A view of the parallel computing landscape
Open accessAbstract
Writing programs that scale with increasing numbers of cores should be as easy as writing programs for sequential computers.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
3 of 20 cited sources checked · 0 supported · 0 flagged · accuracy not yet measured
- Premisecitation
Directed automated testing (concolic unit testing) has shown promise for improving software quality through automated test generation using static and dynamic analyses.
“a recently introduced technique called”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [21] 21. Williams, s. et al. lattice Boltzmann simulation optimization on leading multicore platforms. in Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium (Miami, fl, apr. 14-18, 2008). source
Section 2.2 describes a code generator for auto-tuning lattice Boltzmann simulations, and Section 6 discusses performance optimizations. Neither addresses concolic unit testing, software-quality improvements, or test generation using static and dynamic analyses; searches for those terms returned no relevant passage. Page numbers were not available in our copy. (LLM, conf=0.78)
Experimental — accuracy not yet measured
- Findingreasoning
In the manycore speedup example, a fat core needing 10 times as many resources would be more effective than the 10 thin cores it replaces.
“In this example of manycore processor speedup, a fat core needing 10 times as many resources would be more effective than the 10 thin cores it replaces.5,15”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [5] 5. henzinger, t.a. et al. Permissive interfaces. in Proceedings of the 10th European Software Engineering Conference (lisbon, Portugal, sept. 5-9). acM Press, new york, 2005, 31-40. source
- cites [15] 15. shirako, J., Peixotto, D., sarkar, v., and scherer, W. Phasers: a unified deadlock-free construct for collective and point-to-point synchronization. in Proceedings of the 22nd ACM International Conference on Supercomputing (island of Kos, greece, June 7-12). acM Press, new york, 2008, 277-288. source
- Findingcitation§ Writing programs that scale with increasing numbers of cores
Intel products are today far below even the conservative 2007 ITRS prediction.
“Note that Intel products are today far below even the conservative 2007 prediction.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [16] 16. shirako, J., Kasahara, h., and sarkar, v. language extensions in support of compiler parallelization. in Proceedings of the 20th Workshop on Languages and Compilers for Parallel Computing (urbana, il, oct. 11-13). springer-verlag, Berlin, 2007, 78-94. source
- Findingnone given
The Par Lab developed a nearly work-efficient algorithm for lexical analysis.
“In this context, we developed a nearly work-efficient algorithm for lexical analysis.”
Quote in the paperSubstantial claim - Findingnone given
The resulting pattern language is already employed by the Par Lab to develop software architectures and parallel implementations of content-based image retrieval, large-vocabulary continuous speech recognition, and timing analysis for integrated circuit design.
“The resulting pattern language is still under development but is already employed by the Par Lab to develop the software architectures and parallel implementations of such diverse applications as content-based image retrieval, large-vocabulary continuous speech recognition, and timing analysis for integrated circuit design.”
Quote in the paperNot a substantial claim
- Findingown data
The autotuned code is the fastest known for the three kernels (sparse matrix, stencil for PDEs, and structured grids) on all three multicores.
“This autotuned code is the fastest known for these kernels for all three computers.”
Quote in the paperSubstantial claim - Findingnone given
Efficiency in sketching-based synthesis is achieved by reducing the problem to one solved with two communicating SAT solvers.
“Efficiency is achieved by reducing the problem to one solved with two communicating SAT solvers.”
Quote in the paperSubstantial claim - Interpretationreasoning
Having many simple cores on a chip simplifies hardware design and verification because each core is simple and replication is nearly trivial.
“Moreover, having many such simple cores on a chip simplifi es hardware design and verification, since each core is simple, and replication of cores is nearly trivial.”
Quote in the paperSubstantial claim - Interpretationreasoning§ Writing programs that scale with increasing numbers of cores
After hitting the power wall, architects were forced to find a new paradigm to sustain ever-increasing performance.
“After crashing into the power wall, architects were forced to find a new paradigm to sustain ever-increasing performance.”
Quote in the paperSubstantial claim - Premisereasoning§ Writing programs that scale with increasing numbers of cores
The hardware/software contract worked until the power limit a chip can dissipate was reached.
“The contract worked fine until we hit the power limit a chip is able to dissipate.”
Quote in the paperSubstantial claim - Interpretationreasoning§ Writing programs that scale with increasing numbers of cores
The hardware/software contract led to innovations that were inefficient in transistors and power but increased performance while preserving the sequential programming model.
“This contract led to innovations that were inefficient in terms of transistors and power (such as multiple instruction issue, deep pipelines, out-of-order execution, speculative execution, and prefetching) but that increased performance while preserving the sequential programming model.”
Quote in the paperSubstantial claim - Premisenone given§ Writing programs that scale with increasing numbers of cores
The implicit hardware/software contract was that increased transistor count and power dissipation were acceptable as long as architects maintained the existing sequential programming model.
“The implicit hardware/software contract was that increased transistor count and power dissipation were OK as long as architects maintained the existing sequential programming model.”
Quote in the paperNot a substantial claim - Premisecitation
There is a technology sweet spot around a pipelined processor of five-to-eight stages that is most efficient in performance per joule and silicon area.
“There is a technology sweet spot around a pipelined processor of fi ve-to-eight stages that is most efficient in terms of performance per joule and silicon area.5”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [5] 5. henzinger, t.a. et al. Permissive interfaces. in Proceedings of the 10th European Software Engineering Conference (lisbon, Portugal, sept. 5-9). acM Press, new york, 2005, 31-40.
- Interpretationreasoning
Using simple cores means there is room for hundreds of them on the same chip.
“Using simple cores means there is room for hundreds of them on the same chip.”
Quote in the paperSubstantial claim - Premisenone given
A single autotuner can be used to generate high-quality code for a variety of machines.
“A single autotuner can be used to generate highquality code for a variety of machines.”
Quote in the paperNot a substantial claim - Interpretationreasoning
These implications create serial contracts that specify how modules such as frameworks are used correctly.
“These implications create serial contracts that specify how the modules (such as frameworks) are used correctly.”
Quote in the paperSubstantial claim - Interpretationown data
Autotuning helps with production of parallel code.
“Autotuning also helps with production of parallel code.”
Quote in the paperSubstantial claim - Interpretationreasoning
This flexibility means researchers can tape out every day rather than over years.
“This flexibility means researchers can”
Quote in the paperSubstantial claim - Interpretationnone given
Instead of traditional optimizing compilers, the Par Lab depends on autotuners, using empirical search and performance modeling to create highly optimized libraries tailored to specific machines.
“Instead of traditional optimizing compilers, we depend on autotuners, using a combination of empirical search and performance modeling to create highly optimized libraries tailored to specific machines.”
Quote in the paperSubstantial claim - Interpretationreasoning
Such techniques enable programmers to quickly test executions for data races and deadlocks directly, because directed test input generation and model checking hijack the scheduler and control synchronization primitives.
“Such techniques enable programmers to quickly test executions for data races and deadlocks directly, since a combination of directed test input generation and model checking hijacks the underlying scheduler and controls the synchronization primitives.”
Quote in the paperSubstantial claim - Interpretationreasoning
Correctness is addressed differently at the productivity layer and the efficiency layer.
“Correctness is addressed differently at the two layers.”
Quote in the paperSubstantial claim - Interpretationreasoning
The Tessellation kernel is much thinner than traditional kernels or even hypervisors.
“The Tessellation kernel is much thinner than traditional kernels or even hypervisors.”
Quote in the paperSubstantial claim - Interpretationnone given
The Tessellation kernel is a thin layer responsible only for coarse-grain scheduling and assignment of resources to partitions and implementation of secure restricted communications among partitions.
“Our Tessellation kernel is a thin layer responsible for only the coarse-grain scheduling and assignment of resources to partitions and implementation of secure restricted communications among partitions.”
Quote in the paperSubstantial claim - Interpretationreasoning
The optimal choice among parallel algorithms may depend on processor architecture, the parallelism of the computer, and memory bandwidth.
“The optimal choice may depend not only on the processor architecture but also on the parallelism of the computer and memory bandwidth.”
Quote in the paperSubstantial claim- Rests on an assumption: Parallel architectures introduce many new optimization parameters, and so far there are few successful autotuners for parallel codes.
- Premisenone given
In many cases, autotuned code is faster than vendor libraries specifically hand-tuned for the target.
“In many cases, the autotuned code is faster than vendor libraries that were specifically hand-tuned for the target”
Quote in the paperNot a substantial claim - Interpretationreasoning
The system propagates implications of local assertions to module boundaries through a combination of static verification and directed automated unit testing.
“The system propagates implications of these local assertions to the module boundaries through a combination of static verification and directed automated unit testing.”
Quote in the paperSubstantial claim - Interpretationreasoning
Such diversity will make the goals of efficiency, scaling, and portability even more difficult for conventional compilers.
“Such diversity will make the goals of efficiency, scaling, and portability even more difficult for conventional compilers, at a time when innovation is desperately needed.”
Quote in the paperSubstantial claim - Premisecitation
Mattson et al.'s 2004 book Patterns for Parallel Programming was the first attempt to systematize parallel programming using a complete pattern language.
“Mattson et al's 2004 book Patterns for Parallel Programming 18 was the first such attempt to systematize parallel programming using a complete pattern language.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [18] 18. uPc language specifications, version 1.2. technical report lBnl-59208. lawrence Berkeley national laboratory, Berkeley, ca, 2005.
- Interpretationreasoning
The Par Lab combines directed testing with model-checking algorithms to unit-test parallel frameworks and libraries composed with serial contracts.
“The Par Lab combines directed testing with model-checking algorithms to unit-test parallel frameworks and libraries composed with serial contracts.”
Quote in the paperSubstantial claim - Interpretationnone given
Our sketching-based synthesis searches a space of candidate programs with constraint solving rather than interactively deriving a program.
“Our sketching-based synthesis is to traditional, deductive synthesis what model checking is to theorem proving; rather than interactively deriving a program, our system searches a space of candidate programs with constraint solving.”
Quote in the paperSubstantial claim - Interpretationreasoning
In a parallel setting, the search space for optimization will be much larger than for traditional serial hardware.
“Consequently, in a parallel setting, the search space will be much larger than for traditional serial hardware.”
Quote in the paperSubstantial claim - Interpretationreasoning
Tessellation avoids many performance issues associated with traditional microkernels by providing OS services through secure messaging to spatially co-resident service partitions rather than context-switching to time-multiplexed service processes.
“It avoids many of the performance issues associated with traditional microkernels by providing OS services through secure messaging to spatially co-resident service partitions, rather than context-switching to timemultiplexed service processes.”
Quote in the paperSubstantial claim - Interpretationreasoning
Given FPGA capacity, researchers can prototype full hardware and software systems that run fast enough to investigate architectural innovations.
“Given the capacity of field-programmable gate arrays (FPGAs), researchers can prototype full hardware and software systems that run fast enough to investigate architectural innovations.”
Quote in the paperNot a substantial claim - Interpretationreasoning
Unlike libraries, autotuners allow tuning to the particular problem size.
“Unlike libraries, autotuners also allow tuning to the particular problem size.”
Quote in the paperNot a substantial claim
- Classified as probably not a substantial claim. 79
- May combine two claims. 36
- The quote only partly states this claim. 1
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationGamma et al.'s 1994 book Design Patterns outlined patterns useful for object-oriented programming.
“An example is Gamma et al.'s 1994 book Design Patterns, which outlined patterns useful for object-oriented programming.12”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [12] 12. sen, K. and viswanathan, M. Model checking multithreaded programs with asynchronous atomic methods. in Proceedings of the 18th International Conference on Computer-Aided Verification (seattle, Wa, aug. 17-20, 2006). source
The Introduction discusses an asynchronous-method design idiom and cites Holub’s Taming Java Threads, while the References do not list Gamma et al.’s Design Patterns. Searches for Gamma, Design Patterns, and patterns for object-oriented programming found no passage addressing what that book outlined. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationAutotuners have become popular for producing high-quality, portable scientific code for serial microprocessors by generating many variants of a kernel and measuring each variant on the target platform.
“In recent years, autotuners have become popular for producing highquality, portable scientific code for serial microprocessors, 10 optimizing a set of library kernels by generating many variants of a kernel and measuring each variant by running on the target platform.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [10] 10. o'hanlon, c. a conversation with John hennessy and David Patterson. Queue 4, 10 (Dec. 2005/Jan. 2006), 14-22. source
The DAVID PATTERSON passages (page unavailable) discuss microprocessor architecture, parallel programming, and performance evaluation, but not autotuners. Searches for kernel variants, target-platform measurement, and portable scientific code found no passage addressing the claim. (LLM, conf=0.73)
Experimental — accuracy not yet measured
Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Findingown dataNot every programmer is able to understand the details of concurrent software and parallel hardware; difficult steps include locks, barriers, deadlocks, load balancing, scheduling, and memory consistency.
“Our experience teaching parallelism suggests that not every programmer is able to understand the nitty gritty of concurrent software and parallel hardware; diffi cult steps include locks, barriers, deadlocks, load balancing, scheduling, and memory consistency.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataAutotuning increased performance by factors of two to four over standard code, much better than expected from an optimizing compiler.
“Performance increased by factors of two to four over standard code, much better than you would expect from an optimizing compiler.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenIn 2007, Hewlett-Packard, the largest maker of PCs, shipped more laptops than desktops.
“In 2007, Hewlett-Packard, the largest maker of PCs, shipped more laptops than desktops.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationShaw's and Garlan's report described a variety of architectural styles useful for organizing software.
“In building our own pattern language, we found Shaw's and Garlan's report, 23 which described a variety of architectural styles useful for organizing software, to be very effective.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [23] 23. eecs.berkeley.edu/) at the university of california, Berkeley.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
InterpretationreasoningThe datacenter and mobile client extremes both concern cost, the datacenter because server cost is replicated 50,000 times and mobile clients because of a lower unit-price target.
“Both concern costthe datacenter because server cost is replicated 50,000 times and mobile clients because of a lower unit-price target.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable).
PremisecitationDesign patterns describe time-tested solutions to recurring problems within a well-defined context.
“As explored in his 1977 book, civil architect Christopher Alexander wrote that”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [3] 3. gamma, e. et al. Design Patterns: Elements of Reusable Object-Oriented Software. addison-Wesley Professional, reading, Ma, 1994.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
May combine two claims.
Premisecitation§ Writing programs that scale with increasing numbers of coresThe 2005 ITRS prediction was that clock rates should have exceeded 10GHz in 2008 and topped 15GHz in 2010.
“The 2005 prediction was that clock rates should have exceeded 10GHz in 2008, topping 15GHz in 2010.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [16] 16. shirako, J., Kasahara, h., and sarkar, v. language extensions in support of compiler parallelization. in Proceedings of the 20th Workshop on Languages and Compilers for Parallel Computing (urbana, il, oct. 11-13). springer-verlag, Berlin, 2007, 78-94. source
May combine two claims.
Interpretationcitation§ Writing programs that scale with increasing numbers of coresThe leap to multicore is not based on a breakthrough in programming or architecture and is a retreat from building power-efficient, high-clock-rate, single-core chips.
“Hence, the leap to multicore is not based on a breakthrough in programming or architecture and is actually a retreat from the more difficult task of building power-efficient, high-clock-rate, single-core chips.5”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [5] 5. henzinger, t.a. et al. Permissive interfaces. in Proceedings of the 10th European Software Engineering Conference (lisbon, Portugal, sept. 5-9). acM Press, new york, 2005, 31-40.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing). May combine two claims.
Interpretationnone givenA pattern language does not impose a rigid methodology; it fosters creative problem solving by providing a common vocabulary to capture design problems and identify potential solutions from proven designs.
“A pattern language does not impose a rigid methodology; rather, it fosters creative problem solving by providing a common vocabulary to capture the problems encountered during design and identify potential solutions from among families of proven designs.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.
Premisenone givenProgrammers in high-performance computing have shown that explicit technologies such as MPI and OpenMP can be made to work but too often require heroic effort untenable for most commercial software vendors.
“Programmers in high-performance computing have shown that explicit technologies (such as MPI and OpenMP) can be made to work but too often require heroic effort untenable for most commercial software vendors.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenThe history of parallel programming languages largely reflects researchers deciding what they think would be better and then building it for others to try.
“The history of these languages largely refl ects researchers deciding what they think would be better and then building it for others to try.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Interpretationnone givenSoftware is the main problem in bridging the gap between users and the parallel IT industry.
“Software is the main problem in bridging the gap between users and the parallel IT industry.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationnone givenThe datacenter and mobile client extremes both concern power and energy, the datacenter due to power and cooling cost and the mobile client due to battery life.
“Both concern power and energythe datacenter due to the cost of power and cooling and the mobile client due to battery life.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Premisereasoning§ Writing programs that scale with increasing numbers of coresThe industry decided the only viable option was to replace the single power-inefficient processor with many efficient processors on the same chip.
“The industry decided the only viable option was to replace the single power-inefficient processor with many efficient processors on the same chip.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). The quote only partly states this claim.
Premisenone givenAdvanced physiological blood-flow modeling based on computational analysis of 3D medical images of a patient's cerebral vasculature enables virtual stress testing to risk-stratify stroke victims intraoperatively.
“Advanced physiological blood-flow modeling based on computational analysis of 3D medical images of a patient's cerebral vasculature enables”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationBuschmann noted earlier that architectural styles may also be viewed as design patterns.
“That these architectural styles may also be viewed as design patterns was noted earlier by Buschmann in his 1996 book Pattern-Oriented Software Architecture.7”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [7] 7. international technology roadmap for semiconductors. executive summary, 2005 and 2007; http://public.itrs.net/.
May combine two claims.
InterpretationreasoningManycore computers can have higher yield, just as adding spares masks manufacturing defects.
“Just as it's easy to add spares to mask manufacturing defects,”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenMajor IT vendors have begun renting thousands of machines by the hour to enable smaller companies to benefit from cloud computing.
“They have also begun renting thousands of machines by the hour to enable smaller companies to benefi t from cloud computing.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ Writing programs that scale with increasing numbers of coresThe IT industry has improved the cost-performance of sequential computing by about 100 billion times over the past 60 years.
“Over the past 60 years, the IT industry has improved the cost-performance of sequential computing by about 100 billion times overall.20”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [20] 20. Williams, s., Waterman, a., and Patterson, D. roofline: an insightful visual performance model for floating- point programs and multicore architectures. Commun. ACM 52, 4 (apr. 2009), 65-76.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone givenThe multicore and manycore chips in the datacenter stand to benefit from the same tools and techniques developed for similar chips in mobile clients.
“The multicore and manycore chips in the datacenter stand to benefit from the same tools and techniques developed for similar chips in mobile clients.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Premisenone givenCurrent image classifiers are too slow to deliver adequate response times.
“Current image classifiers are too slow to deliver adequate response times;”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim. May combine two claims.
Premisereasoning§ Writing programs that scale with increasing numbers of coresThe microprocessor industry declared its future was in parallel computing, with increasing numbers of cores each technology generation every two years.
“The whole microprocessor industry thus declared that its future was in parallel computing, with increasing numbers of processors, or cores, each technology generation every two years.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenIT will be driven to extremes in size due to the increasing popularity of software as a service (SaaS).
“Given a fi ve-year project, we project the state of the fi eld in fi ve to 10 years, anticipating that IT will be driven to extremes in size due to the increasing popularity of software as a service, or SaaS:”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenLow error rates in image retrieval require processing very high dimensional feature spaces.
“Low error rates require processing very high dimensional feature spaces.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConsumer-image databases are growing so dramatically they require automated search instead of manual labeling.
“Consumer-image databases are growing so dramatically they require automated search instead of manual labeling.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationThe observation that design patterns and pattern languages might be useful for software design is not new.
“The observation that design patterns and pattern languages might be useful for software design is not new.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Premisenone givenSequential programming accommodates the wide range of skills of today's programmers.
“One especially vexing challenge for the parallel software span is that sequential programming accommodates the wide range of skills of today's programmers.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
InterpretationreasoningSuccess in parallel computing does not require improvement in the performance of all legacy software.
“Success does not require improvement in the performance of all legacy software.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Premisenone given§ Writing programs that scale with increasing numbers of coresMany startups sold parallel computers over the years, but all failed because programmers accustomed to continuous improvement in sequential performance saw little need to explore parallelism.
“Many startups have sold parallel computers over the years, but all failed, as programmers accustomed to continuous improvement in sequential performance saw little need to explore parallelism.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Premisenone givenMillions of cellphones are shipped each day with ever-increasing functionality.
“Millions of cellphones are shipped each day with ever-increasing functionality, a trend we expect to accelerate as well.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone givenTo save the IT industry, researchers must demonstrate greater end-user value from an increasing number of cores.
“To save the IT industry, researchers must demonstrate greater end-user value from an increasing number of cores.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone givenThe notion of better is not defined by only average performance; advances could be in worst-case response time, battery life, reliability, or security.
“Note that the notion of”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
InterpretationreasoningPatients identified at low risk of complications can then be treated to mitigate the effects of the stroke.
“Patients thus identified at low risk of complications can then be treated to mitigate the effects of the stroke.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone givenThe software stacks for datacenter and mobile clients are becoming similar, with more layers for mobile clients and increasing concern about protection and security.
“Finally, the software stacks are becoming similar, with more layers for mobile clients and increasing concern about protection and security.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.
Premisenone givenProgrammers have been trying to craft parallel code for decades and learned a great deal about what works and what doesn't work.
“Programmers have been trying to craft parallel code for decades and learned a great deal about what works and what doesn't work.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone givenPattern languages encourage a less formal, more associative way of thinking about a problem.
“Pattern languages encourage a less formal, more associative way of thinking about a problem.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenDepending on acoustic conditions, current transcribers can generate many errors.
“Depending on acoustic conditions, current transcribers can generate many errors;”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisenone givenThe Cisco Silicon Packet Processor (Metro) has 188 five-stage RISC cores, plus four spares, and dissipates 35 watts.
“The best-designed network processor is arguably the Cisco Silicon Packet Processor, also known as Metro, which has 188 fi ve-stage RISC cores, plus four spares to help yield and dissipate just 35 watts.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based). May combine two claims.
Interpretationnone givenPartitions are lightweight and can be resized or suspended with similar overheads to a process-context swap.
“Partitions are lightweight and can be resized or suspended with similar overheads to a process-context swap.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationThe Universal Parallel Computing Research Center at Illinois focuses on making it easy for domain experts to take advantage of parallelism, emphasizing productivity in specific domains over generality or performance.
“The Universal Parallel Computing Research Center (http://www.upcrc.illinois.edu/)at the University of Illinois focuses on making it easy for domain experts to take advantage of parallelism, so the emphasis is more on productivity in specific domains than on generality or performance.1”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [1] 1. Demmel, J., Dongarra, J., eijkhout, v., fuentes, e., Petitet, a., vuduc, r., Whaley, r., and yelick, K. self- adapting linear algebra algorithms and software. Proceedings of the IEEE, Special Issue on Program Generation, Optimization, and Adaptation 93, 2 (feb. 2005), 293-312. source
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone givenThe difficulty of the parallel challenge is reflected in the numerous parallel failures of the past.
“Though there are reasons for optimism, the difficulty of the challenge is reflected in the numerous parallel failures of the past.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
InterpretationreasoningThe same work-efficiency argument applies to optimistic parallelization.
“The same argument applies to optimistic parallelization.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone givenThe hardware tower of the Par Lab serves the software span and application tower.
“The hardware tower of the Par Lab serves the software span and application tower.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisereasoningThe autotuner search process tries many or all optimization switches and may take hours to complete on the target platform.
“The search process effectively tries many or all optimization switches; hence, searching may take hours to complete on the target platform.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenPreferring data-parallel algorithms over other styles of parallelism amortizes energy expended on instruction delivery, as SIMD and vector computers do.
“Preferring dataparallel algorithms over other styles of parallelism, as SIMD and vector computers amortize the energy expended on instruction delivery”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based). May combine two claims.
InterpretationreasoningSystems like RAMP help researchers explore designs of easy-to-program manycore architectures and build prototypes more quickly than with conventional hardware prototypes.
“Systems like RAMP help researchers explore designs of easy-to-program manycore architectures and build prototypes more quickly than they ever could with conventional hardware prototypes.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisenone givenIllinois relies on advancing compiler technology to find opportunities for parallelism, whereas the Par Lab focuses on autotuning.
“It relies on advancing compiler technology to find opportunities for parallelism, whereas the Par Lab focuses on autotuning.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenMessage-passing programs may be able to save the energy used by cache coherence.
“Message-passing programs may be able to save the energy used by cache coherence.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone givenExamples of such service include support for OS partitioning, explicit control for the memory hierarchy, accurate measurement for performance and energy, and an intuitive multicore performance model.
“Examples of such service include support for OS partitioning, explicit control for the memory hierarchy, accurate measurement for performance and energy, and an intuitive, multicore performance model.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone givenManufacturers will allow each core to vary its clock frequency to save power.
“They will also allow each core to vary its clock frequency to save power.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Interpretationnone givenThese patterns define the structure of a program but do not indicate what is actually computed.
“These patterns define the structure of a program but do not indicate what is actually computed.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisenone givenAutotuner search is performed only once, when the library is installed.
“However, search is performed only once, when the library is installed.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.
Interpretationnone givenSaaS applications in data centers with millions of users are naturally parallel and thus aligned with manycore, even if client apps are not.
“SaaS applications in data centers with millions of users are naturally parallel and thus aligned with manycore, even if clients apps are not”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenLocal assertions and type annotations are often generated from a program's implicit correctness requirements such as data race, deadlock freedom, and memory safety.
“Local assertions and type annotations are often generated from a program's implicit correctness requirements (such as data race, deadlock freedom, and memory safety).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.
InterpretationreasoningAs there is no alternative, the whole IT industry is committed, meaning many more people and companies are working on the problem.
“As there is no alternative, the whole IT industry is committed, meaning many more people and companies are working on the problem”
Quote in the paperNot a substantial claim- Rests on an assumption: No one is building a faster serial microprocessor, so programmers needing more performance have no option other than parallel hardware.
Probably not a substantial claim: may not pass S4 (based).
Interpretationnone givenEfficiency-layer code is checked automatically for subtle concurrency errors.
“The efficiency-layer code is checked automatically for subtle concurrency errors.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationRuby on Rails is a successful sequential programming framework based on the Model-View-Controller pattern.
“An example of a successful sequential programming framework is the Ruby on Rails framework, which is based on the Model-View-Controller pattern.26”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [26] 26. alexander, c. et al. A Pattern Language: Towns, Buildings, Construction. oxford university Press, 1997.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Classified as probably not a substantial claim. May combine two claims.
Interpretationnone givenThe Par Lab's approach to correctness relies on verification where possible, then uses the same tools to reduce testing where verification is not possible.
“Our approach to correctness relies on verification where possible, then uses the same tools to reduce the amount of testing where verification is not possible.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationRice University is developing languages, compilers, managed runtimes, concurrency libraries, and tools that support portable parallel abstractions with high productivity and high performance for multicores.
“The Rice University is developing languages, compilers, managed runtimes, concurrency libraries, and tools that support portable parallel abstractions with high productivity and high performance for multicores; examples include parallel language extensions 25 and optimized synchronization primitives.24”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [25] 25. agarwal, v., liu, l.-K., and Bader, D. financial modeling on the cell broadband engine. in Proceedings of 22nd IEEE International Parallel and Distributed Processing Symposium (Miami, fl, apr. 14-18, 2008). source
- cites [24] 24. adve, s. et al. Parallel Computing Research at Illinois: The UPCRC Agenda. White Paper. university of illinois, urbana-champaign, il, nov. 2008.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S4 (based). May combine two claims.
InterpretationreasoningThe resulting performance predictability improves parallel program performance, simplifies code autotuning and dynamic load balancing, supports real-time applications, and simplifies scheduling.
“The resulting performance predictability improves parallel program performance, simplifies code autotuning and dynamic load balancing, supports real-time applications, and simplifies scheduling.”
Quote in the paperNot a substantial claimMay combine two claims.
InterpretationreasoningCompilers that automatically parallelize sequential code may have great commercial value as computers go from one to two to four cores, but history suggests they will be unable to scale from 32 to 64 to 128 cores.
“Compilers that automatically parallelize sequential code may have great commercial value as computers go from one to two to four cores, though as described earlier, history suggests they will be unable to scale from 32 to 64 to 128 cores.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.
Interpretationnone givenRather than the traditional goal of linear speedup for all software as processors increase, success can reflect improved responsiveness or MIPS/Joule for a few new parallel killer apps.
“Rather than the traditional goal of linear speedup for all software as the number of processors increases, success can reflect improved responsiveness or MIPS/Joule for a few new parallel killer apps”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Interpretationnone givenMulticore diversity exacerbates the already difficult jobs performed by programmers, compiler writers, and architects.
“The multicore diversity mentioned earlier exacerbates the already difficult jobs performed by programmers, compiler writers, and architects.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisereasoningThe resulting autotuned code is often several times faster than naive implementations.
“The resulting code is often several times faster than naive implementations.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone givenThe autotuner's tireless trying of many unusual variants of a particular routine partly explains the surprising autotuning result.
“This surprising result is partly explained by the way the autotuner tirelessly tries many unusual variants of a particular routine.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationnone givenTo save energy with parallelization, parallel algorithms must be close to work efficient, performing no more total work than a sequential algorithm, or else parallelization is counterproductive.
“to save energy with parallelization, parallel algorithms must be close to”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Interpretationnone givenThe software span connecting applications to hardware relies more on parallel software architectures than on parallel programming languages.
“The software span connecting applications to hardware relies more on parallel software architectures than on parallel programming languages.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Premisenone givenConvention holds that truly useful patterns are not invented but mined from successful software applications.
“Convention holds that truly useful patterns are not invented but mined from successful software applications.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.
Interpretationnone givenProductivity, efficiency, and correctness are inextricably linked and must be addressed together.
“Productivity, efficiency, and correctness are inextricably linked and must be addressed together.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based). May combine two claims.
Interpretationnone givenThe productivity layer is free from concurrency problems because its parallelism models are restricted and the restrictions are enforced.
“The productivity layer is free from concurrency problems because the parallelism models are restricted, and the restrictions are enforced.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenHaving all processors on the same chip enables inventions that were impractical or uneconomical when spread across many chips.
“Having all processors on the same chip enables inventions that were impractical or uneconomical when spread across many chips”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone givenUnlike the traditional approach of making hardware king, the Par Lab is application-driven, working with domain experts to create compelling applications in music, image-and speech-recognition, health, and parallel browsers.
“Unlike the traditional approach of making hardware king, the Par Lab is application-driven, working with domain experts to create compelling applications in music, image-and speech-recognition, health, and parallel browsers.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone givenAs the number of cores increases, manufacturers will likely offer products with differing numbers of cores per chip to cover multiple price-performance points.
“In addition, as the number of cores increase, manufacturers will likely offer products with differing numbers of cores per chip to cover multiple price-performance points.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Interpretationnone givenCompleting a task on slow parallel cores will be more efficient than completing it in the same time sequentially on one fast core.
“Completing a task on slow parallel cores will be more efficient than completing it in the same time sequentially on one fast core”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Premisenone givenFor any given problem, there may be several parallel algorithms, each with alternative parallel data layouts.
“For any given problem, there may be several parallel algorithms, each with alternative parallel data layouts.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Interpretationnone givenFor restricted parallelism models with global synchronization, static program analysis becomes more tractable.
“For restricted parallelism models with global synchronization, this analysis becomes more tractable”
Quote in the paperSubstantial claim- Rests on an assumption: Static program analysis in the presence of pointers and heap memory falsely reports many errors that cannot really occur.
Probably not a substantial claim: may not pass S4 (based).
Premisenone givenModular verification and automated unit-test generation require specification of high-level serial semantic constraints on the behavior of individual modules such as parallel frameworks and libraries.
“Modular verification and automated unit-test generation require the specification of high-level serial semantic constraints on the behavior of the individual modules (such as parallel frameworks and parallel libraries).”
Quote in the paperNot a substantial claim- Rests on an assumption: A key challenge in verification is obtaining specifications for programs to verify.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationUnified Parallel C partitions memory among processors but not currently between on- and off-chip.
“inspired by our experience with Unified Parallel C, 27 which partitions memory among processors but not (currently) between on-and off-chip.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [27] 27. asanovic, K. et al. The Parallel Computing Laboratory at U.C. Berkeley: A Research Agenda Based on the Berkeley View. ucB/eecs-2008-23, university of california, Berkeley, Mar. 21, 2008.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing). May combine two claims.
Interpretationnone givenAutotuners preserve clarity and support portability by reducing the temptation to mangle source code to improve performance for a particular computer.
“Autotuners also preserve clarity and support portability by reducing the temptation to mangle the source code to improve performance for a particular computer.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationThe Roofline model plots computational and memory-bandwidth limits and determines the best possible performance of a kernel by examining the average number of operations per memory access.
“The Roofline model plots computational and memorybandwidth limits, then determines the best possible performance of a kernel by examining the average number of operations per memory access.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [20] 20. Williams, s., Waterman, a., and Patterson, D. roofline: an insightful visual performance model for floating- point programs and multicore architectures. Commun. ACM 52, 4 (apr. 2009), 65-76.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
May combine two claims.
InterpretationreasoningCompiling will be even more difficult because the switch to multicore means microprocessors are becoming more diverse, since conventional wisdom is not yet established for multicore architectures.
“Compiling will be even more difficult, as the switch to multicore means microprocessors are becoming more diverse, since conventional wisdom is not yet established for multicore architectures.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable).
InterpretationreasoningStructural and computational patterns can be combined to architect arbitrarily complex parallel software systems.
“Structural and computational patterns can be combined to architect arbitrarily complex parallel software systems.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Interpretationnone givenThese objectives cannot be accomplished with a single-point solution such as a universal language.
“These objectives cannot be accomplished with a single-point solution (such as a universal language).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
InterpretationreasoningThe OSS community is likely to embrace technical advances rather than be limited by legacy code.
“The OSS community is a meritocracy, so it's likely to embrace technical advances rather than be limited by legacy code.”
Quote in the paperNot a substantial claim- Rests on an assumption: The OSS community is a meritocracy.
Probably not a substantial claim: may not pass S2 (checkable), S4 (based).
Premisenone givenHistorically successful parallel frameworks encode the collective experience of the programming community's solutions to recurring problems.
“Historically successful parallel frameworks encode the collective experience of the programming community's solutions to recurring problems.”
Quote in the paperNot a substantial claim
The authors state this as an assumption.
Manycore computers will be homogeneous.
“It may be reasonable to assume that manycore computers will be homogeneous, like the Metro, but there is an argument for heterogeneous manycores as well.”
The paper relies on this without support.
Many datacenter applications have ample parallelism across independent users.
“Many datacenter applications have ample parallelism across independent users, so the Par Lab focuses on parallelizing applications for clients.”
The paper relies on this without support.
It takes four to five years to design and build chips and port software to evaluate them.
“One notable challenge for the hardware tower is that it takes four to fi ve years to design and build chips and port software to evaluate them.”
The paper relies on this without support.
It takes a decade for a new compiler optimization to become part of production compilers.
“One estimate is that it takes a decade for a new compiler optimization to become part of production compilers.”
The paper relies on this without support.
The browser will be the largest and most important application on many mobile devices.
“The browser will be the largest and most important application on many mobile devices.”
The paper relies on this without support.
Automatic parallelism does not work.
“Automatic parallelism doesn't work.”
The paper relies on this without support.
Compilers are great at low-level scheduling decisions but cannot discover new algorithms to exploit concurrency.
“Compilers are great at low-level scheduling decisions but can't discover new algorithms to exploit concurrency.”
The paper relies on this without support.
Existing multicore systems do not offer a common low-level programming model for parallel code.
“Unfortunately, existing multicore systems do not offer a common low-level programming model for parallel code.”
The paper relies on this without support.
Static program analysis in the presence of pointers and heap memory falsely reports many errors that cannot really occur.
“Static program analysis in the presence of pointers and heap memory falsely reports many errors that cannot really occur.”
The paper relies on this without support.
No one is building a faster serial microprocessor, so programmers needing more performance have no option other than parallel hardware.
“Unlike in the past, no one is building the faster serial microprocessor; programmers needing more performance have no option other than parallel hardware”
The paper relies on this without support.
Computer science has not solved the parallel challenge.
“Computer science hasn't solved the parallel challenge though not because it hasn't tried.”
The paper relies on this without support.
Conferences on parallelism traditionally focus on high-performance computing, with target hardware usually large-scale computers with thousands of microprocessors.
“All traditionally focus on high-performance computing; the target hardware is usually large-scale computers with thousands of microprocessors.”
The paper relies on this without support.
A key challenge in verification is obtaining specifications for programs to verify.
“A key challenge in verification is obtaining specifications for programs to verify.”
The paper relies on this without support.
Programmers often find it difficult to specify high-level contracts involving large modules, but most find it convenient to specify local properties using assert statements and type annotations.
“Programmers often find it difficult to specify such high-level contracts involving large modules; however, most find it convenient to specify local properties of programs using assert statements and type annotations.”
The paper relies on this without support.
Parallel architectures introduce many new optimization parameters, and so far there are few successful autotuners for parallel codes.
“However, parallel architectures introduce many new optimization parameters; so far, there are few successful autotuners for parallel codes.”
The paper relies on this without support.
Work efficiency is a demanding requirement; for some inherently sequential problems like finite-state machines, only work-inefficient algorithms are known.
“Work efficiency is a demanding requirement, since, for some”
The paper relies on this without support.
Space-time partitioning is crucial for manycore client operating systems.
“Space-time partitioning is crucial for manycore client operating systems.”
The authors state this as an assumption.
Resources given to a partition are either exclusive or guaranteed via a quality-of-service contract.
“A key tenet of our approach is that resources given to a partition are either exclusive (such as cores or private caches) or guaranteed via a quality-of-service contract (such as a minimum fraction of network or memory bandwidth).”
The paper relies on this without support.
Performance counters on current single-core computers often miss important measurements or are unique to a computer and only understandable by the machine's designers.
“Sadly, performance counters on current single-core computers often miss important measurements (such as prefetched data) or are unique to a computer and only understandable by the machine's designers.”
The paper relies on this without support.
The OSS community is a meritocracy.
“The OSS community is a meritocracy, so it's likely to embrace technical advances rather than be limited by legacy code.”
Cites
(1994) · Cited by 21,711 · see citing works
A Pattern Language: Towns, Buildings, Construction
Alexander, C., Ishikawa, S., Silverstein, M., Jacobson, M., Fiksdahl-King, I., & Angel, S. (1977) · Cited by 4,555 · see citing works
(1996) · Cited by 2,981 · see citing works
Williams, S., Waterman, A., & Patterson, D. A. (2009) · Communications of the ACM · doi:10.1145/1498765.1498785 · Cited by 2,484 · see citing works
Self-citation(2006) · Cited by 1,979 · see citing works
Self-citationSen, K., Marinov, D., & Agha, G. (2005) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/1081706.1081750 · Cited by 1,651 · see citing works
Self-citationComputer Organization and Design: the Hardware/Software Interface
Patterson, D. A., & Hennessy, J. L. (1993) · Cited by 1,623 · see citing works
Self-citationCastro, B. F. (1997) · Computación y Sistemas · Cited by 1,504 · see citing works
Amdahl's Law in the Multicore Era
Hill, M. D., & Marty, M. R. (2008) · Computer · doi:10.1109/mc.2008.209 · Cited by 1,262 · see citing works
Exokernel: an operating system architecture for application-level resource management
Engler, D. R., Kaashoek, M. F., & O'Toole, J. (1995) · Proceedings of the fifteenth ACM symposium on Operating systems principles - SOSP '95 · doi:10.1145/224056.224076 · Cited by 1,118 · see citing works
Introduction to Software Architecture
Garlan, D., & Shaw, M. (2009) · Advanced topics in science and technology in China · doi:10.1007/978-3-540-74343-9_1 · Cited by 1,101 · see citing works
Coordination languages and their significance
Gelernter, D. H., & Carriero, N. J. (1992) · Communications of the ACM · doi:10.1145/129630.129635 · Cited by 1,003 · see citing works
Optimization of sparse matrix-vector multiplication on emerging multicore platforms
Williams, S., Oliker, L., Vuduc, R. W., et al. (2007) · Parallel Computing · doi:10.1016/j.parco.2008.12.006 · Cited by 796 · see citing works
Self-citationOptimization of sparse matrix-vector multiplication on emerging multicore platforms
Williams, S., Oliker, L., Vuduc, R., Shalf, J., Yelick, K., & Demmel, J. (2007) · Proceedings of the 2007 ACM/IEEE conference on Supercomputing · doi:10.1145/1362622.1362674 · Cited by 791
Self-citation(2004) · Cited by 742 · see citing works
Ownership types for flexible alias protection
Clarke, D. G., Potter, J. M., & Noble, J. (1998) · doi:10.1145/286936.286947 · Cited by 579 · see citing works
Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures
Datta, K., Murphy, M., Volkov, V. M., Williams, S., Carter, J. T., Oliker, L., Patterson, D. A., Shalf, J. M., & Yelick, K. (2008) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.5555/1413370.1413375 · Cited by 463 · see citing works
Self-citationSen, K., Marinov, D., & Agha, G. (2005) · ACM SIGSOFT Software Engineering Notes · doi:10.1145/1095430.1081750 · Cited by 314 · see citing works
Self-citationHuman Factors: Understanding People-System Relationships
Kantowitz, B. H., & Sorkin, R. D. (1983) · Medical Entomology and Zoology · Cited by 312 · see citing works
Self-Adapting Linear Algebra Algorithms and Software
Demmel, J., Dongarra, J., Eijkhout, V., Fuentes, E., Petitet, A., Vuduc, R., Whaley, R. C., & Yelick, K. (2005) · Proceedings of the IEEE · doi:10.1109/jproc.2004.840848 · Cited by 204 · see citing works
Self-citationRAMP: Research Accelerator for Multiple Processors
Wawrzynek, J., Patterson, D., Oskin, M., Lu, S.-L., Kozyrakis, C., Hoe, J. C., Chiou, D., & Asanovic, K. (2007) · IEEE Micro · doi:10.1109/mm.2007.39 · Cited by 168 · see citing works
Self-citationPhasers: a unified deadlock-free construct for collective and point-to-point synchronization
Shirako, J., Peixotto, D. M., Sarkar, V., & Scherer, W. N. (2008) · Proceedings of the 22nd annual international conference on Supercomputing · doi:10.1145/1375527.1375568 · Cited by 124 · see citing works
Henzinger, T. A., Jhala, R., & Majumdar, R. (2005) · Proceedings of the 10th European software engineering conference held jointly with 13th ACM SIGSOFT international symposium on Foundations of software engineering · doi:10.1145/1081706.1081713 · Cited by 111 · see citing works
Williams, S., Waterman, A., & Patterson, D. (2009) · doi:10.2172/1407078 · Cited by 110 · see citing works
Self-citationLattice Boltzmann simulation optimization on leading multicore platforms
Williams, S., Carter, J., Oliker, L., Shalf, J., & Yelick, K. (2008) · 2008 IEEE International Symposium on Parallel and Distributed Processing · doi:10.1109/ipdps.2008.4536295 · Cited by 98 · see citing works
Self-citationModel Checking Multithreaded Programs with Asynchronous Atomic Methods
Sen, K., & Viswanathan, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11817963_29 · Cited by 95 · see citing works
Self-citationAmdahl’s Law in the multicore era
Hill, M. D. (2008) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2008.4658638 · Cited by 76 · see citing works
(2008) · Cited by 47 · see citing works
Self-citationA Conversation with John Hennessy and David Patterson: They wrote the book on computing.
O'Hanlon, C. (2006) · Queue · doi:10.1145/1189276.1189286 · Cited by 39 · see citing works
Financial modeling on the cell broadband engine
Agarwal, V., Liu, L.-K., & Bader, D. A. (2008) · 2008 IEEE International Symposium on Parallel and Distributed Processing · doi:10.1109/ipdps.2008.4536320 · Cited by 29 · see citing works
Language Extensions in Support of Compiler Parallelization
Shirako, J., Kasahara, H., & Sarkar, V. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-85261-2_6 · Cited by 16 · see citing works
High performance MPEG-2 software decoder on the cell broadband engine
Bader, D. A., & Patel, S. (2008) · Proceedings - IEEE International Parallel and Distributed Processing Symposium · doi:10.1109/ipdps.2008.4536234 · Cited by 12 · see citing works
Engler, D. R., Kaashoek, M. F., & O'Toole, J. (1995) · ACM SIGOPS Operating Systems Review · doi:10.1145/224057.224076
Ownership types for flexible alias protection
Clarke, D. G., Potter, J. M., & Noble, J. (1998) · ACM SIGPLAN Notices · doi:10.1145/286942.286947
Coordination languages and their significance
Gelernter, D., & Carriero, N. (1992) · Communications of the ACM · doi:10.1145/129630.376083
Henzinger, T. A., Jhala, R., & Majumdar, R. (2005) · ACM SIGSOFT Software Engineering Notes · doi:10.1145/1095430.1081713
Flagged first, then by citations
Research works printed but not linked: 3
- Adve , S. et al. Parallel Computing Research at Illinois: The UPCRC Agenda. White Paper . University of Illinois , Urbana-Champaign, IL, Nov. 2008 . Adve, S. et al. Parallel Computing Research at Illinois: The UPCRC Agenda. White Paper. University of Illinois, Urbana-Champaign, IL, Nov. 2008.
- Thomas , D. et al. Agile Web Development with Rails , Second Edition. The Pragmatic Bookshelf , Raleigh, NC , 2008 . Thomas, D. et al. Agile Web Development with Rails, Second Edition. The Pragmatic Bookshelf, Raleigh, NC, 2008.
- UPC Language Specifications , Version 1.2. Technical Report LBNL-59208. Lawrence Berkeley National Laboratory, Berkeley, CA , 2005 . UPC Language Specifications, Version 1.2. Technical Report LBNL-59208. Lawrence Berkeley National Laboratory, Berkeley, CA, 2005.
Cited by
Sorted by citations
An analysis of Linux scalability to many cores
Boyd-Wickizer, S., Clements, A. T., Mao, Y., et al. (2010) · doi:10.5555/1924943.1924944 · Cited by 339 · see citing works
Fastflow: High‐Level and Efficient Streaming on Multicore
Aldinucci, M., Danelutto, M., Kilpatrick, P., et al. (2017) · doi:10.1002/9781119332015.ch13 · Cited by 244 · see citing works
Blanchette, J. (2011) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21542 · Cited by 217 · see citing works
Shi, X., Zheng, Z., Zhou, Y., Jin, H., He, L., Liu, B., & Hua, Q.-S. (2018) · ACM Computing Surveys · doi:10.1145/3128571 · Cited by 181 · see citing works
Throughput-Effective On-Chip Networks for Manycore Accelerators
Bakhoda, A., Kim, J., & Aamodt, T. M. (2010) · doi:10.1109/micro.2010.50 · Cited by 160 · see citing works
A survey of algorithmic skeleton frameworks: high‐level structured parallel programming enablers
González–Vélez, H., & Leyton, M. (2010) · Software Practice and Experience · doi:10.1002/spe.1026 · Cited by 149 · see citing works
A Simplified and Accurate Model of Power-Performance Efficiency on Emergent GPU Architectures
Song, S. L., Su, C.-Y., Rountree, B., et al. (2013) · doi:10.1109/ipdps.2013.73 · Cited by 138 · see citing works
Exponential laws of computing growth
Denning, P. J., & Lewis, T. G. (2016) · Communications of the ACM · doi:10.1145/2976758 · Cited by 136 · see citing works
Chung, E. S., Hoe, J. C., & Mai, K. (2011) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/1950413.1950435 · Cited by 131 · see citing works
Evaluating and Optimizing OpenCL Kernels for High Performance Computing with FPGAs
Zohouri, H. R., Maruyama, N., Smith, A., et al. (2016) · doi:10.1109/sc.2016.34 · Cited by 122 · see citing works
Tan, Z., Waterman, A. S., Avizienis, R. R., et al. (2010) · doi:10.1145/1837274.1837390 · Cited by 115 · see citing works
Self-citationPartitioning streaming parallelism for multi-cores
Wang, Z., & O’Boyle, M. (2010) · doi:10.1145/1854273.1854313 · Cited by 109 · see citing works
Xu, G. H., Mitchell, N., Arnold, M., et al. (2010) · doi:10.1145/1882362.1882448 · Cited by 104 · see citing works
Evaluating and Optimizing OpenCL Kernels for High Performance Computing with FPGAs
Zohouri, H. R., Zohouri, H. R., 丸山, 直., et al. (2017) · Institutional Repositories DataBase (IRDB) · Cited by 101 · see citing works
Amesos2 and Belos: Direct and Iterative Solvers for Large Sparse Linear Systems
Bavier, E., Hoemmen, M. F., Rajamanickam, S., et al. (2012) · Scientific Programming · doi:10.1155/2012/243875 · Cited by 98 · see citing works
In-memory database acceleration on FPGAs: a survey
Fang, J., Mulder, Y. T. B., Hidders, J., et al. (2019) · The VLDB Journal · doi:10.1007/s00778-019-00581-w · Cited by 92 · see citing works
Evaluating the Impact of SDC on the GMRES Iterative Solver
Elliott, J., Hoemmen, M. F., & Mueller, F. (2014) · doi:10.1109/ipdps.2014.123 · Cited by 84 · see citing works
Tan, Z., Waterman, A. S., Cook, H. M., et al. (2010) · doi:10.1145/1815961.1815999 · Cited by 77 · see citing works
Self-citationSafe programmable speculative parallelism
Prabhu, P., Ramalingam, G., & Vaswani, K. (2010) · doi:10.1145/1806596.1806603 · Cited by 77 · see citing works
Auto-tuning performance on multicore computers
Patterson, D. A., & Williams, S. (2008) · Cited by 75 · see citing works
Self-citationFault-tolerant iterative methods via selective reliability.
Ferreira, K. B., Bridges, P. G., Heroux, M. A., et al. (2011) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · Cited by 75 · see citing works
Integrating profile-driven parallelism detection and machine-learning-based mapping
Wang, Z., Tournavitis, G., Franke, B., & O’boyle, M. F. P. (2014) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/2579561 · Cited by 72 · see citing works
Explicit parallel-in-time integration of a linear acoustic-advection system
Ruprecht, D., & Krause, R. (2012) · Computers & Fluids · doi:10.1016/j.compfluid.2012.02.015 · Cited by 70 · see citing works
Zeng, S., Liu, C., Huang, X., Tang, Z., Liu, L., & Zhou, P. (2022) · Nature Communications · doi:10.1038/s41467-021-27644-3 · Cited by 67 · see citing works
Auto-tuning stencil codes for cache-based multicore platforms
Yelick, K., & Datta, K. (2009) · Cited by 66 · see citing works
Self-citationAccelerating Code on Multi-cores with FastFlow
Aldinucci, M., Danelutto, M., Kilpatrick, P., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23397-5_17 · Cited by 65 · see citing works
Towards Profitable Virtual Machine Placement in the Data Center
Shi, W., & Hong, B. (2011) · doi:10.1109/ucc.2011.28 · Cited by 62 · see citing works
Few-Shots Parallel Algorithm Portfolio Construction via Co-Evolution
Tang, K., Liu, S., Yang, P., et al. (2021) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2021.3059661 · Cited by 61 · see citing works
Nitu, V., Teabe, B., Tchana, A., et al. (2018) · doi:10.1145/3190508.3190537 · Cited by 60 · see citing works
Accelerating pathology image data cross-comparison on CPU-GPU hybrid systems
Wang, K., Huai, Y., Lee, R., et al. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2350229.2350268 · Cited by 59 · see citing works
Fine-grained GPU implementation of assembly-free iterative solver for finite element problems
Martínez‐Frutos, J., Castejón, P. J. M., & Herrero‐Perez, D. (2015) · Computers & Structures · doi:10.1016/j.compstruc.2015.05.010 · Cited by 59 · see citing works
Programming multi‐core and many‐core computing systems
Aldinucci, M., Marco, D., Peter, K., et al. (2017) · doi:10.1002/9781119332015 · Cited by 51 · see citing works
An Event-Triggered Programmable Prefetcher for Irregular Workloads
Ainsworth, S., & Jones, T. M. (2018) · doi:10.1145/3173162.3173189 · Cited by 49 · see citing works
Handbook of FPGA Design Security
Huffmire, T., Irvine, C., Nguyen, T. D., et al. (2010) · doi:10.1007/978-90-481-9157-4 · Cited by 49 · see citing works
Generative Adversarial Construction of Parallel Portfolios
Liu, S., Tang, K., & Yao, X. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2984546 · Cited by 48 · see citing works
Jungle Computing: Distributed Supercomputing Beyond Clusters, Grids, and Clouds
Seinstra, F. J., Maassen, J., van Nieuwpoort, R. V., Drost, N., van Kessel, T., van Werkhoven, B., Jacopo Urbani, A., Jacobs, C. J. H., Kielmann, T., & Bal, H. E. (2010) · Computer communications and networks · doi:10.1007/978-0-85729-049-6_8 · Cited by 46 · see citing works
The ESCAPE project: Energy-efficient Scalable Algorithms for Weather Prediction at Exascale
Müller, A., Deconinck, W., Kühnlein, C., et al. (2019) · Geoscientific model development · doi:10.5194/gmd-12-4425-2019 · Cited by 47 · see citing works
Gong, C., Bao, W., & Tang, G. (2013) · Fractional Calculus and Applied Analysis · doi:10.2478/s13540-013-0041-8 · Cited by 47 · see citing works
Fault-tolerant linear solvers via selective reliabilityPreprint
Bridges, P. G., Ferreira, K. B., Heroux, M. A., et al. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.1390 · Cited by 47 · see citing works
HARE: Hardware accelerator for regular expressions
Gogte, V., Kolli, A., Cafarella, M., et al. (2016) · doi:10.1109/micro.2016.7783747 · Cited by 46 · see citing works
Using machine learning to partition streaming programs
Wang, Z., & O’Boyle, M. (2013) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/2512436 · Cited by 46 · see citing works
Suitability Analysis of FPGAs for Heterogeneous Platforms in HPC
Escobar, F. A., Chang, X., & Valderrama, C. A. (2015) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2015.2407896 · Cited by 45 · see citing works
Strategies for preparing computer science students for the multicore world
Brown, R. A., Shoop, E., Adams, J. C., Clifton, C. C., Gardner, M. K., Haupt, M., & Hinsbeeck, P. (2010) · doi:10.1145/1971681.1971689 · Cited by 44 · see citing works
A machine learning-based approach for thread mapping on transactional memory applications
Castro, M., Góes, L. F. W., Ribeiro, C. P., et al. (2011) · doi:10.1109/hipc.2011.6152736 · Cited by 42 · see citing works
Eliminating Concurrency Bugs with Control Engineering
Kelly, T., Wang, Y., Lafortune, S., et al. (2009) · Computer · doi:10.1109/mc.2009.391 · Cited by 40 · see citing works
Ng, N., Coutinho, J. G. F., & Yoshida, N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-46663-6_11 · Cited by 39 · see citing works
Targeting Distributed Systems in FastFlow
Aldinucci, M., Campa, S., Danelutto, M., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36949-0_7 · Cited by 39 · see citing works
The ParaPhrase Project: Parallel Patterns for Adaptive Heterogeneous Multicore Systems
Hammond, K. L., Aldinucci, M., Brown, C., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-35887-6_12 · Cited by 39 · see citing works
Snow White Clouds and the Seven Dwarfs
Phillips, S., Engen, V., & Papay, J. (2011) · doi:10.1109/cloudcom.2011.114 · Cited by 39 · see citing works
An application-centric evaluation of OpenCL on multi-core CPUs
Shen, J., Fang, J., Sips, H. J., et al. (2013) · Parallel Computing · doi:10.1016/j.parco.2013.08.009 · Cited by 37 · see citing works
Power Modeling and Characterization of Computing Devices: A Survey
Reda, S., & Nowroz, A. N. (2012) · Foundations and Trends® in Electronic Design Automation · doi:10.1561/1000000022 · Cited by 37 · see citing works
Finding, analysing and solving MPI communication bottlenecks in Earth System models
Prims, O. T., Castrillo, M., Acosta, M., et al. (2018) · Journal of Computational Science · doi:10.1016/j.jocs.2018.04.015 · Cited by 36 · see citing works
Liu, L., Wang, D., Zhu, M., et al. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2463735 · Cited by 36 · see citing works
Benchmarking Usability and Performance of Multicore Languages
Nanz, S., West, S., da Silveira, K. S., et al. (2013) · doi:10.1109/esem.2013.10 · Cited by 36 · see citing works
The landscape of GPGPU performance modeling tools
Madougou, S., Vărbănescu, A. L., de Laat, C., et al. (2016) · Parallel Computing · doi:10.1016/j.parco.2016.04.002 · Cited by 35 · see citing works
High quality real-time Image-to-Mesh conversion for finite element simulations
Foteinos, P. A., & Chrisochoides, N. P. (2013) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2013.11.002 · Cited by 35 · see citing works
Brown, R. A., & Shoop, E. (2011) · doi:10.1145/1953163.1953293 · Cited by 35 · see citing works
Making parallel programs reliable with stable multithreading
Yang, J., Cui, H., Wu, J., et al. (2014) · Communications of the ACM · doi:10.1145/2500875 · Cited by 34 · see citing works
Ubiquitous Parallel Computing from Berkeley, Illinois, and Stanford
Catanzaro, B., Fox, A., Keutzer, K., et al. (2010) · IEEE Micro · doi:10.1109/mm.2010.42 · Cited by 33 · see citing works
Self-citationAdams, J. C., Brown, R. A., & Shoop, E. (2013) · doi:10.1109/ipdpsw.2013.275 · Cited by 32 · see citing works
Exaflop/s: The why and the how
Keyes, D. E. (2011) · Comptes Rendus Mécanique · doi:10.1016/j.crme.2010.11.002 · Cited by 32 · see citing works
Analysing astronomy algorithms for graphics processing units and beyond
Barsdell, B. R., Barnes, D. G., & Fluke, C. J. (2010) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2010.17257.x · Cited by 32 · see citing works
Automatic Construction of Parallel Portfolios via Explicit Instance Grouping
Liu, S., Tang, K., & Yao, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011560 · Cited by 31 · see citing works
HARE: hardware accelerator for regular expressions
Gogte, V., Kolli, A., Cafarella, M., et al. (2016) · International Symposium on Microarchitecture · doi:10.5555/3195638.3195692 · Cited by 31 · see citing works
Tyzack, J. D., Mussa, H. Y., Williamson, M. J., et al. (2014) · Journal of Cheminformatics · doi:10.1186/1758-2946-6-29 · Cited by 31 · see citing works
Analysis of Hyperspectral Data to Develop an Approach for Document Images
Zaman, Z., Ahmed, S. B., & Malik, M. I. (2023) · Sensors · doi:10.3390/s23156845 · Cited by 30 · see citing works
26 PFLOPS Stencil Computations for Atmospheric Modeling on Sunway TaihuLight
Ao, Y., Yang, C., Wang, X., et al. (2017) · Proceedings - IEEE International Parallel and Distributed Processing Symposium · doi:10.1109/ipdps.2017.9 · Cited by 30 · see citing works
Analysing astronomy algorithms for graphics processing units and beyond
Barsdell, B. R., Barnes, D. G., & Fluke, C. J. (2024) · Figshare · doi:10.25916/sut.26218352.v1 · Cited by 29 · see citing works
Ziogas, A. N., Ben‐Nun, T., Schneider, T., et al. (2021) · ACM International Conference on Supercomputing (ICS) · doi:10.1145/3447818.3460360 · Cited by 29 · see citing works
Altaf, M. S. B., & Wood, D. A. (2017) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3079856.3080216 · Cited by 29 · see citing works
Pabble: parameterised Scribble
Ng, N., & Yoshida, N. (2014) · Service Oriented Computing and Applications · doi:10.1007/s11761-014-0172-8 · Cited by 29 · see citing works
Performance-aware component composition for GPU-based systems
Dastgeer, U. (2014) · Linköping University Electronic Press eBooks · doi:10.3384/diss.diva-104310 · Cited by 30 · see citing works
A “Minimal Disruption” Skeleton Experiment: Seamless Map & Reduce Embedding in OCaml
Danelutto, M., & Cosmo, R. D. (2012) · Procedia Computer Science · doi:10.1016/j.procs.2012.04.202 · Cited by 28 · see citing works
Radhakrishnan, R. (2020) · AIChE Journal · doi:10.1002/aic.17026 · Cited by 28 · see citing works
High-performance Implementation of Matrix-free High-order Discontinuous Galerkin MethodsPreprint
Müthing, S., Piatkowski, M., & Bastian, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10885 · Cited by 26 · see citing works
On Achieving High Message Rates
Fröning, H., Nüssle, M., Litz, H., et al. (2013) · doi:10.1109/ccgrid.2013.43 · Cited by 26 · see citing works
Porting Decision Tree Algorithms to Multicore Using FastFlow
Aldinucci, M., Ruggieri, S., & Torquati, M. (2010) · UnipiEprints Open Archive (Università di Pisa) · Cited by 26 · see citing works
ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores
Chen, Y., Li, K., Wang, Y., et al. (2024) · doi:10.1145/3627535.3638476 · Cited by 25 · see citing works
A versatile software systolic execution model for GPU memory-bound kernels
Chen, P., Wahib, M., Takizawa, S., Takano, R., & Matsuoka, S. (2019) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3295500.3356162 · Cited by 23 · see citing works
An Event-Triggered Programmable Prefetcher for Irregular Workloads
Ainsworth, S., & Jones, T. M. (2018) · ACM SIGPLAN Notices · doi:10.1145/3296957.3173189 · Cited by 23 · see citing works
Wadden, J., Angstadt, K., & Skadron, K. (2018) · doi:10.1109/hpca.2018.00069 · Cited by 23 · see citing works
Beard, J. C., Li, P., & Chamberlain, R. D. (2015) · doi:10.1145/2712386.2712400 · Cited by 23 · see citing works
Microwave tomography for breast cancer detection on Cell broadband engine processors
Xu, M., Thulasiraman, P., & Noghanian, S. (2011) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2011.10.013 · Cited by 23 · see citing works
Hardware synchronization for embedded multi-core processors
Stoif, C., Schoeberl, M., Liccardi, B., et al. (2011) · doi:10.1109/iscas.2011.5938126 · Cited by 23 · see citing works
Parallelizing packet processing in container overlay networks
Lei, J., Munikar, M., Suo, K., et al. (2021) · doi:10.1145/3447786.3456241 · Cited by 22 · see citing works
Usman, S., Mehmood, R., Katib, I. A., & Albeshri, A. A. (2019) · IEEE Access · doi:10.1109/access.2019.2923565 · Cited by 21 · see citing works
Parallel Multiscale Linear Solver for Highly Detailed Reservoir Models
Manea, A. M., Sewall, J. D., & Tchelepi, H. A. (2016) · SPE Journal · doi:10.2118/173259-pa · Cited by 22 · see citing works
Nugteren, C., & Corporaal, H. (2012) · ACM International Conference on Computing Frontiers (CF) · doi:10.1145/2212908.2212937 · Cited by 22 · see citing works
Udupa, A., Rajan, K., & Thies, W. (2011) · doi:10.1145/1993498.1993555 · Cited by 22 · see citing works
Practical parallel and concurrent programming
Sadowski, C., Ball, T. J., Bishop, J., et al. (2011) · doi:10.1145/1953163.1953222 · Cited by 22 · see citing works
Formal Analysis of Message Passing
Siegel, S. F., & Gopalakrishnan, G. K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-18275-4_2 · Cited by 22 · see citing works
How Good is Static Analysis at Finding Concurrency Bugs?
Kester, D., Mwebesa, M., & Bradbury, J. S. (2010) · doi:10.1109/scam.2010.26 · Cited by 22 · see citing works
Usman, S., Mehmood, R., Katib, I. A., Albeshri, A. A., & Altowaijri, S. M. (2019) · Mobile Networks and Applications · doi:10.1007/s11036-019-01318-3 · Cited by 20 · see citing works
Chaudhury, B., Varma, A., Keswani, Y., et al. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2018.03.001 · Cited by 21 · see citing works
An efficient parallel immersed boundary algorithm using a pseudo-compressible fluid solver
Wiens, J. K., & Stockie, J. M. (2014) · Journal of Computational Physics · doi:10.1016/j.jcp.2014.10.058 · Cited by 21 · see citing works
Pabble: Parameterised Scribble for Parallel Programming
Ng, N., & Yoshida, N. (2014) · doi:10.1109/pdp.2014.20 · Cited by 21 · see citing works
Khaneghah, E. M., & Sharifi, M. (2013) · The Journal of Supercomputing · doi:10.1007/s11227-013-0982-z · Cited by 21 · see citing works
Teaching Parallel and Distributed Computing to Undergraduate Computer Science Students
Arroyo, M. (2013) · doi:10.1109/ipdpsw.2013.276 · Cited by 21 · see citing works
A novel compiler support for automatic parallelization on multicore systems
Andión, J. M., Arenaz, M., Rodríguez, G., et al. (2013) · Parallel Computing · doi:10.1016/j.parco.2013.04.003 · Cited by 21 · see citing works
A Block-Oriented Language and Runtime System for Tensor Algebra with Very Large Arrays
Sanders, B. A., Bartlett, R. J., Deumens, E., et al. (2010) · doi:10.1109/sc.2010.3 · Cited by 21 · see citing works
- Authors
- Asanovic, K., Bodik, R., Demmel, J., Keaveny, T., Keutzer, K., Kubiatowicz, J., Morgan, N., Patterson, D., Sen, K., Wawrzynek, J., Wessel, D., & Yelick, K.
- Affiliations
- University of California, Berkeley
- University of California, Berkeley (US)
- ORCID
- Venue
- Communications of the ACM
- Published
- 2009-10
- Volume
- 52
- Issue
- 10
- Pages
- 56-67
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2039417226
- Cited by
- 627
- References
- 31
- Citations by year
- 2026: 15 · 2025: 18 · 2024: 22 · 2023: 15 · 2022: 20 · 2021: 32 · 2020: 29 · 2019: 30 · 2018: 30 · 2017: 39 · 2016: 32 · 2015: 36 · 2014: 64 · 2013: 66 · 2012: 55
- FWCI
- 92.08
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- Funders
- University of California (DIG07-10227)
- Intel Corporation (20080469)
- Microsoft (20080469)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed and Parallel Computing Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed systems and fault tolerance
- Keywords
- parallel computing, scalability, multi-core processors, parallel programming, programming models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-11.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-11.
Cited sources are checked by gpt-6-sol.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
