Seismic changes are underway in the photomask and semiconductor industry, driving the need for GPU acceleration to enable simulation-based processing in reasonable run times. D2S GPU-accelerated solutions are deployed in production settings by leading semiconductor equipment manufacturers worldwide.

D2S Optimal GPU Acceleration: CPU + GPU

PLDC: Manhattan Shapes
GPU+CPU is ~8 Times Faster in Total Processing
VOA Computation (Manhattanized ILT)
GPU is 54 Times Faster
PLDC: Curvilinear Shapes
GPU+CPU is ~7 Times Faster in Total Processing
VOA Computation (Curvilinear ILT)
GPU is 44 Times Faster
GPU+CPU >10 Times Faster in Total Processing
Etch Bias
GPU+CPU ~10 Times Faster in Total Processing
All Charts Display Run Time in Seconds

Scientific computing, and for that matter all of high performance computing, is quickly migrating to GPU acceleration. Because clock speed is no longer scaling, but computing bandwidth continues to scale, computing algorithms written for single-instruction, multiple data (SIMD) architectures has been and will continue to scale along with Moore’s Law. Both GPU-accelerated algorithms and CPU-only algorithms utilize coarse-level parallelization by dividing the chip or mask data into partitions, and computing the partitions in CPU cores or CPU cores accelerated with GPU(s). But each computing unit computes much more data much faster with GPU acceleration. The performance difference increases every node along Moore’s Law.

This is why for simulation of natural effects, for image processing, and for deep learning, GPU acceleration is the superior platform.

Case Study: NuFlare
“Multi-beam is an enabling technology for writing curvilinear ILT features due to its ability to handle any mask shape without loss of accuracy or speed,” stated Noriaki Nakayamada, chief specialist at NuFlare Technology. “Since curvilinear mask data correction for dose and resist effects is required to make ILT possible, implementing inline linearity correction in multi-beam machines is useful, as it eliminates the need to add an extra offline data preparation step. However, doing so is extremely compute-intensive and difficult to accomplish. D2S GPU-Acceleration technology makes inline linearity correction possible for the first time, which can significantly reduce turnaround time for mask processing.
Free White Paper Download
To download the white paper "GPU-Accelerated Computing: Maximizing Performance for Semiconductor Manufacturing" in PDF format, please register below.