I just ran into something weird when testing my HTC Sensation. I downloaded the PassMark benchmarking software. I ran the test and got a set of scores for CPU, Disk, and Memory categories. I removed the microSD card that came with my phone, copied everything onto a new Class 6 8GB card, and put that in the phone. I then re-ran the benchmark tests to see if the disk performance improved. There was an improvement, but check out the CPU Floating Point math results in the attached pic! Baseline #000486 was run with the 8GB card that came with the phone. Baseline #000501 was run with a new Class 6 8GB card. I copied everything on the original card to the new card and installed it. No other changes. Is this a fluke of some sort, or is there an explanation for the dramatic jump in performance?
That is quite interesting. can you try running quadrant with each of the sdcards? maybe also run Antutu as that has some good sdcard benchmarks.
I ran passmark myself now, and the results varied a bit, on the Floating Point that is. First time i got 50, second time 135, and third time 50 again.. my sdcard is a 32GB Sandisk (only class 2 i think).
The other results were pretty similar to yours, except the Data Compression, where I only scored between 140 and 200, compared to your 450.. no idea why..
Sounds like their beta version still needs a lot of work. As for Quadrant, I'll try running that tonight and posting the results here.
I ran Quadrant and got a score of 2022 with the old card and 2096 with the class 6 card. Not a big increase, so I wonder if its actually due to the variation in the program.
Related
I am looking to benchmark my G1 with several different builds to tweak the performance. I have checked the market and found Neocore and CaffeineMark. Does anyone know of any other benchmarks available or have any suggestions for benchmarking the G1? Thanks.
Their is a linux program I used called "stress". It can probably be easily ported to run on android.
A huge bump for this thread. I am wondering if anyone has done performance comparisons with apps and data moved to sd vs not sd. I understand the benefits of having more space on the phone, but can it actually improve the phones performance or just prevent it from running slow when the space is limited?
Also, anyone seen any class 6 micro sdhc cards that actually tell you the transfer speed other than minimum 6MB/sec write speed? I can find many micro sd cards that advertise the rating and speed, but no sdhc versions.
So after reading nearly 5 hours and spending my time in the wee hours of morning, I finally did all the "stable" mods for the phone... If you haven't been reading, make sure you guys check out the stuff in the development forum.
After all modifications, I was able to get 2701 points in quadrant benchmark. What mods did I do?
-i9000 eclair flash (JM5)
http://forum.xda-developers.com/showthread.php?t=734871
-Alternative mimocans lag fix
(one click installer http://forum.xda-developers.com/showthread.php?t=749495)
-One click root (googled it for i9000)
-Overclock kernel 1.0Ghz to 1.2Ghz
(http://forum.xda-developers.com/showthread.php?t=746343)
This stuff really does help out your phone folks. Bench it now with quadrant, then take a peak at the other stuff and make magic happen. If anyone needs any additional help setting up their captivate, I'm more than happy to help.
I agree those fixes help speed a lot. But the quadrant score is meaningless. the speed hack creates an io loopback. The loopback just tells quadrant what it wants to hear.
Does your BT work on the european ROM. For me all people hear is a gargeled mess on there end?
Sent from my SAMSUNG-SGH-I897 using Tapatalk
Can you post the results of these tests:
Neocore
Linpack
CPU Benchmark
I keep hearing about this quadrant, does it actually improve real world performance? Or is just for the sake of scores?
jhego said:
I keep hearing about this quadrant, does it actually improve real world performance? Or is just for the sake of scores?
Click to expand...
Click to collapse
Quadrant is just benchmarking software that takes the cpu, gpu and memory read/write speeds into account. It runs a series of tests and spits a score number out at the end, so you can compare your device to others (like comparing boner sizes, but less gay).
It doesn't actually do anything to speed up the device though.
modest_mandroid said:
Quadrant is just benchmarking software that takes the cpu, gpu and memory read/write speeds into account. It runs a series of tests and spits a score number out at the end, so you can compare your device to others (like comparing boner sizes, but less gay).
It doesn't actually do anything to speed up the device though.
Click to expand...
Click to collapse
This is correct and to be honest there is way to much weight in the I/O tests. That is the only reason that the stock Droid X bests the Gal X. It has more weight than cpu and gpu so you can't put to much into those scores. They really don't mean anything more than bragging rights. What I am interested in is real world usage.
Real world use with the hack provides amazing speed gains opening and switching apps. Io heavy apps are very much improved while open too. It's finally as fast as the iphone.
Whats your battery life like after the overclock?
The score ended up getting lower and lower every time i used quadrant. 2701 is the highest I was able to get so far, but that's with a fresh install of the rom and all the stuff before I started loading on apps. Everytime I ran the benchmark, I of course killed the apps beforehand.
The battery life is the same- to be honest. This is me comparing a rooted stock ROM to the somewhat fresh install of the eclair i9000. The phone is very snappy. I came from an iPhone 4 and one of the biggest eye sores to me was the less-fluidness of changing programs, response to buttons (homescreen-back button) and pinch to zoom. After all these changes, it's a whole different story. Browsing is very appealing, especially since pinch to zoom isn't jagged or slow. The smoothness of this functionality is on par to an iPhone. And there is no waiting when I press the home button or back button.
True, maybe these numbers aren't considerably accurate (as far as the lag fix and EXT2) but at least it shows raw computing capability in it's current state... meaning, the usage of a virtual EXT2. Never the less, the phone is still all around faster, even if it isn't exactly the proper way of going about it.
The only problem I've seen so far is that it likes to randomly shut off. Won't respond to anything unless if I soft reset it. I haven't really found what causes it, since the consistency of it happening goes about in a non set pattern.
I didn't see any real world increase .. so I reverted back in about 4 hours.... I'd rather have the memory than a number that don't transfer to real world speeds...
I don't know if anyone ever thought about making swap on cappy . I just feel a bit of shortage in ram, even I use talon big mem version still feel inadequate. What I am thinking is to make swap on external sdcard because it's faster, anyone can help me with it? Thanks in advance.
Sent from my GT-I9000
are you talking about a memory swap file?
"make swap" isnt too descriptive.
SD cards under class 6 are slower than our "ram"
if you feel inadequate with a big mem version of talon, you have something wrong.
adding another process to constantly read/write and swap files would be THE LAST THING you would want to do with your phone....
Android is pretty efficient at managing memory .... and swap files are well, terrible when you have high speed storage (ssd's, nand,) and for the class on the sd cards it is misleading. A lot of cards have algorithms that help improve their read speeds, with SSD (or NAND) you want to see the random IO speeds for reads and writes (class speeds are for reads)
Sent from my SAMSUNG-SGH-I897 using XDA Premium App
I mean memory swap.
And I have a class 10 card(tested read 20M/s and write 18M/s).
Thanks for your answersI'll think about it either way.
Does the captivate even have quick enough i/o to support class 10? And either way, like mentioned before Android IS very efficient at managing memory, which shows in their design of activities (read: onResume(), onPause(), onCreate(), onDestroy()). If your foreground app requires more memory than the system can provide, lower activities on the stack will be told to pause or destroy until a later time to free up memory.
If your phone's performance is suffering, it's most likely a processing issue. Perhaps you have some nasty services running (this could also be reflected in poor battery life).
I'm getting this phone soon but just a couple questions.
Ive heard that the sensation has low available ram issues (probably sense?) but when/if a stock rom comes that should be fixed right?
Also since the avalible rom is pretty low. Would a class 10 micro sd be good for running data2sd (once we have root) were the whole data partion is on the sd.
is class 10 faster then the built in rom?
Having class10 won't make such a big difference (I purchased a class10 16Gb card and did not see any improvement compared to my class4) except that it will be faster to place big files (movies, etc) on the card
Concerning RAM, it's true that stock ROMs don't really manage it well, mainly because they start many apps in the background. Some can be killed, some will always come back after killed.
So once I've killed the useless apps after a fresh reboot, I can get a maximum of 350Mo free RAM, that tend to go to an average 250Mo after some hours of use.
Android 2.3 is not that bad in managing RAM (despite stock ROMs are) so I had low ram having a visible impact on something only once, when wanting to play Tekken 3 with Fpse and realized it was lagging because of low ram. My sensation was not laggy, only Fpse was, it demands much ressoruces! (I hadn't rebooted my Sensation for 3 days, that was the reason for low ram....now, I reboot it every 2 days, and no more problem)
So RAM is ok, if it gets kinda low, you won't notice it, and Android will tend to release ram afterwards, and once we'll have custom roms, it will be huge!
Wich app is good for testing sd card speed.
I have a Samsung pro plus 128gb sd card and I have slow speed. I don't know Wich app's are accurate.
My test with a1 sd bench
66 MB/s read and 44 MB/s write.
That's pretty good unless you have a really high end sd card. I only get about 18mb write with the Samsung EVO card that best buy was giving for free. The internal memory screams at 300mb read and 150mb write.
aaronito said:
Wich app is good for testing sd card speed.
I have a Samsung pro plus 128gb sd card and I have slow speed. I don't know Wich app's are accurate.
My test with a1 sd bench
66 MB/s read and 44 MB/s write.
Click to expand...
Click to collapse
I guess first we would have to define what accurate means, Im sure the benchmarks are accurate in what they are measuring and Im sure its not accurate to real life use.
Anyway my A1 bench score is 62MB/s & 16MB/s I/O. I use the long benchmark but the "accurate" test with reboot was similar +-1MB/s. This is with a SanDisk Ultra MicroSDXC 80MB/s Class 10, 64GB.
I guess these tests best represent what speeds you could expect while transferring "large" files, perhaps the random I/O test is better if you want something closer to real life usage?
Lerduvan said:
I guess first we would have to define what accurate means, Im sure the benchmarks are accurate in what they are measuring and Im sure its not accurate to real life use.
Anyway my A1 bench score is 62MB/s & 16MB/s I/O. I use the long benchmark but the "accurate" test with reboot was similar +-1MB/s. This is with a SanDisk Ultra MicroSDXC 80MB/s Class 10, 64GB.
I guess these tests best represent what speeds you could expect while transferring "large" files, perhaps the random I/O test is better if you want something closer to real life usage?
Click to expand...
Click to collapse
I tested out and it's the same about 1MB/s difference. But mine sd card has 95MB/s read and 90MB/s write and I not getting close to it. That's why I ask of the benchmark are accurate.
aaronito said:
I tested out and it's the same about 1MB/s difference. But mine sd card has 95MB/s read and 90MB/s write and I not getting close to it. That's why I ask of the benchmark are accurate.
Click to expand...
Click to collapse
Every manufacturer has their own way of measuring the speeds. All shown speeds in the ads are best case scenario and not real world that you would expect.
There are som many variables that limit the speed of reading/writing so the numbers show are only good for comparison to other cards and best for comparison within the same brand (assuming they always use the same method of measurement).
So no need to worry....
Tiny Wiz said:
Every manufacturer has their own way of measuring the speeds. All shown speeds in the ads are best case scenario and not real world that you would expect.
There are som many variables that limit the speed of reading/writing so the numbers show are only good for comparison to other cards and best for comparison within the same brand (assuming they always use the same method of measurement).
So no need to worry....
Click to expand...
Click to collapse
Okay thanks
The phone could be limiting the speeds as well.
Tried In a GS5 and got 44/12MB/s out of the same SD memory. Perhaps playing around with some kernel tweaks might give you a more satisfying result?
I have tested several cards in my phone. The fastest card I own is a Lexar 1000x 32gb card that claims a 150mbs read and a 45mbs write. The testing only gives about 71mbs read and 34 mbs write. As you can see it is far from the manufacturers stated numbers.
The Samsung EVO 64gb that Best buy was giving away with the phone gave me about 35mbs read and 20mbs write if I remember correctly.
64gb Samsung Pro+
trying a1 sd but seeing my sd card listed 3 times ?? not sure why ok, refresh seems to have sorted it out
Card is a 64gb Samsung Pro+ (paid $39, best buy price match microcenter)
wifi, bluetooth, connected, no tweaks or anything, just ran as i use it.
A1 bench score is 61MB/s & 45MB/s I/O. using the accurate benchmark
score is 7.84MB/s & 1.42MB/s I/O. using the random i/o benchmark
score is 65.47MB/s & 53.90MB/s I/O. using the quick benchmark
CrystalDiskMark 3.0.4 (C) 2007-2015 hiyohiyo
Sequential Read : 93.079 MB/s
Sequential Write : 86.402 MB/s
Random Read 512KB : 84.354 MB/s
Random Write 512KB : 78.683 MB/s
Random Read 4KB (QD=1) : 8.644 MB/s [ 2110.5 IOPS]
Random Write 4KB (QD=1) : 3.937 MB/s [ 961.3 IOPS]
Random Read 4KB (QD=32) : 11.080 MB/s [ 2705.0 IOPS]
Random Write 4KB (QD=32) : 3.702 MB/s [ 903.8 IOPS]
Test : 50 MB [L: 0.0% (0.0/59.6 GB)] (x2)
Date : 2016/03/07 5:39:41
OS : Windows 10 Professional [10.0 Build 10586] (x64)
JS_racer said:
trying a1 sd but seeing my sd card listed 3 times ?? not sure why ok, refresh seems to have sorted it out
Card is a 64gb Samsung Pro+ (paid $39, best buy price match microcenter)
wifi, bluetooth, connected, no tweaks or anything, just ran as i use it.
A1 bench score is 61MB/s & 45MB/s I/O. using the accurate benchmark
score is 7.84MB/s & 1.42MB/s I/O. using the random i/o benchmark
score is 65.47MB/s & 53.90MB/s I/O. using the quick benchmark
CrystalDiskMark 3.0.4 (C) 2007-2015 hiyohiyo
Sequential Read : 93.079 MB/s
Sequential Write : 86.402 MB/s
Random Read 512KB : 84.354 MB/s
Random Write 512KB : 78.683 MB/s
Random Read 4KB (QD=1) : 8.644 MB/s [ 2110.5 IOPS]
Random Write 4KB (QD=1) : 3.937 MB/s [ 961.3 IOPS]
Random Read 4KB (QD=32) : 11.080 MB/s [ 2705.0 IOPS]
Random Write 4KB (QD=32) : 3.702 MB/s [ 903.8 IOPS]
Test : 50 MB [L: 0.0% (0.0/59.6 GB)] (x2)
Date : 2016/03/07 5:39:41
OS : Windows 10 Professional [10.0 Build 10586] (x64)
Click to expand...
Click to collapse
Nice. I may have to invest in one of these cards. Are you getting an occasional notification for your SD card? I'm still trying to figure out if there is something wrong with my phone.
skiddingus said:
Nice. I may have to invest in one of these cards. Are you getting an occasional notification for your SD card? I'm still trying to figure out if there is something wrong with my phone.
Click to expand...
Click to collapse
only on reboot, there is an automatic reboot option, say at a chosen time it will reboot, in the settings somewhere, lol cant recall where i saw it
not sure the phone is making good use of this card or not.
i do have 2 lexmark 633 cards i could bench, just the install is a pita, lol dumb tray
I bought a Sandisk extreme plus 64gb card at Best Buy yesterday. It is testing out at 66mbs read and 57mbs write. They are on sale for $50 which is the same as Amazon.
skiddingus said:
I bought a Sandisk extreme plus 64gb card at Best Buy yesterday. It is testing out at 66mbs read and 57mbs write. They are on sale for $50 which is the same as Amazon.
Click to expand...
Click to collapse
testing how ??
a1 bench ?? CrystalDiskMark?? what method of bench test??
JS_racer said:
testing how ??
a1 bench ?? CrystalDiskMark?? what method of bench test??
Click to expand...
Click to collapse
A1 bench
skiddingus said:
I bought a Sandisk extreme plus 64gb card at Best Buy yesterday. It is testing out at 66mbs read and 57mbs write. They are on sale for $50 which is the same as Amazon.
Click to expand...
Click to collapse
I looked up that card and it looks like today it's even half of what you paid for lol....get your money back man!
http://www.amazon.com/SanDisk-Extre...id=1457876897&sr=1-2&keywords=sandisk+extreme
HTCMDA said:
I looked up that card and it looks like today it's even half of what you paid for lol....get your money back man!
http://www.amazon.com/SanDisk-Extre...id=1457876897&sr=1-2&keywords=sandisk+extreme
Click to expand...
Click to collapse
That is the "extreme". I bought the "extreme plus" It is faster.
skiddingus said:
A1 bench
Click to expand...
Click to collapse
good result, what test was that ?? did you run the other tests ?? accurate, random or quick ??
just trying to get a feel for cards in this phone, thanks!!
A phone has its limits
If i remember correctly, a phone has a speed limit, so if your sd card is capable of higher speeds, that doesn't mean your phone can do the same.
I would agree that the phone has a limit, if we knew what cards are capable of in the phone, then that could help with a purchasing decision for card speed.