The widely anticipated (albeit currently not widely available) prosumer AMD Radeon VII is finally available. It features a next generation Vega 20 GPU which is based on a 7nm manufacturing process, compared to 14nm in the first generation flagship: the RX Vega 64. The Radeon VII has a massive 16GB of expensive high-bandwidth memory (HBM2) which offers a decent degree of future proofing and also makes it a good choice for memory hungry applications, however most current games do not require more than the 8GB that comes with both NVIDIA's RTX 2080 and AMD’s RX Vega 64. The Radeon VII has fewer cores than the RX Vega 64 (3840 vs 4096) but clock speeds have been boosted up to 1800 MHz compared to 1546 MHz in the RX Vega 64, the net result is 13.8 TFLOPS single precision computations (versus 13.4 TFLOPS for the RX Vega 64). On the negative side, the Radeon VII is designed with three cooling fans which can get noisy and early software drivers are reported to be buggy. Whilst there is a modest 16% performance advantage over the RX Vega 64, initial benchmarks indicate that the Radeon VII has an effective speed which is 6% short of the similarly priced RTX 2080. [Feb '19GPUPro]
The new GTX 980 Ti shares the same board as the more expensive Titan-X but with various restrictions including a reduced number of CUDA cores (3072 to 2816, -8.3%). Although the 980 Ti has the same 384-bit memory bandwidth as the Titan-X it only has 6GB of GDDR5 vs. 12GB in the Titan-X. So far we only have one user benchmark from a pre-release unit of the GTX 980 Ti so the following benchmarks are provisional. Comparing the Titan-X and 980 Ti shows that the Ti only lags by around 8%, which is in line with the CUDA core counts on the two cards. On the other hand comparing the GTX 980 and GTX 980 Ti shows that the Ti is around 16% faster. We don't have reliable prices for the GTX 980 Ti yet so a precise value rating isn't possible but as a card aimed at resolutions greater than 1080p it will struggle to match the GTX 970 for the vast majority of users. [May '15GPUPro]
We calculate effective 3D speed which estimates gaming performance for the top 12 games. Effective speed is adjusted by current prices to yield value for money. Our figures are checked against thousands of individual user ratings. The customizable table below combines these factors to bring you the definitive list of top GPUs. [GPUPro]
Welcome to our PC speed test tool. UserBenchmark will test your PC and compare the results to other users with the same components. You can quickly size up your PC, identify hardware problems and explore the best value for money upgrades.