• Ambarella CV7 Applies Edge AI to Multiple 8K Video Streams

    Ambarella CX7 block diagram

    Ambarella is sampling the flagship CV7 processor, which brings transformer/LLM capability to 8K video processing. The company’s first 4nm chip, the CV7 targets including action cameras, drones, advanced driver assistance systems (ADAS), and edge boxes for multistream analysis. continue reading

  • Slash Server Costs Without Hardware or Software Changes

    MEXT Memory Pyramid

    In light of rising DRAM prices, we’re updating this article from June. As of late 2025, server DRAM prices are surging. Memory makers are prioritizing higher-margin HBM for AI accelerators over DDR5. Consequently, DDR5 DIMMs are perhaps the largest and fastest-rising component costs of a server. At the same time, OEMs are passing these cost continue reading

  • BWR 5: AI Creates Seismic Waves in Data Center Interconnect

    teaser image for Byrne-Wheeler Report Episode 5

    Bob and Joe discuss Marvell’s Celestial.AI acquisition, Amazon Trainium using NVLink Fusion, Meta deploying Google’s TPU, and more. continue reading

  • Google TPU Draws Attention Amid Meta’s Interest

    4 Google Ironwood TPU chips on a board

    The recent focus on Google’s TPU, following Gemini 3.0 and Meta’s potential adoption, signals an evolving AI chip landscape. Meta’s move to own and house a TPU pod would be a significant shift from Google’s standard cloud-service model, posing a fresh challenge to GPU vendors. continue reading

  • Power11 Is a Small Step for IBM, Lodestar for Others

    IBM Power S1122 server with top off

    IBM’s Power11 processor introduces technologies like external memory buffers, AI acceleration, and SMT that will become common in other systems. Power11 refines the Power10 design, achieving a 14–50% speedup in IBM’s applications and offering up to 256 cores in a chassis. continue reading

  • The End Is Not Nigh

    green balloon with a pin

    Leading up to Nvidia’s recent earnings call, concerns mounted that the company would confirm fears that the AI bubble would soon burst. Too many companies are prodigiously spending to build the next data center to create the next foundation model. Profitability is well over the time horizon, and their annular funding arrangements are unsustainable. Nvidia continue reading

Popular

Sponsored Content and Plugs

Other Sites You Might Like

Read More

Amazon AMD Arm auto Broadcom business Cerebras Ceva consumer CPU data center DPU DSP edge AI embedded Epyc FPGA Google GPU Imagination industrial Intel interconnect Marvell MCU MediaTek Meta Microsoft MLPerf NPU (AI accelerator) Nvidia NXP OpenAI PC process tech Qualcomm Renesas RISC-V SambaNova SiFive smartphone SoftBank software Tenstorrent Tesla

error: Selecting disabled if not logged in