NVIDIA Tesla C2090 vs NVIDIA Tesla K40d
We compared two Professional market GPUs: 6GB VRAM Tesla C2090 and 12GB VRAM Tesla K40d to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K40d 's Advantages
Released 2 years and 4 months late
Boost Clock876MHz
More VRAM (12GB vs 6GB)
Larger VRAM bandwidth (288.4GB/s vs 177.4GB/s)
2368 additional rendering cores
Lower TDP (245W vs 250W)
Score
Benchmark
FP32 (float)
Tesla C2090
1.332 TFLOPS
Tesla K40d
+278%
5.046 TFLOPS
Graphics Card
Jul 2011
Release Date
Nov 2013
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
745 MHz
-
Boost Clock
876 MHz
924 MHz
Memory Clock
1502 MHz
Memory
6GB
Memory Size
12GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
384bit
177.4GB/s
Bandwidth
288.4GB/s
Render Config
-
-
-
16
SM Count
-
512
Shading Units
2880
64
TMUs
240
48
ROPs
48
-
-
-
-
-
-
64 KB (per SM)
L1 Cache
16 KB (per SMX)
768 KB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
20.83 GPixel/s
Pixel Rate
52.56 GPixel/s
41.66 GTexel/s
Texture Rate
210.2 GTexel/s
-
-
-
1332 GFLOPS
FP32 (float)
5.046 TFLOPS
666.1 GFLOPS
FP64 (double)
1.682 TFLOPS
Board Design
250W
TDP
245W
600 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
-
-
-
Graphics Processor
GF110
GPU Name
GK110B
-
-
-
Fermi 2.0
Architecture
Kepler
TSMC
Foundry
TSMC
40 nm
Process Size
28 nm
3 billion
Transistors
7.08 billion
520 mm²
Die Size
561 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_1)
4.6
OpenGL
4.6
1.1
OpenCL
3.0
N/A
Vulkan
1.1
2.0
CUDA
3.5
5.1
Shader Model
5.1
