Portable GPU Programming About
Updated for 2708dc2 (2025-10-31 11:20:17 +0200)

Slides (HTML)

1. Parallel Programming & Supercomputing

2. GPUs as Accelerators

3. GPU Execution Model

4. Memory Hierarchy and Memory Accesses in GPUs

5. Using LUMI and Mahti supercomputers

6. Getting started with C++

7. Introduction to MPI

Message passing game

1. Introduction to SYCL

2. High-Level SYCL

3. Low-Level SYCL

4. Other SYCL Features

1. Introduction to Kokkos Performance Portability Ecosystem

2. Data parallel patterns in Kokkos

3. Spaces and Views

4. Performance portable memory access patterns

5. Interoperability, Kernels and Tools

1. Introduction to OpenMP offload

2. Controlling data movement

3. Asynchronous kernel execution

4. Reduction

5. Unified shared memory

6. Interoperability with libraries

7. Further material


Slides (PDF)

1. Parallel Programming & Supercomputing

2. GPUs as Accelerators

3. GPU Execution Model

4. Memory Hierarchy and Memory Accesses in GPUs

5. Using LUMI and Mahti supercomputers

6. Getting started with C++

7. Introduction to MPI

Message passing game

1. Introduction to SYCL

2. High-Level SYCL

3. Low-Level SYCL

4. Other SYCL Features

1. Introduction to Kokkos Performance Portability Ecosystem

2. Data parallel patterns in Kokkos

3. Spaces and Views

4. Performance portable memory access patterns

5. Interoperability, Kernels and Tools

1. Introduction to OpenMP offload

2. Controlling data movement

3. Asynchronous kernel execution

4. Reduction

5. Unified shared memory

6. Interoperability with libraries

7. Further material

Download a zip file containing all slides.