Skip to main content

NVIDIA HGX B200 NVLink Switch Changes Explained

·431 words·3 mins
AI NVLINK Switch HGX B200 H100
Table of Contents

At Computex 2024, Foxconn subsidiary Ingrasys displayed a bare Nvidia HGX B200 motherboard without heatsinks, revealing a major hardware update.
The NVLink Switch chip count has been reduced from four (H100 generation) to two (B200 generation), and their placement on the board has shifted.

Nvidia NVLink Switch


First-Generation NVSwitch
#

The first NVSwitch was introduced with the Nvidia DGX-2 supercomputer.

  • 20 billion transistors
  • 18 ports (50 GB/s each)
  • Total bandwidth: 900 GB/s

This switch enabled up to 9 devices to communicate with any other 9 devices.
It also included control I/O interfaces:

  • PCIe Gen 2 x4 management port
  • I²C and GPIO

In DGX-2, each baseboard used 6 NVSwitches to create a fully connected GPU network.

Nvidia NVLink Switch

The DGX-2 system had two baseboards to connect all 16 V100 GPUs. Each NVSwitch had 2 unused ports, which could be used with POWER9 CPUs that natively supported NVLink 2.0.

Nvidia NVLink Switch

Below: Inspur NF5488M5 HGX-2, clearly showing 6 NVSwitch heatsinks.

Nvidia NVLink Switch


Second-Generation NVSwitch (A100 Era)
#

Nvidia NVLink Switch

With the Nvidia A100, NVSwitch heatsinks became larger. The HGX A100 platform was entirely designed and pre-assembled by Nvidia before shipping to OEMs.

Below: Inspur NF5488A5 HGX A100 with 6 NVSwitch heatsinks visible.

Nvidia NVLink Switch


Third-Generation NVSwitch (H100 Era)
#

Nvidia NVLink Switch

In the H100 generation, 4 NVSwitches were placed on one side of the baseboard.

Below: ASUS ESC N8A E12 HGX H100 system.

Nvidia NVLink Switch

The HGX H200 design looks almost identical to HGX H100.

Nvidia NVLink Switch


Fourth-Generation NVLink Switch (B100/B200 Era) #

HGX B100 with Heatsinks Installed
#

Nvidia NVLink Switch

Launch Event Photo of HGX B100
#

Nvidia NVLink Switch

Notice: near the edge connector, PCIe Retimers appear instead of NVSwitch chips.

Nvidia NVLink Switch

With the HGX B200 bare motherboard, the NVLink Switch positions are clear. Nvidia confirmed that the B100 and B200 share the same NVSwitch layout.

Nvidia NVLink Switch

Here, PCIe Retimers are exposed. These typically use smaller heatsinks since their TDP is only ~10–15W, depending on vendor (Astera Labs, Broadcom, Marvell, etc.).

Nvidia NVLink Switch

Key update: Only two NVLink Switches remain, now placed in the center of the motherboard, instead of four near the edges as before.

Nvidia NVLink Switch


Conclusion: Why Nvidia Changed NVSwitch Design
#

The latest NVLink Switch chips are larger and moving them to the center of the board helps:

  • Reduce trace length → improves high-speed signaling
  • Optimize GPU-to-switch communication paths

On the HGX B200, GPUs are grouped in sets of four on each side, minimizing signal distance to the central NVLink Switches.

Nvidia NVLink Switch


Key Takeaways
#

  • Nvidia reduced NVSwitch count from 4 to 2 on HGX B200.
  • Switches are now centrally located for shorter trace length.
  • PCIe Retimers are used along the edges instead of switches.
  • This redesign improves signal integrity, efficiency, and scalability for the next-gen B200 GPUs.

Related

NVIDIA’s Core Moat: CUDA
·532 words·3 mins
AI GenAI NVIDIA GPU CUDA
大厂加速自研AI芯片:Nvidia主导地位受到挑战
·17 words·1 min
AI GenAI NVIDIA GPU OpenAI
英伟达发布H200, 高性价比全面升级
·62 words·1 min
News NVIDIA H200 H100