GRID M40 vs Tesla K20s
We compared two Professional market GPUs: 8GB VRAM GRID M40 and 5GB VRAM Tesla K20s to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GRID M40 's Advantages
Released 3 years and 3 months late
More VRAM (8GB vs 5GB)
Lower TDP (50W vs 225W)
Tesla K20s 's Advantages
Larger VRAM bandwidth (208.0GB/s vs 83.20GB/s)
2112 additional rendering cores
Score
Benchmark
FP32 (float)
GRID M40
793
Tesla K20s
+261%
2870
Graphics Card
May 2016
Release Date
Feb 2013
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1300 MHz
Memory Clock
1300 MHz
Memory
8GB
Memory Size
5GB
GDDR5
Memory Type
GDDR5
128bit
Memory Bus
320bit
83.20GB/s
Bandwidth
208.0GB/s
Render Config
384
Shading Units
2496
32
TMUs
208
16
ROPs
40
64 KB (per SMM)
L1 Cache
16 KB (per SMX)
2 MB
L2 Cache
1280 KB
Theoretical Performance
16.53 GPixel/s
Pixel Rate
29.90 GPixel/s
33.06 GTexel/s
Texture Rate
119.6 GTexel/s
793.3 GFLOPS
FP32 (float)
2.870 TFLOPS
24.79 GFLOPS
FP64 (double)
956.8 GFLOPS
Board Design
50W
TDP
225W
250 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
Graphics Processor
GM107
GPU Name
GK110
Maxwell
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
1.87 billion
Transistors
7.08 billion
148 mm²
Die Size
561 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
5.0
CUDA
3.5
5.1
Shader Model
5.1
