Developer Resources from Intel and Indian Institute of Technology Goa*
Indian Institute of Technology Goa (IIT Goa), a premier academic institute in India, used Intel tools to migrate a computational fluid dynamics (CFD) Poisson solver equation from CUDA* to multivendor-supported SYCL*.
With code migration, the standard equation governing physical processes, such as diffusion and heat transfer, performs better. Plus, a single code base can run seamlessly across heterogeneous architectures.
The solver’s performance improved up to 1.9x on Intel® Data Center GPU Max Series 1550 compared to its performance on NVIDIA* A100 GPU.
Get Started with IIT Goa
The High Performance Computing Nodal Center at IIT Goa, in association with Intel, aims to enhance HPC education and research in India.
Case Study
CFD Poisson Solver Achieved Up to 1.9x Performance Improvements by Migrating from CUDA to SYCL
"The Poisson equation code is developed in CUDA, limiting its execution to vendor-specific GPUs. Using Intel's SYCLomatic tool for oneAPI, this code is migrated to SYCL, thus opening up other vendor and architectural alternatives. After further optimization, the migrated code runs on Intel Data Center GPU Max Series and achieves up to 1.9x speedup compared to the existing GPU solution."
—IIT Goa, India
Intel® oneAPI Base Toolkit
Download the Stand-Alone Version
Develop performant code quickly and correctly across hardware targets, including CPUs, GPUs, and FPGAs, with this standards-based, multiarchitecture compiler.
Download the Stand-Alone Version
Find and fix performance bottlenecks and optimize application and system performance and configuration for HPC, cloud, IoT, media, storage, and more.