Search

Persistent key-value (KV) stores mostly build on the Log-Structured Merge (LSM) tree for high write performance, yet the LSM-tree suffers from the inherently high I/O amplification. KV separation mitigates I/O amplification by storing only keys in the LSM-tree and values in separate storage. However, the current KV separation design remains inefficient under update-intensive workloads due to its high garbage collection (GC) overhead in value storage. We propose HashKV, which aims for high update performance atop KV separation under update-intensive workloads. HashKV uses hash-based data grouping, which deterministically maps values to storage space so as to make both updates and GC efficient. We further relax the restriction of such deterministic mappings via simple but useful design extensions. We extensively evaluate various design aspects of HashKV. We show that HashKV achieves 4.6x update throughput and 53.4% less write traffic compared to the current KV separation design. In addition, we demonstrate that we can integrate the design of HashKV with state-of-the-art KV stores and improve their respective performance., Comment: 28 pages. Accepted by ACM Transactions on Storage

I propose a method to directly measure the space and time dependence of the pair field correlator of a pair density wave. The method is based on two separate ideas. First, we adopt the solenoid insertion method of Kapon et al (2017) to provide the momentum in a tunnel junction. Second, we suggest the use of optimal or over-doped Bi-2201 films as a tunneling electrode with a known charge ordering wave-vector which can match the expected pair density wave wave-vectors we wish to study. The method is applicable to both fluctuating and ordered states. Potential applications are to the proposed stripe pair density wave order in LBCO and the possible pair density wave fluctuations at finite temperature or in high magnetic field in underdoped YBCO as well as other members of the Cuprate family.

In our previous work [arXiv:1803.00999, Phys. Rev. Lett. 121, 046401 (2018)], we found a quantum spin liquid phase with a spinon Fermi surface in the two dimensional spin-1/2 Heisenberg model with four-spin ring exchange on a triangular lattice. In this work we dope the spinon Fermi surface phase by studying the $t$-$J$ model with four-spin ring exchange. We perform density matrix renormalization group calculations on four-leg cylinders of a triangular lattice and find that the dominant pair correlation function is that of a pair density wave; i.e., it is oscillatory while decaying with distance with a power law. The doping dependence of the period is studied. This is the first example where pair density wave is the dominant pairing in a generic strongly interacting system where the pair density wave cannot be explained as a composite order and no special symmetry is required., Comment: 4+2 pages, 4+4 figures

Fault tolerance is critical for distributed stream processing systems, yet achieving error-free fault tolerance often incurs substantial performance overhead. We present AF-Stream, a distributed stream processing system that addresses the trade-off between performance and accuracy in fault tolerance. AF-Stream builds on a notion called approximate fault tolerance, whose idea is to mitigate backup overhead by adaptively issuing backups, while ensuring that the errors upon failures are bounded with theoretical guarantees. Specifically, AF-Stream allows users to specify bounds on both the state divergence and the loss of non-backup streaming items. It issues state and item backups only when the bounds are reached. Our AF-Stream design provides an extensible programming model for incorporating general streaming algorithms as well as exports only few threshold parameters for configuring approximation fault tolerance. Furthermore, we formally prove that AF-Stream preserves high algorithm-specific accuracy of streaming algorithms, and in particular the convergence guarantees of online learning. Experiments show that AF-Stream maintains high performance (compared to no fault tolerance) and high accuracy after multiple failures (compared to no failures) under various streaming algorithms., Comment: 25 pages. Accepted by The VLDB Journal

Consider a binary maximum distance separable (MDS) array code composed of an $m\times (k+r)$ array of bits with $k$ information columns and $r$ parity columns, such that any $k$ out of $k+r$ columns suffice to reconstruct the $k$ information columns. Our goal is to provide {\em optimal repair access} for binary MDS array codes, meaning that the bandwidth triggered to repair any single failed information or parity column is minimized. In this paper, we propose a generic transformation framework for binary MDS array codes, using EVENODD codes as a motivating example, to support optimal repair access for $k+1\le d \le k+r-1$, where $d$ denotes the number of non-failed columns that are connected for repair; note that when $d

Symmetry, dimensionality, and interaction are crucial ingredients for phase transitions and quantum states of matter. As a prominent example, the integer quantum Hall effect (QHE) represents a topological phase generally regarded as characteristic for two-dimensional (2D) electronic systems, and its many aspects can be understood without invoking electron-electron interaction. The intriguing possibility of generalizing QHE to three-dimensional (3D) systems was proposed decades ago, yet it remains elusive experimentally. Here, we report clear experimental evidence for the 3D QHE observed in bulk ZrTe5 crystals. Owing to the extremely high sample quality, the extreme quantum limit with only the lowest Landau level occupied can be achieved by an applied magnetic field as low as 1.5 T. Remarkably, in this regime, we observe a dissipationless longitudinal resistivity rho_xx=0 accompanied with a well-developed Hall resistivity plateau rho_xy=(1\pm0.1) h/e^2 (\lambda_(F,z)/2), where \lambda_(F,z) is the Fermi wavelength along the field direction (z axis). This striking result strongly suggests a Fermi surface instability driven by the enhanced interaction effects in the extreme quantum limit. In addition, with further increasing magnetic field, both rho_xx and rho_xy increase dramatically and display an interesting metal-insulator transition, representing another magnetic field driven quantum phase transition. Our findings not only unambiguously reveal a novel quantum state of matter resulting from an intricate interplay among dimensionality, interaction, and symmetry breaking, but also provide a promising platform for further exploration of more exotic quantum phases and transitions in 3D systems.

Using large-scale quantum Monte Carlo simulations, we exactly solve a model of Fermions hopping on the honeycomb lattice with cluster charge interactions, which has been proposed as an effective model with possible application to twisted bilayer graphene near half-filling. We find an interaction driven semimetal to insulator transition to an insulating phase consisting of a valence bond solid with Kekul\'e pattern. Finite size scaling reveals that the phase transition of the semimetal to Kekul\'e valence bond solid phase is continuous and belongs to chiral XY universality class., Comment: 4+1 pages, 4 figures

Laser wakefield acceleration modeling using the Lorentz-boosted frame technique in the particle-in-cell code has demonstrated orders of magnitude speedups. A convergence study was previously conducted in cases with external injection in the linear regime and without injection in the nonlinear regime, and the obtained results have shown a convergence within the percentage level. In this article, a convergence study is carried out to model electron self-injection in the 2-1/2D configuration. It is observed that the Lorentz-boosted frame technique is capable of modeling complex particle dynamics with a significant speedup. This result is crucial to curtail the computational time of the modeling of future chains of $10\,\mathrm{GeV}$ laser wakefield accelerator stages with high accuracy., Comment: 11 pages, 14 figures

1T-TaS$_2$ is a cluster Mott insulator on the triangular lattice with 13 Ta atoms forming a star of David cluster as the unit cell. We derive a two dimensional XXZ spin-1/2 model with four-spin ring exchange term to describe the effective low energy physics of a monolayer 1T-TaS$_2$, where the effective spin-1/2 degrees of freedom arises from the Kramers degenerate spin-orbital states on each star of David. A large scale density matrix renormalization group simulation is further performed on this effective model and we find a gapless spin liquid phase with spinon Fermi surface at moderate to large strength region of four-spin ring exchange term. All peaks in the static spin structure factor are found to be located on the "$2k_F$" surface of half-filled spinon on the triangular lattice. Experiments to detect the spinon Fermi surface phase in 1T-TaS$_2$ are discussed., Comment: 5+11 pages, 4+13 figures

Recently measurements on various spin-1/2 quantum magnets such as H$_3$LiIr$_2$O$_6$, LiZn$_2$Mo$_3$O$_8$, ZnCu$_3$(OH)$_6$Cl$_2$ and 1T-TaS$_2$ -- all described by magnetic frustration and quenched disorder but with no other common relation -- nevertheless showed apparently universal scaling features at low temperature. In particular the heat capacity C[H,T] in temperature T and magnetic field H exhibits T/H data collapse reminiscent of scaling near a critical point. Here we propose a theory for this scaling collapse based on an emergent random-singlet regime extended to include spin-orbit coupling and antisymmetric Dzyaloshinskii-Moriya (DM) interactions. We derive the scaling $C[H,T]/T \sim H^{-\gamma} F_q[T/H]$ with $F_q[x] = x^{q}$ at small $x$, with $q \in$ (0,1,2) an integer exponent whose value depends on spatial symmetries. The agreement with experiments indicates that a fraction of spins form random valence bonds and that these are surrounded by a quantum paramagnetic phase. We also discuss distinct scaling for magnetization with a $q$-dependent subdominant term enforced by Maxwell's relations., Comment: v2. Expanded argument in Appendix 2 and revised for clarity. v3. Fixed typo in Fig 3 caption. Main text 4 pages 4 figures, Appendix 6 pages 1 figure

Binary maximum distance separable (MDS) array codes are a special class of erasure codes for distributed storage that not only provide fault tolerance with minimum storage redundancy but also achieve low computational complexity. They are constructed by encoding $k$ information columns into $r$ parity columns, in which each element in a column is a bit, such that any $k$ out of the $k+r$ columns suffice to recover all information bits. In addition to providing fault tolerance, it is critical to improve repair performance in practical applications. Specifically, if a single column fails, our goal is to minimize the repair bandwidth by downloading the least amount of bits from $d$ healthy columns, where $k\leq d\leq k+r-1$. If one column of an MDS code is failed, it is known that we need to download at least $1/(d-k+1)$ fraction of the data stored in each of $d$ healthy columns. If this lower bound is achieved for the repair of the failure column from accessing arbitrary $d$ healthy columns, we say that the MDS code has optimal repair. However, if such lower bound is only achieved by $d$ specific healthy columns, then we say the MDS code has weak-optimal repair. In this paper, we propose two explicit constructions of binary MDS array codes with more parity columns (i.e., $r\geq 3$) that achieve asymptotically weak-optimal repair, where $k+1\leq d\leq k+\lfloor(r-1)/2\rfloor$, and "asymptotic" means that the repair bandwidth achieves the minimum value asymptotically in $d$. Codes in the first construction have odd number of parity columns and asymptotically weak-optimal repair for any one information failure, while codes in the second construction have even number of parity columns and asymptotically weak-optimal repair for any one column failure.

Erasure coding is widely used for massive storage in data centers to achieve high fault tolerance and low storage redundancy. Since the cross-rack communication cost is often high, it is critical to design erasure codes that minimize the cross-rack repair bandwidth during failure repair. In this paper, we analyze the optimal trade-off between storage redundancy and cross-rack repair bandwidth specifically for data centers, subject to the condition that the original data can be reconstructed from a sufficient number of any non-failed nodes. We characterize the optimal trade-off curve under functional repair, and propose a general family of erasure codes called rack-aware regenerating codes (RRC), which achieve the optimal trade-off. We further propose exact repair constructions of RRC that have minimum storage redundancy and minimum cross-rack repair bandwidth, respectively. We show that (i) the minimum storage redundancy constructions support a wide range of parameters and have cross-rack repair bandwidth that is strictly less than that of the classical minimum storage regenerating codes in most cases, and (ii) the minimum cross-rack repair bandwidth constructions support all the parameters and have less cross-rack repair bandwidth than that of the minimum bandwidth regenerating codes for almost all of the parameters.

A recent scanning tunneling microscopy (STM) experiment reports the observation of charge density wave (CDW) with period of approximately 8a in the halo region surrounding the vortex core, in striking contrast to the approximately period 4a CDW that are commonly observed in the cuprates. Inspired by this work, we study a model where a bi-directional pair density wave (PDW) with period 8 is at play. This further divides into two classes, (1) where the PDW is a competing state of the d wave superconductor and can exist only near the vortex core where the d wave order is suppressed, and (2) where the PDW is the primary order, the so called mother state that persists with strong phase fluctuations to high temperature and high magnetic field and lies behind the pseudogap phenomenology. We study the charge density wave structures near the vortex core in these models. We emphasize the importance of the phase winding of the d-wave order parameter. The PDW can be pinned by the vortex core due to this winding and become static. Furthermore, the period 8 CDW inherits the properties of this winding, which gives rise to a special feature of the Fourier transform peak, namely, it is split in certain directions. There are also a line of zeros in the inverse Fourier transform of filtered data. We propose that these are key experimental signatures that can distinguish between the PDW-driven scenario from the more mundane option that the period 8 CDW is primary. We discuss the pros and cons of the options considered above. Finally we attempt to place the STM experiment in the broader context of pseudogap physics of underdoped cuprates and relate this observation to the unusual properties of X ray scattering data on CDW carried out to very high magnetic field., Comment: 18 pages, 12 pages; added references and discussed flux density wave

Electron tunneling into a system with strong interactions is known to exhibit an anomaly, in which the tunneling conductance vanishes continuously at low energy due to many-body interactions. Recent measurements have probed this anomaly in a quantum Hall bilayer of the half-filled Landau level, and shown that the anomaly apparently gets stronger as the half-filled Landau level is increasingly spin polarized. Motivated by this result, we construct a semiclassical hydrodynamic theory of the tunneling anomaly in terms of the charge-spreading action associated with tunneling between two copies of the Halperin-Lee-Read state with partial spin polarization. This theory is complementary to our recent work (arXiv:1709.06091) where the electron spectral function was computed directly using an instanton-based approach. Our results show that the experimental observation cannot be understood within conventional theories of the tunneling anomaly, in which the spreading of the injected charge is driven by the mean-field Coulomb energy. However, we identify a qualitatively new regime, in which the mean-field Coulomb energy is effectively quenched and the tunneling anomaly is dominated by the finite compressibility of the composite Fermion liquid., Comment: 24 pages, 2 figures; Final published version