Contents

AMD ROCm™ Blogs

Ecosystems and partners

Stone Ridge Expands Reservoir Simulation Options with AMD Instinct™ Accelerators

June 10, 2024

Stone Ridge Technology (SRT) pioneered the use of GPUs for high performance reservoir simulation (HPC) nearly a decade ago with ECHELON, its flagship...

AMD Collaboration with the University of Michigan offers High Performance Open-Source Solutions to the Bioinformatics Community

May 16, 2024

Long read DNA sequencing technology is revolutionizing genetic diagnostics and precision medicine by helping us discover structural variants and assem...

Siemens taps AMD Instinct™ GPUs to expand high-performance hardware options for Simcenter STAR-CCM+

May 16, 2024

Siemens recently announced that its Simcenter STAR-CCM+ multi-physics computational fluid dynamics (CFD) software now supports AMD Instinct™ GPUs for...

Applications and models

Benchmarking Machine Learning using ROCm and AMD GPUs: Reproducing Our MLPerf Inference Submission

August 28, 2024 by Meena Arunachalam , Miro Hodak , Jeremy Arnold , Eliot Li

Measuring the performance of new technologies is as old as human history, and often as intriguing. The AMD MLPerf Inference v4.1 submission has three entries for Llama 2 70B. The submission used a fully open-source software stack based on the ROCm platform and vLLM inference engine. Read More >

Performing natural language processing tasks with LLMs on ROCm running on AMD GPUs

August 21, 2024 by Eliot Li

In this blog you will learn how to use ROCm, running on AMD’s Instinct GPUs, for a range of popular and useful natural language processing (NLP) tasks, using different large language models (LLMs).

Using AMD GPUs for Enhanced Time Series Forecasting with Transformers

August 19, 2024 by Fabricio Flores

Time series forecasting (TSF) is a key concept in fields such as signal processing, data science, and machine learning (ML).

Inferencing with Grok-1 on AMD GPUs

August 9, 2024 by Eliot Li , Luise Chen , Lei Shao

We demonstrate that the massive Grok-1 model from xAI can run seamlessly on the AMD MI300X GPU accelerator by leveraging the ROCm software platform.

Graph analytics on AMD GPUs using Gunrock

July 29, 2024 by Thomas Gibson,Muhammad Osama

Can AMD GPUs help with graph analytic operations? We will show some cases where GPUs can improve the performance of these valuable algorithms.

Optimizing RoBERTa: Fine-Tuning with Mixed Precision on AMD

July 29, 2024 by Fabricio Flores

In this blog we explore how to fine-tune the Robustly Optimized BERT Pretraining Approach (RoBERTa) large language model, with emphasis on PyTorch’s mixed precision capabilities.

Software tools & optimizations

TensorFlow Profiler in practice: Optimizing TensorFlow models on AMD GPUs

June 18, 2024 by Fabricio Flores

TensorFlow Profiler consists of a set of tools designed to measure resource utilization and performance during the execution of TensorFlow models…

SmoothQuant model inference on AMD Instinct MI300X using Composable Kernel

May 31, 2024 by Cheng Ling

The AMD ROCm™ Composable Kernel (CK) library provides a programming model for writing performance-critical kernels…

Reading AMD GPU ISA

May 13, 2024 by Asitav Mishra , Corbin Robeck

Rocprof is a robust tool designed to analyze and optimize the performance of HIP programs on AMD ROCm platforms…

AMD in Action: Unveiling the Power of Application Tracing and Profiling

May 7, 2024 by Fabricio Flores

Rocprof is a robust tool designed to analyze and optimize the performance of HIP programs on AMD ROCm platforms…

Application portability with HIP

Many scientific applications run on AMD-equipped computing platforms and supercomputers, including Frontier…

C++17 parallel algorithms and HIPSTDPAR

April 18, 2024 by Alessandro Fanfarillo , Alex Voicu

The C++17 standard added the concept of parallel algorithms to the pre-existing C++ Standard Library. The parallel version of algorithms like…

Stay informed