- Mia
- September 10, 2023
- 8:14 am
Harry Collins
Answered on 8:14 am
For 100G mode with QPSK modulation, the FEC type could be oFEC (OpenROADM) or SDFEC (Soft Decision FEC) with probabilistic constellation shaping.
For 200G mode with QPSK modulation, the FEC type could be SDFEC with probabilistic constellation shaping.
For 400G mode with 16-QAM modulation, the FEC type could be SDFEC with probabilistic constellation shaping.
The 400G-BIDI module can work in different ways depending on the switch and the application. It can use different types of FEC (Forward Error Correction) to improve the signal quality. FEC is a method of adding extra bits to the data to detect and correct errors.
One way is to use the 400G-SR4.2 or 4x 100G-SR1.2 mode, where the switch does the FEC and the module does not. The FEC used here is called KP-FEC, which is a type of Reed-Solomon FEC.
Another way is to use the 4x 100G-BIDI (100G-SRBD) mode, where the module does the FEC and the switch does not. The module uses a different FEC for each pair of fibers, which can work with the existing 100G-BIDI modules. This way, you can keep using your old 100G-BIDI modules with the new 400G-BIDI modules.
People Also Ask
NVIDIA’s View on Silicon Photonics
The current explosive growth of AI models and calculations requires parallel operations on multiple GPUs, which has led to an increase in the interface bandwidth between GPUs. NVIDIA is the most direct user in the AI optical module market. It has put forward several requirements and prospects for integrated photonics:
Unveiling the Titans: Nvidia GeForce RTX 4090 vs. Nvidia A100 for Ultimate Performance
The Nvidia GeForce RTX 4090 and the Nvidia A100, in an endless search for improvement in computer technology, are the most advanced graphics processing units that have ever been made. These two technological giants, though they spring from similar roots of invention, have different purposes of existence. In this article,
A100/H100/GH200 Cluster: Network Architecture and Optical Module Requirements
Traditional data centers have undergone a transition from a three-tier architecture to a leaf-spine architecture, primarily to accommodate the growth of east-west traffic within the data center. As the process of data migration to the cloud continues to accelerate, the scale of cloud computing data centers continues to expand. Applications
Development of PCIE
In 2012, communication between two boards was achieved over optical fiber using the PCIE protocol. The advantages of doing so are: the reserved optical port allows the two devices to be physically separated, and the reserved optical interface and memory are compatible with and can be accessed by each other.
Unlocking the Power of NVIDIA H100 GPUs in High-Performance Servers
The high-pressure landscape of contemporary computing that is characterized by increasing data volume and rising computational requirements has witnessed the emergence of the NVIDIA H100 GPU, a trailblazer in high-performance servers. The article seeks to unveil the revolutionary features as well as novel technologies behind the NVIDIA H100 GPU, which
Unlocking the Potential of Nvidia MPO Cables for Next-Gen Fiber Networks
At the forefront of innovation, Nvidia MPO cables are in today’s ever-changing world of telecommunications and data center networking. They promise a significant boost for fiber networks in terms of capacity, efficiency, and scalability this paper seeks to assess the various possibilities offered by these advanced cabling solutions with respect
Related Articles
800G SR8 and 400G SR4 Optical Transceiver Modules Compatibility and Interconnection Test Report
Version Change Log Writer V0 Sample Test Cassie Test Purpose Test Objects:800G OSFP SR8/400G OSFP SR4/400G Q112 SR4. By conducting corresponding tests, the test parameters meet the relevant industry standards, and the test modules can be normally used for Nvidia (Mellanox) MQM9790 switch, Nvidia (Mellanox) ConnectX-7 network card and Nvidia (Mellanox) BlueField-3, laying a foundation for
NVIDIA’s View on Silicon Photonics
The current explosive growth of AI models and calculations requires parallel operations on multiple GPUs, which has led to an increase in the interface bandwidth between GPUs. NVIDIA is the most direct user in the AI optical module market. It has put forward several requirements and prospects for integrated photonics:
Unveiling the Titans: Nvidia GeForce RTX 4090 vs. Nvidia A100 for Ultimate Performance
The Nvidia GeForce RTX 4090 and the Nvidia A100, in an endless search for improvement in computer technology, are the most advanced graphics processing units that have ever been made. These two technological giants, though they spring from similar roots of invention, have different purposes of existence. In this article,
A100/H100/GH200 Cluster: Network Architecture and Optical Module Requirements
Traditional data centers have undergone a transition from a three-tier architecture to a leaf-spine architecture, primarily to accommodate the growth of east-west traffic within the data center. As the process of data migration to the cloud continues to accelerate, the scale of cloud computing data centers continues to expand. Applications
Development of PCIE
In 2012, communication between two boards was achieved over optical fiber using the PCIE protocol. The advantages of doing so are: the reserved optical port allows the two devices to be physically separated, and the reserved optical interface and memory are compatible with and can be accessed by each other.
Unlocking the Power of NVIDIA H100 GPUs in High-Performance Servers
The high-pressure landscape of contemporary computing that is characterized by increasing data volume and rising computational requirements has witnessed the emergence of the NVIDIA H100 GPU, a trailblazer in high-performance servers. The article seeks to unveil the revolutionary features as well as novel technologies behind the NVIDIA H100 GPU, which
Unlocking the Potential of Nvidia MPO Cables for Next-Gen Fiber Networks
At the forefront of innovation, Nvidia MPO cables are in today’s ever-changing world of telecommunications and data center networking. They promise a significant boost for fiber networks in terms of capacity, efficiency, and scalability this paper seeks to assess the various possibilities offered by these advanced cabling solutions with respect