SunSpider benchmarks Froyo/Eclair - Fascinate General

Since DL30 has been released I am curious to see how well the performance improvements have translated. One of the bigger ones was the inclusion of the V8 JavaScript engine into the browser. I just ran Sunspider 0.9 and got a score of 8246 on my DL30 fascinate - a good bit better than what I got on eclair (14532).
For anyone interested in running the test yourselves:
http://www2.webkit.org/perf/sunspider/sunspider.html

Tried to run it on my 2.1 device and it just endlessly looped.

I can honestly say running the dj05 superclean without voodo and coming to this...I've seen a very noticible degradation of speed. Seriously contemplating going back.

I ran the DL09 w/ optimized kernel both voodoo and non voodoo, I ve been with this phone since the beginning and I say that froyo feels faster to me.

Related

Quadrant tests and smoothness

I was just wondering what some people are doing different than me setup-wise on their phones.
I currently have the latest bionix fusion, jac xmod kernel oc'd to 1.2ghz with voodoo. The phone is definitely smoother than stock, but there's still the occasional slight hesitation on what seems like the simplest tasks. I wouldn't be disappointed in the least if the phone stayed this way, but I'm curious if there's some step I'm missing.
Now about quadrant... I've noticed people claiming way over 2,000 quadrant scores. The highest I've gotten was 1960, and this was when I'd just odin'd back to stock, flashed the jac xmod kernel, voodoo and 1.2ghz on an otherwise stock touchwiz. On fusion, I'm seeing just slightly lower..closer to 1900. What gives? I haven't added any apps or widgets, killed all tasks, etc.
Any insight would be appreciated.
Sent from my SGH-T959 using XDA App

Epic vs Fascinate: Quadrant

So I was using a Fascinate on Verizon (obviously) for about a month before coming back to Sprint. I had my Fascinate (which I still have) rooted and deoxed with the voodoo EXT4 fix. My quadrant scores were over 2000. I know its just a number and real world performance is a different animal all together but supposedly the official voodoo fix does not inflate the quadrant scores like the old lag fix did. I love my Epic but was just wondering if there is a reason the quadrant scores were less then half of what I was getting with my Fascinate.
They both seem to perform the same in real world situations and I tested both on 2.1 stock (but the fascinate had the voodoo kernel). I also understand that the Epic doesn't require the voodoo fix but would we benefit from it. I haven't done a lot of kernel flashing with the Epic so I thought I would ask.

[Q] No JIT in DK28

So DK28 is supposedly 2.2.1 but I ran Quandrat with the stock rom and it comes up 873, almost exactly the same as Galaxy S 2.1, leading me to believe that JIT is not in the rom. Correct?
avenger213 said:
So DK28 is supposedly 2.2.1 but I ran Quandrat with the stock rom and it comes up 873, almost exactly the same as Galaxy S 2.1, leading me to believe that JIT is not in the rom. Correct?
Click to expand...
Click to collapse
I may be wrong but quadrant:
1) Isn't the best way to base performance
2) Doesn't really show improvements that JIT provides
Download linpack if you want and your score should be around a 14 or so, compared to the 8.5-9 on 2.1
Quadrant isn't a real life benchmark, and is highly flawed. Check out Quantum's "warp speed edition" ROM for proof.
Sent from my SPH-D700 using XDA App
I got 1205 with stock dk28 but I have noticed others reporting lower scores. Variability in testing with a bad benchmark perhaps?
I've got 1839 lol... For some reason I doubt that's accurate
I did a quadrant test with a stock epic 2.1 and an epic on dk28 and the scores were pretty much the same every time. The major difference was that the Froyo epic ran the cpu benchmarks much faster but hung during the first I/O test. The 2.1 epic ran everything about the same speed and completed the whole test much faster than the froyo epic.
I also noticed this and posted in another thread...
to quote myself
I was getting around 8.3xx in 2.1, and now I'm getting 13.7xx in 2.2.
(I used the 1506bdf2e04b.update-SPH-D700_DI18ToDK28.zip renamed to update.zip method.)
Saw a video the other day showing a nexus 1 scoring 20+ on 1st run and 40+ on 2nd.. My friends Evo (with 2.2) scored @ 38 or so..
Quadrant still shows me well under all of the 2.2+ phones listed.
Click to expand...
Click to collapse
I expected a bit more of an increase..
I too am wondering if the JIT was left out of our Froyo (if that's even possible, I'm still a total nube to andriod stuff).
What exactly is JIT, does it speed the phone up?
Sent from my SPH-D700 using XDA App
Just In Time compiling...
From what I know about .Net (I'm a C# coder), it allows for compilation of the app for the specific CPU during the 1st run.
Someone please correct me if this differes from andriod's JIT...
the epic has fast computation hw between the cpu and gpu, it could be the case that the JIT benefit doesn't show in the benchmark margins.
the device is a fast one, all compared.

Best Way to Improve Performance

So I am wondering what others opinions are of the roms and kernels available for the SF. Doesn't seem to be much of an improvement on Quadrant scores utilizing another rom or even stupidfast kernels.
Are we just kind of screwed a bit until 2.2? Is there a kernel that is overclocked?
TIA.
Quadrant scores are mostly meaningless, and 2.2 is unlikely to be revolutionary. The phone performs well on 2.1 - keep reading the forum and you'll get there.
In my opinion the biggest performance increases ive seen werent in any benchmarks but in dj05. it runs amazing. If u havent tried it i dont know whether you should or not. With the impending froyo release no one knows if they are actually going to release DJ05 or not. I think they should release it and then put froyo on top of that foundation if at all possible
Sent from my SCH-I800(tab) using ksizzle9's crazy kool ROM(bone stock with root) from within the XDA App
What do you feel about DJ that helped it out?
I finally stayed with just a Voodoo lag kernel. There certain operations on the phone I had gotten used to that were slow. The kernel with lag fix did show me noticeable improvement, more than just a higher I/O score in Quadrant.
I think the phone is fairly solid on 2.1 but needs a little help. Hopefully the Froyo upgrade really is around the corner but Im not holding my breath
jfigura said:
What do you feel about DJ that helped it out?
I finally stayed with just a Voodoo lag kernel. There certain operations on the phone I had gotten used to that were slow. The kernel with lag fix did show me noticeable improvement, more than just a higher I/O score in Quadrant.
I think the phone is fairly solid on 2.1 but needs a little help. Hopefully the Froyo upgrade really is around the corner but Im not holding my breath
Click to expand...
Click to collapse
I'm running DJ05 deox, and the stock DJ05 kernel. I used Titanium Backup to remove all the bloatware, and I use ADW instead of TouchWiz crap. (I took TW off with Titanium Backup too). SetCPU to set max to 1ghz, and minimum to 400mhz. (NO PROFILES!!!) It runs just fine for me. Rather damn speedy actually!! I dont do the whole benchmark test business, doesn't really mean much IMO.
Yes benchmarks dont mean too much. But they are a good indication of overall performance in their specific areas that they test. As they fascinate test well in every area except i/o. But we already kne that. Im not sure what about DJ05 Made it feel so solid to me just overall improvement and actual working GPS
Sent from my SCH-I800 using XDA App
ksizzle9 said:
Yes benchmarks dont mean too much. But they are a good indication of overall performance in their specific areas that they test. As they fascinate test well in every area except i/o. But we already kne that. Im not sure what about DJ05 Made it feel so solid to me just overall improvement and actual working GPS
Sent from my SCH-I800 using XDA App
Click to expand...
Click to collapse
Where did you get the dj05 update?
Sent from my SCH-I500 using XDA App
Ive only tried voodoo/lagfix
It made a significant difference on my phone. I reverted and restored all the factory stuff in anticipation of JD05 because I want to get it OTA when it drops.
I tried to get the leaked one in IRC but people just kept calling me n00b so I gave up.
I am hopeful that it will solve all my woes and usher in a new era of speed only previously dreamt about
Powell730 said:
Where did you get the dj05 update?
Sent from my SCH-I500 using XDA App
Click to expand...
Click to collapse
its been discussed dozens of times where and how to get dj05
joe3681 said:
I'm running DJ05 deox, and the stock DJ05 kernel. I used Titanium Backup to remove all the bloatware, and I use ADW instead of TouchWiz crap. (I took TW off with Titanium Backup too). SetCPU to set max to 1ghz, and minimum to 400mhz. (NO PROFILES!!!) It runs just fine for me. Rather damn speedy actually!! I dont do the whole benchmark test business, doesn't really mean much IMO.
Click to expand...
Click to collapse
ksizzle9 said:
Yes benchmarks dont mean too much. But they are a good indication of overall performance in their specific areas that they test. As they fascinate test well in every area except i/o. But we already kne that. Im not sure what about DJ05 Made it feel so solid to me just overall improvement and actual working GPS
Sent from my SCH-I800 using XDA App
Click to expand...
Click to collapse
@Joe: same setup here (DJ05 deo, Stock Kernel and Rom, Frozen bloat in Titanium) without SetCPU. It's FAST. My GF and both my sons have EVOs running 2.2 and my Fascinate is just as fast (or faster)
@ksizzle: I agree, it's hard to quantify exactly what is so good about it. I think it's not what's there, but what's NOT there (lag) I think there are going to be plenty of happy n00bs when the OTA hits. This phone will be a screamer right out of the box!
NOsquid said:
Quadrant scores are mostly meaningless, and 2.2 is unlikely to be revolutionary.
Click to expand...
Click to collapse
Actually, the real performance difference between 2.2. and 2.1 is very revolutionary, though I certainly agree with you about the irrelevance of Quadrant scores. The Java virtual machine, for example, executes code 450% -- that's not a typo -- faster, which directly impacts most apps.
And, 2.2's browser is also significantly faster than 2.1's -- and iOS4's, for that matter.
I like my Fascinate, and yes, I would consider it fast (especially running DJ05 with Geeknik's kernels) but like many others, I too see slowdowns sometimes that just shouldn't happen with the phone's hardware. Froyo isn't a magic pill, per se, but it should significantly reduce or eliminate those slowdowns (as it did on my old Droid 1, despite it's far-slower processor).
http://crave.cnet.co.uk/mobiles/and...r-vs-android-15-cupcake-speed-taste-49305763/
http://www.androidpolice.com/2010/0...-it-compared-to-2-1-oh-only-about-450-faster/
http://arstechnica.com/gadgets/news/2010/07/android-22-demolishes-ios4-in-javascript-benchmarks.ars
Actually, the real performance difference between 2.2. and 2.1 is very revolutionary, though I certainly agree with you about the irrelevance of Quadrant scores. The Java virtual machine, for example, executes code 450% in benchmarks -- that's not a typo -- faster, which do not directly impact most apps.
Click to expand...
Click to collapse
Fixed that for ya. Don't let marketing hype get the best of ya.
Everything I've read states that the performance improvements between 2.1 and 2.2 have little effect on Hummingbird processors (which is what is in all Galaxy S phones), and the biggest performance gains are seen on Snapdragon processors. As far as performance goes, I'll believe it when I see it.
imnuts said:
Everything I've read states that the performance improvements between 2.1 and 2.2 have little effect on Hummingbird processors (which is what is in all Galaxy S phones), and the biggest performance gains are seen on Snapdragon processors. As far as performance goes, I'll believe it when I see it.
Click to expand...
Click to collapse
This is because JIT was designed specifically around a Snapdragon processor.

Best Rom/lagfix/Kernel Combo? as of 2011

Raw Speed: Kernel: DOW 1.4 Voodoo5 "diabled"
Rom: Nero v3
Lagfix: OCLF 2.3
PRO's: I have found this combo to be devastating just freak'n over kill.
+'s 65fps smooth like butta, quick load time animation's are so so smooth.
download speeds ok.
Con's: get's so hot i worrie about whether im frying my phone. it freeze's in your pocket randomly. 720p video dont work, but the worst thing is batt life. forget it.
3 hours using the phone that's it.
-----------------------------------------------------------------------------
I have been using nero v3 for quite some time now and i'm not experiencing your listed cons. I would try reflashing.
OCLF while the easiest is probably the worst / most unsafe lag fix these days (at least before better / safer alternatives became available) and Quadrant scores are just that...scores.
I'd suggest trying the latest Axura with it's included Kernel and the Voodoo lagfix. DO NOT apply before undoing any previous lagfix. READ the entire OP and preferably the 2nd / 3rd post as well. I like it more than Nero v3 but that's more subjective than anything.
Any of the current JL5 based ROM's with stock+voodoo kernel I'd consider stable, as for the best - personal preference.
Quadrant scores do not reflect real life performance, running unstable overclocked kernel combo with a few "problems" I would not consider the best, maybe a bleeding edge, but definitely not your daily driver.
I agree with epakrat75 post. The balance is a fast smooth and good battery life performing phone. So far the axura does that. love the Nero/no ffc yet but the battery life is less and my business is heavily phone dependent The new pepperkake looks good as well but I haven't used it enough to comment fairly about it.

Categories

Resources