Silicon for AI, Cloud, Telecom and Digital Infrastructure Converge Digest tracks the semiconductor platforms powering next-generation networks, AI clusters, optical systems, data centers, wireless infrastructure and edge devices. |
Silicon Pillars AI AcceleratorsNetworking SiliconOptical DSPsChipletsMemorySilicon PhotonicsWireless SoCs |
| Tracking: Tapeouts • Process Nodes • Packaging • Foundry Partnerships • AI Inference • Ethernet Switching • Coherent Optics • Memory Bandwidth • Power Efficiency • Supply Chain |
Intel expanded its Agilex FPGA portfolio and broadened its Programmable Solutions Group (PSG) offerings to handle the increased demand for customized workloads, including enhanced AI capabilities, and to provide lower...
Intel announced glass substrates for next-generation advanced packaging The new material offers ultra-low flatness and better thermal and mechanical stability, resulting in much higher interconnect density in a substrate. Compared...
Shares of Arm Holdings plc surged 25% on their first day of trading, closing at $63.59. The company priced its initial public offering of 95,500,000 American depositary shares at a...
Nokia unveiled its 7730 Service Interconnect Router (SXR) family of next-generation IP access, aggregation and edge platforms based on its new FPcx network processing unit (NPU), 112G SerDes, and SFP-DD...
Credo introduced new Dove 800D and 410D PAM4 DSPs chips optimized for active optical cables and short reach tranceivers targeting hyperscale data centers and AI applications. Sampling is underway. The...
Credo Technology announced the availability of its Seagull 452 family of high-performance, low-power optical Digital Signal Processors (DSPs) targeted at the burgeoning 400G Active Optical Cable (AOC) market for AI...
Tower Semiconductor has agreed to will utilize Intel Foundry Service’s advanced manufacturing facility in New Mexico. Under an agreement announced by the firms, Tower will invest up to $300 million...
Samsung Electronics is preparing to begin mass production of the highest-capacity 32-gigabit (Gb) DDR5 DRAM using 12 nm-class process technology. This achievement comes after Samsung began mass production of its...
by James E. Carroll, Editor Bringing optical I/O as close as possible to the processor is key design aim for high-performance computing. Intel and Ayar Labs demonstrate a 4 Tbps...
Lumotive, a start-up based in Seattle, announced full production implementation of its Light Control Metasurface technology – the world's first digital beam steering solution. The Lumotive LM device is a...
Google unveiled its 5th generation Tensor Processing Unit (TPU v5e), promising up to 2x higher training performance per dollar and up to 2.5x inference performance per dollar for LLMs and...
In a talk at this week’s Hot Chips event at Stanford University, Bill Dally, NVIDIA’s chief scientist and senior vice president of research previewed a deep neural network (DNN) accelerator...
At this week’s Hot Chips event at Stanford University, Intel presented two sessions revealing technical specifications and features of the Xeon platform architecture and offerings coming in 2024, along with...
A private dossier for networking and telecoms