Before the update, I ran three different benchmarks on 4.2.2 (Quadrant, Antutu, and 3DMark). After I upgraded I ran the benchmarks again. Hope this will be the answer to people who are wondering. (See attached image for details).
When I ran these benchmarks, no programs was running in the background, besides my Avast (Anti-Virus).
yelnam2manley said:
Before the update, I ran three different benchmarks on 4.2.2 (Quadrant, Antutu, and 3DMark). After I upgraded I ran the benchmarks again. Hope this will be the answer to people who are wondering. (See attached image for details).
When I ran these benchmarks, no programs was running in the background, besides my Avast (Anti-Virus).
Click to expand...
Click to collapse
How many times did you run them? Things like quadrant always gives me different values each run so.....
I ran them about three times and I got about the same.
Sent from my Galaxy Nexus using xda app-developers app
Everything but the GPU falls within margin of error between runs, so at least we got a nice little bump in graphics performance.
Antutu is disqualified. I am running the factory image 4.3 and the graphics test with the goblin only renders the grass. So my 4733 GPU score is meaningless. Until they update it we won't have a clear picture. Keep in mind also that quadrant hasn't been updated in over a year.
Re:
brees75 said:
Antutu is disqualified. I am running the factory image 4.3 and the graphics test with the goblin only renders the grass. So my 4733 GPU score is meaningless. Until they update it we won't have a clear picture. Keep in mind also that quadrant hasn't been updated in over a year.
Click to expand...
Click to collapse
What's a good benchmarking software should I use then?
3DMark Extreme settings and Epic Citadel on highest settings are good for graphics scoring.
My Antutu Scores dropped down on both n7 and n4 after the 4.3 update.Is this typical after the update?
Could someone run the nbench benchmark and post the results, here http://forum.xda-developers.com/showthread.php?t=1270596 preferably.
Nbench market link: http://play.google.com/store/apps/details?id=com.drolez.nbench
Thanks.
Sent from my Nexus 7 using Tapatalk 4 Beta
==========================ORIGINAL BYTEMARK RESULTS==========================
INTEGER INDEX : 41.430
FLOATING-POINT INDEX: 28.998
Baseline (MSDOS*) : Pentium* 90, 256 KB L2-cache, Watcom* compiler 10.0
==============================LINUX DATA BELOW===============================
CPU : Dual ARMv7 Processor rev 4 (v7l) 1700MHz
L2 Cache : 0
OS : Linux version 3.4.39-flamingmonkey-craigacgomez-g7862726-dirty ([email protected]) (gcc version 4.6.x-google 20120106 (prerelease) (GCC) ) #2 SMP PREEMPT Fri Jul 26 09:41:30 PDT 2013
C compiler : gcc 4.6.0 (-march=armv7-a)
MEMORY INDEX : 7.890
INTEGER INDEX : 12.662
FLOATING-POINT INDEX: 16.083
Baseline (LINUX) : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38
On flaming monkey rom
No clue what the results mean. Anyone care to explain?
Sent from my Nexus 10 using xda app-developers app
johno86 said:
No clue what the results mean. Anyone care to explain?
Click to expand...
Click to collapse
Thanks for posting!
See http://en.wikipedia.org/wiki/NBench for a description of the benchmark used.
The 3 overall numbers for your Nexus 10 running on the "Flaming Monkey ROM" are (7.8,12.6,16) for memory, integer and floating-point indexes. Would be nice to see what the numbers are on the stock ROM.
That would indicate each core/processor in your Nexus 10 is 7.8,12.6,16 times faster than the baseline AMD K6/233 (pretty old) processor for memory, integer and floating-point operations.
My Nexus 7 is (5.1,7.7,8.1) so your Nexus 10 is much faster in all 3 areas. And, it appears faster than a Samsung Galaxy S4 I9500 (12.5,11.7,19) in Integer operations only.
Intel Core i7 (Desktop PC processor) have numbers as high as (49,40,133) for each of their 8 cores (just to show you their awesome computing power).
See http://www.tux.org/~mayer/linux/results2.html for more results.
Related
just my observation: Quadrant run for touchpad only gives score of around 2400... my nook color with 1.3ghz single core gives score of over 2600 all the time!!! i looked into the device info, it seems like it only using 1 core!!! does cm7 only recognizing one core??? what r ur guys thought??? is there a fix for it or any kernels that utilize both cores of touchpad!!!
The Quadrant results on the TP are skewed because the GPU code has not yet been implemented (or optimized) which primarily affects the FPS section (looks like is is only doing about 4 frames per second) where all the other graphics demos (especially the planet one) do 20-60 frames per second which is a 300%-600% improvement over the Nook Color running 1.2GHz.
I would be interested in other benchmarks that are not dependent on the GPU code.
try using Antutu - free from market
it separates the scores according to each test
(also shows total)
i got around 5000 - OC 1.7 ghz
Maybe it is because we are running an un-optimized alpha build...Don't worry about synthetic benchmarks anyway.
Both cores are already being used, what is your processor clocked too?
I'm completely aware benchmarks don't really mean much, but for curiosities sake, out of 3 runs, I averaged 3228 in quadrant. I am overclocked to 1782mhz ondemand.
I suggest you run SunSpider also.
XXXUPDATEXXX
Anandtech have now published the perfromance preview of the Nexus 10, lets the comparison begin!
http://www.anandtech.com/show/6425/google-nexus-4-and-nexus-10-review
Well, the first full result has appeared on GLBenchmark for the iPad4, so I have created a comparison with the Samsung Arndale board, which uses exactly the same SoC as the Nexus 10, so will be very close in performance to Google's newest tablet. GLBenchmark, as its name suggests test Open GL graphics perrformance, which is important criteria for gaming.
Which device wins, click the link to find out.
http://www.glbenchmark.com/compare....ly=1&D1=Apple iPad 4&D2=Samsung Arndale Board
If you're really impatient, the iPad 4 maintains it lead in tablet graphics, the Nexus 10 may performance slightly better in final spec, but the underlying low-level performance will not change much.
I've also made a comparison between the iPad 3 & 4.
Interestingly the in-game tests GLBenchmark 2.5 Egypt HD C24Z16 - Offscreen (1080p) :, which is run independent of native screen resolution show the following
iPad 4: 48.6 FPS
iPad 3: 25.9 FPS
5250 : 33.7 FPS
So the iPad is twice as fast as its older brother, the Exynos will probably score nearer 40 FPS in final spec, with new drivers and running 4.2, the board runs ICS, however Jelly Bean did not really boost GL performance over ICS. What is interesting is that iPad 4, whose GPU is supposed to clocked at 500 MHz vs 250 MHz in the iPad 3 does not perform twice as fast in low-level test.
Fill Rate, triangle throughtput, vertex output etc is not double the power of the iPad 3, so although the faster A6 cpu helps, I reckon a lot of the improvement in the Egypt HD test is caused by improved drivers for the SGX 543 MP4 in the Pad 4. The Galaxy S2 received a big jump in GL performance when it got updated Mali drivers, so I imagine we should see good improvements for the T604, which is still a new product and not as mature as the SGX 543.
http://www.glbenchmark.com/compare....tified_only=1&D1=Apple iPad 4&D2=Apple iPad 3
I'd imagine the new new iPad would take the lead in benchmarks for now as it'll take Sammy and Google some time to optimize the beast, in the end however actual app and user interface performance is what matters, and reports are overwhelmingly positive on the Nexus 10.
So Mali 604T didn't match 5 times better than Mali 400, or maybe Samsung underclocked it.
Still very good but not the best.
________________
Edit: I forgot that Exynos 4210 with Mali400MP4 GPU had very bad GLbenchmark initially (even worse than PowerVR SGX540), but after updating firmware it's way better than other SoCs on Android handsets.
hung2900 said:
So Mali 604T didn't match 5 times better than Mali 400, or maybe Samsung underclocked it.
Still very good but not the best.
Click to expand...
Click to collapse
Not sure about this, but don't benchmark tools need to be upgraded for new architectures to? A15 is quite a big step, SW updates may be necessary for proper bench.
Damn..now I have to get an iPad.
I believe we have to take the Arndale board numbers with pinch of salt. It's a dev board, and I doubt it has optimized drivers for the SoC like it's expected for N10. Samsung has this habit of optimizing the drivers with further updates.
SGS2 makes for a good case study. When it was launched in MWC2011, it's numbers were really pathetic. It was even worse than Tegra2.
Anand ran benchmark on the pre-release version of SGS2 on MWC2011, check this:
http://www.anandtech.com/show/4177/samsungs-galaxy-s-ii-preliminary-performance-mali400-benchmarked
It was showing less than Tegra2 numbers! It was that bad initially.
Then look when Anand finally reviewed the device after few months:
http://www.anandtech.com/show/4686/samsung-galaxy-s-2-international-review-the-best-redefined/17
Egypt (native resolution) numbers went up by 3.6x and Pro also got 20% higher. Now they could have been higher if not limited by vsync. GLbenchmark moved from 2.0 to 2.1 during that phase, but I am sure this would not make such a big difference in numbers.
If you again check the numbers now for SGS2, it's again another 50% improvement in performance from the time Anand did his review.
Check this SGS2 numbers now:
http://www.anandtech.com/show/5811/samsung-galaxy-s-iii-preview
http://www.anandtech.com/show/6022/samsung-galaxy-s-iii-review-att-and-tmobile-usa-variants/4
This is just to show that how driver optimization can have a big affect on the performance. My point is that we have to wait for proper testing on final release of N10 device.
Also, check the fill rate properly in the Arndale board test. It's much less than what is expected. ARM says that Mali-T604 clocked at 500MHz should get a fill rate of 2 GPixels/s. It's actually showing just about 60% of what it should be delivering.
http://blogs.arm.com/multimedia/353-of-philosophy-and-when-is-a-pixel-not-a-pixel/
Samsung has clocked the GPU @ 533MHz. So, it shouldn't be getting so less.
According to Samsung, it more like 2.1 GPixels/s: http://semiaccurate.com/assets/uploads/2012/03/Samsung_Exynos_5_Mali.jpg
Fill rate is a low-level test, and there shouldn't be such a big difference from the quoted value. Let's wait and see how the final device shapes up.
hung2900 said:
So Mali 604T didn't match 5 times better than Mali 400, or maybe Samsung underclocked it.
Still very good but not the best.
________________
Edit: I forgot that Exynos 4210 with Mali400MP4 GPU had very bad GLbenchmark initially (even worse than PowerVR SGX540), but after updating firmware it's way better than other SoCs on Android handsets.
Click to expand...
Click to collapse
In areas where the Mali 400 lacked performance, like fragment and vertex lit triangle output T604 is comfortably 5 x the performance, whereas in these low-level tests iPad is not a concrete 2x the power of iPad 3, but achieves twice the FPS in Egypt HD than its older brother. I suspect drivers are a big factor here, and Exynos 5250 will get better as they drivers mature.
hot_spare said:
I believe we have to take the Arndale board numbers with pinch of salt. It's a dev board, and I doubt it has optimized drivers for the SoC like it's expected for N10. Samsung has this habit of optimizing the drivers with further updates.
SGS2 makes for a good case study. When it was launched in MWC2011, it's numbers were really pathetic. It was even worse than Tegra2.
Anand ran benchmark on the pre-release version of SGS2 on MWC2011, check this:
http://www.anandtech.com/show/4177/samsungs-galaxy-s-ii-preliminary-performance-mali400-benchmarked
It was showing less than Tegra2 numbers! It was that bad initially.
Then look when Anand finally reviewed the device after few months:
http://www.anandtech.com/show/4686/samsung-galaxy-s-2-international-review-the-best-redefined/17
Egypt (native resolution) numbers went up by 3.6x and Pro also got 20% higher. Now they could have been higher if not limited by vsync. GLbenchmark moved from 2.0 to 2.1 during that phase, but I am sure this would not make such a big difference in numbers.
If you again check the numbers now for SGS2, it's again another 50% improvement in performance from the time Anand did his review.
Check this SGS2 numbers now:
http://www.anandtech.com/show/5811/samsung-galaxy-s-iii-preview
http://www.anandtech.com/show/6022/samsung-galaxy-s-iii-review-att-and-tmobile-usa-variants/4
This is just to show that how driver optimization can have a big affect on the performance. My point is that we have to wait for proper testing on final release of N10 device.
Also, check the fill rate properly in the Arndale board test. It's much less than what is expected. ARM says that Mali-T604 clocked at 500MHz should get a fill rate of 2 GPixels/s. It's actually showing just about 60% of what it should be delivering.
http://blogs.arm.com/multimedia/353-of-philosophy-and-when-is-a-pixel-not-a-pixel/
Samsung has clocked the GPU @ 533MHz. So, it shouldn't be getting so less.
According to Samsung, it more like 2.1 GPixels/s: http://semiaccurate.com/assets/uploads/2012/03/Samsung_Exynos_5_Mali.jpg
Fill rate is a low-level test, and there shouldn't be such a big difference from the quoted value. Let's wait and see how the final device shapes up.
Click to expand...
Click to collapse
I agree with most of what you have said. On the GPixel figure this is like ATI GPU teraflops figures always being much higher than Nvidia, in theory with code written to hit the device perfectly you might see that those high figures, but in reality the Nvidia cards with lower on paper numbers equaled or beat ATI in actual game FPS. It all depends on whether the underlying architecture is as efficient in real-world tests, vs maximum technical numbers that can't be replicated in actual game environments.
I think the current resolution of the iPad / Nexus 10 is actually crazy, and will would see prettier games with lower resolutions, the amount of resources needed to drive those high MP displays, means lots of compromises will be made in terms of effects / polygon complexity etc to ensure decent FPS, especially when you think that to drive Battlefield 3 at 2560 x 1600 with AA and high textures, requires a PC that burn 400+ watts of power, not a 10 watt SoC.
Overall when we consider that Nexus 10 has twice the RAM for game developers to use and faster CPU cores, games should look equally as nice as both, the biggest effect will be the level of support game developers provide for each device, the iPad will probably be stronger i that regard. Nvidia was able to coax prettier games out of Tegra 3 through developer support, hopefully Google won't forget the importance of this.
What's the point of speculation? Just wait for the device to be released and run all the test you want to get confirmation on performance. Doesn't hurt to wait
BoneXDA said:
Not sure about this, but don't benchmark tools need to be upgraded for new architectures to? A15 is quite a big step, SW updates may be necessary for proper bench.
Click to expand...
Click to collapse
Both A9 & A15 use the same instruction set architecture (ISA) so no they won't. Benchmarks may need to be modified, if the new SoC are too powerful and max out the old benches, but for GL Benchmark, that has not happened yet and there are already new updates in the pipeline.
I can't wait to see this Exynos 5250 in a 2.0ghz quad-core variant in the semi near future... Ohhhh the possibilities. Samsung has one hell of a piece of silicon on their hand.
Chrome
http://www.anandtech.com/show/6425/google-nexus-4-and-nexus-10-review
Google if you want to use Chrome as the stock browser, then develop to fast and smooth and not an insult, stock AOSP browser would be so much faster.
Turbotab said:
http://www.anandtech.com/show/6425/google-nexus-4-and-nexus-10-review
Google if you want to use Chrome as the stock browser, then develop to fast and smooth and not an insult, stock AOSP browser would be so much faster.
Click to expand...
Click to collapse
True.. Chrome on mobile is still not upto desktop level yet. I believe it's v18 or something, right? The stock browser would have much better result in SunSpider/Browsermark. The N4 numbers looks even worse. Somewhere the optimizations isn't working.
The GLbenchmark tests are weird. Optimus G posts much better result than N4 when both are same hardware. It infact scores lower than Adreno 225 in some cases. This is totally whacked.
For N10, I am still wondering about fill rate. Need to check what guys say about this.
Is it running some debugging code in the devices at this time?
Turbotab said:
Both A9 & A15 use the same instruction set architecture (ISA) so no they won't. Benchmarks may need to be modified, if the new SoC are too powerful and max out the old benches, but for GL Benchmark, that has not happened yet and there are already new updates in the pipeline.
Click to expand...
Click to collapse
Actually not. A8 and A9 are the same ISA (Armv7), while A5 A7 and A15 are in another group (Armv7a)
Once we get rid of the underclock no tablet will be able to match. I'm sure the Mali t604 at 750 MHz would destroy everything.
hung2900 said:
Actually not. A8 and A9 are the same ISA (Armv7), while A5 A7 and A15 are in another group (Armv7a)
Click to expand...
Click to collapse
I have to disagree, this is from ARM's info site.
The ARM Cortex-A15 MPCore processor has an out-of-order superscalar pipeline with a tightly-coupled low-latency level-2 cache that can be up to 4MB in size. The Cortex-A15 processor implements the ARMv7-A architecture.
The ARM Cortex-A9 processor is a very high-performance, low-power, ARM macrocell with an L1 cache subsystem that provides full virtual memory capabilities. The Cortex-A9 processor implements the ARMv7-A architecture and runs 32-bit ARM instructions, 16-bit and 32-bit Thumb instructions, and 8-bit Java bytecodes in Jazelle state.
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.set.cortexa/index.html
Keion said:
Once we get rid of the underclock no tablet will be able to match. I'm sure the Mali t604 at 750 MHz would destroy everything.
Click to expand...
Click to collapse
Except the iPad 4, which has a GPU that is currently 57% faster than the T604.
Sent from my iPad Mini using Tapatalk
Do remember that Awesome resolution does tax the GPU a lot. Heck most lower end desktop GPUs would struggle
Harry GT-S5830 said:
Do remember that Awesome resolution does tax the GPU a lot. Heck most lower end desktop GPUs would struggle
Click to expand...
Click to collapse
Indeed it does,but not in offscreen testing, where Anand made his proclamation.
Sent from my iPad Mini using Tapatalk
Hemlocke said:
Except the iPad 4, which has a GPU that is currently 57% faster than the T604.
Sent from my iPad Mini using Tapatalk
Click to expand...
Click to collapse
Nah, I think we can beat that too.
Drivers + OC.
Planning to return my N10 cause the stuttering on it is driving me insane and im really interested in the Tablet Z currently.
1920x1080 on an 1.5GHz Qualcomm APQ8064 with adreno 320GPU VS 2560x1600 nexus 10 with an exynos 5 and a mali t604 GPU clocked at 1.7 GHZ.
Fasty12 said:
Planning to return my N10 cause the stuttering on it is driving me insane and im really interested in the Tablet Z currently.
1920x1080 on an 1.5GHz Qualcomm APQ8064 with adreno 320GPU VS 2560x1600 nexus 10 with an exynos 5 and a mali t604 GPU clocked at 1.7 GHZ.
Click to expand...
Click to collapse
The S4 is halfway between the Cortex A9 cores and the new Cortex A15 core that we have. So it is decent enough of a CPU. I am not sure how good of a GPU that is. None of my devices the past couple years have had Adreno GPU's At least it wont have to work as hard with the lower resolution
Fasty12 said:
Planning to return my N10 cause the stuttering on it is driving me insane and im really interested in the Tablet Z currently.
1920x1080 on an 1.5GHz Qualcomm APQ8064 with adreno 320GPU VS 2560x1600 nexus 10 with an exynos 5 and a mali t604 GPU clocked at 1.7 GHZ.
Click to expand...
Click to collapse
What stuttering are you talking about?
Draw your own conclusions.
S4 Pro - http://www.anandtech.com/show/6112/...agon-s4-apq8064adreno-320-performance-preview
Exynos 5 - http://www.anandtech.com/show/6148/samsung-announces-a15malit604-based-exynos-5-dual
From everything I've seen and experienced the exynos 5 is the better of the two. The a15 is a more powerful core than the krait core, that with the higher clock speeds and the better GPU makes for a better chip. Personally I have never had my n10 lag at all. Maybe you just got a dud?
Sent from my Nexus 10 using Tapatalk HD
enik_fox said:
From everything I've seen and experienced the exynos 5 is the better of the two. The a15 is a more powerful core than the krait core, that with the higher clock speeds and the better GPU makes for a better chip. Personally I have never had my n10 lag at all. Maybe you just got a dud?
Sent from my Nexus 10 using Tapatalk HD
Click to expand...
Click to collapse
But the Exynos 5 has to run that massive screen res. Also, the reason I think that Qualcomm modified the core was because of the power consumption. Stock A-15 core consumes quite a lot of power.
Sent from my LG-P990 using xda app-developers app
Fasty12 said:
Planning to return my N10 cause the stuttering on it is driving me insane and im really interested in the Tablet Z currently.
1920x1080 on an 1.5GHz Qualcomm APQ8064 with adreno 320GPU VS 2560x1600 nexus 10 with an exynos 5 and a mali t604 GPU clocked at 1.7 GHZ.
Click to expand...
Click to collapse
Every now and then I read ppl complaining about lags and stutters... I have not experienced one since I have the device; can you please explain what you are doing when this happens?
avdaga said:
Every now and then I read ppl complaining about lags and stutters... I have not experienced one since I have the device; can you please explain what you are doing when this happens?
Click to expand...
Click to collapse
Try opening and closing google maps after the map has been loaded there is a NOTICEABLE frame rate drop compare to other apps.
kaspar737 said:
But the Exynos 5 has to run that massive screen res. Also, the reason I think that Qualcomm modified the core was because of the power consumption. Stock A-15 core consumes quite a lot of power.
Sent from my LG-P990 using xda app-developers app
Click to expand...
Click to collapse
The Snapdragon S4 does not use an A15 core or any derivative of an A15. Qualcomm has ALWAYS completely designed their cores custom and has almost nothing to do with the current major core from ARM's reference design. Additionally, the S4 was designed and released before the A15 MP-Core was even finished with its design phase.
The Krait core uses a similar (but not the same) triple wide decode stage like the A15 core, but it uses a completely different 11 stage execution pipeline compared to the A15's 15 stage pipeline. The higher stages of the pipeline allow the A15 design to break things down smaller and achieve higher frequency, but if there were to be a failure in computing then the A15 must wait a longer time before it can start over where the Krait core doesnt have to wait as long, but also isnt as efficient in " normal" circumstances. Honestly the integer performance between the two cores is pretty close, but I think I remember seeing that the A15 has a lot stronger floating point performance. So I guess it really depends on your workload.
FYI, the Exynos 5, Tegra 4, and TI OMAP 5 processors are all based on the A15 core design. Qualcomm is the only major player who does not base their processors on the ARM design
Fasty12 said:
Try opening and closing google maps after the map has been loaded there is a NOTICEABLE frame rate drop compare to other apps.
Click to expand...
Click to collapse
Do you mean a drop in framerate during the animation when closing Maps? I notice a minor framerate drop which lasts as long as the animation does, but if that is it, I'm kinda wondering why you bought an android device in first place... I have not noticed this before and I cannot imagine anyone would using the device for its intended purposes. If you take any android device, you will find a fps drop at some point... Maybe return it and take an iPad? iPads do not have the issue, on the other hand there's a lot that iPads do not have ^^
kaspar737 said:
But the Exynos 5 has to run that massive screen res. Also, the reason I think that Qualcomm modified the core was because of the power consumption. Stock A-15 core consumes quite a lot of power.
Sent from my LG-P990 using xda app-developers app
Click to expand...
Click to collapse
Exynos has higher memory bandwidth so the difference isn't substantial.
Sent from my Galaxy Nexus using Tapatalk 2
---------- Post added at 01:33 PM ---------- Previous post was at 01:29 PM ----------
EniGmA1987 said:
The Snapdragon S4 does not use an A15 core or any derivative of an A15. Qualcomm has ALWAYS completely designed their cores custom and has almost nothing to do with the current major core from ARM's reference design. Additionally, the S4 was designed and released before the A15 MP-Core was even finished with its design phase.
The Krait core uses a similar (but not the same) triple wide decode stage like the A15 core, but it uses a completely different 11 stage execution pipeline compared to the A15's 15 stage pipeline. The higher stages of the pipeline allow the A15 design to break things down smaller and achieve higher frequency, but if there were to be a failure in computing then the A15 must wait a longer time before it can start over where the Krait core doesnt have to wait as long, but also isnt as efficient in " normal" circumstances. Honestly the integer performance between the two cores is pretty close, but I think I remember seeing that the A15 has a lot stronger floating point performance. So I guess it really depends on your workload.
FYI, the Exynos 5, Tegra 4, and TI OMAP 5 processors are all based on the A15 core design. Qualcomm is the only major player who does not base their processors on the ARM design
Click to expand...
Click to collapse
THANK YOU!! my god I've had to explain this so many times! Qualcomm licenses ONLY the armv7 instructions and not arms designs. They design their own chips from the ground up and GPU, so please people stop saying Qualcomm is a cortex series processor because it isn't. Samsung and the rest license arms design and modify it, in Samsungs case they tend to increase the IPC slightly and give it more memory bandwidth.
Also to answer the question, exynos 5 will do better at higher resolutions and they will be very close in lower resolutions. S4 will be better in multi thread workloads more then likely and exynos will have better float performance. Exynos is better for games once the thermal throttling is fixed.
Sent from my Galaxy Nexus using Tapatalk 2
ECOTOX said:
Exynos has higher memory bandwidth so the difference isn't substantial.
Sent from my Galaxy Nexus using Tapatalk 2
---------- Post added at 01:33 PM ---------- Previous post was at 01:29 PM ----------
THANK YOU!! my god I've had to explain this so many times! Qualcomm licenses ONLY the armv7 instructions and not arms designs. They design their own chips from the ground up and GPU, so please people stop saying Qualcomm is a cortex series processor because it isn't. Samsung and the rest license arms design and modify it, in Samsungs case they tend to increase the IPC slightly and give it more memory bandwidth.
Also to answer the question, exynos 5 will do better at higher resolutions and they will be very close in lower resolutions. S4 will be better in multi thread workloads more then likely and exynos will have better float performance. Exynos is better for games once the thermal throttling is fixed.
Sent from my Galaxy Nexus using Tapatalk 2
Click to expand...
Click to collapse
The 50 percent extra memory bandwith doesn't matter so much considered that the Exynos has to move almost twice the amount of pixels.
Sent from my LG-P990 using xda app-developers app
kaspar737 said:
The 50 percent extra memory bandwith doesn't matter so much considered that the Exynos has to move almost twice the amount of pixels.
Sent from my LG-P990 using xda app-developers app
Click to expand...
Click to collapse
Memory bandwidth makes a pretty big difference when it comes too resolutions. I.E 8600gt ddr2 vs ddr3. Wider memory bus and faster memory makes a big difference in higher res performance of any GPU
Also will help with GPU compute performance for future apps utilizing the Mali t604s compute abilities
Sent from my Galaxy Nexus using Tapatalk 2
ECOTOX said:
Memory bandwidth makes a pretty big difference when it comes too resolutions. I.E 8600gt ddr2 vs ddr3. Wider memory bus and faster memory makes a big difference in higher res performance of any GPU
Also will help with GPU compute performance for future apps utilizing the Mali t604s compute abilities
Sent from my Galaxy Nexus using Tapatalk 2
Click to expand...
Click to collapse
But lets say that Exynos uses the whole 12.8 gb/s bandwith. That means that to move twice as less pixels you would need 6.4 gb/s so memory bandwidth isn't an issue.
Sent from my LG-P990 using xda app-developers app
kaspar737 said:
But lets say that Exynos uses the whole 12.8 gb/s bandwith. That means that to move twice as less pixels you would need 6.4 gb/s so memory bandwidth isn't an issue.
Sent from my LG-P990 using xda app-developers app
Click to expand...
Click to collapse
But that bandwidth is shared, unlike on dedicated GPU where it isn't. The total system bandwidth (not including buses for modem or w.e others are there) on the exynos chip being higher is gonna give it the edge in any situation considering the closeness in performance between the two. It also can't be denied that the Mali t604 has a edge in horse power over adreno 320 because even at the n10s resolution it comes within a couple fps of adreno at 1080p resolution. Not saying it's a big difference, but the exynos is the more powerful all around chip and that's just in is dual core form.
Edit: Also its a known fact that Adreno has crap fill rate compared too Mali or Power VR, Adrenos Strength is Geometry performace so it takes more of a hit the higher the resolution than Either the Mali t604 or the SGX 554MP4 which both have higher Fillrate and the SoC we have to compare both have higher bandwidth to facilitate that so we dont get bottle necked.
Sent from my Galaxy Nexus using Tapatalk 2
Finally a lot of exerts here about GPU
, I know it is not related to topic but me and my girlfriend have Galaxy Note 2 and S3. As you all know they are the last ones to use the elder Mali-400 GPU. I love playing games and I am getting my girlfriend used to them too. So I was wondering how is our Mali400 GPU holding up against the new coming 1080p Adreno 320 devices? It is clear the future is 1080p. I am either planning to switch our devices with a couple of Nexus 4s or Xperia Zs. Because I fear our devices are about to be outdated with the next game right around the corner. So far they are doing just fine with Modern Combat 4 and the all other graphic intensive games by playing over 28-30 FPS. But according to the GLBenchmark 2.5Egypt they are useless against new Adreno 320. However I have read that most of the games were designed for high fill rate power and Mali 400 is able to beat Adreno 320. But on the triangle tests, it just bottlenecks.
So what is your opinion about it? I will our devices do another year and half for the new games? Or should I make the trade? Or should I just buy a Nexus 10 with 2 users assigned and continue games on it? I
Thank you for reading.
Sent from my GT-N7100 using xda app-developers app
_delice_doluca_ said:
Finally a lot of exerts here about GPU
, I know it is not related to topic but me and my girlfriend have Galaxy Note 2 and S3. As you all know they are the last ones to use the elder Mali-400 GPU. I love playing games and I am getting my girlfriend used to them too. So I was wondering how is our Mali400 GPU holding up against the new coming 1080p Adreno 320 devices? It is clear the future is 1080p. I am either planning to switch our devices with a couple of Nexus 4s or Xperia Zs. Because I fear our devices are about to be outdated with the next game right around the corner. So far they are doing just fine with Modern Combat 4 and the all other graphic intensive games by playing over 28-30 FPS. But according to the GLBenchmark 2.5Egypt they are useless against new Adreno 320. However I have read that most of the games were designed for high fill rate power and Mali 400 is able to beat Adreno 320. But on the triangle tests, it just bottlenecks.
So what is your opinion about it? I will our devices do another year and half for the new games? Or should I make the trade? Or should I just buy a Nexus 10 with 2 users assigned and continue games on it? I
Thank you for reading.
Sent from my GT-N7100 using xda app-developers app
Click to expand...
Click to collapse
They will hold on, my SGS2 runs all of the current games at the highest settings ( I haven't tried GTA though) without any issues, the Adreno 320 is far better than the Mali 400 MP4 though
Ya, Im pretty sure they will still play games a year from now. Until the market is completely saturated with devices like the Nexus 10 in power we wont really see large jumps in system requirements. That will probably only happen a year or two from now once all the new phones and tablets are made with A15 processors (or Qualcomm equivalent) and beefy GPUs.
Fidelator said:
They will hold on, my SGS2 runs all of the current games at the highest settings ( I haven't tried GTA though) without any issues, the Adreno 320 is far better than the Mali 400 MP4 though
Click to expand...
Click to collapse
The S2(Mali400) plays GTA3 without a hiccup.
The exynos dual is very power hungry compared to the s4pro but it is also the most powerful arm processor out today. Nothing else yet released (I said RELEASED) is as powerful or can match its bandwidth. Having said that I'm sure a normal resolution 1080p screen in this form factor with the s4pro would be a nice fast tablet. Right now the exynos dual is pretty much the only thing outside apple that can push the resolution that the n10 has. I think if they had put another gig of ddr3 in this thing there wouldn't be so much stuttering in certain instances. Besides the thermal cutoff the n10 is starved for memory as it has to share normal duties and its ram with the graphical load of pushing all the pixels of this monster resolution. You are lucky to have 300mb of ram available at idle on the n10 vs over a gig available with the s4pro on the 720p screen of the nexus 4
Sent from my often RMA'd Nexus 4, So that I can use the one I'm using now when I get the 6th and hopefully final one.
Hi. I'd love to see a face to face comparison between 2 identical smartphones, one running Android ARMv7 32-bit and the other one running Android ARMv8 64-bit, preferably Marshmallow, although Lollipop 5.1.1 would do it fine too. I've thought that the LG Nexus 5X would be a good phone to test the difference between these 2 versions of Android.
Which one would be faster restarting?
Which one would have the CPU colder when decoding videos (Full HD or even 4K)? And CPU load?
What would be the main differences?
Ram usage and if it would be a problem having "only" 2GB of RAM like the 5X.
Benchmarks.
CPU usage and load under same conditions in both terminals, CPU temp monitoring to see the theoretical improvements ARMv8 have done.
Can anyone do it?
Up!
I wanted to know if there is performance difference between Windows 11 host and WSA client, so I have installed and run Geekbench 5 on both systems.
The benchmark results:
Windows 11
Single Core Score: 848
Multi Core Score: 2297
Details:
LENOVO 81LY - Geekbench
Benchmark results for a LENOVO 81LY with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
LENOVO 81LY - Geekbench
Benchmark results for a LENOVO 81LY with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
WSA ( Android 11 )
Single Core Score: 677
Multi Core Score: 1487
Details:
Google Pixel 5 - Geekbench
Benchmark results for a Google Pixel 5 with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
Resume:
Although the same hardware ( SoC ) is used when using the WSA a drastic performance loss can be observed: ~25% when running single-core CPU operations, ~35% when running multi-core CPU operations.
Info:
As of version three of GeekBench, the scores have been split into single and multi core categories. The Single Thread CPU benchmark, like all processor benchmarks attempts to estimate how quickly a processor is able to perform a wide variety of calculations. The test issues as series of complex instructions to the processor and times how long the processor takes to complete the tasks. The faster the processor is able to complete the tasks, the higher the benchmark score. The GeekBench Single Thread CPU test only runs one stream of instructions rather than multiple parallel streams per core. The majority of consumer applications (MS World, Internet Explorer, Google Chrome and most games), although multi threaded, rarely utilize more than one thread at a time, so this test, like any single threaded benchmark, can be seen as a reasonable real world test for typical consumer workloads.
Not useful for gaming!
Would've been interesting to add bluestacks to the mix too!
jwoegerbauer said:
I wanted to know if there is performance difference between Windows 11 host and WSA client, so I have installed and run Geekbench 5 on both systems.
The benchmark results:
Windows 11
Single Core Score: 848
Multi Core Score: 2297
Details:
LENOVO 81LY - Geekbench
Benchmark results for a LENOVO 81LY with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
LENOVO 81LY - Geekbench
Benchmark results for a LENOVO 81LY with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
WSA ( Android 11 )
Single Core Score: 677
Multi Core Score: 1487
Details:
Google Pixel 5 - Geekbench
Benchmark results for a Google Pixel 5 with an AMD Ryzen 5 3500U processor.
browser.geekbench.com
Resume:
Although the same hardware ( SoC ) is used when using the WSA a drastic performance loss can be observed: ~25% when running single-core CPU operations, ~35% when running multi-core CPU operations.
Info:
As of version three of GeekBench, the scores have been split into single and multi core categories. The Single Thread CPU benchmark, like all processor benchmarks attempts to estimate how quickly a processor is able to perform a wide variety of calculations. The test issues as series of complex instructions to the processor and times how long the processor takes to complete the tasks. The faster the processor is able to complete the tasks, the higher the benchmark score. The GeekBench Single Thread CPU test only runs one stream of instructions rather than multiple parallel streams per core. The majority of consumer applications (MS World, Internet Explorer, Google Chrome and most games), although multi threaded, rarely utilize more than one thread at a time, so this test, like any single threaded benchmark, can be seen as a reasonable real world test for typical consumer workloads.
Click to expand...
Click to collapse
eduardo.M said:
Not useful for gaming!
Click to expand...
Click to collapse
Correct: Even PUBG Mobile Lite crashes when it is loading.