NVIDIA GRID K100 vs NVIDIA Tesla C2090
We compared two Professional market GPUs: 256MB VRAM GRID K100 and 6GB VRAM Tesla C2090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K100 's Advantages
Released 1 years and 11 months late
Lower TDP (130W vs 250W)
NVIDIA Tesla C2090 's Advantages
More VRAM (6GB vs 256GB)
Larger VRAM bandwidth (177.4GB/s vs 28.51GB/s)
320 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K100
0.326 TFLOPS
Tesla C2090
+308%
1.332 TFLOPS
Graphics Card
Jun 2013
Release Date
Jul 2011
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
891 MHz
Memory Clock
924 MHz
Memory
256MB
Memory Size
6GB
DDR3
Memory Type
GDDR5
128bit
Memory Bus
384bit
28.51GB/s
Bandwidth
177.4GB/s
Render Config
-
-
-
-
SM Count
16
192
Shading Units
512
16
TMUs
64
16
ROPs
48
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
768 KB
-
-
-
Theoretical Performance
3.400 GPixel/s
Pixel Rate
20.83 GPixel/s
13.60 GTexel/s
Texture Rate
41.66 GTexel/s
-
-
-
326.4 GFLOPS
FP32 (float)
1332 GFLOPS
13.60 GFLOPS
FP64 (double)
666.1 GFLOPS
Board Design
130W
TDP
250W
300 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
-
-
-
Graphics Processor
GK107
GPU Name
GF110
-
-
-
Kepler
Architecture
Fermi 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
40 nm
1.27 billion
Transistors
3 billion
118 mm²
Die Size
520 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
3.0
CUDA
2.0
5.1
Shader Model
5.1
