• ActiveLoop
    • Products
      • DeeplakeDatabase
      • HivemindMemory
      • RefinerySoftware Factory
      Case Studies
      Enterprises
      BayerBiomedical

      Chat with X-Rays. Bye-bye, SQL

      MatterportMultimedia

      Cut data prep time by up to 80%

      Flagship PioneeringBiomedical

      +18% more accurate RAG

      MedTechMedTech

      Fast AI search on 40M+ docs

      Tiny MileRobotics

      +19.5% in model accuracy

      BlogCareers
    • X icon
On this page
  • Proliferation of DSLs
  • Example: RMSNorm kernel optimization on GB10 GPU
  • AI coding agent equipped with NCU
  • Iteration 2: Chunk Wide Rows
  • Final RMSNorm Results
← All resources
Tutorial

AI driven Kernel Optimization with CuTeDSL

By Activeloop team·May 20, 2026
CuTeDSLCUTLASSRMSNormGPU KernelsNsight ComputeAI Agent
  • deep lake database

    Continuous Learning Infrastructure

    • Products
      DeeplakeHivemindLoop
    • Case Studies
      BayerMatterportFlagship PioneeringFortune 500 · MedTechTiny Mile
    • Blog
      LatestDeep Lake WhitepaperDeep Lake Academic Paper
    • Careers
      AboutContact UsOpen PositionsPrivacy PolicyDo Not SellTerms & Conditions
  • X icon
  • Tensie

    Featured by

    featuredfeaturedfeaturedfeatured
    • © 2026 Activeloop. All rights reserved.