在本系列关于 NVIDIA Jetson AGX Orin 的前几版中,我们了解了 AGX Orin 是什么、它的技术特性、主要构建模块和关键的嵌入式视觉用例。以下是这两篇文章的链接:
今天,让我们看看这款高性能处理器与其前辈相比如何。
很明显,NVIDIA® Jetson™ 模块具有不同的 AI 计算能力、能效和外形尺寸。这也是NVIDIA相机越来越受欢迎的原因之一。整个 NVIDIA® Jetson™ 产品系列使用通用软件堆栈,以促进和扩大部署。这些平台配备了相同的喷气背包软件开发工具包(SDK),其中包括板级支持包(BSP),Linux操作系统和CUDA。
让我们看看 NVIDIA® Jetson AGX Orin™ 与 Jetson 家族的其他成员相比如何:
在本节中,让我们更深入地了解 Jetson AGX Orin 系列与其他 Jetson 模块相比如何。下表显示了它们之间的逐个功能比较:
Jetson Nano | Jetson TX2/TX2i | Jetson NX Xavier | Jetson AGX Xavier | Jetson NX Orin | Jetson AGX Orin | |
---|---|---|---|---|---|---|
AI Performance | 472 GFLOPs | 1.33 TFLOPs/ 1.26 TFLOPs | 21 TOPS | 32 TOPS | 100 TOPS | 275 TOPS |
Power | 5W / 10W | 7.5W / 15W | 10W / 15W | 10W / 15W / 30W | 10W / 15W / 25W | 15W / 30W / 50W |
GPU | 128-core Maxwell @ 921 MHz | 256-core Pascal @ 1.3 GHz | 384-core Volta | 512-core Volta @ 1.37 GHz | 1024-core NVIDIA Ampere GPU | NVIDIA Ampere architecture with 2048 NVIDIA CUDA cores |
CPU | 4-core ARM A57 @ 1.43 GHz | 4-core ARM Cortex-A57 @ 2 GHz, 2-core Denver2 @ 2 GHz | 6-core ARM Carmel v8.2 | 8-core ARM Carmel v.8.2 @ 2.26 GHz | 8-core Arm® Cortex®-A78AE v8.2 64-bit CPU 2MB L2 + 4MB L3 | 12-core ARM Cortex A78AE v8.2 64bit @ 2 GHz |
Tensor cores | — | — | 48 | 64 | 32 | 64 |
Memory | 4 GB LPDDR4, 25.6 GB/s | 8 GB 128-bit LPDDR4, 58.3 GB/s | 8 GB 128-bit LPDDR4, 51.2GB/s | 16 GB 256-bit LPDDR4, 137 GB/s | 16GB 128-bit LPDDR5 102.4 GB/s | 32 GB 256-bit LPDDR5 204.8 GB/s |
Storage | MicroSD | 32 GB eMMC 5.1 | 16 GB eMMC 5.1 | 32 GB eMMC 5.1 | Supports external NVMe | 64GB eMMC 5.1 |
Video encode | 1x 4K30 (H.265) 2x 1080p60 (H.265) | 1x 4K60 (H.265) 3x 4K30 (H.265) 4x 1080p60 (H.265) | 2x 4K30 (H.265) 6x 1080p60 (H.265) | 4x 4K60 (H.265) 16x 1080p60 (H.265) 32x 1080p30 (H.265) | 1x 4K60 (H.265) 3x 4K30 (H.265) 6x 1080p60 (H.265) 12x 1080p30 (H.265) | 2x 4K60 | 4x 4K30 | 8x 1080p60 | 16x 1080p30 (H.265) |
Video decode | 1x 4K60 (H.265) 4x 1080p60 (H.265) | 2x 4K60 (H.265) 7x 1080p60 (H.265) 14x 1080p30 (H.265) | 2x 4K60 (H.265) 12x 1080p60 (H.265) 16x 1080p30 (H.265) | 2x 8K30 (H.265) 6x 4K60 (H.265) 26x 1080p60 (H.265) 72x 1080p30 (H.265) | 1x 8K30 (H.265) 2x 4K60 (H.265) 4x 4K30 (H.265) 9x 1080p60 (H.265) 18x 1080p30 (H.265) | 1x 8K30 | 3x 4K60 | 6x 4K30 | 12x 1080p60| 24x 1080p30 (H.265) |
USB | (4x) USB 3.0 + Micro-USB 2.0 | (1x) USB 3.0 + (1x) USB 2.0 | (3x) USB 3.1 + (4x) USB 2.0 | (3x) USB 3.1 + (4x) USB 2.0 | 3x USB 3.2 | 3x USB 3.2 |
PCI-Express lanes | 4 lanes PCIe Gen 2 | 5 lanes PCIe Gen 2 | 1 x1 (PCIe Gen3) + 1 x4 (PCIe Gen4) | 16 lanes PCIe Gen 4 | 1 x4 + 3 x1 (PCIe Gen4, Root Port & Endpoint) | 2 x8 (or 1×8 + 2×4), 1 x4, 2 x1 PCIe Gen 4 |
@article{Kumar2022Aug,
author = {Kumar, Prabu},
title = {{NVIDIA Jetson Orin{\texttrademark} vs. other NVIDIA Jetson modules {\textendash} a detailed look - e-con Systems}},
journal = {e-con Systems},
year = {2022},
month = aug,
urldate = {2023-06-17},
language = {english},
url = {https://www.e-consystems.com/blog/camera/technology/nvidia-jetson-orin-vs-other-nvidia-jetson-modules-a-detailed-look/#pll_switcher}
}
@misc{BibEntry2023Jun,
title = {{NVIDIA Jetson Orin}},
journal = {NVIDIA},
year = {2023},
month = jun,
urldate = {2023-06-17},
language = {chinese},
note = {[Online; accessed 17. Jun. 2023]},
url = {https://www.nvidia.cn/autonomous-machines/embedded-systems/jetson-orin}
}
@misc{BibEntry2023Jun,
title = {{适用于新一代自主机器的 NVIDIA 嵌入式系统}},
journal = {NVIDIA},
year = {2023},
month = jun,
urldate = {2023-06-17},
language = {chinese},
note = {[Online; accessed 17. Jun. 2023]},
url = {https://www.nvidia.cn/autonomous-machines/embedded-systems}
}