NVIDIA GRID K1 vs NVIDIA Tesla K40d
We compared two Professional market GPUs: 4GB VRAM GRID K1 and 12GB VRAM Tesla K40d to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K1 's Advantages
Lower TDP (130W vs 245W)
NVIDIA Tesla K40d 's Advantages
Released 8 months late
Boost Clock876MHz
More VRAM (12GB vs 4GB)
Larger VRAM bandwidth (288.4GB/s vs 28.51GB/s)
2688 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K1
0.326 TFLOPS
Tesla K40d
+1447%
5.046 TFLOPS
Graphics Card
Mar 2013
Release Date
Nov 2013
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
745 MHz
-
Boost Clock
876 MHz
891 MHz
Memory Clock
1502 MHz
Memory
4GB
Memory Size
12GB
DDR3
Memory Type
GDDR5
128bit
Memory Bus
384bit
28.51GB/s
Bandwidth
288.4GB/s
Render Config
-
-
-
-
-
-
192
Shading Units
2880
16
TMUs
240
16
ROPs
48
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
16 KB (per SMX)
256 KB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
3.400 GPixel/s
Pixel Rate
52.56 GPixel/s
13.60 GTexel/s
Texture Rate
210.2 GTexel/s
-
-
-
326.4 GFLOPS
FP32 (float)
5.046 TFLOPS
13.60 GFLOPS
FP64 (double)
1.682 TFLOPS
Board Design
130W
TDP
245W
300 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
1x 6-pin
Power Connectors
-
Graphics Processor
GK107
GPU Name
GK110B
GK107-450-A2
GPU Variant
-
Kepler
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
1.27 billion
Transistors
7.08 billion
118 mm²
Die Size
561 mm²
Graphics Features
12 (11_0)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.1
3.0
CUDA
3.5
5.1
Shader Model
5.1
