Tesla D870 vs GRID K100
We compared two Professional market GPUs: 1536MB VRAM Tesla D870 and 256MB VRAM GRID K100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla D870 's Advantages
More VRAM (1536GB vs 256GB)
Larger VRAM bandwidth (76.80GB/s vs 28.51GB/s)
GRID K100 's Advantages
Released 6 years and 1 months late
64 additional rendering cores
Lower TDP (130W vs 520W)
Score
Benchmark
FP32 (float)
Tesla D870
+6%
346
GRID K100
326
Graphics Card
May 2007
Release Date
Jun 2013
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 1.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
800 MHz
Memory Clock
891 MHz
Memory
1536MB
Memory Size
256MB
GDDR3
Memory Type
DDR3
384bit
Memory Bus
128bit
76.80GB/s
Bandwidth
28.51GB/s
Render Config
16
SM Count
-
128
Shading Units
192
32
TMUs
16
24
ROPs
16
-
L1 Cache
16 KB (per SMX)
96 KB
L2 Cache
256 KB
Theoretical Performance
14.40 GPixel/s
Pixel Rate
3.400 GPixel/s
38.40 GTexel/s
Texture Rate
13.60 GTexel/s
345.6 GFLOPS
FP32 (float)
326.4 GFLOPS
-
FP64 (double)
13.60 GFLOPS
Board Design
520W
TDP
130W
900 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
Graphics Processor
G80
GPU Name
GK107
Tesla
Architecture
Kepler
TSMC
Foundry
TSMC
90 nm
Process Size
28 nm
0.681 billion
Transistors
1.27 billion
484 mm²
Die Size
118 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (11_0)
3.3
OpenGL
4.6
1.1 (1.0)
OpenCL
3.0
N/A
Vulkan
1.1
1.0
CUDA
3.0
4.0
Shader Model
5.1
