GeForce GTX 660 Ti vs NVIDIA P104 100 8 GB
We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 660 Ti and 48GB
GB VRAM NVIDIA P104 100 8 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 660 Ti 's Advantages
More VRAM (2GB vs 48GB)
NVIDIA P104 100 8 GB 's Advantages
Released 5 years and 4 months late
Boost Clock has increased by 77% (1733MHz vs 980MHz)
Larger VRAM bandwidth (320.3GB/s vs 144.2GB/s)
576 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 660 Ti
2634
NVIDIA P104 100 8 GB
+152%
6655
Graphics Card
Aug 2012
Release Date
Dec 2017
GeForce 600
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
915 MHz
Base Clock
1607 MHz
980 MHz
Boost Clock
1733 MHz
1502 MHz
Memory Clock
1251 MHz
Memory
2GB
Memory Size
48GB
GB
GDDR5
Memory Type
GDDR5X
192bit
Memory Bus
256bit
144.2GB/s
Bandwidth
320.3GB/s
Render Config
-
SM Count
15
1344
Shading Units
1920
112
TMUs
120
24
ROPs
64
16 KB (per SMX)
L1 Cache
48 KB (per SM)
384 KB
L2 Cache
2 MB
Theoretical Performance
27.44 GPixel/s
Pixel Rate
110.9 GPixel/s
109.8 GTexel/s
Texture Rate
208.0 GTexel/s
-
FP16 (half)
104.0 GFLOPS
2.634 TFLOPS
FP32 (float)
6.655 TFLOPS
109.8 GFLOPS
FP64 (double)
208.0 GFLOPS
Board Design
150W
TDP
Unknown
450 W
Suggested PSU
200 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
No outputs
2x 6-pin
Power Connectors
1x 8-pin
Graphics Processor
GK104
GPU Name
GP104
GK104-300-KD-A2
GPU Variant
GP104-100-A1
Kepler
Architecture
Pascal
TSMC
Foundry
TSMC
28 nm
Process Size
16 nm
3.54 billion
Transistors
7.2 billion
294 mm²
Die Size
314 mm²
Graphics Features
12 (11_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
6.1
5.1
Shader Model
6.8
