Filters








880 Hits in 1.2 sec

SIMD defragmenter

Yongjun Park, Sangwon Seo, Hyunchul Park, Hyoun Kyu Cho, Scott Mahlke
2012 SIGARCH Computer Architecture News  
Single-instruction multiple-data (SIMD) accelerators provide an energy-efficient platform to scale the performance of mobile systems while still retaining post-programmability. The central challenge is translating the parallel resources of the SIMD hardware into real application performance. In scientific applications, automatic vectorization techniques have proven quite effective at extracting large levels of data-level parallelism (DLP). However, vectorization is often much less effective for
more » ... media applications due to low trip count loops, complex control flow, and non-uniform execution behavior. As a result, SIMD lanes remain idle due to insufficient DLP. To attack this problem, this paper proposes a new vectorization pass called SIMD Defragmenter to uncover hidden DLP that lurks below the surface in the form of instruction-level parallelism (ILP). The difficulty is managing the data packing/unpacking overhead that can easily exceed the benefits gained through SIMD execution. The SIMD degragmenter overcomes this problem by identifying groups of compatible instructions (subgraphs) that can be executed in parallel across the SIMD lanes. By SIMDizing in bulk at the subgraph level, packing/unpacking overhead is minimized. On a 16-lane SIMD processor, experimental results show that SIMD defragmentation achieves a mean 1.6x speedup over traditional loop vectorization and a 31% gain over prior research approaches for converting ILP to DLP.
doi:10.1145/2189750.2151014 fatcat:edmwzlcgqjf7lilha3sbusewv4

Quantum Photovoltaic Cells Driven by Photon Pulses [article]

Sangchul Oh, Jungjun Park, Hyunchul Nha
2020 arXiv   pre-print
We investigate the quantum thermodynamics of two quantum systems, a two-level system and a four-level quantum photocell, each driven by photon pulses as a quantum heat engine. We set these systems to be in thermal contact only with a cold reservoir while the heat (energy) source, conventionally given from a hot thermal reservoir, is supplied by a sequence of photon pulses. The dynamics of each system is governed by a coherent interaction due to photon pulses in terms of the Jaynes-Cummings
more » ... tonian together with the system-bath interaction described by the Lindblad master equation. We calculate the thermodynamic quantities for the two-level system and the quantum photocell including the change in system energy, power delivered by photon pulses, power output to an external load, heat dissipated to a cold bath, and entropy production. We thereby demonstrate how a quantum photocell in the cold bath can operate as a continuum quantum heat engine with the sequence of photon pulses continuously applied. We specifically introduce the power efficiency of the quantum photocell in terms of the ratio of output power delivered to an external load with current and voltage to the input power delivered by the photon pulse. Our study indicates a possibility that a quantum system driven by external fields can act as an efficient quantum heat engine under non-equilibrium thermodynamics.
arXiv:2005.13185v1 fatcat:j3r2ln4nufdq3g7buujive6i3y

Polymorphic pipeline array

Hyunchul Park, Yongjun Park, Scott Mahlke
2009 Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture - Micro-42  
Outline Polymorphic Pipeline Array 2  Motivation  Media applications in a mobile environment  Analysis of parallelism in media applications  Polymorphic Pipeline Array  Virtualized Modulo Scheduling  Experimental results  Conclusion Motivation Polymorphic Pipeline Array 3  Mobile computing is a very important topic in current research  Embedded systems used in mobile devices demand high performance and energy efficiency  Traditionally: hardwired accelerators were used to implement
more » ... ications that require high computation (ASICs)  Today: mobile platforms are designed as heterogeneous SoCs consisting of multiple processors and special purpose accelerators constructed for the most compute-intensive tasks  But: the requirements of mobile applications are constantly increasing  More programmable mobile computing platforms are required Media Applications in a Mobile Environment Polymorphic Pipeline Array 4  Applications like high-definition video, audio, 3D graphics and other forms of media processing are high value applications for mobile terminals  The complexity of media processing algorithms is typically high  Power consumption needs to be minimized as audio and video applications are getting more important for mobile devices  This paper focuses on the design of a flexible media accelerator for mobile computing called polymorphic pipeline array (PPA)
doi:10.1145/1669112.1669160 dblp:conf/micro/ParkPM09 fatcat:i2jazb5et5hyrjtcqnqiorrbou

Dial-Based Game Interface with Multi-modal Feedback [chapter]

Wanjoo Park, Laehyun Kim, Hyunchul Cho, Sehyung Park
2010 Lecture Notes in Computer Science  
Wanjoo Park et al. proposed a brickout game using a haptic dial interface and some haptic effects for the game [13] .  ... 
doi:10.1007/978-3-642-15399-0_42 fatcat:sefvhpryqbbx7pn5wxp4xrkkle

Trace estimates for relativistic stable processes [article]

Hyunchul Park, Renming Song
2012 arXiv   pre-print
In this paper, we study the asymptotic behavior, as the time t goes to zero, of the trace of the semigroup of a killed relativistic α-stable process in bounded C^1,1 open sets and bounded Lipschitz open sets. More precisely, we establish the asymptotic expansion in terms of t of the trace with an error bound of order t^2/αt^-d/α for C^1,1 open sets and of order t^1/αt^-d/α for Lipschitz open sets. Compared with the corresponding expansions for stable processes, there are more terms between the
more » ... rders t^-d/α and t^(2-d)/α for C^1,1 open sets, and, when α∈ (0, 1], between the orders t^-d/α and t^(1-d)/α for Lipschitz open sets.
arXiv:1212.2943v2 fatcat:v52mszg46nhz3btevhgxgbp5ye

Trace Estimates for Relativistic Stable Processes

Hyunchul Park, Renming Song
2014 Potential Analysis  
In this paper, we study the asymptotic behavior, as the time t goes to zero, of the trace of the semigroup of a killed relativistic α-stable process in bounded C 1,1 open sets and bounded Lipschitz open sets. More precisely, we establish the asymptotic expansion in terms of t of the trace with an error bound of order t 2/α t −d/α for C 1,1 open sets and of order t 1/α t −d/α for Lipschitz open sets. Compared with the corresponding expansions for stable processes, there are more terms between
more » ... orders t −d/α and t (2−d)/α for C 1,1 open sets, and, when α ∈ (0, 1], between the orders t −d/α and t (1−d)/α for Lipschitz open sets. Mathematics Subject Classification (2010) 60G51 · 60J35
doi:10.1007/s11118-014-9423-8 fatcat:mvnmrm4jobbs5dko66lzbsjzyq

Sodium intercalation chemistry in graphite

Haegyeom Kim, Jihyun Hong, Gabin Yoon, Hyunchul Kim, Kyu-Young Park, Min-Sik Park, Won-Sub Yoon, Kisuk Kang
2015 Energy & Environmental Science  
The solvated-Na-ion intercalation in graphite is investigated in terms of stoichiometry, staging structure, and solvated ion configuration using combined experimental and theoretical studies.
doi:10.1039/c5ee02051d fatcat:usyahwxgvjbynbq3jgwikgwnli

CGRA express

Yongjun Park, Hyunchul Park, Scott Mahlke
2009 Proceedings of the 2009 international conference on Compilers, architecture, and synthesis for embedded systems - CASES '09  
Park [17] also worked on innermost loop, but they focussed on loop level parallelism while Lee worked on instruction level parallelism.  ... 
doi:10.1145/1629395.1629433 dblp:conf/cases/ParkPM09 fatcat:p4durjuuc5b6hoiyq2hfaske6a

Quantum Photovoltaic Cells Driven by Photon Pulses

Sangchul Oh, Jung Jun Park, Hyunchul Nha
2020 Entropy  
We investigate the quantum thermodynamics of two quantum systems, a two-level system and a four-level quantum photocell, each driven by photon pulses as a quantum heat engine. We set these systems to be in thermal contact only with a cold reservoir while the heat (energy) source, conventionally given from a hot thermal reservoir, is supplied by a sequence of photon pulses. The dynamics of each system is governed by a coherent interaction due to photon pulses in terms of the Jaynes-Cummings
more » ... tonian together with the system-bath interaction described by the Lindblad master equation. We calculate the thermodynamic quantities for the two-level system and the quantum photocell including the change in system energy, the power delivered by photon pulses, the power output to an external load, the heat dissipated to a cold bath, and the entropy production. We thereby demonstrate how a quantum photocell in the cold bath can operate as a continuum quantum heat engine with a sequence of photon pulses continuously applied. We specifically introduce the power efficiency of the quantum photocell in terms of the ratio of output power delivered to an external load with current and voltage to the input power delivered by the photon pulse. Our study indicates a possibility that a quantum system driven by external fields can act as an efficient quantum heat engine under non-equilibrium thermodynamics.
doi:10.3390/e22060693 pmid:33286465 pmcid:PMC7517230 fatcat:loz74lpcjja75jn4nkovgvzawm

Libra: Tailoring SIMD Execution Using Heterogeneous Hardware and Dynamic Configurability

Yongjun Park, Jason Jong Kyu Park, Hyunchul Park, Scott Mahlke
2012 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture  
Mobile computing as exemplified by the smart phone has become an integral part of our daily lives. The next generation of these devices will be driven by providing an even richer user experience and compelling capabilities: higher definition multimedia, 3D graphics, augmented reality, games, and voice interfaces. To address these goals, the core computing capabilities of the smart phone must be scaled. However, the energy budgets are increasing at a much lower rate, requiring fundamental
more » ... ments in computing efficiency. SIMD accelerators offer the combination of high performance and low energy consumption through low control and interconnect overhead. However, SIMD accelerators are not a panacea. Many applications lack sufficient vector parallelism to effectively utilize a large number of SIMD lanes. Further, the use of symmetric hardware lanes leads to low utilization and high static power dissipation as SIMD width is scaled. To address these inefficiencies, this paper focuses on breaking two traditional rules of SIMD processing: homogeneity and static configuration. The Libra accelerator increases SIMD utility by blurring the divide between vector and instruction parallelism to support efficient execution of a wider range of loops, and it increases hardware utilization through the use of heterogeneous hardware across the SIMD lanes. Experimental results show that the 32-lane Libra outperforms traditional SIMD accelerators by an average of 1.58x performance improvement due to higher loop coverage with 29% less energy consumption through heterogeneous hardware. *
doi:10.1109/micro.2012.17 dblp:conf/micro/ParkPPM12 fatcat:3skvsbe2vbeujmh2ctwoqwmthe

Resource recycling

Yongjun Park, Hyunchul Park, Scott Mahlke, Sukjin Kim
2010 Proceedings of the 2010 international conference on Compilers, architectures and synthesis for embedded systems - CASES '10  
Mobile computing platforms in the form of smart phones, netbooks, and personal digital assistants have become an integral part of our everyday lives. Moving ahead to the future, mobile multimedia support will become a key differentiating factor for customers. Features such as high-definition audio and video, video conferencing, 3D graphics, and image projection will lead to the adoption of one phone over another. However, in contrast to wireless signal processing which is dominated by
more » ... le computation, mobile multimedia applications often contain complex control flow and variable computational requirements. Moreover, data access is more complex where media applications typically operate on multi-dimensional vectors of data rather than single-dimensional vectors with simple strides. To handle these complexities, composable accelerators such as the Polymorphic Pipeline Array, or PPA, present an appealing hardware platform by adding a degree of hardware configurability over existing accelerators. Hardware resources can be both statically as well as dynamically partitioned among executing tasks to maximize execution efficiency. However, an effective compilation framework is essential to partition and assign resources to make intelligent use of the available hardware. In this paper, a compilation framework is introduced that maximizes application throughput with hybrid resource partitioning of a PPA system. Static partitioning handles part of the resource assignment, but this is followed up by dynamic partitioning to identify idle resources and put them to use -resource recycling. Experimental results show that real-time media applications can take advantage of the static and dynamic configurability of the PPA for increased throughput.
doi:10.1145/1878921.1878925 dblp:conf/cases/ParkPMK10 fatcat:5stvi4c3sbbsxmwlz25tio7feu

Development of Construction and Management Tools for Biological Named Entity Dictionary

Hyunchul Jang, Taehyun Kim, Hyunsook Lee, Soojun Park, Seonhee Park
2003 Genome Informatics Series  
doi:10.11234/gi1990.14.689 fatcat:zgf3dhhhnbb7vdqpodbfks4eue

Quantification of coil slippage during initial coiling with belt wrapper

Yonghui Park, Hyunchul Park
2017 International Journal of Automotive and Mechanical Engineering  
The finite element model and mathematical model for the coiling process with the belt wrapper have been developed by simplifying the belt wrapper to copy the strip head end positioning on free tension reel shortly, known as the initial coiling. The models have tried to quantify the coil slippage that makes a scratch on the coil. However, it is hard to compare the models to the real operation due to some assumptions. Moreover, computations is increased dramatically if the model includes the real
more » ... operation such as non-linear property of the belt wrapper. This study suggests new modelling approach without the belt wrapper to quantify the coil slippage according the compression on the coil. Instead of the belt wrapper, all nodes of the strip are controlled by specific x-y displacements as the belt wrapper compresses the strip coil. Different x-y displacements of each node can change the magnitude of the compression by the belt wrapper. A finite element model of the initial coiling was simulated by the modelling approach and Model Change technique in ABAQUS, and discontinuous processes including removal of the belt wrapper and the application of coiling tension, σ are proceeded in consecutive order. By doing parametric analysis regarding the radial deformation of the coil by the belt wrapper, rd and σ, the coil slippage happens frequently when σ is below critical value or when rd is large. This phenomenon is similar to the spring back, so σ should be high or should be applied before the belt wrapper is removed. This indicates that, rd should be manipulated carefully because the coil slippage happens as rd increases. Besides the initial coiling, the modelling approach can be applied to other problems that need many computations such as the 300 layers of strip lamination.
doi:10.15282/ijame.14.2.2017.11.0340 fatcat:2p7wiu3ee5b5babker44pj543q

Decreased Maximal Tongue Protrusion Length May Predict the Presence of Dysphagia in Stroke Patients

Hyunchul Cho, Jeong Se Noh, Junwon Park, Changwook Park, No Dam Park, Jun Young Ahn, Ji Woong Park, Yoon-Hee Choi, Seong-Min Chun
2021 Annals of Rehabilitation Medicine  
Objective To investigate the relationship between maximal tongue protrusion length (MTPL) and dysphagia in post-stroke patients.Methods Free tongue length (FTL) was measured using the quick tongue-tie assessment tool and MTPL was measured using a transparent plastic ruler in 47 post-stroke patients. The MTPL-to-FTL (RMF) ratio was calculated. Swallowing function in all patients was evaluated via videofluoroscopic swallowing study (VFSS), PenetrationAspiration Scale (PAS), Functional Oral Intake
more » ... Scale (FOIS), and Videofluoroscopic Dysphagia Scale (VDS).Results The MTPL and RMF values were significantly higher in the non-aspirator group than in the aspirator group (MTPL, p=0.0049; RMF, p<0.001). MTPL and RMF showed significant correlations with PAS, FOIS and VDS scores. The cut-off value in RMF for the prediction of aspiration was 1.56, with a sensitivity of 84% and a specificity of 86%.Conclusion There is a relationship between MTPL and dysphagia in post-stroke patients. MTPL and RMF can be useful for detecting aspiration in post-stroke patients.
doi:10.5535/arm.21126 pmid:35000369 pmcid:PMC8743842 fatcat:sntc73l2hvhoviwxg35hymzhum

Verifying nonclassicality beyond negativity in phase space [article]

Jiyong Park, Jaehak Lee, Hyunchul Nha
2020 arXiv   pre-print
We propose a hierachy of nonclassicality criteria in phase space. Our formalism covers the negativity in phase space as a special case and further adresses nonclassicality for quantum states with positive phase-space distributions. Remarkably, it enables us to detect every nonclassical Gaussian state and every finite dimensional state in Fock basis by looking into only three phase-space points. Furthermore, our approach provides an experimentally accessible lower bound for the nonclassicality
more » ... asure based on trace distance. We also extend our method to detecting genuine quantum non-Gaussianity of a state with a non-negative Wigner function. We finally establish our formalism by employing generalized quasiprobability distributions to demonstrate its power for a practical test using an on-off detector array.
arXiv:2005.05739v1 fatcat:tewjbrvxmzg77llvl6mtr3owvi
« Previous Showing results 1 — 15 out of 880 results