• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Benchmark your computer with Handbrake

Page 9 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Handbrake 0.9.9.5530 -64bit Version


i73770k@3.5GHZ Windows 7 64
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[06:03:01] reader: done. 1 scr changes
[06:03:02] work: average encoding speed for job is 226.109848 fps

i73770k@4.2GHz Windows 7 64
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[10:01:08] reader: done. 1 scr changes
[10:01:08] work: average encoding speed for job is 241.328156 fps

i73770k@3.5GHZ Windows 8.1 64
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[10:14:36] reader: done. 1 scr changes
[10:14:36] work: average encoding speed for job is 220.224060 fps

i73770k@4.2GHz Windows 8.1 64
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[10:11:05] reader: done. 1 scr changes
[10:11:06] work: average encoding speed for job is 240.214935 fps
 
Last edited:
Just for comparison, I ran this on my tablet 😛

HandBrake svn5632 (Nightly Build) - 32bit Version
CPU: Intel(R) Atom(TM) CPU Z2760 @ 1.80GHz
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 Cache64
[20:26:37] work: average encoding speed for job is 16.524916 fps
 
Using the same version as the OP on the machine in my sig:
work: average encoding speed for job is 286.440399 fps.
Oh, other stuff: 9-9-9-24-2T MMX2 SSE2Fast SSSE3 SSE4.2

Finally, nice bump using the nightly buid->work: average encoding speed for job is 313.551605 fps

Too bad it is July, I'd be about 20 fps faster in the winter 😛
 
Last edited:
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: Intel(R) Core(TM) i5-3330 CPU @ 3.00GHz
Ram: 3769 MB, Screen: 1680x1050
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[05:49:11] reader: done. 1 scr changes
[05:49:12] work: average encoding speed for job is 144.091934 fps
 
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
Ram: 16333 MB, Screen: 1920x1080

[21:08:45] starting job
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
[21:09:56] work: average encoding speed for job is 203.881424 fps
 
CPU clocked 2 bins up with Intel XTU.
HandBrake svn5632 (Nightly Build) - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i7-4700MQ CPU @ 2.40GHz
Ram: 16271 MB, Screen: 1920x1080

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI2
[00:04:29] work: average encoding speed for job is 240.385437 fps

MSI GT60 2OC, GTX770M. Samsung 840pro 256GB.
 
Jodell88 said:
Pretty sure he isn't.
Click to expand...

I did exactly what the instructions say in the original post. Downloaded Handbrake, the video and set the preset. Other than that I just started Handbrake and ran it, made no changes in format or settings what-so-ever.

Once I get back home to my desktop I will re-run this benchmark, double checking everything to be sure. I will do the same on my notebook as well.
 
Saffron said:
I did exactly what the instructions say in the original post. Downloaded Handbrake, the video and set the preset. Other than that I just started Handbrake and ran it, made no changes in format or settings what-so-ever.

Once I get back home to my desktop I will re-run this benchmark, double checking everything to be sure. I will do the same on my notebook as well.
Click to expand...

Something is up 😛

The highest score for a 3570 is

16 cmdrdredd 236.807419 i5-3570K 4500 2133

And your score is better than that plus a 3930k at 4.3Ghz.
 
Yeah it makes no sense. There are no controls for this testing. Oh well...I know my system is performing optimally when I use other specific CPU and GPU tests that match up to expected results from reputable hardware sites.

I may try this again later and see what I can figure out.
 
cmdrdredd said:
Yeah it makes no sense. There are no controls for this testing. Oh well...I know my system is performing optimally when I use other specific CPU and GPU tests that match up to expected results from reputable hardware sites.

I may try this again later and see what I can figure out.
Click to expand...

I don't think there is a problem on your end.

Your numbers match up fine with the rest using that chip.

And other than using the standard build or nightly and checking the andriod preset you don't really need any more controls this is a simple benchmark.
 
Makaveli said:
I don't think there is a problem on your end.

Your numbers match up fine with the rest using that chip.

And other than using the standard build or nightly and checking the andriod preset you don't really need any more controls this is a simple benchmark.
Click to expand...

There is no guarantee that someone is using said preset is more what I meant. Anyway I'll try both builds again and see if anything changes. I am betting on not seeing anything of significance in regards to my results but I'll try anyway.
 
cmdrdredd said:
There is no guarantee that someone is using said preset is more what I meant. Anyway I'll try both builds again and see if anything changes. I am betting on not seeing anything of significance in regards to my results but I'll try anyway.
Click to expand...

Agreed 🙂

The guarantee tho is looking at the numbers from others that did use the preset and if the numbers are way off we know he did something wrong no investigations needed.

And you will see a increase with the nightly almost every chip has minus the C2Q.
 
Release version 0.9.9.5530
work: average encoding speed for job is 226.826920 fps

Nightly Build 5639
work: average encoding speed for job is 241.218491 fps

If I open handbrake, load the video, and press start with the preset set to normal I get over 500fps. So I tend to think people with absurdly high fps results are not selecting the correct preset.
 
Code: 
HandBrake svn5639 (Nightly Build) - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: AMD A8-3500M APU with Radeon(tm) HD Graphics @2.8GHz
Ram: 5610 MB, Screen: 1366x768
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSEMisalign LZCNT
[20:34:34] work: average encoding speed for job is [B]93.892029 fps[/B]
 
Tried the nightly build and performance was worse. Standard build was about 330fps while the nightly build was 296fps.
 
i7 920 @ 4.2GHz, RAM @ 1600 9-9-9-24 2T:

official 0.9.9.5530: [23:48:07] work: average encoding speed for job is 214.667252 fps

nightly 5639: [23:56:29] work: average encoding speed for job is 228.367584 fps
 
Last edited:
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: Intel(R) Core(TM) i7-3610QM CPU @ 2.30GHz
Ram: 8094 MB, Screen: 1920x1080

Android preset:

2nd run (accidentally deleted my first run log, was ~170 fps but had a ton of other programs running in the background)

x264 [info]: using SAR=43127/43200
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[01:26:50] reader: done. 1 scr changes
[01:26:50] work: average encoding speed for job is 190.674545 fps

Edit:

Ran a 3rd time

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
x264 [info]: profile Main, level 3.0
[01:43:41] reader: done. 1 scr changes
[01:43:42] work: average encoding speed for job is 191.453964 fps

Side Note, Only using 37.1 watts during test, Also the Processor was turbo'd to 3092 Mhz on all 4 cores at time of testing

System
Lenovo Y580 Core I7 3610QM @ 2.3 Ghz Nvidia GTX 660m 8gb @1600Mhz
 
Last edited:
moonbogg said:
Tried the nightly build and performance was worse. Standard build was about 330fps while the nightly build was 296fps.
Click to expand...

Something must be wrong, because we have the same processor I believe, and I got a 11% increase in performance with the nightly build.
 
Well, I have to add a Clarkdale i3 to the mix.


i3-530 @ 2.93Ghz

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2
[20:38:12] work: average encoding speed for job is 72.032059 fps

HT off … 57.771496 fps

i3-530 @ 3.5Ghz … 84.808067 fps

HT (hyperthreading) improves performance 24.7% … 🙂

Clarkdale i3-530 outruns the (Ivy Bridge) G2020@3.0 -- 69.02 fps … thanks to HT.

With mild OC (3.5Ghz), i3-530 is faster than i3-2100@3.1 -- 84.42 fps

It sure sucks that Intel locked down overclocking on non-K CPU's and there are no K versions of i3, G or Pentiums.
 
Blastman said:
HT (hyperthreading) improves performance 24.7% … 🙂
Click to expand...

on the i3 2100 the improvement I got was a little bit lower,

no HT 74.638855 fps
default (HT) 89.590996 fps

about the overclocking, I agree, it's a shame, sandy bridge can easily work at around 4.5GHz, some i3/Pentium at that clock could perform quite well.
 
There was a test a while back comparing Lynnfield vs Sandy Bridge behardware and they included results with and without HT. With no HT, SB averaged 13.2% faster than Lynnfield, with HT SB only averaged 11.3% faster. So, the older Nehalem based core was benefiting more overall from HT than SB, closing the performance gap ~ 2% overall. In a couple of applications, Cinema4D and 3ds Max, the Lynnfield based CPU benefited from HT more than SB by 6.4% and 6.2%. Although, there were a couple of applications where SB benefited slightly more from HT.
 
Hmm, Makaveli pipped me on the line with that sweet Mushkin Ram - they are my favorite RAM maker (awesome customer service), but I cheaped out going from 6 G to 12 GB (which annoyingly doesn't want to run @ 1T).
 
FX-4300 @ 5.0 GHz

work: average encoding speed for job is 144.632568 fps


Will test my A10 and laptops too (i5-580m and C2D T7500)
 
Last edited:
Ajay said:
Hmm, Makaveli pipped me on the line with that sweet Mushkin Ram - they are my favorite RAM maker (awesome customer service), but I cheaped out going from 6 G to 12 GB (which annoyingly doesn't want to run @ 1T).
Click to expand...

🙂

They are also my favourite.

I bought the 6GB set in 2009 then contacted them directly and special ordered the identical set in 2011 to a local computer store close to me.

Agreed great customer service.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top