How Synopsys and NVIDIA Are Accelerating Semiconductor Scaling in the AI Age
For decades, the task of creating masks for the manufacturing process has been an integral part of semiconductor manufacturing. As we move to more advanced nodes like 5nm, 3nm to 2nm, accelerating computational lithography turnaround time is instrumental in getting the chips fabricated efficiently in semiconductor manufacturing companies. Synopsys has been a pioneer in this area with advanced techniques to accelerate distributed processing in areas like supercomputers.
Our latest collaboration with NVIDIA to run Synopsys Proteus Optical Proximity Correction (OPC) software on the NVIDIA cuLitho software library is just one example of how we are providing another powerful way to accelerate that process on GPUs, taking it from weeks to days.
What this means for foundries and customers using these solutions is substantially faster turnaround times to develop chips on increasingly smaller process nodes. “As applications such as AI and machine learning drive the demand for greater density from smaller chips, lithography processes need a substantial speed boost to keep up with the pace of innovation,” said Vivek Singh, vice president, Advanced Technology Group, NVIDIA. “By collaborating with Synopsys, we are accelerating the massive computational workloads that currently consume tens of billions of CPU hours every year, enabling the creation of new lithography solutions and more predictability in future semiconductor technologies.”
Read on to learn more about why this collaboration is good news for semiconductor scaling—and every application demanding more performance from smaller footprints.
To read the full article, click here
Related Semiconductor IP
- MACsec Engine optimized for 10Base-T1S/T1L applications
- Dual Port, Voltage Scaling Register File Compiler on GF22FDX+
- Single Port, Voltage Scaling, High Speed SRAM Memory Compiler on GF22FDX+
- I3C Full Controller / Target
- I3C HCI Host Controller
Related Blogs
- How AI and Edge Computing Are Accelerating RISC-V Adoption
- How Cadence and TSMC Are Accelerating AI Silicon Design at Advanced Nodes
- Arm in the agentic era: Scaling the converged AI data center
- Arm and NVIDIA: Building the trusted compute foundation for the agentic AI era