![gtx 750 ti 2gb graphic card benchmark gtx 750 ti 2gb graphic card benchmark](http://cdn.eteknix.com/wp-content/uploads/2014/04/asus-gtx-750-Ti-OC-lead.jpg)
The GeForce GTX 750 Ti would support GPU Boost 2.0. Bear in mind though, it only offers a bandwidth of 86.4 GB/s, just like 650 TI.
![gtx 750 ti 2gb graphic card benchmark gtx 750 ti 2gb graphic card benchmark](https://www.legitreviews.com/wp-content/uploads/2014/02/geforce-gtx-750ti-cards.jpg)
This is definitely a bottleneck.Īpart form 128b interface, we have 2GB of GDDR5 memory, which is fine, I guess. While having a big number of CUDA cores, it only has 16 ROPs and 128-bit memory interface. In fact the configuration of this card is quite interesting. NVIDIA GeForce GTX 750 Ti specificationsĪccording to the leaked GPU-Z screenshot the first Maxwell based GPU would sport 960 CUDA cores. Luckily for us, a member of PCOnline forums had the opportunity to test the upcoming GTX 750 Ti from NVIDIA. Maxwell also has a new GC5 power state designed to drop the GPU power demand under light workload situations – such as when playing back video.It looks like first Maxwell GPUs are already in the wild. Nvidia report a 8-10 times faster decode rate too. Maxwell incorporates an improved NVENC block to deliver faster encode performance over Kepler – 6-8 times real time compared against 4 times. Nvidia have improved Video capabilities with the latest hardware. The GM107 (v GK107) has 25 percent more texture performance, 1.7 times more CUDA cores and 2.3 greater shader performance. The smaller area means that Nvidia can incorporate many more SM’s per GPU. Each Maxwell SM is smaller than a Kepler SM but delivers around 90% of the performance. The L1 compute cache function is now combined with the texture cache function and shared memory is a separate unit, shared across all four blocks. Pairs of processing blocks share four texture filtering units and a texture cache. The new partitioning simplifies the design and scheduling logic which reduces computation latency and saves area and power demand. GK107 Kepler could have a non power of two number of CUDA cores, with some shared. Each SM has been partitioned into four separate processing blocks, each with their own instruction buffer, scheduler and 32 CUDA cores. Nvidia have explained that the organisation of the SM has been changed. Maxwell SM architecture enabled Nvidia to increase the number of SM’s to five in GM107, compared to two in GK107 – and all with only a 25% increase in die area. Nvidia have changed the architecture with the SM scheduler architecture and algorithms having been rewritten to avoid stalling and further reducing the energy per instruction required for scheduling. The Maxwell SM architecture delivers improved efficiency and 35% more performance per CUDA core on shader limited workloads. The Nvidia reference card is using 2GB of Hynix GDDR5 memory, but ASUS have opted for Samsung branded GDDR5. All cards have 16 ROP's, 53 TMU's and 640 CUDA cores. Unlike the Palit GTX 750 Ti StormX Dual the memory is left at the default speeds of 1,350mhz (5.4Gbps effective). The Asus GTX 750 Ti receives a modest core clock increase, from 1,020 mhz to 1,072 mhz. The new Asus GTX 750 Ti 2GB is a modified design featuring dual fans and enhanced out of the box clock speeds. So far we have analysed the MSI GTX750 Ti OC Twin Frozr and the Palit GTX 750 Ti StormX Dual – both fantastic solutions … so we will be interested to see how the Asus solution stacks up. Today we are taking a look at the new Asus GTX 750 Ti, the third Maxwell card we have reviewed since Nvidia launched back on February 18th.