• Hot Chips 2024 Roundup: Day 1 Takeaways

    man with lasso rounding up hot chips

    Last week, various organizations presented their newest processors at Hot Chips. Typical of recent years, most focused on AI processing, but several talks covered general-purpose CPUs. Below is an observation from each Day 1 presentation. continue reading

  • Computer Historian Finds Pentium Rug

    Pentium Navajo rug

    Computer historian and reverse engineer Ken Shirriff found a traditional Navajo rug woven to resemble a die shot of the original Intel Pentium. Commissioned by Intel as a gift to the American Indian Science & Engineering Society, it’s exhibited at the National Gallery of Art. It’s fun to think back to a time when Intel… continue reading

  • Akeana Emerges with High-Performance RISC-V Cores

    Gmail doesn't like SVG images like this Akeana logo

    Akeana offers a range of configurable RISC-V cores targeting various applications. While high-end RISC-V adoption remains uncertain, Akeana’s high-performance CPUs and experienced team position it well if/when high-end RISC-V cores take off. continue reading

  • AMD Gambles $4.9 Billion on ZT Systems to Accelerate AI Sales

    Breaking Bad char Mike says no half measures

    AMD’s acquisition of ZT Systems aims to bolster its AI accelerator business with complete system designs. It should strengthen AMD’s position in the competitive AI market, but a previous acquisition proves such deals can go bust. continue reading

  • Tests Show Arm Server Chips Rival x86 Processors

    Graviton comic book character

    AWS’s Graviton 4 processor, based on Arm’s Neoverse V2 CPU, delivers performance comparable to AMD’s high-core-count Epyc processors in many server workloads. While Epyc still holds advantages in certain areas, Graviton’s lower cost and strong performance in HPC workloads make it a compelling option. The rise of Arm-based servers marks a significant shift in the… continue reading

  • Fractile Computes in Memory for AI Inference

    Sierpinski carpet

    Startup Fractile claims its data-center NPU will be 100× faster than an Nvidia H100 at 1/10th the cost. The secretive company indicates it’s employing in-memory computation to improve MAC-unit utilization and power efficiency. continue reading

Popular

Sponsored Content and Plugs

Other Sites You Might Like

Read More

Amazon AMD Arm auto Broadcom business Cerebras Ceva CPU data center DPU DSP edge AI embedded FPGA Google GPU Groq IBM Imagination industrial Intel interconnect Marvell MCU MediaTek memory Meta MEXT Microsoft MLPerf NPU (AI accelerator) Nvidia OpenAI PC process tech Qualcomm RISC-V SambaNova smartphone SoftBank software Tensordyne Tenstorrent Upscale

error: Selecting disabled if not logged in