An official website of the United States government
Computing derivatives is key to many algorithms in scientific computing and machine learning such as optimization, uncertainty quantification, and stability analysis. Enzyme is a LLVM compiler plugin that performs reverse-mode automatic differentiation (AD) and thus generates high performance gradients of programs in languages including C/C++, Fortran, Julia, and Rust. Prior to this work, Enzyme and other AD tools were not capable of generating gradients of GPU kernels. Our paper presents a combination of novel techniques that make Enzyme the first fully automatic reversemode AD tool to generate gradients of GPU kernels. Since unlike other tools Enzyme performs automatic differentiation within a general-purpose compiler, we are able to introduce several novel GPU and AD-specific optimizations. To show the generality and efficiency of our approach, we compute gradients of five GPU-based HPC applications, executed on NVIDIA and AMD GPUs. All benchmarks run within an order of magnitude of the original program's execution time. Without GPU and AD-specific optimizations, gradients of GPU kernels either fail to run from a lack of resources or have infeasible overhead. Finally, we demonstrate that increasing the problem size by either increasing the number of threads or increasing the work per thread, does not substantially impact the overhead from differentiation.
more »
« less
Verifying Fortran Programs with CIVL
Fortran is widely used in computational science, engineering, and high performance computing. This paper presents an extension to the CIVL verification framework to check correctness properties of Fortran programs. Unlike previous work that translates Fortran to C, LLVM IR, or other intermediate formats before verification, our work allows CIVL to directly consume Fortran source files. We extended the parsing, translation, and analysis phases to support Fortran-specific features such as array slicing and reshaping, and to find program violations that are specific to Fortran, such as argument aliasing rule violations, invalid use of variable and function attributes, or defects due to Fortran's unspecified expression evaluation order. We demonstrate the usefulness of our tool on a verification benchmark suite and kernels extracted from a real world application.
more »
« less
- Award ID(s):
- 1955852
- PAR ID:
- 10343411
- Editor(s):
- Fisman, Dana; Rosu, Grigore
- Date Published:
- Journal Name:
- TACAS 2022: Tools and Algorithms for the Construction and Analysis of Systems
- Volume:
- LNCS 13243
- Page Range / eLocation ID:
- 106-124
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Safety violations in programmable logic controllers (PLCs), caused either by faults or attacks, have recently garnered significant attention. However, prior efforts at PLC code vetting suffer from many drawbacks. Static analyses and verification cause significant false positives and cannot reveal specific runtime contexts. Dynamic analyses and symbolic execution, on the other hand, fail due to their inability to handle real-world PLC programs that are event-driven and timing sensitive. In this paper, we propose VetPLC, a temporal context-aware, program analysis-based approach to produce timed event sequences that can be used for automatic safety vetting. To this end, we (a) perform static program analysis to create timed event causality graphs in order to understand causal relations among events in PLC code and (b) mine temporal invariants from data traces collected in Industrial Control System (ICS) testbeds to quantitatively gauge temporal dependencies that are constrained by machine operations. Our VetPLC prototype has been implemented in 15K lines of code. We evaluate it on 10 real-world scenarios from two different ICS settings. Our experiments show that VetPLC outperforms state-of-the-art techniques and can generate event sequences that can be used to automatically detect hidden safety violations.more » « less
-
High-level data types are often associated with semantic invariants that must be preserved by any correct implementation. While having implementations enforce strong guarantees such as linearizability or serializability can often be used to prevent invariant violations in concurrent settings, such mechanisms are impractical in geo-distributed replicated environments, the platform of choice for many scalable Web services. To achieve high-availability essential to this domain, these environments admit various forms of weak consistency that do not guarantee all replicas have a consistent view of an application's state. Consequently, they often admit difficult-to-understand anomalous behaviors that violate a data type's invariants, but which are extremely challenging, even for experts, to understand and debug. In this paper, we propose a novel programming framework for replicated data types (RDTs) equipped with an automatic (bounded) verification technique that discovers and fixes weak consistency anomalies. Our approach, implemented in a tool called Q9, involves systematically exploring the state space of an application executing on top of an eventually consistent data store, under an unrestricted consistency model but with a finite concurrency bound. Q9 uncovers anomalies (i.e., invariant violations) that manifest as finite counterexamples, and automatically generates repairs for such anamolies by selectively strengthening consistency guarantees for specific operations. Using Q9, we have uncovered a range of subtle anomalies in implementations of well-known benchmarks, and have been able to apply the repairs it mandates to effectively eliminate them. Notably, these benchmarks were written adopting best practices suggested to manage distributed replicated state (e.g., they are composed of provably convergent RDTs (CRDTs), avoid mutable state, etc.). While the safety guarantees offered by our technique are constrained by the concurrency bound, we show that in practice, proving bounded safety guarantees typically generalize to the unbounded case.more » « less
-
Information leaks in software can unintentionally reveal private data, yet they are hard to detect and fix. Although several methods have been proposed to detect leakage, such as static verification-based approaches, they require specialist knowledge, and are time-consuming. Recently, we introduced HyperGI, a dynamic, hypertest-based approach that can detect and produce potential fixes for hyperproperty violations. In particular, we focused on violations of the noninterference property, as it results in information flow leakage. Our instantiation of HyperGI was able to detect and reduce leakage in three small programs. Its fitness function tried to balance information leakage and program correctness but, as we pointed out, there may be tradeoffs between keeping program semantics and reducing information leakage that require developer decisions. In this work we ask if it is possible to automatically detect and repair information leakage in more realistic programs without requiring specialist knowledge. We instantiate a multi-objective version of HyperGI in a tool, called LeakReducer, which explicitly encodes the tradeoff between program correctness and information leakage. We apply LeakReducer to six leaky programs, including the well-known Heartbleed bug. LeakReducer is able to detect leakage in all, in contrast to state-of-the-art fuzzers, detecting leakage in only two programs. Moreover, LeakReducer is able to reduce leakage in all subjects, with comparable results to previous work, while scaling to much larger software.more » « less
-
Abstract—Safety violations in programmable logic controllers (PLCs), caused either by faults or attacks, have recently garnered significant attention. However, prior efforts at PLC code vetting suffer from many drawbacks. Static analyses and verification cause significant false positives and cannot reveal specific runtime contexts. Dynamic analyses and symbolic execution, on the other hand, fail due to their inability to handle real-world PLC pro- grams that are event-driven and timing sensitive. In this paper, we propose VETPLC, a temporal context-aware, program analysis- based approach to produce timed event sequences that can be used for automatic safety vetting. To this end, we (a) perform static program analysis to create timed event causality graphs in order to understand causal relations among events in PLC code and (b) mine temporal invariants from data traces collected in Industrial Control System (ICS) testbeds to quantitatively gauge temporal dependencies that are constrained by machine operations. Our VETPLC prototype has been implemented in 15K lines of code. We evaluate it on 10 real-world scenarios from two different ICS settings. Our experiments show that VETPLC outperforms state-of-the-art techniques and can generate event sequences that can be used to automatically detect hidden safety violations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-99524-9_6
