So as we all know with our devs pushing the cpu like up to these ridiculous speeds and our benchmarks not really showing the type of jump that we were really expecting, Is it possible that the way the CPU works is causing these scores not to score as high but not affect it's speed in the same way?
So after reading a bit on our CPU, from what I got from it ours does has about the average amount of IPS(instructions per second) compared to the snapdragon and it's custom architecture. However ours is said to be designed in a way that it requires 25-50% less instructions for 20~% of it's functions. So if thats the case we should be doing a little better in different areas.
In turn my real question is...
Because these benchmarks were built prior to our CPU being out, will that affect the numbers considering they probably aren't built for the way ours functions. Or am I just thinking way to far into this and have no idea what i'm talking about .
Which benchmarks are you referencing?
MFLOPS?
lqaddict said:
Which benchmarks are you referencing?
MFLOPS?
Click to expand...
Click to collapse
Anything from Linpack to SetCPU native benchmarks.
xplanowestx said:
Anything from Linpack to SetCPU native benchmarks.
Click to expand...
Click to collapse
You should probably read a bit on LINPACK - it was originally designed in the late 70's, 1979 to be precise, it was a set of Fortran procedures to perform numeric linear algebra. It is quite affected by the OS, and that's why you see LINPACK scores on 2.2+ systems are quite "improved" over 2.1 or earlier systems running better or the same hardware.
As far as SetCPU is concerned - there is no point running the benchmark on the CPU's that do not support NEON instructions, NEON is a Cortex-A specific (our phone and iPhone4 are among the few that have it); running it on a non-Cortex-A CPU, like a G2's GenII Snapdragon/Sciorpion from Qualcomm, does nothing but confuse people with bunch of numbers (the numbers are correct, they show how long it took that CPU to ignore the instruction instead of execute it, ignoring takes a lot less time than executing ).
And the C number in native SetCPU, I would assume it is a condition set on the instruction set to Carry on even if the previous instruction resulted in NOP (No Operation), so in the case of the glorified G2 for instance (you prolly saw the pretty screenshots) after ignoring the NEON instruction, it carries on ignoring the next NEON instruction throwing at it, so I am not sure what it is indicative of though, have to ask the SetCPU dev.
I hope this helps.
lqaddict said:
You should probably read a bit on LINPACK - it was originally designed in the late 70's, 1979 to be precise, it was a set of Fortran procedures to perform numeric linear algebra. It is quite affected by the OS, and that's why you see LINPACK scores on 2.2+ systems are quite "improved" over 2.1 or earlier systems running better or the same hardware.
As far as SetCPU is concerned - there is no point running the benchmark on the CPU's that do not support NEON instructions, NEON is a Cortex-A specific (our phone and iPhone4 are among the few that have it); running it on a non-Cortex-A CPU, like a G2's GenII Snapdragon/Sciorpion from Qualcomm, does nothing but confuse people with bunch of numbers (the numbers are correct, they show how long it took that CPU to ignore the instruction instead of execute it, ignoring takes a lot less time than executing ).
And the C number in native SetCPU, I would assume it is a condition set on the instruction set to Carry on even if the previous instruction resulted in NOP (No Operation), so in the case of the glorified G2 for instance (you prolly saw the pretty screenshots) after ignoring the NEON instruction, it carries on ignoring the next NEON instruction throwing at it, so I am not sure what it is indicative of though, have to ask the SetCPU dev.
I hope this helps.
Click to expand...
Click to collapse
It does help very much so which is sort of what i was seeing regarding SetCPU scores, they didn't seem correct based off the newer frequency's of the TeamWhiskey kernel they are developing. This would make sense.
So regarding linpack and 2.2, why is it that the Snapdragon is able to pull out these 55+ linpack results? It doesn't make sense that our CPU wouldn't be capable to pull off the same with what were are able to OC our CPU too, were getting much lower results compared to other phones moving to 2.2, if you can please explain this a little further. Thanks!
xplanowestx said:
It does help very much so which is sort of what i was seeing regarding SetCPU scores, they didn't seem correct based off the newer frequency's of the TeamWhiskey kernel they are developing. This would make sense.
So regarding linpack and 2.2, why is it that the Snapdragon is able to pull out these 55+ linpack results? It doesn't make sense that our CPU wouldn't be capable to pull off the same with what were are able to OC our CPU too, were getting much lower results compared to other phones moving to 2.2, if you can please explain this a little further. Thanks!
Click to expand...
Click to collapse
It's the OS limitation, and I am trying not to make an excuse for it, but RFS as well.
LINPACK score is highly affected on what your OS is doing, and how it is doing what it does , given a fair chance, with Galaxy S hopefully getting 2.2 this year (LOL), and team z4mod developing the overhaul of the cripple RFS you will see comparable LINPACK scores.
lqaddict said:
It's the OS limitation, and I am trying not to make an excuse for it, but RFS as well.
LINPACK score is highly affected on what your OS is doing, and how it is doing what it does , given a fair chance, with Galaxy S hopefully getting 2.2 this year (LOL), and team z4mod developing the overhaul of the cripple RFS you will see comparable LINPACK scores.
Click to expand...
Click to collapse
You made some realy great points, it is always good to have knowledgeable people around to answer technical questions. However, I don't understand how RFS, a file system affects arithmetic calculation? (from what I read, Linpack is basically a really difficult math problem).
It's the OS limitation, and I am trying not to make an excuse for it, but RFS as well.
LINPACK score is highly affected on what your OS is doing, and how it is doing what it does , given a fair chance, with Galaxy S hopefully getting 2.2 this year (LOL), and team z4mod developing the overhaul of the cripple RFS you will see comparable LINPACK scores.
Click to expand...
Click to collapse
Thanks for the very in depth answers. Hopefully fixing the filesystem would fix the speeds and such of the CPU. I'm hoping your right on that idea. If thats the case, do you think we will be comparable to the G2's Extremely high scores?
You made some realy great points, it is always good to have knowledgeable people around to answer technical questions. However, I don't understand how RFS, a file system affects arithmetic calculation? (from what I read, Linpack is basically a really difficult math problem).
Click to expand...
Click to collapse
+1
On a second note, what would compel Samsung to use such filesystem? Is it because of the proprietary side of it?
xplanowestx said:
Thanks for the very in depth answers. Hopefully fixing the filesystem would fix the speeds and such of the CPU. I'm hoping your right on that idea. If thats the case, do you think we will be comparable to the G2's Extremely high scores?
+1
On a second note, what would compel Samsung to use such filesystem? Is it because of the proprietary side of it?
Click to expand...
Click to collapse
I might've gone there on a limp, but from my understanding is that floating point operations stressed out by computing NxN matrix (LINPACK benchmark) is optimized to take an advantage of the L2 cache on the processor. Well our processor has 512K L2 cache if I am not mistaken, and from what I read on Qualcomm CPU in G2 - it has no cache at all. So where to keep the data? The next fastest media is memory and then disk I/O, and idsk I/O is where the weakest link is, given the fact that we have a decaying FAT32 implementation the weakest link is even weaker.
Remember your system is as good as your weakest link.
Did I make a plausible excuse ?
lqaddict said:
I might've gone there on a limp, but from my understanding is that floating point operations stressed out by computing NxN matrix (LINPACK benchmark) is optimized to take an advantage of the L2 cache on the processor. Well our processor has 512K L2 cache if I am not mistaken, and from what I read on Qualcomm CPU in G2 - it has no cache at all. So where to keep the data? The next fastest media is memory and then disk I/O, and idsk I/O is where the weakest link is, given the fact that we have a decaying FAT32 implementation the weakest link is even weaker.
Remember your system is as good as your weakest link.
Did I make a plausible excuse ?
Click to expand...
Click to collapse
It COULD be possible, considering how freeing up RAM increases linpack scores (to an extend). But how about people who have voodoo? Isn't that ext 4, so linpack on those system should fly off the chart but they don't/
PaiPiePia said:
It COULD be possible, considering how freeing up RAM increases linpack scores (to an extend). But how about people who have voodoo? Isn't that ext 4, so linpack on those system should fly off the chart but they don't/
Click to expand...
Click to collapse
Voodoo only addresses /data, I would assume instructions for LINPACK calculation will be punted to /cache
So then the new z4mod should (hopefully) raise our linpack scores fairly higher since thats a 100% complete conversion correct?
xplanowestx said:
So then the new z4mod should (hopefully) raise our linpack scores fairly higher since thats a 100% complete conversion correct?
Click to expand...
Click to collapse
I believe with mature z4mod and a stable froyo build the Galaxy S will shine, hopefully it is not a wishful thinking, and these things happen sooner than later for us.
lqaddict said:
I believe with mature z4mod and a stable froyo build the Galaxy S will shine, hopefully it is not a wishful thinking, and these things happen sooner than later for us.
Click to expand...
Click to collapse
+1 to that.
I am getting 2356 on the scores... Is this good? I hope I can get it higher once we get root and tweak some things right?
why is everyone worry about quadrant score?
Sent from my PG86100 using XDA Premium App
I got...
1818(before update)
2022(after update hadn't rebooted in a couple days)
2160, 2306, 2276(after fresh reboot)
Quadrant is important to track stuff you do to your phone I can see that the OTA speed up my phone and that after a reboot it's a little bit more badass. And seeing that the OP's score is close to mine I would assume that 2300ish is what most 3D's would score.
I can't wait to try out ROM's, kernels, and overclock this beast!
When it turns into a bragging rights thing then its kinda useless(because they can be faked).
Lucky you guys, I have the update and I get 1500-1900 after a reboot and killing all running apps...
It is actually double what you are getting because both cores are not active at the same time. Take your quadrant and double it. that is your actual score because the qualcom snap dragon is useing asynchronous chip. When you compare TEGRA or any other dual core, both cores are active giving u higher results. Qualcomm made these chips asynchronous to save battery.
Can't wait to get my EVO 3d
I'd just like to know why my scores are so much lower then everyone elses, and I have a ton of stuff disabled with a fresh reboot and all.
I figured I would run quadrant stand and see what I got and I got some interesting results. I got a score of 1830 which is a little bit less then what people have gotten on my phone the Samsung Galaxy Prevail which is a lowend single core 800 MHz Qualcomm MSM7627-3 plus the phone only has 384megs of ram. On top of that quarant says the device only has 1 core so Im not sure whats going on with that
I really don't care for quadrant -- at all. It provides far too divergent results on different devices of the same model/SW, it often does not use all available resources to test a device, and I find its results far too inconsistent to be worth regarding as anything other than a random grouping of numbers.
Im just wondering what other apps see the cpu as 1 core and not the dualcore it really is like quadrant does.
This section is not for discussions like this. This is more suited to the general section.
Moved to General
Montisaquadeis said:
Im just wondering what other apps see the cpu as 1 core and not the dualcore it really is like quadrant does.
Click to expand...
Click to collapse
The Nook Tablet usually turns off the second core in order to conserve battery power. I don't know what the conditions are wherein it will spin up the other core.
hmm could be why some apps are a bit slower then others. and why a lowend smartphone is getting better quadrant scores then this dualcore of a monster
Montisaquadeis said:
I figured I would run quadrant stand and see what I got and I got some interesting results. I got a score of 1830 which is a little bit less then what people have gotten on my phone the Samsung Galaxy Prevail which is a lowend single core 800 MHz Qualcomm MSM7627-3 plus the phone only has 384megs of ram. On top of that quarant says the device only has 1 core so Im not sure whats going on with that
Click to expand...
Click to collapse
Mine got 2140. And a phone with a 800 mhz processor cant reach that unless it is rooted and overclocked. Only on CPU i got around 1500 points. So that means with custom rom the graphics can be improved and with overclock i think it will be able to reach at least around 3500. And quadrant its not so accurate either.
If you check this thread you will see a couple of people that are running CM7 have gotten 1900-2100 scores
http://androidforums.com/galaxy-prevail-all-things-root/479489-quadrant-score.html
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.
Hello everybody,
My friend and me(we have s-on and ics stock last version) when we tried quandrant we usually get 2700 scores.But he told me yesterday he tried different way that he added one line in "buid.prop" and he got 3600 marks quandrant scores
When he opened quandtrant benchmark system information he saw just 1 core is writing.He thought we should see 2 cores because we have 2 cores and ics (even leak)version.
So he wants to added in build.prop ''persist.sys.ui.hw=1'' and he wiped dalvic cache and cache and fix permission then restart system.He checked quandtrant standarts and he saw that 2 cores were writing there and immediately he got run full benchmark and got 3600-3500 marks.So we think that the reason of 2 cores.
But when he checked after 20 min later it was writing again 1 core in quantrand system information.It s chancing by itself.we can get more performans? is it possible to keep it?
I remember some guys talking about cores and they told just check antutu you gonna see 2 cores.Second core works when need it.But my friend added ''persist.sys.ui.hw=1" this line in build.prop and maybe he made 2 cores active So what do you think about it?Maybe somebody try this way and share results with us?
"sorry about my english.it is not perfect "
musti95 said:
Hello everybody,
My friend and me(we have s-on and ics stock last version) when we tried quandrant we usually get 2700 scores.But he told me yesterday he tried different way that he added one line in "buid.prop" and he got 3600 marks quandrant scores
When he opened quandtrant benchmark system information he saw just 1 core is writing.He thought we should see 2 cores because we have 2 cores and ics (even leak)version.
So he wants to added in build.prop ''persist.sys.ui.hw=1'' and he wiped dalvic cache and cache and fix permission then restart system.He checked quandtrant standarts and he saw that 2 cores were writing there and immediately he got run full benchmark and got 3600-3500 marks.So we think that the reason of 2 cores.
But when he checked after 20 min later it was writing again 1 core in quantrand system information.It s chancing by itself.we can get more performans? is it possible to keep it?
I remember some guys talking about cores and they told just check antutu you gonna see 2 cores.Second core works when need it.But my friend added ''persist.sys.ui.hw=1" this line in build.prop and maybe he made 2 cores active So what do you think about it?Maybe somebody try this way and share results with us?
"sorry about my english.it is not perfect "
Click to expand...
Click to collapse
The first few pages of this threadhttp://forum.xda-developers.com/showthread.php?t=1616669 talked extensively about dual-core and quadrant scores, and I would say by page 10 it was agreed upon that quadrant really just sucks. Go check it out, maybe that will shine some light for you..
I remember reading about how ICS improved dual core support, and I could have sworn it was on developer.android.com but I can't find the article that explains it now(and too many results to sift thru) - but basically the tweak "persist.sys.ui.hw=1" would have been found in gingerbread roms, because it DID increase performance, however with the way ICS handles the threading of dual-core+ processors that shouldn't do anything.
And before someone comes in here and says this in a not-as-nice way, be careful using quadrant benchmark as a tool- if ONE little detail is different, you will get TOTALLY different results! A different launcher, a different setting, or even having different background processes or having recently run a different app will change the score TOTALLY. Run it 10 times, chances are it will put out wildly different numbers - now go run 10 apps, then go back into quadrant and run it 10 more time - again, wildly different numbers, no consistency.
Besides, all that REALLY matters is your experience - if your score goes up a thousand(consistently somehow) but it doesn't work noticeably smoother, faster, or better- then what does your score matter? You could add 2 more cores, another gig of ram, better gpu - but if you can't NOTICE a difference then what would the point be?
It is easy to find why people added 'persist.sys.ui.hw=1' to gingerbread, but I can't find ANY documentation/posts that give a real reason to add it in an ICS build.. hope this answers your question.
And if anyone can find the link to googles explanation on how ice cream sandwich handles multi-core cpus compared to gingerbread can you PM it to me?
Thanks my friend your answer.Just ı got that if use quandrant benchmark test when ı check system information if ı see 2 core ı get 3500 marks but if ı see just 1 core system informatin ı can get 2700 marks.
So it depents on cores ı see.Its fault of benchmark app or our phone works one core just when need it use second core?