Imagination Technologies’ new licensable CXM GPU family brings high-dynamic-range (HDR) support to its mainstream offering. With three new models, the company claims high area efficiency.
The company has streamlined its data-center AI roadmap, creating a new version of Falcon Shores that combines the Xe GPU architecture with some aspects of Habana’s AI design, which is delayed to 2025.
Moffett, a startup headquartered in Shenzen, China, has released AI accelerators that address sparsity to increase performance 32x. The company offers three cards spanning a 70–250 W TDP range.
Nanosheet transistors are superior to FinFETs for logic transistors, offering an adjustable gate width, superior electrostatic characteristics, and better channel-thickness uniformity as well as faster switching speed. They have drawbacks for SRAM and I/O transistors, however.
Qualcomm announced a Snapdragon 7+ Gen 2 that reuses the premium Snapdragon 8+ Gen 1 die with altered specs. Market conditions left the company with excess inventory that it’s moving into the midpremium market.
Semidynamics Performs RISC–V Surgery Semidynamics offers fully customized RISC–V CPUs for clients requiring capabilities beyond what’s readily available. The ability to maintain many outstanding memory requests boosts performance for applications
Broadcom is challenging the conventional topology linking AI engines in training supercomputers/clusters, offering a version of its Jericho Ethernet switch chip set for AI.
Israeli startup Hailo has released the Hailo 15, its second-generation chip for smart cameras. Hailo 15 is a standalone processor with an AI engine and comes in three variants ranging from 7 to 20 TOPS.
Google employs optical interconnect when building a 4,096-node AI supercomputer featuring its TPUv4 accelerator chip. The result is much higher potential performance coupled with a sharp drop in carbon emissions.
The Dimensity 9200+ is a midlife kicker for MediaTek’s flagship smartphone processor, offering 5–10% more CPU and graphics performance than the original 9200. The company also renamed its low-end 5G products.
Flex Logix Drops Chips, Sticks With IP Flex Logix is changing its business model, opting to offer its InferX block as IP and ceasing chip-building operations. It’ll serve chipmakers requiring either AI inference or DSP capability. Bryon Moyer Flex
Google Discloses TPUv4 Details Google’s TPUv4 excels at AI models employing embeddings owing to its sea of SparseCores that supplement its two main cores. Targeting inference, the TPUv4i has only a single larger core to reduce power. Joseph Byrne