Report: GeForce GTX 750 and 750 Ti to Carry GM107 GPU
Nvidia's GTX 750 and GTX 750 Ti will be efficient!
VideoCardz.com has brought the world the first photos of the new Nvidia Maxwell GPUs, as well as a number of details. According to the report, the GTX 750 and GTX 750 Ti graphics card will be carrying the GM107 GPUs in two different versions.
The more powerful GTX 750 Ti will carry the GM107-400 GPU. It will have 960 enabled CUDA cores, 80 TMUs and 16 ROPs. The memory bus is expected to be 128-bits wide. The GPU is expected to be made on a 28 nm lithographic process, and the card equipping it will have a power consumption of about 75 W. This is exactly what a PCIe slot is capable of delivering, meaning that the card might run without any extra PCIe power connectors.
The GTX 750 will carry the GM107-300 GPU. This is a similar GPU as the one found on the GTX 750 Ti, though it will only pack 768 CUDA cores along with 64 TMUs. This slightly lighter version will of course have a slightly lower power consumption, also allowing it to run without any PCIe power connectors. That said, it wouldn't surprise us if a number of manufacturers equip the cards with power connectors anyway, in order to sustain overclocked frequencies or larger amounts of memory.
Both of the graphics cards are expected to make their debut on February 18.
Not GTX 660 speed, just in shader count and clocks (if legit). It's missing a significant amount of ROPs (1/3rd) and the memory is clocked lower to top off a 128 bit memory bus vs a 192 bit leading to a vastly smaller memory throughput. The power envelope of 75w vs 140w on the same process technology should tell you something. All the tweaking in the world isn't going to get that low and maintain the same performance as a 660.The other cards coming out (860, 870, and 880) could indeed be legendary if Project Denver is everything we hope it's cracked up to be.
Just make slim designs with them and you might get my money, nVitards.
Cheers!
most gpu around this performance level have narrowed memory interface. sometimes gpu manufacturer do it on purpose so they can put it on the performance level they want
well it is the price they have to pay to get better performance/watt. also i thought for compute parts GK110 are doing fine.
well it is the price they have to pay to get better performance/watt. also i thought for compute parts GK110 are doing fine.
GK110 parts are anywhere from 1/2 to 1/10 the performance of their intended competitors in terms of Compute. But then again Kepler was a panicked direct answer to Tahiti XT. This might explain a lot.
well it is the price they have to pay to get better performance/watt. also i thought for compute parts GK110 are doing fine.
GK110 parts are anywhere from 1/2 to 1/10 the performance of their intended competitors in terms of Compute. But then again Kepler was a panicked direct answer to Tahiti XT. This might explain a lot.
why is that?