
Marvell’s Structera CXL chips boost memory bandwidth and capacity. Structera A, a DPU with 16 Neoverse-V2 cores, accelerates workloads, while Structera X expands memory capacity and supports dual-host pooling. Sampling now, both accelerate encryption and compression to add security and increase effective memory capacity. continue reading

Intel will soon only employ only E-cores, a strategy consistent with the view that general-purpose processors’ role is feeding and managing AI accelerators. This will end in disaster for the company. continue reading

Marvell’s custom silicon operation now offers copackaged optics (CPO). Enabling systems to connect fiber-optic networks directly to chips such as AI accelerators (NPUs) and network switches raises per-chip bandwidth and extends interchip connectivity distances. Few companies offer CPO. Broadcom, Marvell’s main custom-silicon rival, has developed a few Ethernet switches implementing the technology and, this past… continue reading

For posterity’s sake, here are my LinkedIn posts from the Arm vs. Qualcomm trial. A key takeaway is that although I thought neither side argued well, Arm performed better but ultimately lost. Greed The Arm-Qualcomm trial has kicked off. Q has successfully portrayed Arm as greedy and obliterated Arm’s first witness. However, nothing so far… continue reading

VeriSilicon has launched a new GPU family, Vitality. Available to license now and supporting DirectX 12, it includes tensor cores and targets cloud gaming. continue reading
Amazon AMD Arm auto Broadcom business Cerebras Ceva CPU data center DPU DSP edge AI embedded Epyc FPGA Google GPU Groq Imagination industrial Intel Marvell MCU MediaTek memory Meta Microsoft MLPerf NPU (AI accelerator) Nvidia NXP OpenAI PC process tech Qualcomm RISC-V SambaNova Semidynamics SiFive smartphone SoftBank software Tenstorrent Tesla