ROCm for Windows Training Course
ROCm is an open-source platform for GPU programming that supports AMD GPUs and offers compatibility with CUDA and OpenCL. It provides developers with direct access to hardware details, granting full control over the parallelization process. However, this requires a solid understanding of device architecture, memory models, execution models, and optimization techniques.
ROCm for Windows is a recent advancement that allows users to install and utilize ROCm on the Windows operating system, which is widely used for both personal and professional applications. This enables users to harness the power of AMD GPUs for various applications, including artificial intelligence, gaming, graphics, and scientific computing.
This instructor-led, live training (available online or onsite) is designed for beginner to intermediate-level developers who want to install and use ROCm on Windows to program AMD GPUs and leverage their parallel processing capabilities.
By the end of this training, participants will be able to:
- Set up a development environment that includes the ROCm Platform, an AMD GPU, and Visual Studio Code on Windows.
- Create a basic ROCm program that performs vector addition on the GPU and retrieves results from GPU memory.
- Use the ROCm API to query device information, allocate and deallocate device memory, copy data between host and device, launch kernels, and synchronize threads.
- Use the HIP language to write kernels that execute on the GPU and manipulate data.
- Use HIP built-in functions, variables, and libraries to perform common tasks and operations.
- Use ROCm and HIP memory spaces, such as global, shared, constant, and local, to optimize data transfers and memory accesses.
- Use ROCm and HIP execution models to control the threads, blocks, and grids that define the parallelism.
- Debug and test ROCm and HIP programs using tools such as ROCm Debugger and ROCm Profiler.
- Optimize ROCm and HIP programs using techniques such as coalescing, caching, prefetching, and profiling.
Format of the Course
- Interactive lecture and discussion.
- Extensive exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Course Outline
Introduction
- What is ROCm?
- What is HIP?
- ROCm vs CUDA vs OpenCL
- Overview of ROCm and HIP features and architecture
- ROCm for Windows vs ROCm for Linux
Installation
- Installing ROCm on Windows
- Verifying the installation and check the device compatibility
- Updating or uninstall ROCm on Windows
- Troubleshooting common installation issues
Getting Started
- Creating a new ROCm project using Visual Studio Code on Windows
- Exploring the project structure and files
- Compiling and run the program
- Displaying the output using printf and fprintf
ROCm API
- Using ROCm API in the host program
- Querying device information and capabilities
- Allocating and deallocate device memory
- Copying data between host and device
- Launching kernels and synchronize threads
- Handling errors and exceptions
HIP Language
- Using HIP language in the device program
- Writing kernels that execute on the GPU and manipulate data
- Using data types, qualifiers, operators, and expressions
- Using built-in functions, variables, and libraries
ROCm and HIP Memory Model
- Using different memory spaces, such as global, shared, constant, and local
- Using different memory objects, such as pointers, arrays, textures, and surfaces
- Using different memory access modes, such as read-only, write-only, read-write, etc.
- Using memory consistency model and synchronization mechanisms
ROCm and HIP Execution Model
- Using different execution models, such as threads, blocks, and grids
- Using thread functions, such as hipThreadIdx_x, hipBlockIdx_x, hipBlockDim_x, etc.
- Using block functions, such as __syncthreads, __threadfence_block, etc.
- Using grid functions, such as hipGridDim_x, hipGridSync, cooperative groups, etc.
Debugging
- Debugging ROCm and HIP programs on Windows
- Using Visual Studio Code debugger to inspect variables, breakpoints, call stack, etc.
- Using ROCm Debugger to debug ROCm and HIP programs on AMD devices
- Using ROCm Profiler to analyze ROCm and HIP programs on AMD devices
Optimization
- Optimizing ROCm and HIP programs on Windows
- Using coalescing techniques to improve memory throughput
- Using caching and prefetching techniques to reduce memory latency
- Using shared memory and local memory techniques to optimize memory accesses and bandwidth
- Using profiling and profiling tools to measure and improve the execution time and resource utilization
Summary and Next Steps
Requirements
- An understanding of C/C++ language and parallel programming concepts
- Basic knowledge of computer architecture and memory hierarchy
- Experience with command-line tools and code editors
- Familiarity with Windows operating system and PowerShell
Audience
- Developers who wish to learn how to install and use ROCm on Windows to program AMD GPUs and exploit their parallelism
- Developers who wish to write high-performance and scalable code that can run on different AMD devices
- Programmers who wish to explore the low-level aspects of GPU programming and optimize their code performance
Open Training Courses require 5+ participants.
ROCm for Windows Training Course - Booking
ROCm for Windows Training Course - Enquiry
ROCm for Windows - Consultancy Enquiry
Upcoming Courses
Related Courses
Developing AI Applications with Huawei Ascend and CANN
21 HoursHuawei Ascend comprises a suite of AI processors engineered for high-performance inference and training workloads.
This instructor-led live training, available in online or onsite formats, targets intermediate AI engineers and data scientists seeking to develop and optimise neural network models leveraging Huawei’s Ascend platform alongside the CANN toolkit.
Upon completion of this training, participants will be equipped to:
- Establish and configure the CANN development environment.
- Construct AI applications utilizing MindSpore and CloudMatrix workflows.
- Enhance performance on Ascend NPUs through custom operators and tiling techniques.
- Deploy models across edge or cloud infrastructure.
Course Format
- Interactive lectures coupled with group discussions.
- Practical application of Huawei Ascend and the CANN toolkit within sample projects.
- Guided exercises centred on model construction, training, and deployment.
Customisation Options
- For tailored training aligned with your specific infrastructure or datasets, please reach out to us to arrange a bespoke session.
Deploying AI Models with CANN and Ascend AI Processors
14 HoursCANN (Compute Architecture for Neural Networks) serves as Huawei's AI compute stack, designed for deploying and optimizing AI models on Ascend AI processors.
This instructor-led, live training (available online or onsite) is tailored for intermediate-level AI developers and engineers who aim to efficiently deploy trained AI models onto Huawei Ascend hardware using the CANN toolkit along with tools such as MindSpore, TensorFlow, or PyTorch.
Upon completing this training, participants will be able to:
- Gain insight into the CANN architecture and its significance within the AI deployment pipeline.
- Convert and adapt models from widely-used frameworks into formats compatible with Ascend.
- Utilize tools like ATC, OM model conversion, and MindSpore for inference tasks in both edge and cloud environments.
- Troubleshoot deployment challenges and optimize performance on Ascend hardware.
Course Format
- Interactive lectures accompanied by live demonstrations.
- Practical lab exercises employing CANN tools along with Ascend simulators or physical devices.
- Real-world deployment scenarios based on actual AI models.
Customization Options
- For a customized version of this training, please contact us to make arrangements.
AI Inference and Deployment with CloudMatrix
21 HoursCloudMatrix, Huawei’s unified platform for AI development and deployment, enables scalable, production-grade inference pipelines.
This instructor-led live training, available online or on-site, targets beginner to intermediate AI professionals seeking to deploy and monitor AI models via CloudMatrix, integrating CANN and MindSpore.
Upon completing this training, participants will be able to:
- Leverage CloudMatrix for model packaging, deployment, and serving.
- Convert and optimize models for Ascend chipsets.
- Establish pipelines for both real-time and batch inference tasks.
- Monitor deployments and tune performance in production environments.
Course Format
- Interactive lectures and discussions.
- Practical application of CloudMatrix with real-world deployment scenarios.
- Guided exercises focusing on conversion, optimization, and scaling.
Customization Options
- For customized training aligned with your specific AI infrastructure or cloud environment, please reach out to arrange a session.
GPU Programming on Biren AI Accelerators
21 HoursBiren AI Accelerators are high-performance GPUs engineered for AI and HPC workloads, enabling large-scale training and inference.
This instructor-led live training (available online or onsite) targets intermediate to advanced developers who want to program and optimize applications using Biren’s proprietary GPU stack, with practical comparisons to CUDA-based environments.
Upon completing this training, participants will be able to:
- Grasp the Biren GPU architecture and its memory hierarchy.
- Configure the development environment and utilize Biren’s programming model.
- Translate and optimize CUDA-style code for Biren platforms.
- Implement performance tuning and debugging strategies.
Course Format
- Interactive lectures and discussions.
- Hands-on exploration of the Biren SDK using sample GPU workloads.
- Guided exercises concentrating on porting and performance tuning.
Customization Options
- For customized training tailored to your specific application stack or integration requirements, please contact us to arrange a session.
Cambricon MLU Development with BANGPy and Neuware
21 HoursCambricon MLUs (Machine Learning Units) are specialized AI chips designed to optimize both inference and training tasks in edge computing and data center environments.
This instructor-led live training, available either online or on-site, targets intermediate-level developers who aim to construct and deploy AI models leveraging the BANGPy framework and Neuware SDK on Cambricon MLU hardware.
Upon completion of this training, participants will be able to:
- Establish and configure the development environments for BANGPy and Neuware.
- Create and optimize models using Python and C++ specifically for Cambricon MLUs.
- Deploy models onto edge and data center devices operating on the Neuware runtime.
- Integrate machine learning workflows with acceleration capabilities specific to MLUs.
Course Format
- Engaging lectures paired with interactive discussions.
- Practical, hands-on sessions involving development and deployment with BANGPy and Neuware.
- Guided exercises concentrating on optimization, integration, and testing.
Customization Options for the Course
- If you require customized training tailored to your specific Cambricon device model or use case, please get in touch with us to make the necessary arrangements.
Introduction to CANN for AI Framework Developers
7 HoursCANN (Compute Architecture for Neural Networks) serves as Huawei’s AI computing toolkit designed to compile, optimize, and deploy AI models on Ascend AI processors.
This instructor-led live training, available either online or onsite, targets beginner-level AI developers keen on understanding CANN's role within the model lifecycle—from training to deployment—and its interaction with frameworks such as MindSpore, TensorFlow, and PyTorch.
Upon completing this training, participants will be able to:
- Grasp the purpose and architecture of the CANN toolkit.
- Configure a development environment integrating CANN and MindSpore.
- Convert and deploy a basic AI model onto Ascend hardware.
- Build foundational knowledge for future CANN optimization or integration initiatives.
Course Format
- Interactive lectures and discussions.
- Practical hands-on labs focused on simple model deployment.
- Step-by-step walkthroughs of the CANN toolchain and integration points.
Course Customization Options
- To arrange customized training for this course, please get in touch with us.
CANN for Edge AI Deployment
14 HoursThe Huawei Ascend CANN toolkit facilitates robust AI inference on edge devices like the Ascend 310. It offers critical tools for compiling, optimizing, and deploying models in environments with limited compute and memory resources.
This instructor-led live training, available online or onsite, is designed for intermediate-level AI developers and integrators looking to deploy and optimize models on Ascend edge devices using the CANN toolchain.
Upon completing this training, participants will be equipped to:
- Prepare and convert AI models for the Ascend 310 using CANN tools.
- Construct lightweight inference pipelines leveraging MindSpore Lite and AscendCL.
- Enhance model performance in environments with restricted compute and memory.
- Deploy and monitor AI applications in practical, real-world edge scenarios.
Format of the Course
- Interactive lectures and demonstrations.
- Practical lab sessions focusing on edge-specific models and scenarios.
- Live deployment examples on virtual or physical edge hardware.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Understanding Huawei’s AI Compute Stack: From CANN to MindSpore
14 HoursHuawei's AI stack, spanning from the low-level CANN SDK to the high-level MindSpore framework, provides a closely integrated environment for developing and deploying AI solutions, specifically optimized for Ascend hardware.
This instructor-led, live training (available online or onsite) is designed for technical professionals at beginner to intermediate levels who wish to comprehend how the CANN and MindSpore components collaborate to facilitate AI lifecycle management and inform infrastructure decisions.
Upon completion of this training, participants will be equipped to:
- Grasp the layered architecture of Huawei's AI compute stack.
- Recognise how CANN aids in model optimization and hardware-level deployment.
- Assess the MindSpore framework and its toolchain in comparison to industry alternatives.
- Place Huawei's AI stack within the context of enterprise or cloud/on-premises environments.
Course Format
- Interactive lectures and discussions.
- Live system demonstrations and case-based walkthroughs.
- Optional guided labs covering the model flow from MindSpore to CANN.
Course Customization Options
- For those seeking a customized training version of this course, please reach out to us to make arrangements.
Optimizing Neural Network Performance with CANN SDK
14 HoursThe CANN SDK (Compute Architecture for Neural Networks) serves as Huawei’s foundational AI compute framework, empowering developers to fine-tune and maximise the performance of neural networks deployed on Ascend AI processors.
This instructor-led training session, available both online and onsite, is designed for advanced-level AI developers and system engineers who aim to enhance inference performance by leveraging CANN’s sophisticated toolset. Key components include the Graph Engine, TIK, and custom operator development.
Upon completing this training, participants will be equipped to:
- Gain a comprehensive understanding of CANN’s runtime architecture and performance lifecycle.
- Utilise profiling tools and the Graph Engine for thorough performance analysis and optimisation.
- Develop and optimise custom operators using TIK and TVM.
- Address memory bottlenecks and significantly improve model throughput.
Course Format
- Engaging interactive lectures and discussions.
- Practical hands-on labs featuring real-time profiling and operator tuning.
- Optimisation exercises utilising edge-case deployment examples.
Customisation Options
- To arrange a bespoke training session for this course, please reach out to us for further assistance.
CANN SDK for Computer Vision and NLP Pipelines
14 HoursThe CANN SDK (Compute Architecture for Neural Networks) delivers robust deployment and optimization capabilities for real-time AI applications in computer vision and NLP, particularly on Huawei Ascend hardware.
This instructor-led, live training (available online or onsite) targets intermediate-level AI professionals seeking to build, deploy, and optimize vision and language models using the CANN SDK for production-grade solutions.
Upon completion of this training, participants will be equipped to:
- Deploy and optimize CV and NLP models leveraging CANN and AscendCL.
- Utilize CANN utilities to convert models and seamlessly integrate them into active pipelines.
- Enhance inference performance for tasks such as detection, classification, and sentiment analysis.
- Construct real-time CV/NLP pipelines suitable for edge or cloud-based deployment environments.
Course Format
- Interactive lectures combined with practical demonstrations.
- Hands-on labs focusing on model deployment and performance profiling.
- Live pipeline design exercises utilizing real-world CV and NLP use cases.
Customization Options
- To request a customized training session for this course, please contact us to make arrangements.
Building Custom AI Operators with CANN TIK and TVM
14 HoursCANN TIK (Tensor Instruction Kernel) and Apache TVM facilitate advanced optimization and customization of AI model operators for Huawei Ascend hardware.
This instructor-led live training, available both online and onsite, is designed for advanced-level system developers looking to build, deploy, and tune custom operators for AI models by leveraging CANN’s TIK programming model and TVM compiler integration.
Upon completion of this training, participants will be capable of:
- Writing and testing custom AI operators utilizing the TIK DSL for Ascend processors.
- Integrating custom operations into the CANN runtime and execution graph.
- Employing TVM for operator scheduling, auto-tuning, and benchmarking.
- Debugging and optimizing instruction-level performance for custom computational patterns.
Course Format
- Interactive lectures and demonstrations.
- Practical coding exercises for operators using TIK and TVM pipelines.
- Testing and tuning on Ascend hardware or simulators.
Course Customization Options
- For inquiries regarding customized training for this course, please get in touch with us to arrange it.
Migrating CUDA Applications to Chinese GPU Architectures
21 HoursChinese GPU architectures, including Huawei Ascend, Biren, and Cambricon MLUs, provide CUDA alternatives specifically designed for the local AI and High-Performance Computing (HPC) markets.
This instructor-led live training, available online or onsite, targets advanced GPU programmers and infrastructure specialists looking to migrate and optimize their existing CUDA applications for deployment on Chinese hardware platforms.
Upon completion of this training, participants will be able to:
- Evaluate the compatibility of existing CUDA workloads with Chinese chip alternatives.
- Port CUDA codebases to Huawei CANN, Biren SDK, and Cambricon BANGPy environments.
- Compare performance metrics and identify key optimization points across different platforms.
- Address practical challenges related to cross-architecture support and deployment.
Format of the Course
- Interactive lectures and discussions.
- Hands-on labs focused on code translation and performance comparison.
- Guided exercises emphasizing multi-GPU adaptation strategies.
Course Customization Options
- For customized training tailored to your specific platform or CUDA project, please contact us to arrange a session.
Performance Optimization on Ascend, Biren, and Cambricon
21 HoursAscend, Biren, and Cambricon represent the forefront of AI hardware platforms in China, each providing distinct acceleration and profiling capabilities designed for large-scale AI workloads.
This instructor-led live training session (available online or onsite) is tailored for advanced-level AI infrastructure and performance engineers looking to enhance model inference and training workflows across various Chinese AI chip architectures.
Upon completion of this training, participants will be equipped to:
- Evaluate and benchmark models across Ascend, Biren, and Cambricon environments.
- Pinpoint system bottlenecks and identify inefficiencies in memory and compute resources.
- Implement optimizations at the graph, kernel, and operator levels.
- Optimize deployment pipelines to achieve superior throughput and reduced latency.
Training Format
- Interactive lectures coupled with open discussions.
- Practical application of profiling and optimization tools on each specific platform.
- Guided exercises centered on real-world tuning scenarios.
Customization Options
- For tailored training sessions based on your specific performance environment or model requirements, please reach out to us to coordinate.
