SHF:Small:Test Data Learning for Ultra High Dignostic Resolution

集成电路(IC)渗透到我们生活的方方面面，从电脑到手机再到汽车，无所不在。然而，由于基础制造过程中固有的巨大复杂性，制造既能工作又可靠的IC变得极其困难。因此，了解一些IC无法正常运行的原因是极其重要的。在这个NSF项目中，将开发新的方法来定位和表征IC故障的根本原因。现有的方法通常会产生不确定的结果，因为它们依赖于关于IC设计的有限信息。在这项工作中，额外的设计信息和从其他故障IC中提取的数据将被综合使用，以有效地从故障IC的测量数据中得出IC故障的原因。有效地发现IC失败的根本原因将使IC的设计、制造甚至测试得到显著改进，有助于确保电子行业的持续发展。首席调查员(PI)致力于通过培训不同的本科生和研究生研究人员来产生更广泛的影响。他的研究小组的成员来自代表性不足的群体，包括妇女、非裔美国人、西班牙裔美国人和美洲原住民。此外，作为卡内基梅隆大学硅系统实施中心(CSSI)的主任，PI管理着一个项目，该项目从不同的大学(包括为少数族裔服务的机构)招募本科生研究人员，以及全国黑人工程师协会的年度大会。该项目非常成功，招收了许多本科生研究人员，包括女性和非裔美国人。在过去的几年里，PI自己指导了九名本科生研究人员，其中三名是非裔美国人(两名男性和一名女性)。此外，NSF合同承担的初步工作现在已经公布，实际上是由我们的一名非裔美国研究人员完成的。国际和平研究所将继续招募不同的学生群体，包括研究生和本科生，参与这一项目。

Integrated circuits (ICs) are pervasive in all aspects of our lives, used in everything from computers to mobile phones to automobiles. However, fabricating ICs that both work and are reliable is becoming extremely difficult due to the significant complexity inherent in the underlying fabrication processes. It is therefore extremely important to understand the reasons why some ICs fail to operate properly. In this NSF project, new methodologies for locating and characterizing the root cause for IC failure will be developed. Existing approaches typically produce uncertain results because they rely on limited information about the IC design. In this work, additional design information and data extracted from other failing ICs will be holistically used to efficiently derive the reason for IC failure from data measured from failing ICs. Efficiently discovering the root-cause of failure for an IC will enable the design, the fabrication and even the testing of ICs to be significantly improved, helping to ensure the continued advancement of the electronics industry.The principal investigator (PI) is committed to having a broader impact through training a diverse group of undergraduate and graduate researchers. His research group has members from under-represented groups that include women, African Americans, Hispanic Americans, and Native Americans. In addition, as director of the Center for the Silicon System Implementation (CSSI) at Carnegie Mellon University, the PI manages a program that recruits undergrads researchers from various universities (including minority-serving institutions), and the annual convention of the National Society of Black Engineers. This program has been very successful, resulting in the recruitment of many undergraduate researchers, including both women and African-Americans. In the last few years, the PI himself has supervised nine undergraduate researchers, three of which were African-American (two male and one female). In addition, the preliminary work undertaken by this NSF contract is now published and was actually accomplished by one of our African-American researchers. The PI will continue to recruit a diverse group of students, both at the graduate and undergraduate levels, for participation in this project.