AMD Radeon HD 7870 GHz Edition & Radeon HD 7850 Review: Rounding Out Southern Islands
by Ryan Smith on March 5, 2012 12:01 AM ESTCompute Performance
Moving on from our look at gaming performance, we have our customary look at compute performance. With GCN AMD significantly overhauled their architecture in order to improve compute performance, as their long-run initiatives rely on GPU compute performance becoming far more important than it is today.
Our first compute benchmark comes from Civilization V, which uses DirectCompute to decompress textures on the fly. Civ V includes a sub-benchmark that exclusively tests the speed of their texture decompression algorithm by repeatedly decompressing the textures required for one of the game’s leader scenes. Note that this is a DX11 DirectCompute benchmark.
The Civ V compute shader benchmark once again shows off just how much the compute shader performance of the 7800 series has improved relative to the 6900 series, with both 7800 cards coming in well, well ahead of any previous generation AMD cards. Compared to NVIDIA’s lineup the 7800 series does fairly well for itself too, although not quite as well as the commanding lead the 7900 series took.
Our next benchmark is SmallLuxGPU, the GPU ray tracing branch of the open source LuxRender renderer. We’re now using a development build from the version 2.0 branch, and we’ve moved on to a more complex scene that hopefully will provide a greater challenge to our GPUs.
SmallLuxGPU continues to showcase the 7800 series’ improvements over past AMD architectures, and while it’s not the same kind of massive leap we saw with CivV, it’s still enough to bring the 7850 up to near the performance of the 6970, and pushing the 7870 well beyond that. The only real competition here for AMD is AMD.
For our next benchmark we’re looking at AESEncryptDecrypt, an OpenCL AES encryption routine that AES encrypts/decrypts an 8K x 8K pixel square image file. The results of this benchmark are the average time to encrypt the image over a number of iterations of the AES cypher.
On the one hand, the 7870 gets quite close to the 7950 here in our AESEncryptDecrypt benchmark, in spite of the latter’s higher number of shaders. On the other hand, it’s still not enough to dethrone the GTX 570; the only NVIDIA cards the 7800 series can beat start at the GTX 560 Ti.
Finally, our last benchmark is once again looking at compute shader performance, this time through the Fluid simulation sample in the DirectX SDK. This program simulates the motion and interactions of a 16k particle fluid using a compute shader, with a choice of several different algorithms. In this case we’re using an (O)n^2 nearest neighbor method that is optimized by using shared memory to cache data.
In our final compute test the 7800 series once again makes a run at the top, with both cards rising past the GTX 570, although they can’t quite match the GTX 580. In an interesting turn of events the 7870 ends up being some 6% faster than the 7950, in spite of the fact that in a compute benchmark the 7950 should have a solid lead. This just goes to show that core clockspeeds do matter, and that adding more shaders alone can’t conquer all benchmarks.
Facebook
Twitter
RSS
173 Comments
View All Comments
chizow - Monday, March 5, 2012 - link
Sorry, fact checking 101 says the 7850 is still clearly behind the 570, about 10% faster than the GTX 560Ti ($200). The 7870 may be the SKU you're referring to but it costs $350, which again, brings very little movement on pricing:performance relative to 14-16 month old parts.CeriseCogburn - Thursday, March 8, 2012 - link
Hey don't be so factual. medi01 can also look forward to blurred up MLAA, lack of LOD detail compensation, no PhysX, drivers crashing like mad inexplicably for a year or two until things get "ironed out", new games "not running", mouse cursors stuck in corners, whining about tessellation levels in games "it can't handle", and generally blaming nvidia for all it's failures...The "$80" imaginary dollars he saves he can "reinvest" in a "solid" with a "for sure" payoff - his endless hours "fixing" his 7850 "issues".
SlyNine - Monday, March 5, 2012 - link
That's a very 1 dimensional opinion. Compared to the 5870 node change which equaled 2x performance for around the same price, A fab shrink that doesn't double your performance for the money is disappointing.We are comparing it to how past node changes changed the price/performance model. This one is HORRIBLE because it basically slides right in to the old one, so now we have a node change that does very little for price.
I'm running a 5870 which is basically 75% the performance of a 7970, and I paid 379 for the 5870. Which is also 75% of the cost of a 7970. The price of a 7970 is basically the exact same price structure as the 2 1/2 year old 5870, So we are stuck where we were in 2009, yay.
morfinx - Monday, March 5, 2012 - link
75% performance of 7970 would mean that it's 33% faster than a 5870. And that's just not accurate. I have a 5870 as well, so I was paying a lot of attention on how much faster the 7970 is in various reviews. Everything I've read indicates that it's anywhere from 70-110% faster at 2560x1600 resolution (I run 3600x1920, so likely even even more of a difference). That's not even even considering the massive overclocking headroom of the 7970 vs barely any OC headroom of the 5870. Overclocked, a 7970 is easily twice as fast as a 5870.SlyNine - Thursday, March 8, 2012 - link
I should have said 66% for 66% of the price. Point being the price/Performance has not improved...Its around 40-60% faster according to Anandtech's benchmarks.
Overclocked, don't make me laugh.
chizow - Monday, March 5, 2012 - link
@Kiste: Agreed, don't worry about the criticism you're taking. This site has a lot of readers with very low standards or very limited perspective when it comes to the GPU industry.7000 series pricing and performance is a disappointment so far, there's no doubt about it. You can throw as much historical perspective and factual pricing/performance at them but you''ll just be greeted with blank stares and accusations of fanboyism.
Bottomline is this, if Nvidia follows this price and performance structure, EVERYONE would be disappointed.
If Nvidia took 14-16 months and only improved their entire product stack 15-25% on a new architecture and new process node with Kepler while increasing prices accordingly, it'd be a colossal failure.
It makes you wonder why the AMD fans don't see it the same way?
Kaboose - Monday, March 5, 2012 - link
you're acting like Kepler has been released and Nvidia won't be doing the same exact thing, I really doubt we will see Nvidia releasing higher performing cards then AMD at much lower prices like you see to think.chizow - Monday, March 5, 2012 - link
I didn't say we know what Kepler holds, what I'm saying is *IF* Nvidia did this, it would be a colossal failure and we could just write off 28nm entirely. That's why it makes you wonder why AMD fans are giving them a pass for such little improvement in performance and pricing.Honestly, with 15-25% improvement top to bottom over existing SKUs, Nvidia could have simply refreshed their entire Fermi line-up and hit those targets with just clockspeed increases from the smaller process.
At no other point in the history of GPUs has a new process/architecture from either IHV brought so little movement in price and performance. There's no innovation here and no incentive for anyone who bought in the last few generations to bother upgrading.
If you have a 5850/470 or better, there is VERY little reason to upgrade right now especially at the asking prices.
Kaboose - Monday, March 5, 2012 - link
What % of people have 5850/470 or better GPUs though? Im going to say not many. 7850/7870 are good cards for people entering the market on mid range desktops that want to add a GPU for gaming. As well as HTPC use. And for system builders who are looking for a good OC and current gen. technology.Ananke - Monday, March 5, 2012 - link
See Steam statistics. The 5th series was the majority. The largest target market are owners of 5850/5870. I have 5850 and I can afford any card, but I see no reason to upgrade. At this price point gaming is not the only usage, I want quality hardware video encoding acceleration by MANY software packages, GPGPU applications. Today, in those areas, AMD has actually even less applications than when they launched the 5th series.For SO much money and NO applications outside gaming the ONLY reason not to use NVidia would be heat dissipation. If Kepler cards are colder, NVidia has a win.