Tesla C2070 vs Tesla K8
We compared two Professional market GPUs: 6GB VRAM Tesla C2070 and 8GB VRAM Tesla K8 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla K8 Advantages
Released 3 years and 2 months late
Boost Clock811MHz
More VRAM (8GB vs 6GB)
Larger VRAM bandwidth (160.0GB/s vs 143.4GB/s)
1088 additional rendering cores
Lower TDP (100W vs 238W)
Score
Benchmark
FP32 (float)
Tesla C2070
1028
Tesla K8
+142%
2491
Graphics Card
Jul 2011
Release Date
Sep 2014
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
Base Clock
693 MHz
-
Boost Clock
811 MHz
747 MHz
Memory Clock
1250 MHz
Memory
6GB
Memory Size
8GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
256bit
143.4GB/s
Bandwidth
160.0GB/s
Render Config
14
SM Count
-
448
Shading Units
1536
56
TMUs
128
48
ROPs
32
64 KB (per SM)
L1 Cache
16 KB (per SMX)
768 KB
L2 Cache
512 KB
Theoretical Performance
16.07 GPixel/s
Pixel Rate
25.95 GPixel/s
32.14 GTexel/s
Texture Rate
103.8 GTexel/s
1028 GFLOPS
FP32 (float)
2.491 TFLOPS
513.9 GFLOPS
FP64 (double)
103.8 GFLOPS
Board Design
238W
TDP
100W
550 W
Suggested PSU
300 W
1x DVI
Outputs
No outputs
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
GF100
GPU Name
GK104
Fermi
Architecture
Kepler
TSMC
Foundry
TSMC
40 nm
Process Size
28 nm
3.1 billion
Transistors
3.54 billion
529 mm²
Die Size
294 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
1.1
OpenCL
3.0
N/A
Vulkan
1.1
2.0
CUDA
3.0
5.1
Shader Model
5.1
