TECH NEWS | d-Matrix adopts NVIDIA technology for AI inference racks
d-Matrix said the approach will allow it to use established rack designs, power and cooling infrastructure and supply-chain capabilities as it prepares to deploy its XPU technology at larger scale.
AI inference chipmaker d-Matrix will use NVIDIA’s NVLink Fusion technology to connect its next-generation Raptor XPUs to NVIDIA’s AI infrastructure platform, as the companies seek to accelerate the deployment of specialized processors at rack scale.
The move will connect Raptor XPUs to NVIDIA’s NVLink scale-up and Spectrum-X scale-out networking, as well as the NVIDIA MGX rack architecture and broader AI platform.
d-Matrix said the approach will allow it to use established rack designs, power and cooling infrastructure and supply-chain capabilities as it prepares to deploy its XPU technology at larger scale.
“Demand for inference is soaring, but capital, time and energy remain finite,” said Sid Sheth, co-founder and CEO of d-Matrix. “With NVLink Fusion and MGX, we can integrate our Raptor XPUs into a broadly deployed, liquid-cooled architecture, giving customers a faster, lower-risk path to deploy and scale ultralow-latency inference.”
NVLink Fusion is designed to allow custom XPUs and CPUs to connect to NVIDIA’s infrastructure platform. The company said the technology gives silicon developers access to networking, rack architecture, power, cooling and other infrastructure while allowing them to focus on their processor designs.
For d-Matrix, the technology is intended to reduce the complexity of moving its Raptor XPUs from custom silicon to large-scale deployments. The company plans to use NVIDIA NVLink to connect its XPUs in a high-bandwidth, low-latency scale-up domain.
The Raptor-based systems will also be able to operate alongside NVIDIA GPU-based systems such as the Vera Rubin NVL72 for disaggregated inference, according to NVIDIA.
d-Matrix also plans to integrate NVIDIA Vera CPUs, ConnectX-9 SuperNICs, BlueField-4 DPUs and Spectrum-X Ethernet networking into its systems.
NVIDIA said combining these technologies with NVLink and MGX will give d-Matrix a common platform for deploying specialized inference alongside NVIDIA systems.
The arrangement reflects NVIDIA’s effort to extend its rack-scale infrastructure beyond its own GPUs to other processor architectures. NVLink Fusion allows silicon companies to use NVIDIA’s networking, systems, software and supply-chain capabilities while developing specialized compute products.
NVIDIA said the approach is intended to give data centers greater flexibility by allowing a common rack architecture to accommodate GPUs, CPUs and XPUs instead of requiring separate designs for different processor types.
Full disclosure: All news articles published on the TechSabado website are written by human journalists, unless otherwise specified. Final text editing is also performed by human editors, with artificial intelligence (AI) used only to assist with additional grammar and style guide corrections..
————————————————————————-
TEN YEARS OF TECHSABADO!
PLEASE LIKE our FACEBOOK PAGE and SUBSCRIBE to OUR YOUTUBE & SPOTIFY channels.
WATCH TECHSABADO ON OUR YOUTUBE CHANNEL:
Full disclosure: All news articles published on the TechSabado website are written by human journalists, unless otherwise specified. Final text editing is also performed by human editors, with artificial intelligence (AI) used only to assist with additional grammar and style guide corrections..
————————————————————————-
TEN YEARS OF TECHSABADO!
PLEASE LIKE our FACEBOOK PAGE and SUBSCRIBE to OUR YOUTUBE & SPOTIFY channels.
WATCH TECHSABADO ON OUR YOUTUBE CHANNEL:
WE ARE ALSO ON SPOTIFY
WATCH OUR OTHER YOUTUBE CHANNELS:
PLEASE LIKE our FACEBOOK PAGE and SUBSCRIBE to OUR YOUTUBE CHANNEL.
WE ARE ALSO ON SPOTIFY
WATCH OUR OTHER YOUTUBE CHANNELS:
PLEASE LIKE our FACEBOOK PAGE and SUBSCRIBE to OUR YOUTUBE CHANNEL.
