Gunjan Dhanuka — Learning Notes

arithmetic-intensity

9 items with this tag.

  • Sep 02, 2026

    Arithmetic Intensity

    • gpu
    • arithmetic-intensity
    • roofline
    • flops
    • bandwidth
    • memory-bound
    • compute-bound
    • llm-systems
  • Sep 02, 2026

    GEMM (General Matrix Multiply)

    • gpu
    • gemm
    • matmul
    • tensor-core
    • arithmetic-intensity
    • tiling
    • transformer
    • llm-systems
  • Sep 02, 2026

    IO-Aware Algorithms

    • gpu
    • io-aware
    • memory-wall
    • arithmetic-intensity
    • co-design
    • flashattention
    • data-movement
    • llm-systems
  • Sep 02, 2026

    Kernel Fusion

    • gpu
    • kernel-fusion
    • memory-wall
    • arithmetic-intensity
    • torch-compile
    • triton
    • llm-systems
  • Sep 02, 2026

    Roofline Model

    • gpu
    • roofline
    • arithmetic-intensity
    • ridge-point
    • memory-bound
    • compute-bound
    • performance-modeling
    • llm-systems
  • Sep 02, 2026

    Shared-Memory Tiling (Blocking)

    • gpu
    • gemm
    • tiling
    • shared-memory
    • arithmetic-intensity
    • data-reuse
    • llm-systems
  • Sep 02, 2026

    Learn: Performance Modeling & Roofline

    • gpu
    • roofline
    • arithmetic-intensity
    • mfu
    • mixed-precision
    • fp8
    • tensor-cores
    • profiling
    • performance-modeling
  • Sep 02, 2026

    Learn: Your First CUDA Kernels

    • gpu
    • cuda
    • kernels
    • vector-add
    • matmul
    • grid-stride
    • cuda-events
    • arithmetic-intensity
    • llm-systems
  • Sep 02, 2026

    Learn: The Memory Wall & FlashAttention

    • gpu
    • flashattention
    • kernel-fusion
    • online-softmax
    • memory-wall
    • io-aware
    • attention
    • arithmetic-intensity
    • hopper
    • blackwell

Created with Quartz v5.0.0 © 2026

  • Personal site
  • Research
  • Field notes
  • Source