# WMMA guide for AMD RDNA 4 architecture GPUs - part 3

DevFeed: [WMMA guide for AMD RDNA 4 architecture GPUs - part 3](<https://devfeed.tech/articles/wmma-guide-for-amd-rdna-4-architecture-gpus-part-3-15053.md>)

Original publisher: [Read original article](<https://gpuopen.com/learn/wmma-guide-amd-rdna-4-gpus-part-3/>)

Author: Hui Zhang

Published: 2026-06-02T19:02:00Z

Content type: tutorial

Language: en

Sources: [AMD GPUOpen](<https://devfeed.tech/sources/amd-gpuopen.md>)

Topics: [Code](<https://devfeed.tech/topics/code.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>), [Warp](<https://devfeed.tech/topics/warp.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [amd](<https://devfeed.tech/tags/amd.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [cpp](<https://devfeed.tech/tags/cpp.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [getting-started](<https://devfeed.tech/tags/getting-started.md>), [guide](<https://devfeed.tech/tags/guide.md>), [hip](<https://devfeed.tech/tags/hip.md>), [implement](<https://devfeed.tech/tags/implement.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [maths](<https://devfeed.tech/tags/maths.md>), [memory](<https://devfeed.tech/tags/memory.md>), [ml](<https://devfeed.tech/tags/ml.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rdna](<https://devfeed.tech/tags/rdna.md>), [reference-guide](<https://devfeed.tech/tags/reference-guide.md>), [technical-article](<https://devfeed.tech/tags/technical-article.md>), [technical-articles](<https://devfeed.tech/tags/technical-articles.md>), [user-guides-manuals](<https://devfeed.tech/tags/user-guides-manuals.md>)

## AI overview

This tutorial explains how to implement an in-register matrix transpose using the WMMA layout on AMD RDNA 4 GPUs. It describes an identity-matrix approach that avoids additional memory operations and notes its use in Llama.cpp for Flash Attention.

## Source excerpt

Learn how to implement fast in-register matrix transpose on AMD RDNA™ 4 architecture GPUs with a WMMA-based identity trick, delivering a lightweight, memory-free alternative proven in Llama.cpp.