據Phoronix 報道 ，AMD對C/C++編譯器'AOCC'4.0進行了優化，讓Zen 4架構的鋭龍處理器和EPYC服務器處理器的性能得到一定提升。

Phoronix的邁克爾·拉貝爾表示，經過優化的AOCC4.0最引人注目的地方是帶來了對Zen 4 "znver4"支持和優

SiPearl, the company designing the highperformance, low-power microprocessor for European supercomputers, has entered into a business collaboration agreement with AMD to provide a joint offering for exascale supercomputing systems, combining SiPearl's HPC microprocessor, Rhea, with AMD Instinct accelerators.

Initially, AMD and SiPearl will jointly assess the interoperability of the AMD ROCm open software with the SiPearl Rhea microprocessor and build an optimized software solution that would strengthen the capabilities of a SiPearl microprocessor combined with an AMD Instinct accelerator. This joint work targets porting and optimization activities

AMD in its technical presentation for its new Radeon RX 7900 series "Navi 31" GPU, gave us its most elaborate explanation on why it had to take the chiplets route for high-end GPUs, devices that are far more complex than CPUs. The company also enlightened us on what sets chiplet-based packages apart from classic multi-chip modules (MCMs). An MCM is a package that consists of multiple independent devices sharing a fiberglass substrate.

An example of an MCM would be a mobile