and smooth for you. then ^^^^ everyone else.
the display alone is worth keepin the sgs for me. sure people might like i phone 4 display more. but nothing in my eyes come close to the contrast and colors of the super amoled. watching a movie or playing a game is a joy in this device.
hell yesterday evening a local htc store had a demo of desire hd. and the guy was nice enough to me play with it for like 1 hour.
device as a hardware look. its friggin sexy as hell. screen ? beauitful large 4.3 screen. quality colors compared to sgs ? fail. a lil slow and laggy " i am sure its because of the firmware. once roms are out, it will be faster "
i was thinking to change to desire hd honestly. but i wake away from the store kissing my sgs.
i love the desire hf look and feel. but as of now its not as smooth as my sgs. and the screen isnt as vibrant.
Click to expand...
Click to collapse
Honestly couldn't agree anymore, even with all the problems the SGS has. The screen+hardware combination is just too overwhelming for me to swap the phone for something else.

Holly Quadrant Batman! 1700+

Seems like I got a pretty quick device I got a best of 1703

fifedogg said:
Seems like I got a pretty quick device I got a best of 1703
Click to expand...
Click to collapse
Nice score man, I would suggest running Smartbench 2010 however. Quadrant is skewed towards Snapdragon processors so its really not a good benchmark.

kenvan19 said:
Nice score man, I would suggest running Smartbench 2010 however. Quadrant is skewed towards Snapdragon processors so its really not a good benchmark.
Click to expand...
Click to collapse
Compared to other types of processors your right. But as far as our phones go I think its a pretty good score.
Smartbench is byast to phones with higher GPU's like the Epic just like quadrant is more byast to CPU speed, with Snapdragon having the upper hand. I'm sure the Epic will do much better on quadrant with a legit 2.2 build and JIT enabled. From what I understand Quadrant uses more CPU when processing the 2d/3d as opposed to Smartbench using mainly the GPU. IMO quadrant gets high scores with fast cpu's and Smartbench gets super high scores with high GPU phones. I have an Epic and my Shift is faster all around except when its something to do with pure GPU.

fifedogg said:
Compared to other types of processors your right. But as far as our phones go I think its a pretty good score.
Click to expand...
Click to collapse
Oh I wasn't saying you had a bad score, its just that Quadrant scores are meaningless, sure you can compare a Shift to a Shift but it won't give you any scores that are applicable in the real world. If you're just looking for a big number then quadrant is great for that, however if you want something that provides an accurate representation of your phone's power Smartbench is the ticket!
~Edit~
Also, I forgot to mention how easy it is to trick quadrant and fake scores. People have gotten it to give last gen devices 2500+ scores. Quadrant is just a terrible benchmarking tool all around.
~Edit #2~
I know I sound like a **** who is trolling you but what I'm really trying to do is prove to the Evo and Epic fanboys that this device is really great. If you quote a big quadrant score they'll jump all over you and discredit you. If you quote a Smartbench score they will 1) have to go look up what smartbench is (c'mon its really new lol) and 2) make up some other fake reason to claim the other devices are better.
My point is that having owned an Epic since launch day, an Evo for a few days and my wife owning a Shift for a few days I can find only one thing I dislike about the shift whereas I have a myriad of issues with the others (that one issue is the screen size).

Thread cleaned, let's get this back on track

Sorry for taking it down that path Impaler
Sent from my HTC Evo Shift 4G

My bad
Sent from my HERO200 using XDA App

BrandoKC said:
Sorry for taking it down that path Impaler
Sent from my HTC Evo Shift 4G
Click to expand...
Click to collapse
the5ifty said:
My bad
Sent from my HERO200 using XDA App
Click to expand...
Click to collapse
It's ok guys, just trying to get stuff back on track

Anyway...i ran a smartbench on the wifes shift and it scored considerably lower than the G2...i get ~1650s in quadrant
Sent from my HERO200 using XDA App

fifedogg said:
Compared to other types of processors your right. But as far as our phones go I think its a pretty good score.
Smartbench is byast to phones with higher GPU's like the Epic just like quadrant is more byast to CPU speed, with Snapdragon having the upper hand. I'm sure the Epic will do much better on quadrant with a legit 2.2 build and JIT enabled. From what I understand Quadrant uses more CPU when processing the 2d/3d as opposed to Smartbench using mainly the GPU. IMO quadrant gets high scores with fast cpu's and Smartbench gets super high scores with high GPU phones. I have an Epic and my Shift is faster all around except when its something to do with pure GPU.
Click to expand...
Click to collapse
Slight correction - Smartbench simply reports the performance of each phones in comparison to Nexus One. Productivity Index scores aren't supposed to be compared with Games Index scores since the bases for each are different.
I own a G2, Vibrant and N1 (also Optimus One). I am pretty happy with what Smartbench reports vs real experience.
The numbers may change drastically in v2011 if another phone is chosen as the base (I am tempted to do this since it appears that almost every phone in the market today grossly outperforms Snapdragon QSD8x50 in GPU by a big margin...

I scored a little over 1500 on Quadrant. Smart bench gave me 759/1097 and 693/1116
not sure if that is good or not. But my phone does seem a little sluggish.

Heelfan71 said:
I scored a little over 1500 on Quadrant. Smart bench gave me 759/1097 and 693/1116
not sure if that is good or not. But my phone does seem a little sluggish.
Click to expand...
Click to collapse
For some reason, Evo Shifts (in general) aren't reporting numbers as high as the G2 or Desire Z. Have a look at http://smartphonebenchmarks.com you will see some numbers for G2 and Desire Z, both stock and overclocked.

I also found my Shift scores are considerably lower than the G2, but then again I don't put too much stock into benchmarking programs. I find that out of the box the Shift is buttery smooth and at 800Mhz the quadrant/SB scores soundly beat my EVO clocked at 1Ghz and the EVO is pretty beastly.
Also considering people have been able to overclock the processor in the G2 from 800 to 1.9Ghz, we should be able to boost the Shift considerably once we have root. Hopefully the Shift is embraced by the dev community because overclock plus AOSP will be a beautiful thing.

I'll be adding Evo Shift score to the chart shortly. So far, 759/1097 is the best score I've seen on here. If anyone can beat this score (in a stock form), please let me know here!

Acei said:
I'll be adding Evo Shift score to the chart shortly. So far, 759/1097 is the best score I've seen on here. If anyone can beat this score (in a stock form), please let me know here!
Click to expand...
Click to collapse
Will do, man thanks!

Acei said:
I'll be adding Evo Shift score to the chart shortly. So far, 759/1097 is the best score I've seen on here. If anyone can beat this score (in a stock form), please let me know here!
Click to expand...
Click to collapse
832/1240 is what I got 1st try. I'm gonna try a few more times and see what she does. I can post screen shots if need be as well.

fifedogg said:
832/1240 is what I got 1st try. I'm gonna try a few more times and see what she does. I can post screen shots if need be as well.
Click to expand...
Click to collapse
Great! Thanks.