arXiv subjects

Kwangmin Yu

Publications and source records attributed to Kwangmin Yu.

31 records · Page 2Linked to original sources

arXiv2021

SPACE: 3D Parallel Solvers for Vlasov-Maxwell and Vlasov-Poisson Equations for Relativistic Plasmas with Atomic Transformations

A parallel, relativistic, three-dimensional particle-in-cell code SPACE has been developed for the simulation of electromagnetic fields, relativistic particle beams, and plasmas. In addition to the standard second-order Particle-in-Cell (PIC) algorithm, SPACE includes efficient novel algorithms to resolve atomic physics processes such as multi-level ionization of plasma atoms, recombination, and electron attachment to dopants in dense neutral gases. SPACE also contains a highly adaptive particle-based method, called Adaptive Particle-in-Cloud (AP-Cloud), for solving the Vlasov-Poisson problems. It eliminates the traditional Cartesian mesh of PIC and replaces it with an adaptive octree data structure. The code's algorithms, structure, capabilities, parallelization strategy and performances have been discussed. Typical examples of SPACE applications to accelerator science and engineering problems are also presented.

physics.comp-ph↗

arXiv2021

Implementation of efficient quantum search algorithms on NISQ computers

Despite the advent of Grover's algorithm for the unstructured search, its successful implementation on near-term quantum devices is still limited. We apply three strategies to reduce the errors associated with implementing quantum search algorithms. Our improved search algorithms have been implemented on the IBM quantum processors. Using them, we demonstrate three- and four-qubit search algorithm with higher average success probabilities compared to previous works. We present the successful execution of the five-qubit search on the IBM quantum processor for the first time. The results have been benchmarked using degraded ratio, which is the ratio between the experimental and the theoretical success probabilities. The fast decay of the degraded ratio supports our divide-and-conquer strategy. Our proposed strategies are also useful for implementation of quantum search algorithms in the post-NISQ era.

quant-ph↗

arXiv2021

Porting HEP Parameterized Calorimeter Simulation Code to GPUs

The High Energy Physics (HEP) experiments, such as those at the Large Hadron Collider (LHC), traditionally consume large amounts of CPU cycles for detector simulations and data analysis, but rarely use compute accelerators such as GPUs. As the LHC is upgraded to allow for higher luminosity, resulting in much higher data rates, purely relying on CPUs may not provide enough computing power to support the simulation and data analysis needs. As a proof of concept, we investigate the feasibility of porting a HEP parameterized calorimeter simulation code to GPUs. We have chosen to use FastCaloSim, the ATLAS fast parametrized calorimeter simulation. While FastCaloSim is sufficiently fast such that it does not impose a bottleneck in detector simulations overall, significant speed-ups in the processing of large samples can be achieved from GPU parallelization at both the particle (intra-event) and event levels; this is especially beneficial in conditions expected at the high-luminosity LHC, where extremely high per-event particle multiplicities will result from the many simultaneous proton-proton collisions. We report our experience with porting FastCaloSim to NVIDIA GPUs using CUDA. A preliminary Kokkos implementation of FastCaloSim for portability to other parallel architectures is also described.

hep-ex↗

arXiv2021

Evaluation of Portable Acceleration Solutions for LArTPC Simulation Using Wire-Cell Toolkit

The Liquid Argon Time Projection Chamber (LArTPC) technology plays an essential role in many current and future neutrino experiments. Accurate and fast simulation is critical to developing efficient analysis algorithms and precise physics model projections. The speed of simulation becomes more important as Deep Learning algorithms are getting more widely used in LArTPC analysis and their training requires a large simulated dataset. Heterogeneous computing is an efficient way to delegate computing-heavy tasks to specialized hardware. However, as the landscape of the compute accelerators is evolving fast, it becomes more and more difficult to manually adapt the code constantly to the latest hardware or software environments. A solution which is portable to multiple hardware architectures while not substantially compromising performance would be very beneficial, especially for long-term projects such as the LArTPC simulations. In search of a portable, scalable and maintainable software solution for LArTPC simulations, we have started to explore high-level portable programming frameworks that support several hardware backends. In this paper, we will present our experience porting the LArTPC simulation code in the Wire-Cell toolkit to NVIDIA GPUs, first with the CUDA programming model and then with a portable library called Kokkos. Preliminary performance results on NVIDIA V100 GPUs and multi-core CPUs will be presented, followed by a discussion of the factors affecting the performance and plans for future improvements.

cs.DC↗

arXiv2020

Accelerated impurity solver for DMFT and its diagrammatic extensions

We present ComCTQMC, a GPU accelerated quantum impurity solver. It uses the continuous-time quantum Monte Carlo (CTQMC) algorithm wherein the partition function is expanded in terms of the hybridisation function (CT-HYB). ComCTQMC supports both partition and worm-space measurements, and it uses improved estimators and the reduced density matrix to improve observable measurements whenever possible. ComCTQMC efficiently measures all one and two-particle Green's functions, all static observables which commute with the local Hamiltonian, and the occupation of each impurity orbital. ComCTQMC can solve complex-valued impurities with crystal fields that are hybridized to both fermionic and bosonic baths. Most importantly, ComCTQMC utilizes graphical processing units (GPUs), if available, to dramatically accelerate the CTQMC algorithm when the Hilbert space is sufficiently large. We demonstrate acceleration by a factor of over 600 (100) in a simulation of $δ$-Pu at 600 K with (without) crystal fields. In easier problems, the GPU offers less impressive acceleration or even decelerates the CTQMC. Here we describe the theory, algorithms, and structure used by ComCTQMC in order to achieve this set of features and level of acceleration.

cond-mat.str-el↗

arXiv2020

Evolution of the self-injection process in the transition of an LWFA from self-modulation to blowout regime

Long wavelength infrared (LWIR) laser driven plasma wakefield accelerators are investigated here in the self-modulated laser wakefield acceleration (SM-LWFA) and blowout regimes using 3D Particle-in-Cell simulations. The simulation results show that in SM-LWFA regime, self-injection arises with wave breaking, whereas in the blowout regime, self-injection is not observed under the simulation conditions. The wave breaking process in SM-LWFA regime occurs at a field strength that is significantly below the 1D wave-breaking threshold. This process intensifies at higher laser power and plasma density and is suppressed at low plasma densities ($\leq 1\times10^{17}$ $cm^{-3}$ here). The produced electrons show spatial modulations with a period matching that of the laser wavelength, which is a clear signature of direct laser acceleration (DLA).

physics.plasm-ph↗

arXiv2020

Quantum amplitude estimation algorithms on IBM quantum devices

Since the publication of the Quantum Amplitude Estimation (QAE) algorithm by Brassard et al., 2002, several variations have been proposed, such as Aaronson et al., 2019, Grinko et al., 2019, and Suzuki et al., 2020. The main difference between the original and the variants is the exclusion of Quantum Phase Estimation (QPE) by the latter. This difference is notable given that QPE is the key component of original QAE, but is composed of many operations considered expensive for the current NISQ era devices. We compare two recently proposed variants (Grinko et al., 2019 and Suzuki et al., 2020) by implementing them on the IBM Quantum device using Qiskit, an open source framework for quantum computing. We analyze and discuss advantages of each algorithm from the point of view of their implementation and performance on a quantum computer.

quant-ph↗

arXiv2020

Comparison of Amplitude Estimation Algorithms by Implementation

Since the quantum amplitude estimation (QAE) was invented by Brassard et al., 2002, several advanced algorithms have recently been published (Grinko et al., 2019, Aaronson et al, and Suzuki et al., 2020). The main difference between the variants and the original algorithm is that the variants do not need quantum phase estimation (QPE), a key component of the canonical QAE (Brassard et al., 2002), that is composed of many expensive operations on NISQ devices. In this paper, we compare and analyze two of these new QAE approaches (Grinko et al., 2019, and Suzuki et al., 2020) by implementation using the Qiskit package. The comparisons are drawn based on number of oracle queries, quantum circuit depth, and other complexities of implementation for a fixed accuracy. We discuss the strengths and limitations of each algorithm from a computational perspective.

quant-ph↗

arXiv2020

Practical numerical integration on NISQ devices

This paper addresses the practical aspects of quantum algorithms used in numerical integration, specifically their implementation on Noisy Intermediate-Scale Quantum (NISQ) devices. Quantum algorithms for numerical integration utilize Quantum Amplitude Estimation (QAE) (Brassard et al., 2002) in conjunction with Grovers algorithm. However, QAE is daunting to implement on NISQ devices since it typically relies on Quantum Phase Estimation (QPE), which requires many ancilla qubits and controlled operations. To mitigate these challenges, a recently published QAE algorithm (Suzuki et al., 2020), which does not rely on QPE, requires a much smaller number of controlled operations and does not require ancilla qubits. We implement this new algorithm for numerical integration on IBM quantum devices using Qiskit and optimize the circuit on each target device. We discuss the application of this algorithm on two qubits and its scalability to more than two qubits on NISQ devices.

quant-ph↗

arXiv2019

Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training

Stochastic Gradient Descent (SGD) is the most popular algorithm for training deep neural networks (DNNs). As larger networks and datasets cause longer training times, training on distributed systems is common and distributed SGD variants, mainly asynchronous and synchronous SGD, are widely used. Asynchronous SGD is communication efficient but suffers from accuracy degradation due to delayed parameter updating. Synchronous SGD becomes communication intensive when the number of nodes increases regardless of its advantage. To address these issues, we introduce Layered SGD (LSGD), a new decentralized synchronous SGD algorithm. LSGD partitions computing resources into subgroups that each contain a communication layer (communicator) and a computation layer (worker). Each subgroup has centralized communication for parameter updates while communication between subgroups is handled by communicators. As a result, communication time is overlapped with I/O latency of workers. The efficiency of the algorithm is tested by training a deep network on the ImageNet classification task.

cs.LG↗

arXiv2018

Simulation of beam-induced plasma in gas-filled rf cavities

Processes occurring in a radio-frequency (rf) cavity, filled with high pressure gas and interacting with proton beams, have been studied via advanced numerical simulations. Simulations support the experimental program on the hydrogen gas-filled rf cavity in the Mucool Test Area (MTA) at Fermilab, and broader research on the design of muon cooling devices. SPACE, a 3D electromagnetic particle-in-cell (EM-PIC) code with atomic physics support, was used in simulation studies. Plasma dynamics in the rf cavity, including the process of neutral gas ionization by proton beams, plasma loading of the rf cavity, and atomic processes in plasma such as electron-ion and ion-ion recombination and electron attachment to dopant molecules, have been studied. Through comparison with experiments in the MTA, simulations quantified several uncertain values of plasma properties such as effective recombination rates and the attachment time of electrons to dopant molecules. Simulations have achieved very good agreement with experiments on plasma loading and related processes. The experimentally validated code SPACE is capable of predictive simulations of muon cooling devices.

physics.acc-ph↗

arXiv2017

Simulation of plasma loading of high-pressure RF cavities

Muon beam-induced plasma loading of radio-frequency (RF) cavities filled with high pressure hydrogen gas with 1% dry air dopant has been studied via numerical simulations. The electromagnetic code SPACE, that resolves relevant atomic physics processes, including ionization by the muon beam, electron attachment to dopant molecules, and electron-ion and ion-ion recombination, has been used. Simulations studies have been performed in the range of parameters typical for practical muon cooling channels.

physics.acc-ph↗

arXiv2016

AP-Cloud: Adaptive Particle-in-Cloud Method for Optimal Solutions to Vlasov-Poisson Equation

We propose a new adaptive Particle-in-Cloud (AP-Cloud) method for obtaining optimal numerical solutions to the Vlasov-Poisson equation. Unlike the traditional particle-in-cell (PIC) method, which is commonly used for solving this problem, the AP-Cloud adaptively selects computational nodes or particles to deliver higher accuracy and efficiency when the particle distribution is highly non-uniform. Unlike other adaptive techniques for PIC, our method balances the errors in PDE discretization and Monte Carlo integration, and discretizes the differential operators using a generalized finite difference (GFD) method based on a weighted least square formulation. As a result, AP-Cloud is independent of the geometric shapes of computational domains and is free of artificial parameters. Efficient and robust implementation is achieved through an octree data structure with 2:1 balance. We analyze the accuracy and convergence order of AP-Cloud theoretically, and verify the method using an electrostatic problem of a particle beam with halo. Simulation results show that the AP-Cloud method is substantially more accurate and faster than the traditional PIC, and it is free of artificial forces that are typical for some adaptive PIC techniques.

math.NA↗