NVIDIA GTX 980 Ti Review

👤by Richard Weatherstone Comments 📅31-05-15

Graphics Processing Clusters: 6
Streaming Multiprocessors: 22
CUDA Cores (single precision): 2816
Texture Units: 176
ROP Units: 96
Base Clock: 1000 MHz
Boost Clock: 1075 MHz
Memory Clock: 3505 MHz
Memory Data Rate: 7 Gbps
L2 Cache Size: 3072K
Total Video Memory: 6144MB GDDR5
Memory Interface: 384-bit
Total Memory Bandwidth: 336.5 GB/s
Texture Rate (Bilinear): 176 GigaTexels/sec
Fabrication Process: 28 nm
Transistor Count: 8 Billion
Connectors: 3 x DisplayPort
1 x HDMI
1 x Dual-Link DVI
Form Factor: Dual Slot
Power Connectors: One 8-pin and one 6-pin
Recommended Power Supply: 600 Watts
Thermal Design Power: 250 Watts
Thermal Threshold: 92 C


Being a 'Ti' variant you can expect more performance to be unlocked from the GM200 core it is based upon. It has a 38% increase in CUDA cores to an astonishing 2816 over the 2048 provided by the GTX 980 while 176 texture units are on tap for texture processing. This makes 22 SM units if you are keeping count - 2 less than the TITAN-X which leads us to believe that the GTX 980 Ti has the TITAN-X core at its heart but with two of the SMs disabled/non-functional. Core frequency has taken a slight hit, reduced back to 1000MHz against the GTX 980's 1126MHz however, memory size has been increased to 6GB GDDR5 giving a peak memory bandwidth some 50% higher the the GTX 980 at 336.5GB/sec. There's also 3MB of L2 cache and 96 ROPs against the GTX980's 64 ROPs. A further comparison can be had simply by evaluating the number of transistors each model has: 8 billion vs 5.2 billion in the GTX 980's favour!

20 pages 1 2 3 4 > »