Supermicro, Inc. (SMCI), a Total IT Solution Provider for AI/ML, HPC, Cloud, Storage, and 5G/Edge, has officially linked-up with NVIDIA to showcase new-age retail solutions at the National Retail Federation (NRF) annual show.
According to certain reports, these solutions are meticulously designed to help retailers facilitate personalized shopping experiences, automation of logistical processes, and prevention of shrinkage, each one geared towards helping the user attract customers to their establishments and improve their overall profitability.
Now, in order to access such an intelligence brand of solutions; you would previously need specialized hardware, something which has its own affordability limitations. In response, Supermicro brings forth industry’s biggest portfolio of edge AI solutions to give retailers the tools they need for optimizing the ROI of their AI-based applications. For instance, by processing data directly where the customer is located, results are delivered with minimal latency so to eventually conceive an exceptional user experience.
“Supermicro’s innovative server, storage, and edge computing solutions improve retail operations, store security, and operational efficiency,” said Charles Liang, president and CEO of Supermicro. “At NRF, Supermicro is excited to introduce retailers to AI’s transformative potential and to revolutionize the customer’s experience. Our systems here will help resolve day-to-day concerns and elevate the overall buying experience.”
Talk about these edge AI solutions on a slightly deeper level, we begin from SYS-112B-FWT, which is a short-depth system designed to offer powerful edge compute, and at the same, leverage the latest Intel Xeon processors. Markedly enough, despite being less than 17″ in depth, the solution can seamlessly hold upto NVIDIA L40S GPUs.
Next up, we have AS -1115S-FWTRT. The stated solution is actually built upon the technical capabilities of AMD’s EPYC series processors. As a result, it is able to offer flexibility in both core counts and GPU capability by having the capacity for holding a single double-width NVIDIA L40S GPU.
Then, there is SYS-E403-14B. This one would be a compact server well-equipped to provide data center performance at remote and space-constrained locations. The promised compactness, notably enough, makes it possible to accommodate 2 single-width or 1 double-width GPU cards, including the NVIDIA L40S or NVIDIA RTX 6000 Ada Generation GPU, in remote edge locations.
Moving on to SYS-212B-FN2T, it is understood to be a 2U, short-depth edge AI system which can offer more features and capacity, as compared to the competition, while simultaneously supporting multiple data streams or workloads. More on the same would reveal how SYS-212B-FN2T arrives on the scene optimized for inferencing at the edge, meaning it can support upto 2 double-width GPU or single-width GPUs, such as the NVIDIA L4 GPU.
Another component which Supermicro is set to showcase at NRF would be SYS-222HE-TN, a dual-processor system featuring the latest Intel Xeon processors that, on their part, bring data center power into a shorter-depth platform. With the ability to hold up to 3 NVIDIA L40S GPUs, the solution in question can be expected to deliver serious inferencing power at disposal of customers.
Hold on, we still have a few bits left to unpack, considering we haven’t yet touched upon the planned showcase of AS -2115HE-FTNR. Focused on handling the most demanding workloads, this solution translates to a powerful and versatile 3U edge AI platform that boasts 10 PCIe 5.0 x16 slots or 20 PCIe 5.0 x8 slots (in physical x16 slots). Furthermore, slots can be fitted, at launch, with up to 8 double-width GPU cards, such as NVIDIA’s H100 GPU leveraging NVIDIA NVLink.
On top of that, the system can also be configured with 19 single-width GPU cards, including NVIDIA’s low-profile or single-width product families, or combined with different add-on cards, such as graphics controllers, thus enabling the technology to remain ideal for environments including large control rooms.