With the ever-increasing demand for more computing performance, the HPC industry is moving towards a heterogeneous computing model, where GPUs and CPUs work together to perform general-purpose computing tasks. In this heterogeneous computing model, the GPU serves as an accelerator to the CPU, to offload the CPU and to increase computational efficiency. To exploit this computing model and the massively parallel GPU architecture, the application software will need to be redesigned. Synopsys and NVIDIA engineers have been working together to use GPUs to accelerate circuit simulation technology.
IC Design complexity has continued to grow exponentially. Just in the last decade, as process technology has advanced from planar to FinFET technology, device counts and parasitics have increased significantly. Modern process technologies also require verification across many more process, voltage, and temperature corners, resulting in design complexity increasing by orders of magnitude. During this time CPU performance gains have largely plateaued while GPU performance has been growing and continues to scale well beyond Moore’s Law. These trends will only further increase the gap between the two computing methodologies over time. GPUs provide significant advantages in dealing with circuit simulation challenges including the high volume of floating-point operations and memory bandwidth usage as well as the large number of massively independent computing jobs with large post-layout circuits.
Synopsys announced today at its SNUG World international user conference PrimeSim™ Continuum, a unified workflow of best-in-class SPICE and FastSPICE technologies, speeding the creation of analog, RF, mixed-signal, custom digital and memory designs. The PrimeSim Continuum solution is built on innovative SPICE and FastSPICE architectures providing design teams 10X faster simulation while maintaining signoff accuracy. PrimeSim’s next-generation architecture with unique GPU technology delivers significant performance improvements needed to perform comprehensive analog and RF design analysis while meeting signoff accuracy requirements. Benchmarks models run on NVIDIA DGX systems show speedups ranging from 4-12X over multi-core CPUs. While performance gains are across the board on a variety of circuit types, the best improvements are seen when running large post-layout simulations. When coupled with long transient run times, the performance improvement is even more noticeable.