NVIDIA GRID K2 vs NVIDIA Quadro GP100
We compared two Professional market GPUs: 4GB VRAM GRID K2 and 16GB VRAM Quadro GP100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K2 's Advantages
Lower TDP (225W vs 235W)
NVIDIA Quadro GP100 's Advantages
Released 3 years and 5 months late
Boost Clock1442MHz
More VRAM (16GB vs 4GB)
Larger VRAM bandwidth (732.2GB/s vs 160.0GB/s)
2048 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K2
2.289 TFLOPS
Quadro GP100
+351%
10.34 TFLOPS
Graphics Card
May 2013
Release Date
Oct 2016
GRID
Generation
Quadro
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
1304 MHz
-
Boost Clock
1442 MHz
1250 MHz
Memory Clock
715 MHz
Memory
4GB
Memory Size
16GB
GDDR5
Memory Type
HBM2
256bit
Memory Bus
4096bit
160.0GB/s
Bandwidth
732.2GB/s
Render Config
-
-
-
-
SM Count
56
1536
Shading Units
3584
128
TMUs
224
32
ROPs
96
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
24 KB (per SM)
512 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
23.84 GPixel/s
Pixel Rate
138.4 GPixel/s
95.36 GTexel/s
Texture Rate
323.0 GTexel/s
-
FP16 (half)
20.67 TFLOPS
2.289 TFLOPS
FP32 (float)
10.34 TFLOPS
95.36 GFLOPS
FP64 (double)
5.168 TFLOPS
Board Design
225W
TDP
235W
550 W
Suggested PSU
550 W
No outputs
Outputs
1x DVI
4x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GK104
GPU Name
GP100
GK104-895-A2
GPU Variant
-
Kepler
Architecture
Pascal
TSMC
Foundry
TSMC
28 nm
Process Size
16 nm
3.54 billion
Transistors
15.3 billion
294 mm²
Die Size
610 mm²
Graphics Features
12 (11_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.2.175
Vulkan
1.3
3.0
CUDA
6.0
6.5 (5.1)
Shader Model
6.4
