The idea of connecting multiple graphics cards isn’t a new one. On the contrary, it has existed since at least the late 1990s.
Although this concept sounds enticing on paper, SLI never really took off as anticipated. However, NVIDIA wasn’t prepared to back down, so they created NVLink as a direct successor.
Continue reading if you desire to learn about the differences between NVLink and its previous version and if it has successfully accomplished the goal of two graphics cards working as a unified unit.
So, what is NVLink?
If you want the technical definition, NVLink is a wire-based communications protocol serial multi-lane short-range communication link. In simple terms, it’s a method of utilizing two graphics cards as one for a significant boost in performance.
Table of ContentsShow
The Difference Between NVLink And SLI Has Huge Potential
Unlike SLI, NVLink uses mesh networking, a local network configuration in which the infrastructure nodes connect directly in a non-hierarchical manner.
This enables each node to relay information instead of routing everything through a particular node. What’s useful about this setup is that nodes dynamically self-organize and self-configure, which allows adaptable distribution of the workload.
Essentially, where SLI struggled is where NVLink shines the brightest, and that is the velocity at which data is exchanged.
NVLink doesn’t care about SLI’s master-slave structure, where one card in the setup functions as the master and is responsible for collecting slaves’ data and creating the final output. By utilizing the mesh networking infrastructure, it can treat every node equally and thus substantially boost rendering speed.
The largest benefit of NVLink, in comparison to SLI, is that, because of the mesh network, both graphics cards’ memories are constantly accessible.
This was a point of bewilderment for those unfamiliar with SLI’s multi-GPU setup. It was reasonable that if two GPUs each have a gigabyte of RAM, their combined memory would be two gigabytes. However, that simply wasn’t the case in practice. With NVLink, it’s finally safe to say that one plus one equals two.
To handle frame rendering, SLI used Alternative Frame Rendering (or AFR for short), which meant that each linked card handled separate frames.
In a two GPU setup, one card would render even frames while the other rendered odd frames. While this was a reasonable solution, it was not executed in the best way (mostly due to hardware limitations) and caused a lot of problematic micro stuttering.
Another key to faster image processing is the NVLink Bridge. SLI bridges had a 2 GB/s bandwidth at most, but the NVLink Bridge promises an astounding 200 GB/s in the most extreme cases. However, as you might have expected from such a colossal number, it can be misleading.
The 160 and 200 GB/s NVLink bridges can only be used for NVIDIA’s professional-grade GPUs, the Quadro GP100 and GV100, respectively. While this means there is technically a device out there with those bandwidth speeds, they are intended for tasks such as AI testing or CGI production.
The bridges for consumer-focused GPUs are slower but still a significant improvement over SLI. Top-tier enthusiasts who acquire two Titan RTXs or two RTX 2080 Ti’s can potentially experience a remarkable 100 GB/s bandwidth.
Is This Finally The Way A Multi-GPU System Becomes The Standard?
Regrettably, it appears that we are still distant from that. However, NVLink has the potential to introduce change with its “simpler than ever” way for game developers to utilize everything that a multiple-GPU setup has to offer fully.
Ironically, older games might produce fewer FPS with NVLink than with a single GPU. There are only a restricted number of modern games that can actually provide the 2-as-1 GPU experience.
This is not meant to discourage anyone, but it’s a candid truth that, even though the possibility exists, it’s presently not beneficial to acquire two GPUs and link them using NVLink. The same goes for its forerunner, SLI.
That isn’t to say that this tech will never be viable, but the same issues that plagued SLI are presently limiting NVLink.
With the arrival of a new generation of GPUs from both NVIDIA and AMD, it will be fascinating to see if, and to what degree, we will see support for multi-GPU systems.
As of 2025, only NVIDIA’s high-end RTX 3090 GPU has multi-GPU support built-in. On AMD’s side, it appears that implementation has also phased out.
