NVIDIA Tesla K20X vs NVIDIA Tesla C2050
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 3GB VRAM Tesla C2050 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K20X 's Advantages
Released 1 years and 4 months late
More VRAM (6GB vs 3GB)
Larger VRAM bandwidth (249.6GB/s vs 144.0GB/s)
2240 additional rendering cores
Lower TDP (235W vs 238W)
Score
Benchmark
FP32 (float)
Tesla K20X
+282%
3.935 TFLOPS
Tesla C2050
1.028 TFLOPS
Graphics Card
Nov 2012
Release Date
Jul 2011
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
1300 MHz
Memory Clock
750 MHz
Memory
6GB
Memory Size
3GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
384bit
249.6GB/s
Bandwidth
144.0GB/s
Render Config
-
-
-
-
SM Count
14
2688
Shading Units
448
224
TMUs
56
48
ROPs
48
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
64 KB (per SM)
1536 KB
L2 Cache
768 KB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
16.07 GPixel/s
164.0 GTexel/s
Texture Rate
32.14 GTexel/s
-
-
-
3.935 TFLOPS
FP32 (float)
1028 GFLOPS
1312 GFLOPS
FP64 (double)
513.9 GFLOPS
Board Design
235W
TDP
238W
550 W
Suggested PSU
550 W
No outputs
Outputs
1x DVI
1x 6-pin + 1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GK110
GPU Name
GF100
-
GPU Variant
GF100-850-A3
Kepler
Architecture
Fermi
TSMC
Foundry
TSMC
28 nm
Process Size
40 nm
7.08 billion
Transistors
3.1 billion
561 mm²
Die Size
529 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
1.1
1.1
Vulkan
N/A
3.5
CUDA
2.0
5.1
Shader Model
5.1
