Posts by Jayacharan Kolla
ROCm 6.4: Breaking Barriers in AI, HPC, and Modular GPU Software
- 11 April 2025
In the rapidly evolving landscape of high-performance computing and artificial intelligence, innovation is the currency of progress. AMD’s ROCm 6.4 isn’t just another software update—it’s a leap forward that redefines the boundaries of what is possible for AI, developers, researchers, and enterprise innovators.
Introducing ROCprofiler SDK - The Latest Toolkit for Performance Profiling
- 25 March 2025
Profiling is the backbone of performance optimization in AI and HPC workloads, enabling developers to extract maximum efficiency from AMD Instinct™ GPUs. With ROCm’s rapid evolution, the need for a unified, scalable, and extensible profiling framework has never been more critical. The new ROCprofiler-SDK framework represents a significant step forward in profiling capabilities, offering enhanced features, streamlined integration, and a better user experience while also solving past limitations with former profiler interface versions. This guide aims to help users seamlessly transition from legacy profiling tools to the ROCprofiler-SDK infrastructure. We will explore new features, highlight key differences from previous tools, and provide actionable steps for a smooth migration.
Introducing ROCprofiler SDK - The Latest Toolkit for Performance Profiling
- 25 March 2025
Profiling is the backbone of performance optimization in AI and HPC workloads, enabling developers to extract maximum efficiency from AMD Instinct™; GPUs. With ROCm’s rapid evolution, the need for a unified, scalable, and extensible profiling framework has never been more critical. The new ROCprofiler-SDK framework represents a significant step forward in profiling capabilities, offering enhanced features, streamlined integration, and a better user experience while also solving past limitations with former profiler interface versions. This guide aims to help users seamlessly transition from legacy profiling tools to the ROCprofiler-SDK infrastructure. We will explore new features, highlight key differences from previous tools, and provide actionable steps for a smooth migration.
Understanding RCCL Bandwidth and xGMI Performance on AMD Instinct™; MI300X
- 02 March 2025
Efficient inter-GPU communication is the backbone of high-performance AI and HPC workloads, where technologies like RCCL and xGMI play pivotal roles. However, some limitations in achieving theoretical peak bandwidth have raised questions about performance bottlenecks. In this blog we explain the limitations to achieve the theoretical maximum bandwidth in multi-GPU clusters, and teach you how to perform a set of diagnostics and performance-tuning strategies that will help you optimize RCCL and xGMI bandwidth on AMD MI300X systems. We will first introduce you to xGMI and its performance constraints, to RCCL and its bandwidth limitations, and then cover several practical benchmarks and best practices for maximizing RCCL efficiency.