Understanding how hardware-imposed performance ceilings impact your code can be a pain in the … ummm … can be challenging. Commonly, developers struggle to assess the optimization tradeoffs between memory bottlenecks and compute use for CPU and GPU code.
Enter Intel® Advisor and its Roofline Analysis feature, a visual representation of application performance in relation to hardware limitations, including memory bandwidth and computational peaks.
Join technical consulting engineer and high-performance computing (HPC) programming expert Cedric Andreolli for a session covering:
- How to perform a GPU headroom and GPU cache locality analysis using Roofline extensions in Intel Advisor for oneAPI and OpenMP*
- An introduction to a new memory-level Roofline feature that helps pinpoint which specific memory level (L1, L2, L3, or DRAM) is causing the bottleneck
- A walkthrough of the Intel Advisor improved user interface
Get the Software
- Introduction to Roofline Model with Intel Advisor
- User Guide: Analyze Intel Advisor for GPU Roofline
- Intel Advisor Cookbooks
Software technical consulting engineer, Intel Corporation
Cedric supports Intel® Software Development Tools with special focus on Intel® compilers and Intel Advisor, particularly in the realm of HPC. In addition, he has extensive experience in Android* development with applications for augmented reality via both OpenGL* and the Radiance lighting simulation tool.
Cedric holds a BS degree in computer science from the University of Rennes 1 in France. In his spare time, he enjoys playing guitar in rock bands, skiing, and playing ice hockey and football.