-
Axelera’s Europa NPU Hits 629 TOPS in 45 W
Edge-AI specialist Axelera is moving upmarket. The company’s new Europa AI accelerator (NPU) triples the raw performance of its Metis NPU to 629 TOPS (and more than quadruples its Yolo V8 throughput), positioning it for automotive, robotics, and even data-center applications. Slated to ship in the first half of 2026, the new device adds capabilities continue reading
-
Nvidia’s 800 VDC Proves Jensen is Listening
Among the revelations and reintroductions of rack-scale systems at OCP earlier this month, Nvidia’s contribution of the 800 VDC architecture seems to have stolen the show. This past year, Nvidia’s most prominent customers have experienced the rising inefficiencies of using established power architectures as they rapidly ramped up GB200 NVL72 (Blackwell) racks. The announcement of continue reading
-
Byrne-Wheeler Report, Episode 3 (Revenge of the 5 MW Rack)
The boys discuss the AMD-OpenAI deal and OCP news including AMD Helios, Broadcom Thor Ultra, Intel Crescent Island, and SUE/ESUN/SUE-T. continue reading
-
SiFive Adds to Intelligence Family
SiFive’s refreshed Intelligence family features vector/matrix units, a low-cost option, and upgrades for AI, encryption, customization, and performance. continue reading
-
Intel Details 18A Panther Lake & Clearwater Forest Chips
Intel has revealed architectural updates for its 18A-based PC (Panther Lake) and server (Clearwater Forest) processors, the first chips on the new node. The 18A process features Ribbon FET (GAA) transistors and Power Via backside power delivery. Clearwater Forest uses 12 computing tiles with Darkmont E-cores; it and Panther Lake update their E-cores for better… continue reading
-
Tenstorrent Licenses Ascalon RISC-V CPU and Tensix Neo NPU IP
Tenstorrent now broadly licenses its CPU and NPU cores. The Ascalon X delivers IPC approaching Arm’s fastest CPUs, and the Tensix Neo is a scalable NPU block. The company also provides supporting design resources. continue reading
Popular
Sponsored Content and Plugs
- Slash Server Costs Without Hardware or Software Changes
- Ceva Boosts NeuPro-M NPU Throughput and Efficiency
- MEXT Helps IT Leaders Find the Sweet Spot
- Chips Act Backs Chiplets
- Arteris Expands NoC Offerings for AI Accelerators
Other Sites You Might Like
Read More
Amazon AMD Arm auto Broadcom business Cerebras Ceva consumer CPU data center DPU DSP edge AI embedded FPGA Google GPU Imagination industrial Intel interconnect Marvell MCU MediaTek Meta Microsoft MLPerf NPU (AI accelerator) Nvidia NXP OpenAI PC process tech Qualcomm Renesas RISC-V SambaNova Semidynamics SiFive smartphone SoftBank software Tenstorrent Tesla