NVIDIA Tesla K20c vs NVIDIA Tesla S1070
We compared two Professional market GPUs: 5GB VRAM Tesla K20c and 4GB VRAM Tesla S1070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K20c 's Advantages
Released 4 years and 5 months late
More VRAM (5GB vs 4GB)
Larger VRAM bandwidth (208.0GB/s vs 102.4GB/s)
2256 additional rendering cores
Lower TDP (225W vs 800W)
Score
Benchmark
FP32 (float)
Tesla K20c
+466%
3.524 TFLOPS
Tesla S1070
0.622 TFLOPS
Graphics Card
Nov 2012
Release Date
Jun 2008
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
1300 MHz
Memory Clock
800 MHz
Memory
5GB
Memory Size
4GB
GDDR5
Memory Type
GDDR3
320bit
Memory Bus
512bit
208.0GB/s
Bandwidth
102.4GB/s
Render Config
-
-
-
-
SM Count
30
2496
Shading Units
240
208
TMUs
80
40
ROPs
32
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
-
1280 KB
L2 Cache
256 KB
-
-
-
Theoretical Performance
36.71 GPixel/s
Pixel Rate
19.52 GPixel/s
146.8 GTexel/s
Texture Rate
48.80 GTexel/s
-
-
-
3.524 TFLOPS
FP32 (float)
622.1 GFLOPS
1175 GFLOPS
FP64 (double)
77.76 GFLOPS
Board Design
225W
TDP
800W
550 W
Suggested PSU
1200 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
GK110
GPU Name
GT200B
GK110-885-KA-A1
GPU Variant
-
Kepler
Architecture
Tesla 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
55 nm
7.08 billion
Transistors
1.4 billion
561 mm²
Die Size
470 mm²
Graphics Features
12 (11_0)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1
1.1
Vulkan
N/A
3.5
CUDA
1.3
5.1
Shader Model
4.0
