Tesla K20s vs GRID K100
We compared two Professional market GPUs: 5GB VRAM Tesla K20s and 256MB VRAM GRID K100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla K20s 's Advantages
More VRAM (5GB vs 256GB)
Larger VRAM bandwidth (208.0GB/s vs 28.51GB/s)
2304 additional rendering cores
GRID K100 's Advantages
Lower TDP (130W vs 225W)
Score
Benchmark
FP32 (float)
Tesla K20s
+780%
2870
GRID K100
326
Graphics Card
Feb 2013
Release Date
Jun 2013
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1300 MHz
Memory Clock
891 MHz
Memory
5GB
Memory Size
256MB
GDDR5
Memory Type
DDR3
320bit
Memory Bus
128bit
208.0GB/s
Bandwidth
28.51GB/s
Render Config
2496
Shading Units
192
208
TMUs
16
40
ROPs
16
16 KB (per SMX)
L1 Cache
16 KB (per SMX)
1280 KB
L2 Cache
256 KB
Theoretical Performance
29.90 GPixel/s
Pixel Rate
3.400 GPixel/s
119.6 GTexel/s
Texture Rate
13.60 GTexel/s
2.870 TFLOPS
FP32 (float)
326.4 GFLOPS
956.8 GFLOPS
FP64 (double)
13.60 GFLOPS
Board Design
225W
TDP
130W
550 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
Graphics Processor
GK110
GPU Name
GK107
Kepler
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
7.08 billion
Transistors
1.27 billion
561 mm²
Die Size
118 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.1
3.5
CUDA
3.0
5.1
Shader Model
5.1
