Related
I have a question about the 3D's dual core that I'd like more clarification on the vague answers I'm getting by searching this site and google. So I've read that the core is asynchronous so basically meaning the second core doesn't do much work unless needed as others like the tegra 2 and exynos have both cores running or something similar to that, and that this is affecting the benchmark scores. I also read that one would basically double the score of the 3D to get a more accurate reading. Can anyone confirm or further explain this?
Yes, asynchronous is when something operates on another thread whereas the main thread is still available for operating. This allows for better performance in terms of managing tasks. Now just because it doesn't score high on a benchmark, it doesn't mean it is going to perform. Also this allows for better performance for the battery.
I haven't slept for the past 12 hours so if this doesn't help you, just let me know and I will fully elaborate on how the processor will operate on the phone. Now time for bed :'(
In short, asynchronous operation means that a process operates independently of other processes.
Think of transferring a file. A separate thread will utilized for doing so. You will then be able to do background things such as playing with the UI, such as Sense since you will be using the main thread. If anything were to happen to the transferring file (such as it failing), you will be able to cancel it because it is independent on another thread.
I hope this makes sense man, kind of tired. Now I'm really going to bed.
Sent from my PC36100 using XDA App
To be more specific by asynchronous they mean that each core can run at different clock speeds. Core 1 could be at 1.2 ghz while core 2 is at 200 mhz. Most multi core processors are synchronous meaning all the cores are running at the same speed.
donatom3 said:
To be more specific by asynchronous they mean that each core can run at different clock speeds. Core 1 could be at 1.2 ghz while core 2 is at 200 mhz. Most multi core processors are synchronous meaning all the cores are running at the same speed.
Click to expand...
Click to collapse
^This too
Sent from my PC36100 using XDA App
I was also very curious to learn a little more about the async cores and how it differes from a standard "Always-On" dual core arctechiure.
Thh first page/video I found talks about the SnapDragon core specifically.
http://socialtimes.com/dual-core-snapdragon-processor-qualcomm-soundbytes_b49063
From what I've gathered, it comes down to using the second core and thus more power, only when needed. Minimizing voltage and heat to preserve battery life.
The following video goes into similar and slightly deeper detail about the processor specifically found in the EVO 3D. The demo is running a processor benchmark with a visual real time usage of the two cores. You can briefly see how the two cores are trading off the workload between each other. It was previously mentioned somewhere else on this forum, but I believe by seperating a workload between two chips, the chip will use less power across the two chips vs putting the same workload on a sinlge chip. I'm sure someone else will chime in with some additional detail. Also, after seeing some of these demos, I'm inclined to think that the processor found in the EVO 3D is actually stable at 1.5 but has been underclocked to 1.2 to conserve battery. Only time spent within our hands will tell.
Another demo of the MSM8660 and Adreno 220 GPU found in the EVO 3D. Its crazy to think we've come this far for mobile phone technology.
What occurred to me is how complex Community ROMs for such a device may become with the addition of Video Drivers that may continue to be upgraded and improved (think early Video Card tweaks for PC). Wondering how easy/difficult it will be to get our hands on them, possibly through extraction of updated stock ROMs.
EDIT: As far as benchmarks are concerned, I blame the inability of today's bench marking apps to consider async cores or properly utilize them during testing to factor the over all score. Because the current tests are most likely to be spread across cores which favors efficiency, the scores are going to be much lower than what the true power and performance of the chips can produce. I think of it as putting a horsepower governor on a Ferrari.
thanks for the explanation everyone
The best demonstration is in the first video posted, notice when Charbax looks at the monitor. There on the top right are the frequencies of the two cores, and you'll notice the both of them jumping around a lot, independent of the other. Using the cores "on-demand" only when needed ends up saving a lot of battery power, but doesn't give you any performance loss.
Harfainx said:
The best demonstration is in the first video posted, notice when Charbax looks at the monitor. There on the top right are the frequencies of the two cores, and you'll notice the both of them jumping around a lot, independent of the other. Using the cores "on-demand" only when needed ends up saving a lot of battery power, but doesn't give you any performance loss.
Click to expand...
Click to collapse
Actually I was thinking that not just the battery savings but there could be a performance gain. Think of this if the manufacturer knows they only have to clock one core up to speed when needed they can be more aggressive about their timings and have the core clock up faster than a normal dual core would since they know they don't have to clock up both processors when only one needs the full speed.
I wonder if the drop to 1.2 GHz also serves to keep heat under control. It might not just be battery savings, maybe the small case of a phone doesn't allow for proper cooling to hit 1.5 safely.
I'd love to see some confirmation that the asynchronous nature of this chipset is what's responsible for the seemingly lackluster benchmarking.
mevensen said:
I wonder if the drop to 1.2 GHz also serves to keep heat under control. It might not just be battery savings, maybe the small case of a phone doesn't allow for proper cooling to hit 1.5 safely.
I'd love to see some confirmation that the asynchronous nature of this chipset is what's responsible for the seemingly lackluster benchmarking.
Click to expand...
Click to collapse
The "horrible" benchmark scores are simply due to the tests inability to consider async core performance. Wait till the tests are able to take this into consideration.
Sent from my HERO200 using XDA Premium App
RVDigital said:
The "horrible" benchmark scores are simply due to the tests inability to consider async core performance. Wait till the tests are able to take this into consideration.
Sent from my HERO200 using XDA Premium App
Click to expand...
Click to collapse
I went through all of your links, I didn't see anything that confirms that the benches are somehow affected by the asynchronous nature of the chipset. It's not that I don't believe you, I actually had that same theory when the benches first came out. I just don't have any proof or explanation of it. Do you have a link that provides more solid evidence that this is the case?
NVIDIA actually tells a different story (of course)
http://www.intomobile.com/2011/03/24/nvidia-tegra-2-outperforms-qualcomm-dualcore-1015/
AnandTech's article does explain some of the differences
http://www.anandtech.com/show/4144/...gra-2-review-the-first-dual-core-smartphone/4
It appears that Snapdragon (Scorpion) will excel in some tasks (FPU, non-bandwith constrained applications), but will fall short in others .
I'm pretty sure none of the benchmark apps have even been updated past the release of the sensation so yeah....How could they update the app to use the asynchronus processors the if the only phones to use them have only recently been released.
Sent from my zombified gingerbread hero using XDA Premium App
I had the G2x for like 3 days and never got to root. Poor service where I live. But could the cores be set to a specific frequency independently when rooted like computers?
tyarbro13 said:
I had the G2x for like 3 days and never got to root. Poor service where I live. But could the cores be set to a specific frequency independently when rooted like computers?
Click to expand...
Click to collapse
Yea, if someone were to develop an app for that. I do not see why not.
Sent from my PC36100 using XDA App
Hmm...
If a program such as Smart bench (which takes advantage of dual cores) is stressing both cores to 1.2ghz then regardless of if both cores are active or not the bench will be accurate.
I would rather NOT have asyncronus cores as there would be lag during frequency changes...
Ex:
2 cores running at 500mhz vs 1 core @ 1ghz and other not active.
The 2 cores will produce less heat and use less energy...
Maedhros said:
Hmm...
If a program such as Smart bench (which takes advantage of dual cores) is stressing both cores to 1.2ghz then regardless of if both cores are active or not the bench will be accurate.
I would rather NOT have asyncronus cores as there would be lag during frequency changes...
Ex:
2 cores running at 500mhz vs 1 core @ 1ghz and other not active.
The 2 cores will produce less heat and use less energy...
Click to expand...
Click to collapse
There dual, it would be better for them to run asynchronous. Not only that, but it is a phone so there will be no lag between frequency changing. 2 Cores running at 500mhz will perform better than 1 core at 1ghz.
Sent from my PC36100 using XDA App
tyarbro13 said:
I had the G2x for like 3 days and never got to root. Poor service where I live. But could the cores be set to a specific frequency independently when rooted like computers?
Click to expand...
Click to collapse
This is something that the hardware needs to be capable of. Software can only do so much. As far as I've seen Tegra isn't capable of it.
I read the anandtech article and I came with conclusion that everyday task you might not see the difference between the two and while tegra2 might bench higher. The main thing people dont talk about is the GPU. Adreno 220 is a powerhouse GPU, it will probably stand strong when tegra 3 comes out.
DDiaz007 said:
There dual, it would be better for them to run asynchronous. Not only that, but it is a phone so there will be no lag between frequency changing. 2 Cores running at 500mhz will perform better than 1 core at 1ghz.
Sent from my PC36100 using XDA App
Click to expand...
Click to collapse
Huh... what are u saying? Sorry dont understand... On one hand you say asynchronous is better and on the other ur saying 2 cores @ 500 will work better?
nkd said:
I read the anandtech article and I came with conclusion that everyday task you might not see the difference between the two and while tegra2 might bench higher. The main thing people dont talk about is the GPU. Adreno 220 is a powerhouse GPU, it will probably stand strong when tegra 3 comes out.
Click to expand...
Click to collapse
What?!?
Andreno 220 is a horrible GPU. AT BEST it is equal to the GPU in the Original SGS.
The reason benches are so different is because Qualcomm has made NO improvements in the CPU. Desire HD CPU is the same as Sensations. While... SGS2 + Tegra have IMPROVED CPUs.
Arm 7 vs arm 9?
Maedhros said:
Huh... what are u saying? Sorry dont understand... On one hand you say asynchronous is better and on the other ur saying 2 cores @ 500 will work better?
What?!?
Andreno 220 is a horrible GPU. AT BEST it is equal to the GPU in the Original SGS.
The reason benches are so different is because Qualcomm has made NO improvements in the CPU. Desire HD CPU is the same as Sensations. While... SGS2 + Tegra have IMPROVED CPUs.
Arm 7 vs arm 9?
Click to expand...
Click to collapse
Dude go back to sleep. You have no clue what you are talking about.
Sent from my PC36100 using XDA Premium App
I've noticed that the evo 3d has been scoring lower than the sensation, which is spec'd performance-wise. Exactly the same except for the evo having more ram. So I don't really understand why it would eb scoeing lower
Also if you're here to try and dispute the credibility of benchmarks leave now because that's not the point of this topic.
Sent from my G2X
Well, the Evo 3D does have the ability to do 3D, so I imagine it will take up some resources, but I have a feeling that the benchmark scores will only get better as HTC and Sprint release updates and fixes for it.
Probably the bloatware
Benchmarks are boo boo! For a benchmark to read correctly the cores need to be ramped up to max for the test. The app does not draw full ramp from the dual cores. Plus they are asynchronous, once we root and have kernel source for added tweeks we will blow tegra away (even with tegra tweeked)!
For the most part synthetic benchmarks are not really useful. How much are they off anyways? I'll bet you'll never notice the difference.
Swyped from my Atari 2600
because you touch yourself at night.
cordell12 said:
Benchmarks are boo boo! For a benchmark to read correctly the cores need to be ramped up to max for the test. The app does not draw full ramp from the dual cores. Plus they are asynchronous, once we root and have kernel source for added tweeks we will blow tegra away (even with tegra tweeked)!
Click to expand...
Click to collapse
pretty much what I came into say. the Nexus S scores don't blow you away before you root either,but once Rooted, it is capable of truly amazing power.
pretty much every review says the Evo 3d feels much faster and much more fluid than the sensation.
hondarider525 said:
because you touch yourself at night.
Click to expand...
Click to collapse
LMAO!
10 char
the processor is an ASYNC and the cores are able to run at different speeds for different task. The programs testing are better suited to your normal SYNC processor which are both always running at full all the time.
The need to write code to take advantage of the ASYNC and its methods to reach max must be included in the programming before they will ever be able to measure the full potential of the ASYNC.
you could say in those test I could garuntee you one processor is running max one is not. if at all. But if it is. its just a little as the program has not told it to run both processors at max if its a ASYNC,
ADD the qHD and the program would need to account for that.
imagine if the screen was amoled or just 800 x 480. this thing would be brutal beast.
but at the end of the day I love HTC phones.
HTC Sense is known to produce low benchmark scores. Once AOSP gets on this baby, it will fly through the irrelevant benchmarks like nothing.
Not only that but benchmarks are known to produce pointless infighting and petty bickering over measures that are not only highly suspect but also not related to actual use...
...or so the old wives tale goes...
Sent from my PC36100
xdmds said:
I've noticed that the evo 3d has been scoring lower than the sensation, which is spec'd performance-wise. Exactly the same except for the evo having more ram. So I don't really understand why it would eb scoeing lower
Also if you're here to try and dispute the credibility of benchmarks leave now because that's not the point of this topic.
Sent from my G2X
Click to expand...
Click to collapse
Actually, check out Anandtech's bench of the Evo 3D and Sensation from a couple of weeks ago, and the check out the same bench of those 2 devices when they tested the Droid 3 a couple of days ago.
Comparing the scores, the 3vo scored the same both times. First time it was higher than the Sensation, and second time lower. So somewhere in between, the Sensation got a software update that made it score higher on those benchmarks. I'm guessing we'll see the same kind of improvement with the 3vo in time.
leaving now. Just beating a dead horse here, this has been debated a million times.
your holding it wrong?
NewZJ said:
your holding it wrong?
Click to expand...
Click to collapse
Yeah he should call up for his free rubber band.
freeza said:
HTC Sense is known to produce low benchmark scores. Once AOSP gets on this baby, it will fly through the irrelevant benchmarks like nothing.
Click to expand...
Click to collapse
While I did run asop on my evo no way will an asop rom touch my evo 3d. Sense 3.0 is great and I doubt asop will supoort 3d.
Sent from my GT-P7510 using XDA Premium App
I hate people who point out benchmarks on a phone... :|
LOL if htc's scrap snapdragon duel core had good benchmarks I bet all of you would be posting about how elite your phone is and how good it does in benchmarks but since it sucks you say benchmarks don't matter. Don't fool yourself benchmarks do matter. Yes quadrant can be tricked by unlocked phones with edits but benchmarks ran on tegra 2 & crap snapdragon using smartbench 2011 (does use both cores) gives realistic performance.
evo 3d
2089 cpu
1648 gpu (lol slower then galaxy s 1)
tegra 2 (stock atrix 2.3.4 with crap motoblur)
2737 cpu
2661 gpu
tegra 2 overclocked
3989 cpu
2900 gpu
shep211 said:
LOL if htc's scrap snapdragon duel core had good benchmarks I bet all of you would be posting about how elite your phone is and how good it does in benchmarks but since it sucks you say benchmarks don't matter. Don't fool yourself benchmarks do matter. Yes quadrant can be tricked by unlocked phones with edits but benchmarks ran on tegra 2 & crap snapdragon using smartbench 2011 (does use both cores) gives realistic performance.
evo 3d
2089 cpu
1648 gpu (lol slower then galaxy s 1)
tegra 2 (stock atrix 2.3.4 with crap motoblur)
2737 cpu
2661 gpu
tegra 2 overclocked
3989 cpu
2900 gpu
Click to expand...
Click to collapse
Bro its because tegra manages different. Tegra uses both cores to do one single task. While the EVO 3D chip set is asynchronous. This means when you run a benchmark only one core is being processed during that application. The other core is running other processes to keep your EVO lag free and running smoothly. Benchmark is only a number anyway.
Remember this tho forever. benchmarks are like a girl in a bikini, they show a lot but not quite everything.
Sent from a dual core beast 3VO. Do this on your iFail 4
How are other android touchpads doing? W / the 1.7ghz overclock I'm hitting a Max of 98ish mflops and 3300+ on quadrant! Which makes it my fastest Droid to date. Lets see if anybody can post a better quadrant screenshot?
richard head said:
How are other android touchpads doing? W / the 1.7ghz overclock I'm hitting a Max of 98ish mflops and 3300+ on quadrant! Which makes it my fastest Droid to date. Lets see if anybody can post a better quadrant screenshot?
Click to expand...
Click to collapse
i overclock my touchpad to 1.782 ghz. do you know how to overclock gpu
adreno 220 is in 266 mhz original but i need to overclock it to 300 mhz because its a very good frequency or 320 mhz
Sent from my SGH-T989 using xda premium
Gotcha
Think I beat you
Fastest I've gotten. Have not really tried with the latest versions.
general feeling is that as far as benchmarks go, quadrant is crap
should try antutu instead.
ive a thread in this section somewhere where some people have posted results
This discussion seems a bit flawed, in that you're gauging performance based upon benchmark software, etc. We've talked about this a lot over the past year, and most of these tests are very dependent upon specific hardware setups, usually in much older devices with older chipsets. My Nexus S w/ a single-core 1ghz UNDERCLOCKED to 880mhz scores a 3500 all the time in Quadrant. No way in hell it's better than the touchpad. It's not even a fair fight, if you compare raw specs.
Do you judge the performance of your computer based on how fast it can perform iterations of Prime 95? No, you judge it based on user experience.
Is your user experience with CM7 very fast? I know mine is. Based on that, and the experience I get with gfx-intense apps like GTA3, etc, I say the performance is very good.
PS. The fact that Quadrant to this day still has the Nexus One as its top reference device says something about it being old and outdated. The Nexus One came out in Jan 2010, 2 years ago.
So i just ran a test for the antutu benchmark with just the phone and nothing else and this is what i got Ill be running quadrant bench test also and that will be in my next reply Cant wait for root and unlock!
EDIT: Heres quadrant test stock with no 4g or extra stuff
wow how is the Antutu score so high???
hairdewx said:
wow how is the Antutu score so high???
Click to expand...
Click to collapse
quadcore and that 2gb of ram haha imagine if i put my 64gb sd card in there haha
theDK10 said:
quadcore and that 2gb of ram haha imagine if i put my 64gb sd card in there haha
Click to expand...
Click to collapse
Sd cards don't help performance.
I got an Antutu score of 18424 right after activation
For reference, my Galaxy Note 10.1 tablet only had scores in the 12,000 range... WOW
I just received my Galaxy Note II today and was a bit shocked that it scored a lower score in AnTuTu's benchmark than my HTC Droid DNA. Given that it has a faster CPU and less pixels to render, you would think it would be faster.
I scored 19164 with my HTC Droid DNA, which is much higher than the 18084 I got with the Galaxy Note II.
makoto said:
I just received my Galaxy Note II today and was a bit shocked that it scored a lower score in AnTuTu's benchmark than my HTC Droid DNA. Given that it has a faster CPU and less pixels to render, you would think it would be faster.
I scored 19164 with my HTC Droid DNA, which is much higher than the 18084 I got with the Galaxy Note II.
Click to expand...
Click to collapse
Processor is newere on the droid dna, I will always say we don't use benchmarks, so stop being disappointed in your score it by no means represents everyday use..They are both future proof for a few years..
I have to laugh at people who care about benchmark scores when they have a device with a quad core cpu in it running Android.
Haha I don't care really about benchmarks I was just impressed that's all. DNA is nice but I need sd card and something with battery life. Only got about 3/4 through a day on a full charge.
Sent from my SCH-I535 using xda app-developers app
My s3 scores 6200 on quadrant, 11000 on antutu...tells you benchmarks are worthless.
droidstyle said:
My s3 scores 6200 on quadrant, 11000 on antutu...tells you benchmarks are worthless.
Click to expand...
Click to collapse
Im guessing rooted and unlocked? lol i got mine up 12000 rooted with a different kernal. As long as the phone runs fast and smooth i could care less lol
Benchmarks are far from worthless. They are an objective indicator of how certain components perform under the exact same stress test.
Now what you can say is worthless is people who look at a final score that is rather irrational instead of looking at individual component scores.
For example, CPU scores in these benchmarks is a clear indicator of which phone has a faster processor. While the very same phone that had a slower processor may have a significantly better GPU. What this means to the end user is that expect games to perform better on the slower CPU phone, but also expect things like web browsing to perform worse on the same device.
It's all objective comparisons, certainly not something to claim as "worthless" but at the same time if you do not look at it the right way and just throw a generic total score number around, then you won't be fairly comparing any two devices properly.
slide83 said:
Sd cards don't help performance.
Click to expand...
Click to collapse
Wrong. The higher class sdcard, the faster the read/write speeds = better performance.
Sent from my SCH-I605 using Tapatalk 2
ks3rv3rg said:
Wrong. The higher class sdcard, the faster the read/write speeds = better performance.
Sent from my SCH-I605 using Tapatalk 2
Click to expand...
Click to collapse
thank you :victory: My 64gb sd card increased the benchmark also. :good: And ya i usually look at certain things when running benchmarks but thats usually when im rooted and unlocked is when i really look at them closely.
After running Quadrant, my phone seems to warm up and each subsequent score is somewhat lower. I started at 6500 and it bottoms out around 6000. Anyone else have this heat problem?
Make sure everything is closed out when u run a test. It's putting everything to work in the phone so it's stressed out which could cause a lot of heat
Sent from my SCH-I535 using xda app-developers app
Is it possible to get our 820 soc overclocked with a custom kernel so it can compare to 821 chip?
No stable custom kernel available so far
And you can compare soc on web
Leo7D said:
No stable custom kernel available so far
Click to expand...
Click to collapse
Link?
georgesalo said:
Link?
Click to expand...
Click to collapse
http://wccftech.com/snapdragon-821-vs-snapdragon-820/
http://www.techgrapple.com/apple-a10-sd-821-820/
http://www.trustedreviews.com/opinions/snapdragon-820-vs-snapdragon-810
Leo7D said:
No stable custom kernel available so far
And you can compare soc on web
Click to expand...
Click to collapse
I think he didn't want to compare but to overclock to make it faster.
Regards Filozof71
Sent from my Le X820 using Tapatalk
Difference between 820 and 821 is pretty negligible. I very much doubt that you could find any meaningful difference between the two in real-life performance, given that few if any apps currently push these CPUs anywhere near their full capability. All you'd probably achieve by slightly overclocking is very marginal gains in synthetic benchmark scores at the cost of battery life and possibly stability. In fact, thermal throttling would probably make performance worse. IMHO it would be a pointless exercise.
Not seeing much advantage on SD821.
Is there anything to gain on SD821 the higher clocking in CPU and GPU doesnt seem to translate into actually advantage and seems more like an gimmick to sell SD820 in new clothing, but fair enough it is an solid chipset..
Have my X822 (the dark grey version) for an couple of weeks now and been filling it up, but it still delivers insanse scores from an 222US handset-
from today in Basemark X' a +43k score. (at household temperaure ' - overall not to shabby from an little over 200US-handset)
anyone got an up to date ranking on Basemark X. (nb in high sett. L2M getting an little under 37k)
but ewen the Pixel XL that should be an SD821 is clocked in SD820s values, and comming in at ofc. 35.598k (hence X822 : 43.001)
http://powerboard.basemark.com/filter?benchmark=10&page=1&categories=0&os=0,2