Logo
24.1
  • Linaro Forge
  • DDT
  • MAP
    • Get started with MAP
    • MAP user interface
    • Program details
    • Time display mode
    • Program output
    • Source code (MAP)
    • Selected lines view
    • Stacks view
    • OpenMP Regions view
    • Functions view
    • Library view
    • Project Files view
    • Metrics view
    • Thread affinity advisor
    • Compiler remarks
    • MPI Call Statistics dialog
    • Configurable Perf metrics
    • Main-thread, OpenMP, and Thread view modes
    • Processes and cores window
    • Run MAP from the command line
    • Export profiler data in JSON format
    • NVIDIA GPU profiling
      • GPU Kernels tab
      • CUDA Kernel analysis
      • Memory transfers analysis
      • Compilation
      • Performance impact
      • Customize NVIDIA GPU profiling behavior
      • Known issues for NVIDIA GPU profiling
    • AMD GPU profiling
    • Python profiling
    • Performance analysis with Caliper instrumentation
    • Arm Statistical Profiling Extension (SPE)
  • Performance Reports
  • Supported platforms
  • Get support
  • General troubleshooting
  • Known issues and notes
  • Configuration
  • Queue template script syntax
  • Worked Examples
  • Security
Linaro Forge
  • MAP
  • NVIDIA GPU profiling
Previous Next

NVIDIA GPU profiling

You can use the GPU profiling capabilities when working with NVIDIA CUDA programs.

See also Accelerator metrics.

  • GPU Kernels tab
  • CUDA Kernel analysis
  • Memory transfers analysis
  • Compilation
  • Performance impact
    • CUDA kernel analysis
    • CUDA memory transfer analysis
    • Overhead mitigation
  • Customize NVIDIA GPU profiling behavior
  • Known issues for NVIDIA GPU profiling
Previous Next

© Copyright 2023-2024 Linaro Limited. All rights reserved.

v: 24.1
Versions
latest
24.1
24.0.6
23.1.2
Userguides
Linaro Forge
Linaro Forge Licence Server
Linaro Custom Metric Plugin Interface
Downloads
PDF
Product

www.linaroforge.com . www.linaro.org