Latest Machine Learning News

GaN-based power delivery board targets 96.5% efficiency and 2,100 W/in3 for NVIDIA's next-generation 800 VDC data center…

GaN-based power delivery board targets 96.5% efficiency and 2,100 W/in3 for NVIDIA's next-generation 800 VDC data center architecture.

Learn how the EU's premier lending institution is deploying billions in loans, equity, and blended finance to build a…

Learn how the EU's premier lending institution is deploying billions in loans, equity, and blended finance to build a sovereign European chip ecosystem.

The Netherlands is securing global leadership in integrated photonics, a technology using light instead of electricity…

The Netherlands is securing global leadership in integrated photonics, a technology using light instead of electricity for faster, more energy-efficient data processing, essential for AI, healthcare, and mobility.

The Renesas 365 Development platform unifies electronics design from MCU recommendation to validation.

The Renesas 365 Development platform unifies electronics design from MCU recommendation to validation.

Announced at Embedded World, the new Genio lineup spans value to flagship tiers, with on-device GenAI acceleration…

Announced at Embedded World, the new Genio lineup spans value to flagship tiers, with on-device GenAI acceleration ranging from 6 TOPS to over 50 TOPS.

Announced today at Embedded World, Synaptics claims the SYN765x as the first industry's first AI Native Wi-Fi 7 solution…

Announced today at Embedded World, Synaptics claims the SYN765x as the first industry's first AI Native Wi-Fi 7 solution developed specifically for the IoT. It provides Wi-Fi 7, Bluetooth 6.0, and 802.15.4 connectivity and features a Cortex-M52 and Ethos-U55 NPU.

In this exclusive interview, the Seattle startup says its software-ML-hardware co-design—announced today—converts…

In this exclusive interview, the Seattle startup says its software-ML-hardware co-design—announced today—converts off-the-shelf FPGA servers into high-efficiency AI inference engines.

Announced today, the new ChipStack AI Super Agent from Cadence automates front end silicon design and verification,…

Announced today, the new ChipStack AI Super Agent from Cadence automates front end silicon design and verification, delivering a 10X productivity increase.

Singulation (wafer dicing) is critical for IC wafer manufacturing. Laser/plasma dicing is replacing mechanical methods.…

Singulation (wafer dicing) is critical for IC wafer manufacturing. Laser/plasma dicing is replacing mechanical methods. Lidrotec's laser-liquid technology offers virtually zero-damage cuts.

Announced today, the new FPGAs build off of AMD’s existing ecosystem with modernized memory, I/O, and security.

Announced today, the new FPGAs build off of AMD’s existing ecosystem with modernized memory, I/O, and security.

Announced today, Cadence's new Tensilica HiFi iQ DSP doubles compute, octuples AI performance, and cuts power by 25% over…

Announced today, Cadence's new Tensilica HiFi iQ DSP doubles compute, octuples AI performance, and cuts power by 25% over its predecessor, targeting next-gen AI-voice and immersive automotive audio.

All About Circuits met with Texas Instruments at CES 2026 to learn about the company’s newest automotive SoCs.

All About Circuits met with Texas Instruments at CES 2026 to learn about the company’s newest automotive SoCs.

In this article, Gordon posed a set of questions to TSMC about their next steps going forward.

In this article, Gordon posed a set of questions to TSMC about their next steps going forward.

Do you remember when supercomputers were described by their processing power? That was so 2024. Today, we talk about the…

Do you remember when supercomputers were described by their processing power? That was so 2024. Today, we talk about the power for processing. Goodbye terraops, hello terrawatt-hours!

Enjoy this roundup of our favorite All About Circuits research news articles of 2025!

Enjoy this roundup of our favorite All About Circuits research news articles of 2025!

By 2030, Korean chipmakers are projected to dominate AI memory (HBM), strengthen foundry/packaging, and gain traction in…

By 2030, Korean chipmakers are projected to dominate AI memory (HBM), strengthen foundry/packaging, and gain traction in the stable analog/power IC market, boosting profitability and global influence.

Korean semiconductor giants—like Samsung and SK hynix—are shifting focus from traditional memory to AI-driven tech,…

Korean semiconductor giants—like Samsung and SK hynix—are shifting focus from traditional memory to AI-driven tech, such as HBM, amid global competition, US controls, and government support.

In the final part of this series, we zero in on three photonics technologies expected to be essential for demanding…

In the final part of this series, we zero in on three photonics technologies expected to be essential for demanding computing and communication systems of the future.

Announced today, Broadcom’s Gen 8 128G Fibre Channel switch portfolio is claimed as the first quantum-safe, SAN…

Announced today, Broadcom’s Gen 8 128G Fibre Channel switch portfolio is claimed as the first quantum-safe, SAN architecture with 128G speed, AI-powered SAN management, and quantum-safe cryptography.