Broadcom is working to combine optical connectivity instantly into GPUs

0
35
Broadcom is working to combine optical connectivity instantly into GPUs


Ahead-looking: We’re approaching some extent the place conventional copper interconnections will not be capable to carry sufficient knowledge to maintain GPUs and different specialised chips absolutely utilized. The AI market is urgently demanding a next-generation resolution to this interconnection bottleneck, and Broadcom seems to be engaged on an optics-based resolution that’s nearer to the chip itself.

Broadcom is creating new silicon photonics know-how aimed toward considerably rising the bandwidth out there to GPUs and different AI accelerators. By using co-packaged optics (CPOs), the fabless chip producer goals to combine optical connectivity elements instantly into GPUs, enabling greater knowledge charges whereas concurrently decreasing energy necessities.

The corporate has been engaged on CPO options for a number of years and showcased its newest developments on the latest Sizzling Chips conference. Broadcom’s “optical engine” reportedly delivers a complete interconnect bandwidth of 1.6 TB/sec, equal to six.4 Tbit/sec or 800 GB/sec in every course.

This new connection can present “error-free” knowledge switch to a single chiplet, reaching efficiency ranges akin to Nvidia’s NVLink and different specialised knowledge middle options. Nevertheless, Broadcom has not but included its optical interconnections right into a market-ready GPU, such because the A100 or MI250X. As a substitute, it used a take a look at chip designed to emulate an actual GPU for demonstration functions.

In keeping with Manish Mehta, Broadcom’s vp of the optical techniques division, copper connections begin to degrade after simply 5 meters. Whereas optical communications have lengthy been seen as the answer to this sign degradation concern, they historically require way more energy than copper-based applied sciences.

For instance, Nvidia estimates that an optics-powered NVL72 system would require a further 20 kilowatts per rack, on high of the 120 kilowatts the system already consumes.

Broadcom has managed to scale back energy consumption with the usage of co-packaged optics, which locations particular person transceivers in direct contact with the GPU. The corporate utilized TSMC’s chip-on-wafer-on-substrate (CoWoS) packaging know-how to bond a pair of high-bandwidth reminiscence stacks to the compute die. The logic and reminiscence elements of the chip sit on a silicon interposer, whereas Broadcom’s optical engine is situated on the substrate.

Mehta defined that CPO know-how may join as much as 512 particular person GPUs throughout eight racks, permitting all the setup to operate as a single system. Compared, Nvidia’s NVL72 can obtain comparable unified computing capabilities with “simply” 72 GPUs, suggesting that Broadcom’s resolution may ultimately supply a aggressive benefit for next-generation AI workloads.

LEAVE A REPLY

Please enter your comment!
Please enter your name here