An official website of the United States government
Motivated by the increasing importance of general-purpose Graphic Processing Units (GPGPU) programming, exemplified by NVIDIA’s CUDA framework, as well as the difficulty, especially for novice programmers, of reasoning about performance in GPGPU kernels, we introduce a novel quantitative program logic for CUDA kernels. The logic allows programmers to reason about both functional correctness and resource usage of CUDA kernels, paying particular attention to a set of common but CUDA-specific performance bottlenecks: warp divergences, uncoalesced memory accesses, and bank conflicts. The logic is proved sound with respect to a novel operational cost semantics for CUDA kernels. The semantics, logic, and soundness proofs are formalized in Coq. An inference algorithm based on LP solving automatically synthesizes symbolic resource bounds by generating derivations in the logic. This algorithm is the basis of RaCUDA, an end-to-end resource-analysis tool for kernels, which has been implemented using an existing resource-analysis tool for imperative programs. An experimental evaluation on a suite of benchmarks shows that the analysis is effective in aiding the detection of performance bugs in CUDA kernels.
more »
« less
Reclaiming Logic Modeling for Evaluation: A Theory of Action Framework
Logic modeling, the process that explicates how programs are constructed and theorized to bring about change, is considered to be standard evaluation practice. However, logic modeling is often experienced as a transactional, jargon-laden, discrete task undertaken to produce a document to comply with the expectations of an external entity, the consequences of which have minimal or even negative influence on the quality of program evaluation. This article presents the Logic Modeling Theory of Action Framework (LMTAF) which elucidates needs, resources, and central activities of logic modeling, and describes its potential evaluation-related benefits. The LMTAF situates evaluators as the primary intended users of logic modeling, and logic modeling as a fundamental element of each stage of a program evaluation life cycle. We aim to reassert the value of logic modeling for evaluation and provide evaluation practitioners a useful touchstone for reflective practice and future action.
more »
« less
- PAR ID:
- 10535656
- Publisher / Repository:
- American Journal of Evaluation
- Date Published:
- Journal Name:
- American Journal of Evaluation
- ISSN:
- 1098-2140
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
From co-authored publications to sponsored projects involving multiple partner institutions, collaborative practice is an expected part of work in the academy. As evaluators of a National Science Foundation (NSF) Alliances for Graduate Education and the Professoriate (AGEP) grant awarded to four university partners in a large southern state, the authors recognized the increasing value of collaborative practice in the design, implementation, evaluation, and dissemination of findings in the partnership over time. When planning a program among partnering institutions, stakeholders may underestimate the need for, and value of, collaborative practice in facilitating partnership functioning. This method paper outlines an evaluative model to increase the use of collaborative practice in funded academic partnership programs. The model highlights collaborative practice across multiple stakeholder groups in the academic ecology: Sponsors of funded programs (S), Program partners and participants (P), Assessment and evaluation professionals (A), academic researchers (R), and the national and global Community (C). The SPARC model emphasizes evidence-based benefits of collaborative practice across multiple outcome domains. Tools and frameworks for evaluating collaborative practice take a view of optimizing partnership operational performance in achieving stated goals. Collaborative practice can also be an integral element of program activities that support the academic success and scholarly productivity, psychosocial adjustment, and physical and psychological well-being of stakeholders participating in the program. Given the goal of our alliance to promote diversification of the professoriate, the model highlights the use of collaborative practice in supporting stakeholders from groups historically underrepresented in STEM fields across these outcome domains. Using data from a mixed-methods program evaluation of our AGEP alliance over 4 years, the authors provide concrete examples of collaborative practice and their measurement. Results discuss important themes regarding collaborative practice that emerged in each stakeholder group. Authors operationalize the SPARC model with a checklist to assist program stakeholders in designing for and assessing collaborative practice in support of project goals in funded academic partnership projects, emphasizing the contributions of collaborative practice in promoting diversification of the professoriate.more » « less
-
Our work with teams funded through the National Science Foundation REvolutionizing Engineering and Computer Science Departments (RED) program began in 2015. Our project—funded first by a NSF EAGER grant, and then by a NSF RFE grant—focuses on understanding how the RED teams make change on their campuses and how this information about change can be captured and communicated to other STEM programs that seek to make change happen. Because our RED Participatory Action Research (REDPAR) Project is a collaboration between researchers (Center for Evaluation & Research for STEM Equity at the University of Washington) and practitioners (Making Academic Change Happen Workshop at Rose-Hulman Institute of Technology), we have challenged ourselves to develop means of communication that allow for both aspects of the work—both research and practice—to be treated equitably. As a result, we have created a new dissemination channel—the RED Participatory Action Project Tipsheet. The tipsheet format accomplishes several important goals. First, the content is drawn from both the research conducted with the RED teams and the practitioners’ work with the teams. Each tipsheet takes up a single theme and grounds the theme in the research literature while offering practical tips for applying the information. Second, the format is accessible to a wide spectrum of potential users, remaining free of jargon and applicable to multiple program and departmental contexts. Third, by publishing the tipsheets ourselves, rather than submitting them to an engineering education research journal, we make the information timely and freely available. We can make a tipsheet as soon as a theme emerges from the intersection of research data and observations of practice. Permalink: https://peer.asee.org/32275.more » « less
-
General-purpose programming on GPUs (GPGPU) is becoming increasingly in vogue as applications such as machine learning and scientific computing demand high throughput in vector-parallel applications. NVIDIA's CUDA toolkit seeks to make GPGPU programming accessible by allowing programmers to write GPU functions, called kernels, in a small extension of C/C++. However, due to CUDA's complex execution model, the performance characteristics of CUDA kernels are difficult to predict, especially for novice programmers. This paper introduces a novel quantitative program logic for CUDA kernels, which allows programmers to reason about both functional correctness and resource usage of CUDA kernels, paying particular attention to a set of common but CUDA-specific performance bottlenecks. The logic is proved sound with respect to a novel operational cost semantics for CUDA kernels. The semantics, logic and soundness proofs are formalized in Coq. An inference algorithm based on LP solving automatically synthesizes symbolic resource bounds by generating derivations in the logic. This algorithm is the basis of RaCuda, an end-to-end resource-analysis tool for kernels, which has been implemented using an existing resource-analysis tool for imperative programs. An experimental evaluation on a suite of CUDA benchmarks shows that the analysis is effective in aiding the detection of performance bugs in CUDA kernels.more » « less
-
null (Ed.)Our work with teams funded through the National Science Foundation REvolutionizing Engineering and Computer Science Departments (RED) program began in 2015. Our project—funded first by a NSF EAGER grant, and then by a NSF RFE grant—focuses on understanding how the RED teams make change on their campuses and how this information about change can be captured and communicated to other STEM programs that seek to make change happen. Because our RED Participatory Action Research (REDPAR) Project is a collaboration between researchers (Center for Evaluation & Research for STEM Equity at the University of Washington) and practitioners (Making Academic Change Happen Workshop at Rose-Hulman Institute of Technology), we have challenged ourselves to develop means of communication that allow for both aspects of the work—both research and practice—to be treated equitably. As a result, we have created a new dissemination channel—the RED Participatory Action Project Tipsheet. The tipsheet format accomplishes several important goals. First, the content is drawn from both the research conducted with the RED teams and the practitioners’ work with the teams. Each tipsheet takes up a single theme and grounds the theme in the research literature while offering practical tips for applying the information. Second, the format is accessible to a wide spectrum of potential users, remaining free of jargon and applicable to multiple program and departmental contexts. Third, by publishing the tipsheets ourselves, rather than submitting them to an engineering education research journal, we make the information timely and freely available. We can make a tipsheet as soon as a theme emerges from the intersection of research data and observations of practice. During the poster session at ASEE 2019, we will share the three REDPAR Tipsheets that have been produced thus far: Creating Strategic Partnerships, Communicating Change, and Shared Vision. We will also work with attendees to demonstrate how the tipsheet content is adaptable to the attendees’ specific academic context. Our goal for the poster session is to provide attendees with tipsheet resources that are useful to their specific change project.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1177/10982140231224495
