• BrainChip Akida Pico Scales Down AI Processing

    mouse with big brain

    Executing spiking neural networks (SNNs), BrainChip’s licensable Akida NPU can be more power and area efficient than NPUs for convolutional neural networks (CNNs). However, converting a CNN to an SNN lessens Akida’s advantage and entails additional developer complexity. BrainChip, therefore, is leaning into its advantage, offering a new scaled-down Pico configuration that can operate without… continue reading


  • SiFive XM CPUs Accelerate RISC-V Matrix Math for AI

    modified Matrix movie poster

    SiFive has added matrix instructions to its RISC-V CPUs for AI. Targeting microcontrollers to data centers, the new cores can be used singly or replicated hundreds of times. continue reading


  • Imagination Website Trims RISC-V Portfolio

    Imagination website screenshot

    As of 25 September 2024, the Imagination Technologies website no longer features CPUs under the heading Technologies. Considering RISC-V market dynamics, it’s not for a lack of imagination the company is scaling back. continue reading


  • Altera Spins Cyclone Replacement with an Old Arm Core

    flying cow in Twister

    The forthcoming Agilex 3 family is an overdue update to the Altera product line, scaling its FPGA architecture to lower densities and (presumably) prices. Its integrated Cortex-A55, however, highlights how Arm has yet to improve upon the Cortex-A55. continue reading


  • Intel Delivers Granite Rapids Without a Hitch

    Granite Rapids

    Granite Rapids is Intel’s third consecutive Xeon launch to have gone well, meeting expectations the company has been setting for the past two years. Closing the say-do gap is essential to restore confidence in the company. continue reading


  • Potential Intel Buyers and Their Challenges

    typical sequence of articles about company mergers

    Intel has been the subject of acquisition rumors. A Broadcom or private equity deal makes more sense than a Qualcomm acquisition, but an independent Intel is the best course. continue reading



error: Unable to select