Posts by Asitav Mishra
Performance Profiling on AMD GPUs - Part 7: AI/PyTorch® Edition
- 04 November 2026
This blog, like the previous articles in the profiling guide series
(Part 1,
Part 2,
Part 3,
Part 4,
Part 5,
and Part 6),
applies a systematic profiling workflow to
a GPU-accelerated application. Those posts establish the core loop on
HIP and Fortran applications: baseline timing, kernel hotspots with rocprofv3, rooflines and
hardware counters with rocprof-compute, and whole-system timelines with rocprof-sys. Here we apply
that loop to a PyTorch training workload, where one logical operator can lower to many
GPU kernels and optimization often means changing how the framework dispatches work rather
than rewriting a kernel.
Performance Profiling on AMD GPUs - Part 4: Fortran OpenMP Offload Edition
- 01 June 2026
This blog, like the previous articles in the profiling guide series (Part 1, Part 2, and Part 3), is designed to help you systematically analyze and improve the performance of your Fortran OpenMP offload applications running on AMD GPUs. This guide builds upon the foundational skills from the previous articles and introduces profiling techniques specifically tailored for Fortran applications that use OpenMP target offloading.
Performance Profiling on AMD GPUs - Part 3: Advanced Usage
- 23 October 2025
Error parsing meta tag attribute “keywords”: No content.
Performance Profiling on AMD GPUs – Part 2: Basic Usage
- 13 August 2025
Error parsing meta tag attribute “keywords”: No content.
Performance Profiling on AMD GPUs – Part 1: Foundations
- 26 June 2025
Error parsing meta tag attribute “keywords”: No content.
Reading AMD GPU ISA
- 13 May 2024
For an application developer it is often helpful to read the Instruction Set Architecture (ISA) for the GPU architecture that is used to perform its computations. Understanding the instructions of the pertinent code regions of interest can help in debugging and achieving performance optimization of the application.