• Guest, The rules for the P & N subforum have been updated to prohibit "ad hominem" or personal attacks against other posters. See the full details in the post "Politics and News Rules & Guidelines."

Benchmark your computer with Handbrake

Page 15 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

SlowSpyder

Lifer
Jan 12, 2005
17,305
998
126
Just wanted to say that I think I killed my FX 9370 while running this bench. :D But right up until my machine froze, never to boot again, I was getting 250FPS @ 5.1GHz.

RIP FX9370, I hardly knew ya! :'(
 

Magic Carpet

Diamond Member
Oct 2, 2011
3,265
75
91
Just wanted to say that I think I killed my FX 9370 while running this bench. :D But right up until my machine froze, never to boot again, I was getting 250FPS @ 5.1GHz.

RIP FX9370, I hardly knew ya! :'(
Just "wow". I feel deeply saddened for your loss.

Are you sure, however, it's the chip and not the power delivery of the board? Did you experience any smell at all? Tragic loss indeed, but hey, it was good while it lasted :)
 
Last edited:

BallaTheFeared

Diamond Member
Nov 15, 2010
8,128
0
71
Just wanted to say that I think I killed my FX 9370 while running this bench. :D But right up until my machine froze, never to boot again, I was getting 250FPS @ 5.1GHz.

RIP FX9370, I hardly knew ya! :'(
Grab a i5-4670k next so you can get 320 fps and not kill it :p


Sorry for your loss, at least you beat it down into the dirt the best way possible, over achieving.
 

SlowSpyder

Lifer
Jan 12, 2005
17,305
998
126
Just "wow". I feel deeply saddened for your loss.

Are you sure, however, it's the chip and not the power delivery of the board? Did you experience any smell at all? Tragic loss indeed, but hey, it was good while it lasted :)
It is possible it is the motherboard, I'll check the codes tonight and see what I can find. But my hunch is the CPU.


Grab a i5-4670k next so you can get 320 fps and not kill it :p


Sorry for your loss, at least you beat it down into the dirt the best way possible, over achieving.

Yea, but then I'd just be another guy with an overclocked i5/i7... that won't satisfy the fanboy in me. ;)
 

SlowSpyder

Lifer
Jan 12, 2005
17,305
998
126
If you killed the board I dont think you'd see codes.

Just to verify, you cleared CMOS right?

Well, this is a bit embarrassing. I tried a few things yesterday, last being I yanked the CMOS and pressed the power button to clear any residual power, then replaced it and tried to boot. No signal to the monitor still.

Well, I looked again just a little while ago, the DVI cable came out when I pulled the CMOS battery (my 7970 is in the 2nd PCIE slot because of how my water tubes are run, covering the CMOS battery). So when I replaced the 7970 and battery, the cable to my monitor moved and wasn't connected because I didn't tighten the screws.

So, she's back. Now the only question is, do I accept a lower clock speed? Or more voltage? :twisted:
 

Magic Carpet

Diamond Member
Oct 2, 2011
3,265
75
91
It is decent perf per watt compared with fellow AMD watt burners, but not really competitive with Intel stuff. Haswell big quads are using 4-5 times more system power but encoding 6-7 times faster. So perf per watt is up to 50% higher on Intel stuff.
Haswell is more efficient in this particular task, no questions asked. However, If all you do is light browsing, casual video watching, etc. Jaguar platform is quite a bit more economical. For any content creation, it's seriously underpowered, though.

New entry:

HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i5-4570S CPU @ 3.60GHz
Ram: 3958 MB, Screen: 1680x1050
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI1 BMI2
[01:29:20] work: average encoding speed for job is 193.783203 fps

HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i5-4570S CPU @ 3.60GHz
Ram: 7862 MB, Screen: 1680x1050
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI1 BMI2
[02:52:29 work: average encoding speed for job is 201.937912 fps
 
Last edited:

TerryMathews

Lifer
Oct 9, 1999
11,474
2
0
Well, this is a bit embarrassing. I tried a few things yesterday, last being I yanked the CMOS and pressed the power button to clear any residual power, then replaced it and tried to boot. No signal to the monitor still.

Well, I looked again just a little while ago, the DVI cable came out when I pulled the CMOS battery (my 7970 is in the 2nd PCIE slot because of how my water tubes are run, covering the CMOS battery). So when I replaced the 7970 and battery, the cable to my monitor moved and wasn't connected because I didn't tighten the screws.

So, she's back. Now the only question is, do I accept a lower clock speed? Or more voltage? :twisted:
The way I always overclock is I set the voltage as high as I'm willing to go for that particular process and core, the keep ramping the speed up until it gets unstable.

Back it down a touch then test for stability. Finally, start turning down voltage and continue testing for stability.
 

Conroe

Senior member
Mar 12, 2006
324
32
91
Had to try this on my LGA 771 to 775 modded E5450 in my MSI p35 Platinum

E5450 @ 4.2 GHz

HandBrake 0.9.9.5530 - 32bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: Intel(R) Xeon(R) CPU E5450 @ 3.00GHz
Ram: 4095 MB, Screen: 1920x1080
...
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 Cache64
...
[18:25:22] work: average encoding speed for job is 204.314743 fps


Dang fast for a seven year old CPU. I still don't have SSE4 working. I need to mod the BIOS. I don't know how I got the 32 bit version?
 
Last edited:

philhalo66

Junior Member
Feb 6, 2014
4
0
0
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: AMD Phenom(tm) II X4 955 Processor
Ram: 6143 MB, Screen: 2560x1600

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSEMisalign LZCNT
[21:02:27] work: average encoding speed for job is 93.051430 fps
 

Tweakin

Platinum Member
Feb 7, 2000
2,532
0
71
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: Intel(R) Core(TM) i5-4670K CPU @ 3.40GHz
Ram: 16336 MB
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI1 BMI2
x264 [info]: profile Main, level 4.0
[09:06:42] reader: done. 1 scr changes
[09:06:42] work: average encoding speed for job is 401.361115 fps
 

monstercameron

Diamond Member
Feb 12, 2013
3,829
1
0
a10-7850k gpu
Code:
HandBrake svn6091 (Nightly Build) - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
Ram: 7108 MB, Screen: 1920x1080
[08:28:13] CPU: 
[08:28:13]  - logical processor count: 4
[08:28:13] OpenCL device #1: Advanced Micro Devices, Inc. Spectre
[08:28:13]  - OpenCL version: 1.2 AMD-APP (1411.4)
[08:28:13]  - driver version: 1411.4 (VM)
[08:28:13]  - device type:    GPU
[08:28:13]  - supported:      YES
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX XOP FMA4 FMA3 LZCNT BMI1
x264 [info]: profile Main, level 3.0
[08:28:14] dxva2:Available decoder output format 61 (AV_PIX_FMT_DXVA2_VLD)
[08:28:14] Scaling With OpenCL
[08:28:14] Using Zero Copy
[08:29:58] reader: done. 1 scr changes
[08:29:59] work: average encoding speed for job is 136.423447 fps
a10-7850k cpu
Code:
HandBrake svn6091 (Nightly Build) - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
[08:32:01] CPU: 
[08:32:01]  - logical processor count: 4
[08:32:01] OpenCL device #1: Advanced Micro Devices, Inc. Spectre
[08:32:01]  - OpenCL version: 1.2 AMD-APP (1411.4)
[08:32:01]  - driver version: 1411.4 (VM)
[08:32:01]  - device type:    GPU
[08:32:01]  - supported:      YES
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX XOP FMA4 FMA3 LZCNT BMI1
x264 [info]: profile Main, level 3.0
[08:33:54] reader: done. 1 scr changes
[08:33:55] work: average encoding speed for job is 126.792763 fps
 
Last edited:

Magic Carpet

Diamond Member
Oct 2, 2011
3,265
75
91
Got rid of the boring 4570 chip, this one is much better :whiste:

HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz
Ram: 8120 MB, Screen: 1680x1050

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI1 BMI2
x264 [info]: profile Main, level 3.0
[22:24:02] reader: done. 1 scr changes
[22:24:02] work: average encoding speed for job is 302.333618 fps
 
Last edited:

Tristor

Senior member
Jul 25, 2007
314
0
71
This is the only benchmark where I wished I'd gone with the i7. As they say, there's no replacement for displacement (or more cores/threads).

x264 [info]: using SAR=43127/43200
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZ
CNT BMI1 BMI2
x264 [info]: profile Main, level 3.0
Encoding: task 1 of 1, 99.44 % (249.19 fps, avg 248.05 fps, ETA 00h00m00s)[19:39
:48] reader: done. 1 scr changes
Encoding: task 1 of 1, 99.99 % (249.19 fps, avg 248.05 fps, ETA 00h00m00s)[19:39
:49] work: average encoding speed for job is 248.046432 fps
Encoding: task 1 of 1, 99.99 % (249.19 fps, avg 248.05 fps, ETA 00h00m00s)[19:39
:49] sync: got 14315 frames, 14315 expected
[19:39:49] render: 14315 frames output, 0 dropped and 0 duped for CFR/PFR
[19:39:49] render: lost time: 0 (0 frames)
[19:39:49] render: gained time: 0 (0 frames) (0 not accounted for)
Encoding: task 1 of 1, 99.99 % (249.19 fps, avg 248.05 fps, ETA 00h00m00s)[19:39
:50] h264-decoder done: 14315 frames, 0 decoder errors, 0 drops
x264 [info]: frame I:148 Avg QP:17.06 size: 50673 PSNR Mean Y:46.98 U:51.03
V:51.47 Avg:47.80 Global:46.42
x264 [info]: frame P:5195 Avg QP:21.43 size: 6873 PSNR Mean Y:42.78 U:47.17
V:47.68 Avg:43.67 Global:42.66
x264 [info]: frame B:8972 Avg QP:25.81 size: 1019 PSNR Mean Y:42.87 U:47.08
V:47.64 Avg:43.76 Global:42.60
x264 [info]: consecutive B-frames: 8.7% 18.0% 15.3% 57.9%
x264 [info]: mb I I16..4: 20.7% 0.0% 79.3%
x264 [info]: mb P I16..4: 2.9% 0.0% 4.5% P16..4: 31.1% 13.6% 9.3% 0.0% 0
.0% skip:38.6%
x264 [info]: mb B I16..4: 0.1% 0.0% 0.6% B16..8: 22.4% 2.5% 0.7% direct:
1.3% skip:72.4% L0:36.7% L1:56.1% BI: 7.2%
x264 [info]: coded y,uvDC,uvAC intra: 59.1% 70.2% 46.6% inter: 9.7% 12.4% 2.6%
x264 [info]: i16 v,h,dc,p: 42% 24% 8% 26%
x264 [info]: i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 16% 13% 6% 8% 9% 7% 7% 6%
x264 [info]: i8c dc,h,v,p: 49% 22% 19% 10%
x264 [info]: Weighted P-Frames: Y:4.7% UV:2.7%
x264 [info]: ref P L0: 64.1% 16.3% 13.4% 6.1% 0.2%
x264 [info]: ref B L0: 83.5% 14.6% 1.9%
x264 [info]: ref B L1: 92.4% 7.6%
x264 [info]: SSIM Mean Y:0.9849682 (18.230db)
x264 [info]: PSNR Mean Y:42.882 U:47.155 V:47.692 Avg:43.767 Global:42.648 kb/s:
702.08
[19:39:50] aac-decoder done: 0 frames, 0 decoder errors, 0 drops
[19:39:50] mux: track 0, 14315 frames, 52339031 bytes, 701.95 kbps, fifo 4096
[19:39:50] mux: track 1, 27961 frames, 9542025 bytes, 127.97 kbps, fifo 8192
[19:39:50] libhb: work result = 0

Encode done!

HandBrake has exited.

Just for giggles, I ran it with the nightly as well:

x264 [info]: using SAR=43127/43200
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZ
CNT BMI2
x264 [info]: profile Main, level 3.0
Encoding: task 1 of 1, 99.37 % (258.90 fps, avg 286.21 fps, ETA 00h00m00s)[19:45
:02] reader: done. 1 scr changes
Encoding: task 1 of 1, 99.90 % (258.90 fps, avg 286.21 fps, ETA 00h00m00s)[19:45
:02] work: average encoding speed for job is 286.207611 fps
Encoding: task 1 of 1, 99.99 % (258.90 fps, avg 286.21 fps, ETA 00h00m00s)[19:45
:02] sync: got 14315 frames, 14315 expected
[19:45:02] render: 14315 frames output, 0 dropped and 0 duped for CFR/PFR
[19:45:02] render: lost time: 0 (0 frames)
[19:45:02] render: gained time: 0 (0 frames) (0 not accounted for)
[19:45:02] h264-decoder done: 14315 frames, 0 decoder errors, 0 drops
x264 [info]: frame I:155 Avg QP:16.46 size: 50749
x264 [info]: frame P:5190 Avg QP:21.28 size: 6860
x264 [info]: frame B:8970 Avg QP:25.80 size: 1020
x264 [info]: consecutive B-frames: 8.8% 18.0% 15.3% 57.9%
x264 [info]: mb I I16..4: 20.9% 0.0% 79.1%
x264 [info]: mb P I16..4: 2.8% 0.0% 4.5% P16..4: 31.1% 13.6% 9.3% 0.0% 0
.0% skip:38.8%
x264 [info]: mb B I16..4: 0.1% 0.0% 0.6% B16..8: 22.4% 2.5% 0.7% direct:
1.3% skip:72.4% L0:36.7% L1:56.1% BI: 7.2%
x264 [info]: coded y,uvDC,uvAC intra: 59.9% 70.9% 47.3% inter: 9.7% 12.3% 2.6%
x264 [info]: i16 v,h,dc,p: 42% 23% 8% 26%
x264 [info]: i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 16% 13% 6% 8% 9% 7% 7% 6%
x264 [info]: i8c dc,h,v,p: 49% 22% 19% 10%
x264 [info]: Weighted P-Frames: Y:5.5% UV:3.1%
x264 [info]: ref P L0: 64.1% 16.1% 13.2% 6.3% 0.3%
x264 [info]: ref B L0: 83.5% 14.6% 1.9%
x264 [info]: ref B L1: 92.4% 7.6%
x264 [info]: kb/s:705.70
[19:45:02] aac-decoder done: 0 frames, 0 decoder errors, 0 drops
[19:45:02] mux: track 0, 14315 frames, 52609061 bytes, 705.62 kbps, fifo 4096
[19:45:02] mux: track 1, 27959 frames, 9567413 bytes, 128.32 kbps, fifo 8192
Muxing: this may take awhile...[19:45:02] libhb: work result = 0

Encode done!

HandBrake has exited.
Until the end when it dropped, my average was over 300fps with the nightly. Still, gained 40fps. Shows that software improvements/optimizations make a HUGE difference, even more so than hardware in some ways.
 

Kodiack

Junior Member
Mar 14, 2014
7
0
0
I got QuickSync working alongside my dedicated GPU since I wanted to use it for very large encodes (i.e. raw Blu-ray rips) and streaming. I benchmarked it against my Core i7-4770K.

4770K @4.4GHz:

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI2
x264 [info]: profile Main, level 3.0
[14:37:31] reader: done. 1 scr changes
[14:37:31] work: average encoding speed for job is 293.507782 fps
Enabling QuickSync, and using Best Quality preset:

[14:33:42] qsv_enc_init: using 'hardware (2)' implementation, API: 1.7
[14:34:10] reader: done. 1 scr changes
[14:34:10] work: average encoding speed for job is 509.455475 fps
I'm happy with the performance increase! The possibilities feel endless since I can offload so much work from the CPU!

*EDIT: I would also like to note that the source file and output file are on two separate hard drives, which may also help performance.
 
Last edited:

Aikouka

Lifer
Nov 27, 2001
29,764
516
126
I'm happy with the performance increase! The possibilities feel endless since I can offload so much work from the CPU!

*EDIT: I would also like to note that the source file and output file are on two separate hard drives, which may also help performance.
What are your thoughts on the quality difference between x264 and QuickSync? As I mentioned in a thread in the HTPC sub-forum, I've been messing with it a bit, because like you describe, it can be great for users with dedicated GPUs as it leaves our PCs completely usable.
 

Kodiack

Junior Member
Mar 14, 2014
7
0
0
What are your thoughts on the quality difference between x264 and QuickSync? As I mentioned in a thread in the HTPC sub-forum, I've been messing with it a bit, because like you describe, it can be great for users with dedicated GPUs as it leaves our PCs completely usable.
The quality loss is measurable, but it's not really going to be an issue in most cases. The picture quality is more than acceptable even for quality encodes. When I'm encoding, it's usually because I'm going for a much smaller file size that can be fit onto a mobile device or USB flash drive. You're not really going to see any major differences at that point. If I'm watching at home on my computer, I'm just going to be watching raw, uncompressed MKV rips from Blu-rays. QuickSync is a life saver for my use since it puts no strain on the CPU and it's bloody fast!

For comparison, I'd like to share how The Avengers looked straight from a Blu-ray rip (27.2 GB), and how it looks now after using QuickSync (5.05 GB). (sorry that they're slightly different frames!)

I've been experimenting with various uses of QuickSync for the last few hours and it's definitely something I'm going to be heavily utilizing. I've been able to get it to cooperate quite nicely with Open Broadcaster Software, so I'll be able to stream with virtually no additional CPU load. This will be great for World of Warcraft!

I still see a decent hit to performance when streaming, but that's only because my GPU is extremely bad. I have a Radeon HD 5450 in use because my 7970 died on an international flight. I'll be fitting my computer with a Radeon R9 290 within a week or two, which probably won't even notice the small load placed on the GPU for streaming. Honestly, I'd have just used the integrated HD 4600 instead of the 5450 if it was equipped a dual-link DVI port (I'm pushing 2560x1440). It's been fun to experiment with getting the 5450+HD 4600 to work together, though, and it's been a raging success. This integrated GPU is going to stay enabled for QuickSync after I get the R9 290 for sure.
 

Aikouka

Lifer
Nov 27, 2001
29,764
516
126
The quality loss is measurable, but it's not really going to be an issue in most cases. The picture quality is more than acceptable even for quality encodes. When I'm encoding, it's usually because I'm going for a much smaller file size that can be fit onto a mobile device or USB flash drive. You're not really going to see any major differences at that point. If I'm watching at home on my computer, I'm just going to be watching raw, uncompressed MKV rips from Blu-rays. QuickSync is a life saver for my use since it puts no strain on the CPU and it's bloody fast!
Ah, I encode my rips to help keep the size down. I own a lot of movies, and trying to keep them all at full quality would be very difficult storage-wise... especially when I keep more around than just movies! So, my encoding tends to be for long-time storage. I like how I don't tie down my main machine for QuickSync, but I wouldn't want to waste time with garbage encodes. The problem is that in all the tests that I've done on QuickSync vs. x264, I can't really find a fault with QuickSync. I had a friend check out an episode that was encoded with each encoder, and he had no qualms with either.

For comparison, I'd like to share how The Avengers looked straight from a Blu-ray rip (27.2 GB), and how it looks now after using QuickSync (5.05 GB). (sorry that they're slightly different frames!)
I can't really find much of a fault with the QuickSync encode other than it's a bit blurrier, but that's understandable given it has a far lower bitrate. Oh, and if you want a good tip for how to capture stuff at the same frame, it's pretty easy with Media Player Classic - Home Cinema.


  1. Find the scene you want and pause.
  2. File > Save Image to save a screenshot. It will always be at the source's size!
  3. Navigate > Go To... , and copy the current time listed.
  4. Open the other video file.
  5. Navigate > Go To... , paste the copied time, and hit OK.
  6. File > Save Image
...and you've got the exact same frame with pretty much no effort! :D


I've been experimenting with various uses of QuickSync for the last few hours and it's definitely something I'm going to be heavily utilizing. I've been able to get it to cooperate quite nicely with Open Broadcaster Software, so I'll be able to stream with virtually no additional CPU load. This will be great for World of Warcraft!
I saw that OBS can use QuickSync, but I also saw that it has NVENC support. You talk a bit later on about using AMD cards, so I realize that doesn't really apply. However, I do wonder which one would work better. I assume if NVENC works similar to NVIDIA's ShadowPlay, it might be procedurally simpler if the majority of the work takes place on the video card. That's assuming it works by taking the frame (that goes out to the monitor), sending it to the encoder, and then the resulting encoded image going back to the CPU.

This integrated GPU is going to stay enabled for QuickSync after I get the R9 290 for sure.
I know what you mean... it might put an annoying cursor at the upper left of my main monitor at all times, but even my OCD self can ignore it for fast yet not too shabby encodes.
 

johnny_boy

Junior Member
Sep 29, 2012
24
0
0
AMD A10 5800K downclocked to 3.2GHz. IGP @ 1169MHz. 8GBs of 2133 RAM.
Quote:
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: AMD A10-5800K APU with Radeon(tm) HD Graphics
Ram: 7123 MB, Screen: 1600x1200
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX XOP FMA4 FMA3 SSEMisalign LZCNT BMI1
[23:47:12] work: average encoding speed for job is 92.001625 fps
Looks like handbrake scales almost perfectly with clock speed (at least in this case).

AMD A10-5800K overclocked to 4.3GHz (IGP @ 1013MHz), 8GB DDR3 2133.

HandBrake 0.9.9 - x86_64
OS: Kubuntu 13.10 (kernel 3.14)
CPU: AMD A10-5800K APU with Radeon(tm) HD Graphics
Screen: 1920x1080
x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX XOP FMA4 FMA3 SSEMisalign LZCNT BMI1
x264 [info]: profile Main, level 3.0
[14:08:54] reader: done. 1 scr changes
[14:08:54] work: average encoding speed for job is 121.655495 fps
 

jcniest5

Senior member
Jun 2, 2005
369
0
76
I skipped everything to this last page: Where do I see the result? The program runs like 1/10 of a second and disappear.
 

Engr62

Senior member
May 31, 2001
832
28
91
Got rid of the boring 4570 chip, this one is much better :whiste:

HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.2.9200.0
CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz
Ram: 8120 MB, Screen: 1680x1050

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX AVX2 FMA3 LZCNT BMI1 BMI2
x264 [info]: profile Main, level 3.0
[22:24:02] reader: done. 1 scr changes
[22:24:02] work: average encoding speed for job is 302.333618 fps
Is your CPU overclocked any? My i7-4770K at stock speed only gets 244.437164 using Handbrake 0.9.9.5530 - 64 bit version. I also have 8 Gb of RAM, but I'm running Windows 7.
 

pilot757

Junior Member
Apr 13, 2014
1
0
0
I found this very interesting. I have been wanting better encode speeds in Handbrake. I have an old i7-920. Figuring since it's 4 generations old now it must be time for an upgrade. I ran the test to see how much faster encodes I could get. The results were very surprising.
Code:
HandBrake 0.9.9.5530 - 64bit Version
OS: Microsoft Windows NT 6.1.7601 Service Pack 1
CPU: Intel(R) Core(TM) i7 CPU         920  @ 3.8GHz
Ram: 6135 MB, 800Mhz 9-9-9-24 1T[SIZE=2]   

x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2
x264 [info]: profile Main, level 3.0
[16:34:29] reader: done. 1 scr changes
[16:34:30] work: average encoding speed for job is [/SIZE][B][SIZE=4][COLOR=red][SIZE=4][B]204.372101 [/B][/SIZE]fps[/COLOR][/SIZE][/B]
I would have thought in 4 generations we should be a least double the encoding speeds. Granted, I am overclocked but I'm still around a Haswell i5-4570S performance. It's all just a bit disappointing.
 

Magic Carpet

Diamond Member
Oct 2, 2011
3,265
75
91
Is your CPU overclocked any? My i7-4770K at stock speed only gets 244.437164 using Handbrake 0.9.9.5530 - 64 bit version. I also have 8 Gb of RAM, but I'm running Windows 7.
Of course, it was oc'ed. ~240 is what you get running at stock speed, so worry not :)

I would have thought in 4 generations we should be a least double the encoding speeds. Granted, I am overclocked but I'm still around a Haswell i5-4570S performance. It's all just a bit disappointing.
Yeah, we haven't seen substantial performance advances since Conroe. Yet that 4570S provides some of the best performance per watt available today. I had this chip and was able to cool it passively without issues. I bet your OC'ed 920 needs quite a bit of more cooling ;)
 

ASK THE COMMUNITY