![]() ![]() The fluid simulation is another benchmark that includes a stronger mix of memory bandwidth and cache rather than being purely dependent on compute resources. At 395ms it’s a hair slower than the 7850, never mind the 7870. Our AES benchmark was one of the few compute benchmarks where the GTX 660 Ti had any kind of lead, but the significant loss of compute resources has erased that for the GTX 660. The results of this benchmark are the average time to encrypt the image over a number of iterations of the AES cypher. The 7870 more than trebles the GTX 660’s performance, an indisputable victory if there ever was one.įor 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. It goes without saying that with the GTX 660’s poor compute performance here, the 7800 series is well in the lead. Thank goodness the 8800GT is terrible at this benchmark, otherwise the GTX 660 would be in particularly bad shape. ![]() ![]() Over 2 years after the launch of the GTX 460 and SLG performance has gone exactly nowhere, with the GTX 460 and GTX 660 turning in the same exact scores. SmallLuxGPU sees us shift towards an emphasis on pure compute performance, which of course is going to be GTX 660’s weak point here. 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. Our next benchmark is SmallLuxGPU, the GPU ray tracing branch of the open source LuxRender renderer. Still, the GTX 660 is effectively tied with the 7850 and well behind the 7870. Given the GTX 660 Ti’s poor showing in this benchmark this is a good thing for NVIDIA since this means they don’t fall any farther behind. Despite being a compute benchmark, Civlization V’s texture decompression benchmark is more sensitive to memory bandwidth and cache performance than it is shader performance, giving us the results we see above. It’s interesting then that despite the obvious difference between the GTX 660 and GTX 660 Ti in theoretical compute performance, the GTX 660 actually beats the GTX 660 Ti here. Note that this is a DX11 DirectCompute benchmark. 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. Our first compute benchmark comes from Civilization V, which uses DirectCompute to decompress textures on the fly. Further compounding this is the fact that GK106 only has 5 SMXes versus the 8 SMXes of GK104, which will likely further depress compute performance. As we have seen with GTX 680 and GTX 670, Kepler appears to be significantly less balanced between rendering and compute performance than GF110 or GF114 were, and as a result compute performance suffers. AMD’s last-minute BIOS tweaks mean that the Radeon HD 7950 is in close contention, but in the mid-range battleground, the GTX 660 Ti just edges ahead as the new champion.As always our final set of real-world benchmarks is composed of a look at compute performance. Nvidia’s GTX 660 Ti is faster, available for comparable prices and runs more quietly, too. The GTX 660 Ti betters the HD 7950 convincingly in Just Cause 2 and DiRT 3, and is a little faster in Crysis it wasn’t until we fired up Crysis 2 that the Radeon HD 7950 managed to turn the tables. Performance is very close, although we’d say the Nvidia card nudges ahead here, too. Prices will vary depending on the overclock and other features included, but that bodes well for competing with the Radeon HD 7950, with AMD chips costing anywhere between £250 and £300. Our Asus model costs £281 inc VAT, and similar cards from Zotac and MSI will cost £260 inc VAT and £250 inc VAT. The final piece of the puzzle is value for money, and in this regard the GTX 660 Ti remains competitive. A peak temperature of 74˚C is nothing to worry about, and it’s exceptionally quiet, which is a far cry from the whirr emitted from our AMD sample when it ran more demanding benchmarks. Under load, it pulled 251W from the mains, which is only 5W more than AMD’s HD 7950. The GTX 660 Ti’s performance is married with impressive efficiency. The gap was just as wide across three monitors, with the GTX 660 Ti card scoring 47fps and the Radeon bringing up the rear with 39fps. At 1,920 x 1,080 and with Ultra settings, its 114fps result trounced the 87fps of the Radeon, and it continued the rout at 2,560 x 1,440, where it scored 73fps compared to the HD 7950’s 61fps. Our final gaming test, DiRT 3, saw the GTX 660 Ti card take the lead. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |