Chuck was also the moderator for the opening plenary session Chiplets: Where We Are Today. The speakers were Jim Handy of ...

Breaking complex chips into smaller pieces allows for much more customization, particularly for domain-specific applications, ...

Reasoning models like OpenAI's "o1" demand exponentially more inference compute, which benefits AMD due to its superior ... employs a monolithic die. Modular chiplets are well-suited for inference ...

The new console may leverage AMD's "Halo" tech to stack cache RAM chiplets on both the CPU and GPU. Although the specific packaging method has not yet been disclosed, stacked cache technology ...

Instead, they consist of chiplets lashed together with 2.5D ... One of the first AI chips based on 3.5D packaging is AMD’s latest 3D-stacked accelerator chip, the Instinct MI300A, which is ...

BOE, a leading Chinese manufacturer of LCD and OLED displays, is considering making glass core substrates for next-gen domestic chips.

Experts, including Jim Handy and Jawad Nasrullah, tackled AMD/Xilinx innovations, AI-driven HBM demand, Moore's modular foresight, and the high costs of EUV machines shaping the future.

Despite integration challenges, third-party chiplets offer cost savings and flexibility. Intel and AMD are optimizing performance with advanced interconnects, PHYs, and 3D stacking.

AMD's next-gen Zen 6 desktop CPUs codenamed Medusa Point rumored to bump up the core count: 24 cores, 48 threads coming with ...