A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Code coverage, performance approximation and automatic recognition of idioms in scientific applications
2008
Proceedings of the 17th international symposium on High performance distributed computing - HPDC '08
In this paper, we start with a manual analysis of code coverage on the NAS Parallel Benchmark (NPB) and find that five idioms suffice to cover 100% of the NPB codes. ...
We then compare the performance of our idiom benchmarks and their corresponding instances in different NPB codes on two different platforms and find that they differ by about 30%. ...
ACKNOWLEDGEMENTS We thank the Intel R Internship Program and University Cooperation Program for supporting this work, Dr. Lars Jonsson for supervising the project. ...
doi:10.1145/1383422.1383456
dblp:conf/hpdc/HeSWF08
fatcat:v4v4q5nqdfhdxdwjja7uh6db5a
Automatic Recognition of Performance Idioms in Scientific Applications
2011
2011 IEEE International Parallel & Distributed Processing Symposium
Our results showed that the above five idioms suffice to cover 100% of the six NPB codes (MG, CG, FT, BT, SP and LU). ...
We hypothesize that a small number of idioms can cover most programming constructs that dominate the execution time of scientific codes and can be used to approximate the application performance. ...
ACKNOWLEDGEMENTS We thank the Intel R Internship Program and University Cooperation Program for supporting this work, Dr. Lars Jonsson for supervising the project. ...
doi:10.1109/ipdps.2011.21
dblp:conf/ipps/HeSWF11
fatcat:c2gnizhrdjggbh4xapf6krrdla
Source Matching and Rewriting
[article]
2022
arXiv
pre-print
This paper presents Source Matching and Rewriting (SMR), a user-oriented source-code-based approach for MLIR idiom matching and rewriting that does not require a compiler expert's intervention. ...
On the other hand, modern ISA extensions and hardware accelerators can benefit from the compiler's ability to detect and raise program idioms to acceleration instructions or optimized library calls. ...
The work proposed herein for idiom recognition (SMR) uses a similar approach as instruction selection but differs in two major aspects. ...
arXiv:2202.04153v1
fatcat:ervhj575n5hzvd5i55vzcpt4km
Automatic Matching of Legacy Code to Heterogeneous APIs
2018
Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '18
In those cases where idioms are a significant part of the sequential execution time, we generate code that achieves 1.26× to over 20× speedup on integrated and external GPUs. ...
We call them idioms and use a custom constraint-based Idiom Description Language (IDL) to discover them within user code. ...
/1) and the University of Edinburgh. ...
doi:10.1145/3173162.3173182
dblp:conf/asplos/GinsbachRSBDO18
fatcat:d23trzn4ujdgvbynkzmruqzj54
Boosting the Performance of Multimedia Applications Using SIMD Instructions
[chapter]
2005
Lecture Notes in Computer Science
In this paper, we introduce a powerful and extendable recognition engine to solve this problem, which only needs a small amount of rules to recognize many such idioms and generate efficient SIMD instructions ...
However, automatic vectorization support for them is not very mature. The key difficulty is how to vectorize those SIMD-ISA-supported idioms in source code in an efficient and general way. ...
Compiler Support for MMEs To solve the idiom recognition problem in compiler support for MMEs, we design a powerful recognition engine and add it as an extra stage at the beginning of the classic algorithm ...
doi:10.1007/978-3-540-31985-6_5
fatcat:bqoiqf2ltjh47h7dgank2k7szi
An experiment in table driven code generation
1982
Proceedings of the 1982 SIGPLAN symposium on Compiler construction - SIGPLAN '82
Almtract We have constructed a local code generator for the VAX-II e using a parser-like instruction pattern marcher. The code generator replaces the second pass of the UNIX s Portable "C" compiler. ...
In our experience, this approach makes the instruction selection phase of the compiler easier and faster to implement, and more likely to be correct than traditional techniques. ...
Phase 3b: Idiom Recognition We recognize two classes of idioms, binding idioms and range idioms. ...
doi:10.1145/800230.806978
dblp:conf/sigplan/GrahamHS82
fatcat:2ossbdyj7zgulfm42hpzkbkdb4
Its automatically generated back-end code comes within 5%-30% of the performance of hand-optimized implementations. ...
Many systems for the parallel processing of big data are available today. Yet, few users can tell by intuition which system, or combination of systems, is "best" for a given workflow. ...
Idiom recognition Some back-end execution engines are specialized for a specific type of computation. ...
doi:10.1145/2741948.2741968
dblp:conf/eurosys/GogSCGCH15
fatcat:j67jem3ohzef7pwh2ymldjwehy
Efficient HPC Data Motion via Scratchpad Memory
2012
2012 SC Companion: High Performance Computing, Networking Storage and Analysis
The energy required to move data accounts for a significant portion of the energy consumption of a modern supercomputer. ...
Because the motion of each bit throughout the memory hierarchy has a large energy and performance cost, energy efficiency will improve if we can ensure that only the bits absolutely necessary for the computation ...
ACKNOWLEDGMENT This work was supported in part by the DOE Office of Science through the Advanced Scientific Computing Research (ASCR) award titled "Thrifty: An Exascale Architecture for Energy-Proportional ...
doi:10.1109/sc.companion.2012.111
dblp:conf/sc/SeagerTLPCC12
fatcat:4bwayaibuvfy3erlrlqaibd2qa
Extracting compiler provenance from program binaries
2010
Proceedings of the 9th ACM SIGPLAN-SIGSOFT workshop on Program analysis for software tools and engineering - PASTE '10
We evaluate our techniques on a large set of real-world test binaries, showing that our models identify the source compiler of binary code with over 90% accuracy, even in the presence of interleaved code ...
Program provenance answers fundamental questions of malware analysis and software forensics, such as whether programs are generated by similar tool chains; it also can allow development of debugging, performance ...
Acknowledgments This work is supported in part by Department of Energy grants 93ER25176, 07ER258000 and 09ER25940, and National Science Foundation Cybertrust grants CNS-0627501 and CNS-0716460. ...
doi:10.1145/1806672.1806678
dblp:conf/paste/RosenblumMZ10
fatcat:yomar7luuzbsvfynhlvvxl5t6y
Generalized profile-guided iterator recognition
2018
Proceedings of the 27th International Conference on Compiler Construction - CC 2018
In this paper we propose a compiler analysis for recognizing loop iterators code for a wide class of loops. ...
Our analysis enables advanced loop optimizations such as decoupled software pipelining, commutativity analysis and source code rejuvenation for real-world applications, which escape analysis and transformation ...
17.0) [10] , LLVM/Polly [20] , and constraint-based parallel idiom recognition [18] . ...
doi:10.1145/3178372.3179511
dblp:conf/cc/ManilovVF18
fatcat:ofszt3qekvh6phoyiommap7pey
Page 4267 of Mathematical Reviews Vol. , Issue 83j
[page]
1983
Mathematical Reviews
Snyder, Lawrence 83):68010 ition and selection of idioms for code optimization. Acta Inform. 17 (1982), no. 3, 327-348. ...
For example, in ALGOL-60 the expression abs( X— X+2 2) is idiomatic for parity of X. With optimization as a motive, two problems, idiom recognition and selection, are defined. ...
Vapor SIMD: Auto-vectorize once, run everywhere
2011
International Symposium on Code Generation and Optimization (CGO 2011)
sizes, memory alignment and access constraints, to special computational idioms. ...
We demonstrate the effectiveness of our design using a set of kernels that exercise innermost loop, outer loop, as well as straight-line code vectorization, all automatically extracted by the common offline ...
ACKNOWLEDGEMENTS This work was partly supported by the European Commission through the HiPEAC network of excellence, and by the French Ministry of Industry and STMicroelectronics through the Mediacom grant ...
doi:10.1109/cgo.2011.5764683
dblp:conf/cgo/NuzmanDRRWYCZ11
fatcat:pawpjpuurzgyrpdwapv2qpl3uq
Phrasal Learning Is a Horse Apiece: No Recognition Memory Advantages for Idioms in L1 and L2 Adult Learners
2021
Frontiers in Psychology
It employed a learning paradigm to test whether there is a recognition memory advantage for idioms compared to literal phrases in adult L1 and L2 learners considering both form and meaning recognition. ...
We conclude that there is no inherent recognition memory advantage for idioms based on figurativeness alone, and word- and phrasal meaning interact differently in learner groups. ...
Additional thanks to Thanh Lan Truong and Simón Ruiz as well as the student assistants at the University of Tübingen's LingTüLab for support in collecting data. ...
doi:10.3389/fpsyg.2021.591364
pmid:33935852
pmcid:PMC8081890
fatcat:pium3aedpbfb5ayazaodd2xmqi
The Metaphorical Interpretation of English and Chinese Body-part Idioms Based on Relevance Theory
2021
Journal of Language Teaching and Research
In English and Chinese idioms, what are the similarities and differences in the use and interpretation of body-part metaphors? ...
They are based on our physical experience of the world around us. Idioms are the crystallization of human language and culture and play an important role in human communication. ...
However, idioms and their recognition in context are often the weak of learners' learning. ...
doi:10.17507/jltr.1205.24
fatcat:hedcadyxobb37p4ihde3lit6pm
Program Synthesis and Semantic Parsing with Learned Code Idioms
[article]
2019
arXiv
pre-print
It accomplishes this by automatically mining common code idioms from a given corpus, incorporating them into the underlying language for neural synthesis, and training a tree-based neural synthesizer to ...
use these idioms during code generation. ...
Mining Code Idioms The first step of PATOIS is obtaining a set of frequent and useful AST fragments as code idioms. ...
arXiv:1906.10816v4
fatcat:frgb473ctjgz7pklc5ut5jfvpq
« Previous
Showing results 1 — 15 out of 5,421 results