SandBox Semiconductor Adds Hybrid Metrology Capabilities to Industry's Leading Physics-based, AI-enabled Process Optimization Platform, Creating the First Software Solution to Holistically Address Process Development Challenges
SandBox Studio™ AI strengthens platform with new product, Weave™, to accelerate metrology analysis, reduce development costs, and speed up innovation in advanced chips
September 19, 2023 – AUSTIN, Texas – SandBox Semiconductor, a pioneer in applying physics-based, AI-enabled modeling to accelerate the development of semiconductor manufacturing processes, has launched a new product for its industry-leading process development platform, SandBox Studio AI.
One of the biggest challenges in the semiconductor industry is developing manufacturing processes for increasingly advanced chip designs with high yield and reliability. Fabrication processes typically involve over a thousand steps that each must be carefully controlled and optimized. Today, this optimization is largely performed by iterative trial and error and requires companies to invest heavily in process development and recipe scaling to meet increasingly stringent manufacturing requirements. As chip technology advances, the complexity of the fabrication process continues to increase.
“SandBox Semiconductor was founded to help process engineers leverage powerful computational models in their day-to-day process development,” said Dr. Meghali Chopra, CEO and co-founder of SandBox Semiconductor. “Our platform empowers engineers to build their own AI models to solve specific development challenges.”
SandBox Studio AI is in use at the world’s leading chip manufacturers and equipment suppliers, where it significantly reduces learning cycles, provides faster insights into process trends and sensitivities, and facilitates exploration of new process options for recipe development that must consider hundreds of process parameters.
“Deriving early insights on potential process or tool deviations allows equipment and chip manufacturers to take corrective measures, optimize process time, reduce defects, and improve yields and overall efficiency, all at a reduced cost. SandBox is carving out a unique position in taking productivity and innovation in chip manufacturing to new levels by establishing an intelligent ecosystem for semiconductor process development,” said Dr. Ashwath Rao, Senior Research Analyst, Semiconductors and Components, Counterpoint Research.
SandBox’s newest product, Weave, focuses on the hybrid metrology challenge.
With hybrid metrology, data from more than one toolset is used to improve overall measurement performance – this allows semiconductor manufacturers to reliably measure complex structures that cannot be comprehensively viewed with a single toolset. By leveraging multiple metrology sources, hybrid metrology can facilitate a more accurate understanding of device structures. However, managing and gaining insights from the large number of disparate data sources in a fab is time-consuming and prone to errors.
“Hybrid metrology approaches that combine data gathered from multiple toolsets are becoming increasingly necessary, particularly in the era of 3D NAND, DRAM, and gate-all-around architectures, to address the complexity and spectrum of measuring tasks involved in developing a leading-edge process. With our new metrology automation features, engineers can now use our platform to manage and analyze multi-modal data to gain process insights, predict outcomes, and ultimately develop new processes not possible before,” said Dr. Chopra.
SandBox Studio AI’s new product, Weave, significantly improves metrology accuracy and precision by utilizing advanced machine learning capabilities to extract and analyze profiles from SEM and TEM data. Process development engineers can spend up to 20% of their time manually measuring SEM and TEM images. With Weave, process engineers minimize tedious manual tasks and increase metrology accuracy, resulting in more insights, quicker experimentation, and reduced costs during process definition, ramp-up, and high-volume manufacturing.
Weave plugs directly into SandBox Studio AI’s modeling platform providing engineers with an efficient method to curate data from metrology sources at different length scales, resolve conflicting data, and preprocess and organize data for modeling and analysis. This holistic solution reduces metrology costs, improves metrology and model accuracy, and accelerates process development.
About SandBox Semiconductor
Founded in 2016, SandBox Semiconductor is a pioneer in developing AI based software solutions to accelerate process development for semiconductor manufacturing. Its fully integrated AI tool suite gives process engineers the ability to build their own physics-based, AI-enabled models to solve challenges during process definition, ramp-up, and high-volume manufacturing.
Using SandBox’s physics-based models and machine learning tools, engineers can virtually simulate, predict, and measure process outcomes. Even with small sets of experimental data, SandBox’s tools can extract valuable insights and patterns, helping engineers to gain a deeper understanding of manufacturing processes and to make informed decisions about recipe adjustments. SandBox leverages expertise in numerical modeling, machine learning, and manufacturing optimization to develop its proprietary toolsets, which are used by the world’s leading chip manufacturers and semiconductor equipment suppliers. SandBox is based in Austin, Texas. More information can be found here: www.sandboxsemiconductor.com.
|
Related News
- MIPS Releases P8700, Industry's First High-Performance AI-Enabled RISC-V Automotive CPU for ADAS and Autonomous Vehicles
- Siemens' Calibre platform now certified for IFS' Intel 16 process technology
- Quadric's DevStudio Speeds Software Development with Industry's First Integrated ML + DSP Cloud-Based Code Development Platform
- Siemens' state-of-the-art Symphony Pro platform expands mixed signal IC verification capabilities
- Siemens announces EDA milestones and tool certifications for TSMC's latest process technologies
Breaking News
- Jmem Tek and Andes Technology Partner on the World' s First Quantum-Secure RISC-V Chip
- Synopsys Announces Industry's First Ultra Ethernet and UALink IP Solutions to Connect Massive AI Accelerator Clusters
- Quobly announces key milestone for fault-tolerant quantum computing
- CEA-Leti Demonstrates Embedded FeRAM Platform Compatible with 22nm FD-SOI Node
- Cadence and Rapidus Collaborate on Leading-Edge 2nm Semiconductor Solutions for AI and HPC Applications
Most Popular
- SiFive Empowers AI at Scale with RISC-V Innovation
- MIPS Releases P8700, Industry's First High-Performance AI-Enabled RISC-V Automotive CPU for ADAS and Autonomous Vehicles
- Alphawave IP - Announcement regarding leadership transition
- Now Gelsinger is gone, what is Intel's Plan B?
- Sondrel now shipping chips as part of a complete turnkey project
E-mail This Article | Printer-Friendly Page |