Tesla D870 vs Tesla C2070
We compared two Professional market GPUs: 1536MB VRAM Tesla D870 and 6GB VRAM Tesla C2070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla C2070 's Advantages
Released 4 years and 2 months late
More VRAM (6GB vs 1536GB)
Larger VRAM bandwidth (143.4GB/s vs 76.80GB/s)
320 additional rendering cores
Lower TDP (238W vs 520W)
Score
Benchmark
FP32 (float)
Tesla D870
346
Tesla C2070
+197%
1028
Graphics Card
May 2007
Release Date
Jul 2011
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 1.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
800 MHz
Memory Clock
747 MHz
Memory
1536MB
Memory Size
6GB
GDDR3
Memory Type
GDDR5
384bit
Memory Bus
384bit
76.80GB/s
Bandwidth
143.4GB/s
Render Config
16
SM Count
14
128
Shading Units
448
32
TMUs
56
24
ROPs
48
-
L1 Cache
64 KB (per SM)
96 KB
L2 Cache
768 KB
Theoretical Performance
14.40 GPixel/s
Pixel Rate
16.07 GPixel/s
38.40 GTexel/s
Texture Rate
32.14 GTexel/s
345.6 GFLOPS
FP32 (float)
1028 GFLOPS
-
FP64 (double)
513.9 GFLOPS
Board Design
520W
TDP
238W
900 W
Suggested PSU
550 W
No outputs
Outputs
1x DVI
-
Power Connectors
1x 8-pin
Graphics Processor
G80
GPU Name
GF100
Tesla
Architecture
Fermi
TSMC
Foundry
TSMC
90 nm
Process Size
40 nm
0.681 billion
Transistors
3.1 billion
484 mm²
Die Size
529 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (11_0)
3.3
OpenGL
4.6
1.1 (1.0)
OpenCL
1.1
N/A
Vulkan
N/A
1.0
CUDA
2.0
4.0
Shader Model
5.1
