Database Develop

[Q] Mflops?

I had a Samsung Moment and most of the rom descriptions included the Mflop scores. I sold it and got a Hero and I've noticed pretty much no one lists or talks about Mflop scores? Is there a reason for this, is it not important since the Hero is so slow anyways?
The fastest score I've seen was with the new AospMod rom 5.6. Do any of the 2.1 roms compare?

reckoner13 said:
I had a Samsung Moment and most of the rom descriptions included the Mflop scores. I sold it and got a Hero and I've noticed pretty much no one lists or talks about Mflop scores? Is there a reason for this, is it not important since the Hero is so slow anyways?
The fastest score I've seen was with the new AospMod rom 5.6. Do any of the 2.1 roms compare?
Click to expand...
Click to collapse
I think it's because no one here really cares about it. Mostly because it doesn't matter. Most of us on the hero boards are more concerned with important stuff like stability, and coming from a moment and calling the hero slow is a case of the pot calling the kettle black. ;-)

reckoner13 said:
I had a Samsung Moment and most of the rom descriptions included the Mflop scores. I sold it and got a Hero and I've noticed pretty much no one lists or talks about Mflop scores? Is there a reason for this, is it not important since the Hero is so slow anyways?
The fastest score I've seen was with the new AospMod rom 5.6. Do any of the 2.1 roms compare?
Click to expand...
Click to collapse
MFlops is an arbitrary cpu scoring system much like Bogomips for Linux and you see it posted on almost every roms OP. The problem is that its affected by tons of stuff and just because aospbot posts a 5.6 doesn't mean thats what you'll get, you might be running a ton of widgets and facebook sync and other stuff.
CM6 also got a 5.6 or so and I've seen 2.1 sense rom also post a high scores like this. You should use it yourself and determine what is a good score on your phone under normal conditions and then use that as a bases for scoring other roms on YOUR phone.
Mflops are usually calculated by how many Floating Point operations it can calculate per second (usually pi to some exponent), while Mips is how many Fixed point operations it can calculate a second.
So pretty much ignore it unless your running it on your phone.

user7618 said:
I think it's because no one here really cares about it. Mostly because it doesn't matter. Most of us on the hero boards are more concerned with important stuff like stability, and coming from a moment and calling the hero slow is a case of the pot calling the kettle black. ;-)
Click to expand...
Click to collapse
Come on the moment has an 800mhz processor that can be overclocked and the same amount of RAM as the Hero (288). It's faster, but that doesn't mean it's better. I prefer the Hero.

reckoner13 said:
I had a Samsung Moment and most of the rom descriptions included the Mflop scores. I sold it and got a Hero and I've noticed pretty much no one lists or talks about Mflop scores? Is there a reason for this, is it not important since the Hero is so slow anyways?
The fastest score I've seen was with the new AospMod rom 5.6. Do any of the 2.1 roms compare?
Click to expand...
Click to collapse
Mflops is still used, but it is no longer a primary measure of a phone's capabilities. Most people use Quadrant to determine a phone's performance, as that incorporates 2D and 3D graphic performance in addition to calculations. But I've heard people use BenchmarkPi, CPU Benchmark, etc. It all is really quite irrelevant if your phone is fast enough and performs well enough for you; posting scores of any type is really just a digital pissing contest.

[FROYO]Quadrant and Linpack scores

Hello guys, I've just benched my Captivate after installing the leaked Froyo rom and I'm quite disappointed to say the least....

This has really been beaten to death. Quadrant and Linpack are geared towards Snapdragon.

ntdb said:
This has really been beaten to death. Quadrant and Linpack are geared towards Snapdragon.
Click to expand...
Click to collapse
I agree, and in the end who cares?
If my phone runs fast, runs all apps fast, and does everything i want it to do; then i really don't care what the benchmark says.

The Droid X is only faster in Quadrant because it doesn't use Samsung's crappy RFS filesystem, but that's easy for us to fix with lagfixes. The Nexus is only faster because the JIT is optimized specifically for Snapdragon processors and these benchmark programs favor Snapdragon processors as well. With a lag fix our phones are the fastest thing out there. Don't get too caught up in synthetic benchmarks.

dont worry about numbers as much as real world performance.. turn on flash and go browse pages.. proof is in the pudddin!

I agree it is all about real world use. Not to mention if I am not wrong that it has already been stated that Quad doesnt give 100% accurate results. Thread closed

[Q] Linpack for android..am i lacking?

Ok so i flash theses beautiful roms and now ive tried some testing and currently on my captivate i ran the "linpack for andoid" app and it states:
MFLOPS: 13.982
time: 6.0
Norm Res:5.68
Precision: Inaccurate result
ok so i looked at the top 10 section ounder my phone and their MFLOPS is between 20-50 MFLOPS...So do i need some tweaking?..I mean the phone is good , Rom is awesome...any thoughts?
Captivate 1007
Phoenix 5.2 (2.2.1 JS5)
Speedmod i897 500hz k13c
UGJK4
Lagfix enabled
(r) Tweaks enabled

I wouldn't worry about it. First, your test said inaccurate results, so try running it a few times, though you probably won't get much more out of it. Secondly, most people believe these benchmarks are a load of BS, and I would trends to agree. If the ROM feels snappier and works smoother than stock for you, there really isn't any use in the benchmark scores. I'm running Serendipity 5.11 with the same kernel as you, and I find my scores are in the low 14's- which, as is for you, seems slow compared to the online results. However, my phone supposedly blows the other results out of the water in the Quadrant Standard benchmark, regularly achieving scores over 1500, and I imagine yours would perform similarly, so no, I wouldn't worry at all.
Overall, most of the roms on here achieve faster performance along with better battery life compared to a stock cappy. I suggest trying out as many roms as possible to find the one that fits you best, as everybody has different tastes, and each rom behaves differently for everybody.
Personally, I think Serendipity is something you should try, as it looks friggen sweet as is, and even better IMO with some tweaks. I changed the battery indicator to the android dude, the font to Armani, and use launcher pro over the base rom. Altogether, my phone is super slick and snappy. Oh yeah, it also accesses HSPA networks, so downloads are way quicker than stock (pretty sure your current rom does too).
Sent from my SAMSUNG-SGH-I897 using XDA App

that's about right, repeated tests should get you 14+. it does say inacurate so i dont think you have a problem, just a process running somewhere. the hummingbird lacks a bit in this area and snapdragons excel only in this area. i know it is weird that the nexus one and droid incredible smoke this phone in linpack but it is hardly a thorough benchmark. run quadrant on CM7 when it comes out and see what the hardware is really doing without the samsung influence. despite the low mflops you will see good scores across the board.

Thanks alot for the input everyone...jus curious how gen-pop was adding up... but who cares about the numbers i suppose when my phone is soo [email protected]## cool hahha
Sent from my GT-I9000 using XDA App

Just for the record, I'm on stock Froyo, With no SpeedMod, but with voodoo lagfix and I got better benchmark, linpack and quadrant scores than I did with a custom rom and Speedmod kernel before. Add to that the stability of a native ROM and kernel, and I think you know what I am saying here...

clemmie said:
Just for the record, I'm on stock Froyo, With no SpeedMod, but with voodoo lagfix and I got better benchmark, linpack and quadrant scores than I did with a custom rom and Speedmod kernel before. Add to that the stability of a native ROM and kernel, and I think you know what I am saying here...
Click to expand...
Click to collapse
Hmmm. Intresting. Makes sense. Whered ya get the stock from..curious about the release tomorrow for At&t. Think i might try some configs with it.
Sent from my GT-I9000 using XDA App

Low Quadrant Standard Test Score

Hi guys,
I've just run a Quad Standard test on my N1 running CM7 RC2 and am getting a score of 1199, which is lower than even the stock 2.2. I've tried with SetCPU ON & OFF, but got pretty much the same score?
A while back, I've flashed the RODS MIUI ROM & the WM Kernel (1152MHz) and ran the test only to get a score of 1192.
Wonder what could be wrong??

It's a synthetic benchmark and therefore meaningless. Does the phone run ok, does it feel like there's a problem?
The only thing Quadrant is good at measuring is how well a ROM is optimised for Quadrant

The phone runs absolutely fine. Its not like i have any issues with it, but just wanted to compare how it performs with different ROM's.

karthik247 said:
The phone runs absolutely fine. Its not like i have any issues with it, but just wanted to compare how it performs with different ROM's.
Click to expand...
Click to collapse
Best to break out the stopwatch and perform some real world tests. They're the only ones that matter

The only major difference i noticed after switching to MIUI from CM7 is that booting is super fast. Besides that, everything else felt pretty much the same.
OFF TOPIC
Does anyone know how to get rid of the power widget on the notification bar?

The option is in the CM settings which can be found in the usual settings

I noticed this too when i ran the benchmark, but simply dismissed it because its not the final version of the rom, and just a RC

DirkGently1 said:
The option is in the CM settings which can be found in the usual settings
Click to expand...
Click to collapse
I meant in the MIUI ROM.
Also wanted to know which kernel is the better among Pershoot and WM?
After using the phone with MIUI for a couple of hours now, figured out two issues.
1. When im getting a call, the trackball starts flashing and only after a good 2-3secs does the ringer go off.
2. And while playing music videos, the audio-video sync doesnt seem to be perfect. Its as if the phone is lagging a wee bit. Could this be cuz i only got around 40mb of free space on the device??

Quadrant scores, IMO, mean nothing. They give you a numerical value on the specs and capabilities thattthe phone can do under certain situations but they don't give you any real world numbers.
Yes the scores on my 2.3.3 N1 were "low" as. Well but how do you explain it being just as fast (no exaggeration here) as a stick Atrix? I had both and took the Atrix back.
The Atrix has amazing specs and its hardware is awesome, but as an overall feel I didn't like it, the whole experience didn't feel fluid to me.
All in all, quadrant scores are good for testing stock phones and comparing specs to each other, but you should by no means use that to judge the quality or value of a phone.
That would be like buying a car off of eBay by only comparing specs and stuff written on paper; you ddon't have a feel for the car.
Sent from my Nexus One using XDA Premium App

[Q] Best antutu scores on roms?

Hi, i went down quite a lot of pages and did not find any antutu score tests on galaxy s.
I was just wondering whats the best ones in what rom's and what kernels. I tried to google i9000 antutu best scores but seems there was not really that many hits and best scores i found was like 4k what sound quite a lot but not sure how legit those are when there was no pics.
I mean my friend got a galaxy note and it get a bit over 7k point and then reading more the damn old sucker galaxy s2 best with pic proof is like 8k.
Was just wondering how my fine old faithful galaxy s can do. I got a decent gingerbread rom and i get a bit over 3k without OC. Can't remember how much more i got with ICS OC'd to 1,4ghz. it was over 3k too tough but not remembering how much above.
Would be nice if you can post your roms that score over 3k and what roms + kernels you are using and how much OC you done. I mean the i9000 is not the fastest phone by far at this point but would be intressed to see if people got how high antutu scores.

Nowadays benchmark doesnt mean anything. There's many ways to cheat, and even if those score were honest it doesn't matter much. What does matter is real life performance

Oh antutu score can be fixed too these days? I mean i now the quadrant score has been always a bit question mark and i heard lots of cheating in it. Well i was just wondering the honest score. I'm trying to find a decent fast rom and the better score in benchmarks the less processor power it uses on stuff and that means a bit better battery life too.. well not always.
I'm just trying to get all out of my sgs before sgs3 comes out.. i must say i just love t his phone.. when i had a fast rom where it worked stable at 1.4ghz it was as fast as iphone 4s in same internet pages on stock browser.
But if people could post the LEGIT non cheated scores it would be better than the cheating ones lol

an0nym0us_ said:
Nowadays benchmark doesnt mean anything. There's many ways to cheat, and even if those score were honest it doesn't matter much. What does matter is real life performance
Click to expand...
Click to collapse
+1. SGS with Froyo and EXT2 lagfix got a much higher score in Quadrant, but with ICS the experience is much better.

So the real question is what ROMs have given the best real life performance for you?

For me, it's 3827( on Antutu ) ;D with TiramiSlim RC2.0