NVIDIA Tesla K20X vs NVIDIA GRID K2
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 4GB VRAM GRID K2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K20X 's Advantages
More VRAM (6GB vs 4GB)
Larger VRAM bandwidth (249.6GB/s vs 160.0GB/s)
1152 additional rendering cores
NVIDIA GRID K2 's Advantages
Released 6 months late
Lower TDP (225W vs 235W)
Score
Benchmark
FP32 (float)
Tesla K20X
+71%
3.935 TFLOPS
GRID K2
2.289 TFLOPS
Graphics Card
Nov 2012
Release Date
May 2013
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
1300 MHz
Memory Clock
1250 MHz
Memory
6GB
Memory Size
4GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
256bit
249.6GB/s
Bandwidth
160.0GB/s
Render Config
-
-
-
-
-
-
2688
Shading Units
1536
224
TMUs
128
48
ROPs
32
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
16 KB (per SMX)
1536 KB
L2 Cache
512 KB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
23.84 GPixel/s
164.0 GTexel/s
Texture Rate
95.36 GTexel/s
-
-
-
3.935 TFLOPS
FP32 (float)
2.289 TFLOPS
1312 GFLOPS
FP64 (double)
95.36 GFLOPS
Board Design
235W
TDP
225W
550 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GK110
GPU Name
GK104
-
GPU Variant
GK104-895-A2
Kepler
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
7.08 billion
Transistors
3.54 billion
561 mm²
Die Size
294 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.2.175
3.5
CUDA
3.0
5.1
Shader Model
6.5 (5.1)
