GPU Transcoding Throwdown: Elemental's Badaboom vs. AMD's Avivo Video Converter
by Anand Lal Shimpi & Derek Wilson on December 15, 2008 3:00 PM EST- Posted in
- GPUs
ATI Catalyst 8.12 Changes and Bug Fixes
As far as the 8.12 drivers themselves go, we have seen a few bug fixes. Far Cry 2 now supports CrossFire without requiring 4xAA to be enabled for it to work (and the rest of the FC2 hotfix has been incorporated as well). The stability and performance issues we noticed on Nehalem systems have been improved. Game tests make sense and behave more or less the way we expect they should.
Until this driver, using ATI graphics hardware in a Core i7 system was unstable and buggy, especially in non-Intel X58 boards. The worst problems were with CrossFire, but we had single card issues as well. When we began testing on Nehalem, we wanted to use a Radeon HD 4870 1GB in our launch article. In trying to make it work, Anand lost almost a week in tests that to just be thrown away because of the stability and performance issues with AMD hardware in the i7 system. We had to switch over to NVIDIA hardware to get the launch article done. Normally we don't go into detail about all the trouble we have when testing prerelease products, but even after launch we continued to have the same issues. Initially 8.10 was the problem, then the Far Cry 2 hotfix didn't really fix much. It almost seemed like 8.11 made things worse and the hotfixes following 8.11 didn't really help either.
For us, Catalyst 8.12 was the make or break driver for recommending ATI hardware on Core i7 systems. We had decided that unless most (if not all) of our outstanding issues were resolved we would recommend that anyone who wanted the latest Intel hardware stay very far away from AMD video cards. Fortunately for AMD, this latest release resolves enough of our issues that we are comfortable recommending that those who want AMD hardware in their Core i7 systems go ahead and give it a shot (note from Anand: I'm still having some issues in my media encoder tests with ATI hardware in my i7 test bed).
There has been a change in the layout of the Catalyst driver as well. It's really more of a minor tweak actually. In the 3D menu on the left side in the Advanced view, the last option on the list ("More Settings") used to be miscellaneous options for toggling z depth, texture compression and triple buffering with OpenGL. All of these options have been removed except for OpenGL triple buffering, which has been rolled into the "All Settings" menu option (it's at the very bottom).
We haven't yet completed a full performance analysis using Catalyst 8.12, but we expect to see practical gains similar to what we saw with NVIDIA's 180 series driver release: mostly modest gains with maybe some corner cases that may or may not be relevant to gamers getting a bigger boost. We are working on gathering data for upcoming articles using Catalyst 8.12 and the latest NVIDIA beta driver 180.84. We haven't run into anything that used to work being broken this time around, but the night is young, as they say. We are hopeful that at least the game tests we are looking at won't present us with any problems.
Using these drivers as a starting point on our Core i7 system should allow us to finally do more with our testing. We are looking forward to finally having a stable platform on which to test both CrossFire and SLI. We are also anxious to get comparisons of graphics hardware using the latest games up as well. This should all be much easier now that we have these drivers in our hands.
Facebook
Twitter
RSS
36 Comments
View All Comments
plonk420 - Tuesday, December 16, 2008 - link
this review is irksome... no mention of x264 version, no mention of resolution or bitrate used on the chart. as a previous comment says, the PQ on the x264 encode looks like the resize was screwed up... the comparison to a software solution was pretty poor.plonk420 - Tuesday, December 16, 2008 - link
http://plonkmedia.org/demo/test.html">http://plonkmedia.org/demo/test.html <-low resolution stream (zoomed 2x)http://www.megaupload.com/?d=ECOIUXQL">http://www.megaupload.com/?d=ECOIUXQL <-low resolution download
http://www.megaupload.com/?d=TPJVM0Y6">http://www.megaupload.com/?d=TPJVM0Y6 <-high resolution
http://www.viddler.com/explore/plonk420/videos/1/">http://www.viddler.com/explore/plonk420/videos/1/ <-what i'm assuming is a transcode (but same site that Anandtech used)
plonk420 - Tuesday, December 16, 2008 - link
quick and dirty tests... (emphesis on dirty; i have Opera with 30+ tabs open, uTorrent, VNC Viewer, handful of other programs open)source: Star Wars 4 VTS_02_4, 18 mins
low res: 320x128 took 310 seconds (±10 sec), processor use was ~30-40%
high res: 640x272 took 325 seconds (±10 sec), processor use was 60-70%
bicubic resizing, no cropping to exactly 2.39:1; couldn't be arsed. just used MeGUI's default iPod encoding settings, but set Quant 19. did SubME 2, 4, 5, and one test with 6 (the high res). it didn't seem to change the time it took to encode.
i'm sure you could up quality, significantly, too with better resizing options (i ususally use Lanczos4), other iPod compatible switches, at minimal speed cost. i don't usually encode for low bitrate/PMPs, but settings to do so are a google away.
but this pq looks decent to me. no issues the hardware encode had. using x264 has a BIT of a learning curve, but can be as fast as these hardware solutions (and possibly excede PQ with the proper options). recent builds have Peryn, i7, and even Phenom optimizations (that weren't utilized in one of the other site's i7 x264 tests).
my tests were encoded on a "mere" Phenom 9550 @ 2.2ghz on Vista x64 SP1, drives fragmented to hell.
options were --qp 19 --level 3 --nf --no-cabac --partitions none --merange 12 --threads auto --thread-input --progress --no-psnr --no-ssim (with --level being 1.3 for low or 3 for high, and --subme being 2, 4, 5, 6). build was 1051 (a few builds out of date; 1055 has better CAVLC PQ according to changelog)
mvrx - Monday, December 15, 2008 - link
I've been grumpy about this for years. Most all the commercial video editing packages have treated mananging and encoding 1080p as a pro-only, or "coming next year" feature.. 1080p isn't pro folks. It's consumer level.I have to use StaxRip with x264.exe encoder to do what I really want, as most commericial packages still have issues with 1080p. Everything should be ready for any resolution, including super high def. Don't try to charge customers more just because they are ready for what will be considered common in another year or two.
I'd also like to see the upconverting technolologies that HD dvd/BR players do in real time mature for software converters. I'd like to take my home movies and DVDs and convert them to 1080p, then encode to h.264. I know that doesn't give me true native quality content, I just like the idea of standardizing all my media to 1080p.
MadMan007 - Monday, December 15, 2008 - link
Thanks for keeping up with these articles. GPGPU's killer app for most consumers is video encoding. One thing that's missing from this article as was alluded to by an earlier comment is a reasonable price comparison - I'd like to see how the GPGPU encoders stack up to a dual core CPU since adding a video card is a much easier upgrade and lots of people have dual core CPU systems already.psychobriggsy - Monday, December 15, 2008 - link
It's interesting comparing this review to the Avivo vs Badaboom article I read elsewhere earlier this month (using the leaked pre-release Catalyst) where they achieved significant performance improvements over using a CPU (i.e., it was actually encoding on the GPU in that review, whereas the conclusion here is that it isn't). They didn't use a Core i7 however. Still, when it comes to using a $200 video card with a $200 CPU, or a $1000 CPU to achieve the same thing, the choice is obvious (well, when the quality is sorted out).Regardless AMD really shouldn't have released Avivo in that state, or they could have at least just called it a preview. What's wrong with AMD/ATI's developers? Don't they have any pride in their work?
bobsm1 - Tuesday, December 16, 2008 - link
Looks like Anand is actually reviewing the products instead of taking the marketing crap that is being provided and just posting it. Takes a bit more work but the result is more interestingdaletkine - Tuesday, December 16, 2008 - link
I used my Sapphire Toxic 4870 to convert the MPEG2 recording of Lost in Space VCR tape, to DivX using Avivo Video converter. My size went from 5.10GB to 3.48GB, from 720x480 (12Mbps) to 640x480 (converter doesn't give res options). Speed wasn't drammatic, like around 40min for 2h10min movie, on an Athlon 64 X2 @ 3.23GHz. CPU was utilized 100% and GPU was utilized (can be seen with RivaTuner) around 8-10%. Video quality was great, nothing to complain, no artifacts like anand pointed out, looks fine. So, seems to have worked for me, but not what I expected. The bad: WMV displays artifacting just like anand showed, Catalyst 8.12 drivers have issue with Xvid stuttering playback, so I saw that in WMP when playing my converted file (solved by using VLC player), no compression that I can see taking place (I used max quality setting, but medium only gives savings of 500MB, don't know about low), and it still needs a quad core.The good: it actually works for me, free, simple, good quality (when works).
This on Vista 64, 8GB ram, Athlon 64 X2 5000+ @ 3.23GHz.
Jovec - Monday, December 15, 2008 - link
8.12 Avivio just creates a 0 byte file when trying to transcode my Xvid (AutoGK) videos. Ah well...Etsp - Monday, December 15, 2008 - link
Man, that's some high level of compression. Careful with that, it may just have made an information black-hole on your hard-drive. :)