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
In the Arm vs. Qualcomm case, the jury returned a partial verdict, leading Arm to seek a retrial. The judge directed both parties to seek a mediated solution instead. The jury ruled on Qualcomm’s breach of Nuvia’s Arm Licensing Agreement (ALA) and the coverage of Nuvia’s designs under the Qualcomm ALA. However, they did not… continue reading
Altera AMD Ampere Apple APU/IGP Arm auto Broadcom Cerebras Computex CPU data center DPU edge AI embedded Epyc Flow Computing FPGA Google GPU Imagination Immortalis Intel Mali Marvell MediaTek Meta Microsoft MLPerf NDP250 NPU (AI accelerator) Nvidia NXP PC process tech Qualcomm RISC-V SiFive smartphone SoftBank Syntiant T-Head Tenstorrent Tesla Zen 5