NVIDIA GRID K100 vs NVIDIA Tesla K20X
We compared two Professional market GPUs: 256MB VRAM GRID K100 and 6GB VRAM Tesla K20X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K100 's Advantages
Released 7 months late
Lower TDP (130W vs 235W)
NVIDIA Tesla K20X 's Advantages
More VRAM (6GB vs 256GB)
Larger VRAM bandwidth (249.6GB/s vs 28.51GB/s)
2496 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K100
0.326 TFLOPS
Tesla K20X
+1107%
3.935 TFLOPS
Graphics Card
Jun 2013
Release Date
Nov 2012
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
891 MHz
Memory Clock
1300 MHz
Memory
256MB
Memory Size
6GB
DDR3
Memory Type
GDDR5
128bit
Memory Bus
384bit
28.51GB/s
Bandwidth
249.6GB/s
Render Config
-
-
-
-
-
-
192
Shading Units
2688
16
TMUs
224
16
ROPs
48
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
16 KB (per SMX)
256 KB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
3.400 GPixel/s
Pixel Rate
40.99 GPixel/s
13.60 GTexel/s
Texture Rate
164.0 GTexel/s
-
-
-
326.4 GFLOPS
FP32 (float)
3.935 TFLOPS
13.60 GFLOPS
FP64 (double)
1312 GFLOPS
Board Design
130W
TDP
235W
300 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
-
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GK107
GPU Name
GK110
-
-
-
Kepler
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
1.27 billion
Transistors
7.08 billion
118 mm²
Die Size
561 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.1
3.0
CUDA
3.5
5.1
Shader Model
5.1
