NVIDIA Jetson Nano GPU vs NVIDIA Tesla T4
We compared a Integrated graphics card GPU: 0System Shared VRAM Jetson Nano GPU and a Professional market GPU: 16GB VRAM Tesla T4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Jetson Nano GPU 's Advantages
Released 8 months late
Lower TDP (10W vs 70W)
NVIDIA Tesla T4 's Advantages
Boost Clock has increased by 73% (1590MHz vs 921MHz)
2432 additional rendering cores
Score
Benchmark
FP32 (float)
Jetson Nano GPU
0.236 TFLOPS
Tesla T4
+3349%
8.141 TFLOPS
Graphics Card
May 2019
Release Date
Sep 2018
Tegra
Generation
Tesla
Integrated
Type
Professional
IGP
Bus Interface
PCIe 3.0 x16
Clock Speeds
640 MHz
Base Clock
585 MHz
921 MHz
Boost Clock
1590 MHz
System Shared
Memory Clock
1250 MHz
Memory
System Shared
Memory Size
16GB
System Shared
Memory Type
GDDR6
System Shared
Memory Bus
256bit
System Dependent
Bandwidth
320.0GB/s
Render Config
-
-
-
-
SM Count
40
128
Shading Units
2560
16
TMUs
160
16
ROPs
64
-
Tensor Cores
320
-
RT Cores
40
48 KB (per SMM)
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
14.74 GPixel/s
Pixel Rate
101.8 GPixel/s
14.74 GTexel/s
Texture Rate
254.4 GTexel/s
471.6 GFLOPS
FP16 (half)
65.13 TFLOPS
235.8 GFLOPS
FP32 (float)
8.141 TFLOPS
7.368 GFLOPS
FP64 (double)
254.4 GFLOPS
Board Design
10W
TDP
70W
-
Suggested PSU
250 W
No outputs
Outputs
No outputs
-
Power Connectors
None
Graphics Processor
GM20B
GPU Name
TU104
TM660M-A2
GPU Variant
TU104-895-A1
Maxwell 2.0
Architecture
Turing
TSMC
Foundry
TSMC
20 nm
Process Size
12 nm
2 billion
Transistors
13.6 billion
118 mm²
Die Size
545 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
1.2
OpenCL
3.0
1.1
Vulkan
1.3
5.3
CUDA
7.5
6.4
Shader Model
6.6
