#asplos21 search results

Join us tomorrow @ASPLOSConf for our talk! SIMDRAM: An End-to-End Framework for Bit-Serial SIMD Computing in DRAM April 20, 4 PM Pacific Time @NHajinazar & @geraldofojunior (co-first authors), @_onurmutlu_ Talk: youtube.com/watch?v=g0fE1c… Paper: people.inf.ethz.ch/omutlu/pub/SIM… #ASPLOS21

We will be at @ASPLOSConf next week! Jisung Park @jspark_phd will present "Reducing Solid-State Drive Read Latency by Optimizing Read-Retry". Join us for his talk: Thursday, April 22, 7 AM pacific time. Paper: people.inf.ethz.ch/omutlu/pub/Red… #ASPLOS21 @_onurmutlu_ @loisorosa

WORDS'21 will bring together people from different domains to engage in a lively discussion on resource disaggregation and serverless computing. WORDS 2021: The Second Workshop On Resource Disaggregation and Serverless wuklab.github.io/words/ #ASPLOS21

Learn why kernel objects, such as page cache pages, journals, metadata radix trees, block driver buffers, and socket buffers need tiering. KLOCs: Kernel-Level Object Contexts for Heterogeneous Memory System asplos-conference.org/abstracts/aspl… @SudarsunKannan #ASPLOS21 #KernelObjects

NOPE is a venue that encourages publishing negative results in all their "badness"! Workshop on Negative results, Opportunities, Perspectives, and Experiences nope.pub #ASPLOS21 #NegativeResults

Robomorphic computing is a new methodology for designing accelerators based on the high-level physical topology of a robot. Robomorphic Computing: A Design Methodology for Domain-Specific Accelerators Parameterized by Robot Morphology asplos-conference.org/abstracts/aspl… #ASPLOS21 #Robots

LATTE focuses on new languages and tools that aim to let domain specialists produce efficient accelerators: ASICs, FPGAs, CGRAs, or future reconfigurable hardware. Workshop: LATTE: Languages, Tools, and Techniques for Accelerator Design capra.cs.cornell.edu/latte21/ #ASPLOS21

How does an approximate multiplier design act as a defense against adversarial attacks? Defensive Approximation: Securing CNNs using Approximate Computing asplos-conference.org/abstracts/aspl… @AmiraGuesmi4 @ihstein @nael_ag #ASPLOS21 #AdversarialML #Approximation

Learn about MLPerf, the ongoing industry-wide effort, involving over 30+ companies, to standardize “training” and “inference” performance. Tutorial: ML Performance: Benchmarking Deep Learning Systems sites.google.com/g.harvard.edu/… #ASPLOS21 #Benchmarking #DNN

How to optimize the barriers in synchronization primitives on weak memory models? VSync: Push-Button Verification and Optimization for Synchronization Primitives on Weak Memory Models asplos-conference.org/abstracts/aspl… @mingffu #ASPLOS21 #MemoryModel #Verification

How to support complex operations in DRAM? SIMDRAM: A Framework for Bit-Serial SIMD Processing using DRAM asplos-conference.org/abstracts/aspl… @NHajinazar @geraldofojunior @amazong @nika_mgh @mealser @SaugataGhose @el1goluj @_onurmutlu_ @SAFARI_ETH_CMU #ASPLOS21 #Processing-in-Memory

Here is a quantum circuit simulation toolchain for variational algorithms! Noisy Variational Quantum Algorithm Simulation via Knowledge Compilation for Repeated Inference Abstract: asplos-conference.org/abstracts/aspl… @yipenghuang0302 @zengola @guyvdb @margmartonosi #ASPLOS21 #Quantum

Tutorial: BenchCouncil AIBench Attend the AIBench tutorial to learn about a comprehensive AI benchmark suite for Datacenter, HPC, IoT and Edge. benchcouncil.org/aibench-tutori… #ASPLOS21 #Benchmarking

How to guarantee correctness of real-world optimizing compilers? Title: Language-Parametric Compiler Validation with Application to LLVM Abstract: asplos-conference.org/abstracts/aspl… @vadve @zhengyaoo @daejunpark @RosuGrigore #ASPLOS21 #Compilation #Verification

Have you ever wondered what are the challenges and opportunities of using neural networks for data prefetching? Title: A Hierarchical Neural Model of Data Prefetching Abstract: asplos-conference.org/abstracts/aspl… @ZhanShi44105240 @akankshajain @miladhash @kswersk #ASPLOS21 #NeuralNetwork

Read about the benefit of reformulating neural architecture search techniques as program transformations. Title: Neural Architecture Search as Program Transformation Exploration Abstract: asplos-conference.org/abstracts/aspl… @jack_willturner #ASPLOS21 #DNN #ProgramTransformation

How do you think SherLock solves Locking issues, such as synchronization-operation inference problem? Title: SherLock: Unsupervised Synchronization-Operation Inference Abstract: asplos-conference.org/abstracts/aspl… #ASPLOS21 #Synchronization #DynamicMonitoring

Do you want to know how keeping functions alive in FaaS platforms can be mapped to a caching problem? Title: FaasCache: Keeping Serverless Computing Alive With Greedy-Dual Caching Abstract: asplos-conference.org/abstracts/aspl… @fuh #FaaS #KeepFunctionsAlive #ASPLOS21

How to partition general quantum circuits and distribute the workload? Title: CutQC: Using Small Quantum Computers for Large Quantum Circuit Evaluations Abstract: asplos-conference.org/abstracts/aspl… @T1993Wei, @TeaTom19, @martinsuchara, @margmartonosi #QuantumComputing #ASPLOS21

How should resource management happen for in-network computation? Title: Switches for HIRE: Resource Scheduling for Data Center In-Network Computing Abstract: asplos-conference.org/abstracts/aspl… @marcelbloecher @EugsterPatrick @imlinwang #ASPLOS21 #InNetworkComputation #DataCenter

NOPE is a venue that encourages publishing negative results in all their "badness"! Workshop on Negative results, Opportunities, Perspectives, and Experiences nope.pub #ASPLOS21 #NegativeResults

How to support complex operations in DRAM? SIMDRAM: A Framework for Bit-Serial SIMD Processing using DRAM asplos-conference.org/abstracts/aspl… @NHajinazar @geraldofojunior @amazong @nika_mgh @mealser @SaugataGhose @el1goluj @_onurmutlu_ @SAFARI_ETH_CMU #ASPLOS21 #Processing-in-Memory

How to partition general quantum circuits and distribute the workload? Title: CutQC: Using Small Quantum Computers for Large Quantum Circuit Evaluations Abstract: asplos-conference.org/abstracts/aspl… @T1993Wei, @TeaTom19, @martinsuchara, @margmartonosi #QuantumComputing #ASPLOS21

LATTE focuses on new languages and tools that aim to let domain specialists produce efficient accelerators: ASICs, FPGAs, CGRAs, or future reconfigurable hardware. Workshop: LATTE: Languages, Tools, and Techniques for Accelerator Design capra.cs.cornell.edu/latte21/ #ASPLOS21

We will be at @ASPLOSConf next week! Jisung Park @jspark_phd will present "Reducing Solid-State Drive Read Latency by Optimizing Read-Retry". Join us for his talk: Thursday, April 22, 7 AM pacific time. Paper: people.inf.ethz.ch/omutlu/pub/Red… #ASPLOS21 @_onurmutlu_ @loisorosa

Here is a quantum circuit simulation toolchain for variational algorithms! Noisy Variational Quantum Algorithm Simulation via Knowledge Compilation for Repeated Inference Abstract: asplos-conference.org/abstracts/aspl… @yipenghuang0302 @zengola @guyvdb @margmartonosi #ASPLOS21 #Quantum

Read about the benefit of reformulating neural architecture search techniques as program transformations. Title: Neural Architecture Search as Program Transformation Exploration Abstract: asplos-conference.org/abstracts/aspl… @jack_willturner #ASPLOS21 #DNN #ProgramTransformation

Have you ever wondered what are the challenges and opportunities of using neural networks for data prefetching? Title: A Hierarchical Neural Model of Data Prefetching Abstract: asplos-conference.org/abstracts/aspl… @ZhanShi44105240 @akankshajain @miladhash @kswersk #ASPLOS21 #NeuralNetwork

How does an approximate multiplier design act as a defense against adversarial attacks? Defensive Approximation: Securing CNNs using Approximate Computing asplos-conference.org/abstracts/aspl… @AmiraGuesmi4 @ihstein @nael_ag #ASPLOS21 #AdversarialML #Approximation

How should resource management happen for in-network computation? Title: Switches for HIRE: Resource Scheduling for Data Center In-Network Computing Abstract: asplos-conference.org/abstracts/aspl… @marcelbloecher @EugsterPatrick @imlinwang #ASPLOS21 #InNetworkComputation #DataCenter

How do you think SherLock solves Locking issues, such as synchronization-operation inference problem? Title: SherLock: Unsupervised Synchronization-Operation Inference Abstract: asplos-conference.org/abstracts/aspl… #ASPLOS21 #Synchronization #DynamicMonitoring

How to optimize the barriers in synchronization primitives on weak memory models? VSync: Push-Button Verification and Optimization for Synchronization Primitives on Weak Memory Models asplos-conference.org/abstracts/aspl… @mingffu #ASPLOS21 #MemoryModel #Verification

How to guarantee correctness of real-world optimizing compilers? Title: Language-Parametric Compiler Validation with Application to LLVM Abstract: asplos-conference.org/abstracts/aspl… @vadve @zhengyaoo @daejunpark @RosuGrigore #ASPLOS21 #Compilation #Verification

Do you want to know how keeping functions alive in FaaS platforms can be mapped to a caching problem? Title: FaasCache: Keeping Serverless Computing Alive With Greedy-Dual Caching Abstract: asplos-conference.org/abstracts/aspl… @fuh #FaaS #KeepFunctionsAlive #ASPLOS21

Learn why kernel objects, such as page cache pages, journals, metadata radix trees, block driver buffers, and socket buffers need tiering. KLOCs: Kernel-Level Object Contexts for Heterogeneous Memory System asplos-conference.org/abstracts/aspl… @SudarsunKannan #ASPLOS21 #KernelObjects

How do you tile your 7-dimensional nested loop CNN in a multi-level memory hierarchy? Title: Analytical characterization and design space exploration for optimization of CNNs Abstract: asplos-conference.org/abstracts/aspl… #CNN #DesignSpaceExploration #ASPLOS21

Robomorphic computing is a new methodology for designing accelerators based on the high-level physical topology of a robot. Robomorphic Computing: A Design Methodology for Domain-Specific Accelerators Parameterized by Robot Morphology asplos-conference.org/abstracts/aspl… #ASPLOS21 #Robots

Tutorial: BenchCouncil AIBench Attend the AIBench tutorial to learn about a comprehensive AI benchmark suite for Datacenter, HPC, IoT and Edge. benchcouncil.org/aibench-tutori… #ASPLOS21 #Benchmarking

WORDS'21 will bring together people from different domains to engage in a lively discussion on resource disaggregation and serverless computing. WORDS 2021: The Second Workshop On Resource Disaggregation and Serverless wuklab.github.io/words/ #ASPLOS21

Learn about MLPerf, the ongoing industry-wide effort, involving over 30+ companies, to standardize “training” and “inference” performance. Tutorial: ML Performance: Benchmarking Deep Learning Systems sites.google.com/g.harvard.edu/… #ASPLOS21 #Benchmarking #DNN