What you’re looking at are the first pictures of the NVIDIA Maxwell GPUs.
The GM107 enters the game
The GM107 is a hybrid between GK107 and GK106. It has a CUDA count of GK106, but a memory bus of GK107. The area of the die has been reduced by 30%, compared to GK106.
The footprint on power consumption will be dramatically lower than any Kepler GPU. In fact, most GeForce GTX 750 series cards will not require any power connectors, but of course there some with 6-pin installed.
Long story short, there are two versions of GM107. The slower variant GM107-300 will be used for GeForce GTX 750, while the faster GM107-400 will equip GTX 750 TI. The 300 has 768 CUDA cores, whereas the 400 features 960 processors.
Kepler vs Maxwell | ||||
---|---|---|---|---|
GK107-450 | GK106-400 | GM107-300 | GM107-400 | |
GPU | 28nm | 28nm | 28nm | 28nm |
Die Size | 118 mm2 | 221 mm2 | 156 mm2 | 156 mm2 |
CUDAs | 384 | 960 | 768 | 960 |
TMUs | 32 | 80 | 64 | 80 |
ROPs | 16 | 24 | 16 | 16 |
Memory Bus | 128-bit | 192-bit | 128-bit | 128-bit |
TDP | 65W | 140W | ? | ~75W |
Launch Date | September 2012 | September 2012 | February 2014 | February 2014 |
Everyone expected Maxwell to be on 20nm process from the very beginning, but TSMC was not ready to manufacture it. Honestly, I’m not even sure if we are going to see 20nm GPUs in Q2. Maybe it’s just too early to talk about them, but one thing is certain though. NVIDIA did not call these cards with GeForce 800 series nametag, because it will be reserved for the real 20nm Maxwell.
It doesn’t look like GM107 is bringing any new technology to the table, it is just better binned and much more efficient processor. Technically you could easily call Maxwell a Kepler Refresh2.
If you still don’t understand what is so special about Maxwell, just compare GK107-450 to GM107-300. Both GPUs will most likely consume the same amount of power, but GM107 has twice as much CUDAs.
NVIDIA GeForce GTX 750 and GTX 750 Ti equipped with GM107 GPU will be released on February 18th.