The left picture was captured from: http://www.youtube.com/watch?v=JZ6i1RAJwD4
and the right one was captured from: http://www.youtube.com/watch?v=ilx_cpGZczM
Both were captured at the last frame of Quadrant 3D test.
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
SGS is definitely better than droid X in 3D test.
I observed this test carefully, and saw that Galaxy S seriously fell behind droidx in I/O Database write test, which might related to slow internal SD speed. That's why the sgs got lower score in quadrant test.
Hmm so I wonder what would have happened if he applied the stalling fix, what score would have been achieved on the SGS. This comforts me in buying the SGS.
I will take very good 3d performance over a small difference in processor speed any day.
Not trying to sound like a newb but what exactly do you benefit from by having good 3D performance?
djsmvp said:
Not trying to sound like a newb but what exactly do you benefit from by having good 3D performance?
Click to expand...
Click to collapse
The games, man, smooooth running.
On my SGS with r2 rom i'm having average 850 points at Quadrant.
And how the hell moto x is getting 1131?! LOOOL
There have been some talking about the SGX not having 2D graphics acceleration, but in 2D tests (at min 2:11 in the first video, and 1:39 in the second one), we can see that Galaxy S has a clear lead. 8FPS across all the test VS 5 to 6 FPS in the DROID X.
In Linpack with measures CPU performance, Galaxy S has a score of 8.458 MFLOPS VS 8.19 in the DROID X (in line with Samsung claim that the Hummingbird if about 5 to 10% faster than a stock Cortex A8)..
The slow NAND performance seems to be the only explanation to the poor results in Quadrant when compared to DROID X. It isn't certainly the SoC that is slowing down the Galaxy S.
BTW: The Samsung Galaxy S seems to be capped at 56FPS in 3D.. Neo Core, Quadrant, Etc.. etc.. Every 3D bench seem to stop at 56 FPS. This makes sense since more FPS wold only hit more the battery, not improve game experience.. But if this is true, this cap is hidding an even greater difference in 3D performance because the benchmarks are measuring an soft cap, and not the GPU limit.
djsmvp said:
Not trying to sound like a newb but what exactly do you benefit from by having good 3D performance?
Click to expand...
Click to collapse
Don't you want a phone that can play games as well as an iPhone but not be locked to Steve Job's rule?
When I look at the speed of a phone, I often look at how fast the GPU is. My touch diamond didn't have a driver installed to handle the GPU and made for a crappy slow experience even on the UI.
Related
Hi, today i've installed quadrant benchmark app, my nexus one score is very low, only 770, it's behind n1 with 2.2, droid x and galaxy s...i'm wondering why! My flashed rom is this one:
http://forum.xda-developers.com/showthread.php?t=714184
1351 for Me. Do you have a lot of windows open on your browser?
maybe is time for a different room
1520 on CM V6.0.0-RC2
1495 for CM 6.0.0 RC2
mrbkkt1 said:
1351 for Me. Do you have a lot of windows open on your browser?
Click to expand...
Click to collapse
I've tried after a reboot and nothing changes...
that rom is a stock with few mods, it's very strange!
Did you do the Pandora/streaming music audio quality fix? If so that causes your phone to score a lot lower in quadrant. In the benchmark it checks ACC encoding and decoding, and the fix for the audio quality causes those two tests to run significantly slower. Even so, the general speed of the phone is unaffected.
1748 on rod's rom with wildmonks kernel
+1 to the "get CM6 RC2" recommendations. I am on it, and I scored 1542 on my 1.113 GHz N1 running CM6RC2, with SetCPU on "interactive."
1657 on Kang-O-Rama 1.0b1 SP1
Flashed to Wildmonk's latest 800mV BFS kernel, and I got 1805. This is a very nice kernel!
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
ManticoreX said:
Did you do the Pandora/streaming music audio quality fix? If so that causes your phone to score a lot lower in quadrant. In the benchmark it checks ACC encoding and decoding, and the fix for the audio quality causes those two tests to run significantly slower. Even so, the general speed of the phone is unaffected.
Click to expand...
Click to collapse
Dude you found the point
Now i must found out how to remove that fix, that i don't even need
well if that affect just the score of the benchmark i don't mind keeping it as it is obviously!
Vanilla Nexus One, except iR Kernel, latest .34, 900-something mV.
1577 on Quadrant. SetCPU on userspace, 998 Mhz min and max.
Glad that solved it. I'm not sure why this thread became a pissing contest for people's benchmark scores. Anyways the fix shouldn't provide any real world slowdown as far as I know of, and it makes Pandora sound a heck of a lot better.
I'm almost getting 1800 quadrant..
are you sure you're running on Android 2.2? I think 2.1 got these low scores
ManticoreX said:
Glad that solved it. I'm not sure why this thread became a pissing contest for people's benchmark scores. Anyways the fix shouldn't provide any real world slowdown as far as I know of, and it makes Pandora sound a heck of a lot better.
Click to expand...
Click to collapse
But i don't use pandora, so who cares?
I've posted this problem in the thread of the rom i use and the dev have already posted a new version that remove that fix (removing a fix for fixing a bug)
1477 was the highest score I got.
Stock Froyo.
I ran these apps to see what this device was capable of and I'm impressed. I know scores isn't everything but the device has a very good built quality. It runs very quick and smooth. I was not expecting this when I bought it for my younger brother. It doesn't feel like you are using a Mid-Range phone as it's categorized as.
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Sent from my Droid Incredible using XDA App
I have been saying this since before it was released. This phone has the same TI OMAP 3630 as the droid 2 and droid x just clocked at 800MHz instead of 1GHz. I think it's even the same screen as the droid 2.
I think it is the same screen. This phone is definitely going to be underestimated. If Motorola ever updates it to 2.2 it will be a contender against all current high end phones. Can some devs look into overclocking or making a recovery file for this phone.
I scored a 17.25 and 1443 on quadrant. Running Bravo at 1200/300 63sel ondemand. The phone will lockup if you run it at 1200 performance with no min and stock sel. FYI
photobuddha said:
I scored a 17.25 and 1443 on quadrant. Running Bravo at 1200/300 63sel ondemand. The phone will lockup if you run it at 1200 performance with no min and stock sel. FYI
Click to expand...
Click to collapse
Are you running 2.1 or 2.2? I've gotten 1609 with 1.5GHz on 2.2
2.2 What did you use to get the core to 1.5?
photobuddha said:
2.2 What did you use to get the core to 1.5?
Click to expand...
Click to collapse
Woops...I have a feeling I made a typo... I think it was either 1.05GHz or 1.1GHz. But I don't really remember. I highly doubt it was 1.5GHz tho.
heydabop said:
Woops...I have a feeling I made a typo... I think it was either 1.05GHz or 1.1GHz. But I don't really remember. I highly doubt it was 1.5GHz tho.
Click to expand...
Click to collapse
I have run at 1.05GHz stable so it was probably close to that area.
Managed to squeeze out 16.657 on Linpack @1200 MHz
I take that back, I got 19.679 MFLOPS with the newest version of Linpack.
1.2ghz @ 62 vsel.
HTC Wildfire
my HTC Wildfire with Cyanogenmod 9 - 2822 points in Linpack
Our phone is better than galaxy nexus lol
Sent from my MB520 using XDA App
Saw this now on engadet...could it be the phonethat keeps me awway from sammy?
http://www.engadget.com/2011/03/16/htc-shooter-appears-for-sprint-with-android-2-3-2-qhd-screen-an/
God I hope.
Adreno 220, MEH.
http://www.glbenchmark.com/phonedetails.jsp?D=HTC+Shooter&benchmark=glpro20
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
So its not even half as fast as the PowerVr SGX543MP2. Pass.
Edit:
http://www.glbenchmark.com/phonedetails.jsp?D=Motorola+ATRIX+4G+MB860&benchmark=glpro20
SLIGHTLY faster than Tegra 2.
I really have to see how this phone turns out. I think I'll wait awhile before I make the jump. I want to see how smooth it is, the battery life, and also which devs get this phone, because if all the Evo devs & Epic devs move to this phone then I know what I'm getting. But also I'm thinking about the Nexus S too, decisions, decisions
Sent From My Command Center... (aka basement)
I might make the jump. It looks niiiiiiiice. We shall see.
Sent from my SPH-D700 using XDA Premium App
muyoso said:
Adreno 220, MEH.
http://www.glbenchmark.com/phonedetails.jsp?D=HTC+Shooter&benchmark=glpro20
So its not even half as fast as the PowerVr SGX543MP2. Pass.
Edit:
http://www.glbenchmark.com/phonedetails.jsp?D=Motorola+ATRIX+4G+MB860&benchmark=glpro20
SLIGHTLY faster than Tegra 2.
Click to expand...
Click to collapse
what exactly are u showing...n9othing in therehas anything to do with the adreno 220
imtjnotu said:
what exactly are u showing...n9othing in therehas anything to do with the adreno 220
Click to expand...
Click to collapse
The first link is the phone in question. And it gives a score.
This is my previous post in story form:
The HTC Shooter has an Adreno 220. This is a link to a GLbenchmarks of the HTC Shooter. Look at the score, 22.7fps. Now check out the iPad2 running a larger resolution and scoring DOUBLE the HTC Shooter. Meh. I will wait for a phone running the GPU the iPad2 uses or better. Edit: Here is a Tegra 2 phone with the same resolution as the HTC Shooter for comparison.
muyoso said:
The first link is the phone in question. And it gives a score.
This is my previous post in story form:
The HTC Shooter has an Adreno 220. This is a link to a GLbenchmarks of the HTC Shooter. Look at the score, 22.7fps. Now check out the iPad2 running a larger resolution and scoring DOUBLE the HTC Shooter. Meh. I will wait for a phone running the GPU the iPad2 uses or better. Edit: Here is a Tegra 2 phone with the same resolution as the HTC Shooter for comparison.
Click to expand...
Click to collapse
The gpu alone isnt everything. Look at the optimus 3d, it scored higher than tegra devices and this device with the our gpu. Any why are you comparing the ipad 2, we are talking smartphones here. Currently no smartphone houses this gpu, only tablets and psp. This gpu might never even make it into a phone. the comparison is pointless.
Here's something I noticed while testing my phone in smart bench. I dialed my CPU down to 816mhz and 912mhz and look at these scores
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Then I set it back to 1ghz and look at the scores.
Doesn't make sense. We need 2.3(2.4) to truely run out dual core at its best.
But thats just my 2 cents
Sent from my Atrix
drock212 said:
Here's something I noticed while testing my phone in smart bench. I dialed my CPU down to 816mhz and 912mhz and look at these scores
View attachment 591817
View attachment 591818
Then I set it back to 1ghz and look at the scores.
View attachment 591819
Doesn't make sense. We need 2.3(2.4) to truely run out dual core at its best.
But thats just my 2 cents
Sent from my Atrix
Click to expand...
Click to collapse
strange..!!
I find I get better scores on smartbench when I have tons of apps running and less free ram, how odd is that???
These benchmark tools are bogus. In the end what really matters is your experience, do you feel it fast? So it's fast...
drock212 said:
Here's something I noticed while testing my phone in smart bench. I dialed my CPU down to 816mhz and 912mhz and look at these scores
View attachment 591817
View attachment 591818
Then I set it back to 1ghz and look at the scores.
View attachment 591819
Doesn't make sense. We need 2.3(2.4) to truely run out dual core at its best.
But thats just my 2 cents
Sent from my Atrix
Click to expand...
Click to collapse
Are you running single tests or multiple?
I've noticed the same results and thought it quite strange and I ran multiple tests. Its interesting also that the more tests you run the better the scores get until a certain amount of times, around 6 or so on mine, that the scores drop dramatically to a lower score than the first run score.
Sent from my MB860 using XDA App
Benchmarks need to be repeatable for them to be reliable. Any outfit worth its salt does benchmarks on a freshly installed system with all unnecessary services disabled and nothing running etc.
Otherwise you're going to get some unseen interaction that will screw with your benchmark result.
Lieutenant_Dan said:
Are you running single tests or multiple?
Click to expand...
Click to collapse
Ran multiple test to make sure the results were consistent and always got the same results
But thats just my 2 cents
Sent from my Atrix
Remember all kinds of stuff comes into factor. Heat from multiple tests, heat from charging, heat from pocket, rebooting before test, less apps being used, data turned off... and tons more. You cant really compare tests back too back, you must run tons of them with the same variables and take a median not a mean.
well i got my nexus 7 a few days ago and im enjoying it so far. my question is this: are the quadrant scores supposed to be low? im getting 3450, well below the asus transformer and htc one x. is this normal or is it just me?
edward650 said:
well i got my nexus 7 a few days ago and im enjoying it so far. my question is this: are the quadrant scores supposed to be low? im getting 3450, well below the asus transformer and htc one x. is this normal or is it just me?
Click to expand...
Click to collapse
stock? testing at what speed? if your stock, that means you are benching at highest/lowest cpu, not highest/highest. which lets your device scale. quadrant doesnt tax your device enough for all four cores to kick in, i bet its even only benching with one core too. theres no way to know what cpu speed or how many cores are being used in the benchmark, so your scores will be random at best. root it, set your cpu speed to highest/highest, turn off tegra hotplug so that all four cores are used, then benchmark.
simms22 said:
stock? testing at what speed? if your stock, that means you are benching at highest/lowest cpu, not highest/highest. which lets your device scale. quadrant doesnt tax your device enough for all four cores to kick in, i bet its even only benching with one core too. theres no way to know what cpu speed or how many cores are being used in the benchmark, so your scores will be random at best. root it, set your cpu speed to highest/highest, turn off tegra hotplug so that all four cores are used, then benchmark.
Click to expand...
Click to collapse
yes stock and unrooted. well this answered my question! thank you very much
simms22 said:
stock? testing at what speed? if your stock, that means you are benching at highest/lowest cpu, not highest/highest. which lets your device scale. quadrant doesnt tax your device enough for all four cores to kick in, i bet its even only benching with one core too. theres no way to know what cpu speed or how many cores are being used in the benchmark, so your scores will be random at best. root it, set your cpu speed to highest/highest, turn off tegra hotplug so that all four cores are used, then benchmark.
Click to expand...
Click to collapse
How do you turn off tegra hotplug?
sayeef said:
How do you turn off tegra hotplug?
Click to expand...
Click to collapse
the kernel you are using has to have the option to do so built into it(most custom kernels do). for example..
tegra hotplug on(default)
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
all four cores are active
two cores active
also, turning of fsync will increase benchmark score(especially i/o)