Month: October 2024
-
Arteris Expands NoC Offerings for AI Accelerators
Arteris has introduced mesh-topology support for its FlexNoC and Ncore NoC IP, catering to the growing demand from AI accelerators and many-core processors. The company’s parameterizable NoC solutions offer flexibility, performance, power efficiency, and—most importantly—scalability.
-

AMD Epyc 9005, MI325X, and Salina Debut at AI Gala
AMD paraded new data-center and PC processors at an AI-themed pep rally this week that featured partners and customers cheering the company’s advancements. Most of the products had been discussed previously but in only vague terms.
-

Intel’s Arrow Lake-S (Core Ultra 200S) Reduces Power
Intel’s Arrow Lake-S desktop processors improve performance and power efficiency compared with their predecessors, maintaining Intel’s solid competitive market position. The weak NPU is a branding problem, but the bigger AI problem is the technology’s weak consumer benefits.
-

Will the MediaTek Dimensity 9400 Put Gen AI in the Rearview Mirror?
The MediaTek Dimensity 9400 promises 28% greater multithread performance than its predecessor, and the company says its faster NPU ushers in the agentic AI era.
-

BrainChip Akida Pico Scales Down AI Processing
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…
