Search

Compute Express Link (CXL) serves as a rising industry standard, delivering high-speed cache-coherent links to a variety of devices, including host CPUs, computational accelerators, and memory devices. It is designed to promote system scalability, enable peer-to-peer exchanges, and accelerate data transmissions. To achieve these objectives, the most recent CXL protocol has brought forth several innovative features, such as port-focused routing, device-handled coherence, and PCIe 6.0 compatibility. However, due to the limited availability of hardware prototypes and simulators compatible with CXL, earlier CXL research has largely depended on emulating CXL devices using remote NUMA nodes. Unfortunately, these NUMA-based emulators have difficulties in accurately representing the new features due to fundamental differences in hardware and protocols. Moreover, the absence of support for non-tree topology and PCIe links makes it complex to merely adapt existing simulators for CXL simulation. To overcome these problems, we introduce ESF, a simulation framework specifically designed for CXL systems. ESF has been developed to accurately reflect the unique features of the latest CXL protocol from the ground up. It uses a specialized interconnect layer to facilitate connections within a wide range of system topologies and also includes key components to carry out specific functions required by these features. By utilizing ESF, we thoroughly investigate various aspects of CXL systems, including system topology, device-handled coherence, and the effects of PCIe characteristics, leading to important findings that can guide the creation of high-performance CXL systems. The ESF source codes are fully open-source and can be accessed at https://anonymous.4open.science/r/ESF-1CE3.

The simultaneous presence of polarity and metallicity in a material signifies an exotic polar metal state, but such materials are extremely rare, especially in bulk form, due to mutually exclusive nature of the fundamental defining properties. Here, we report experimental findings that HgPSe3 is a robust bulk polar metal at room temperature with a chiral structure stabilized by pressure and, remarkably, this polar metal hosts superconductivity with critical temperature Tc up to 11 K. Theoretical analysis reveals a two-step interlayer sliding-then-compressing mechanism for coexistence of polarity and metallicity in HgPSe3. This work unveils a new paradigm for creating the bulk polar metal state and simultaneous presence of coexisting quantum orders, raising the prospect of discovering novel emergent physics using pressure as a tuning knob., Comment: 19 pages, 4 main figures + 6 extented figures

A graph is diameter-$k$-critical if its diameter equals $k$ and the deletion of any edge increases its diameter. The Murty-Simon Conjecture states that for any diameter-2-critical graph $G$ of order $n$, $e(G) \leq \lfloor \frac{n^2}{4}\rfloor$, with equality if and only if $G \cong K_{\lfloor \frac{n}{2}\rfloor,\lceil \frac{n}{2}\rceil}$. F\"uredi (JGT,1992) proved that this conjecture is true for sufficiently large $n$. Over two decades later, Loh and Ma (JCT-B, 2016) proved that $e(G) \leq \frac{n^2}{6}+o(n^2)$ for diameter-3-critical graphs $G$, and $e(G) \leq \frac{3n^2}{k}$ for diameter-$k$-critical graphs $G$ with $k \geq 4$. In this paper, we improve the bound for diameter-$k$-critical graphs to $ \frac{n^2}{2k}+o(n^2)$.

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constraint scenarios (e.g., edge computing and personal devices). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstInfer, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstInfer designs a dedicated flash-aware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstInfer improves throughput for long-sequence inference by up to 11.1$\times$, compared to existing SSD-based solutions such as FlexGen.

We use satellite observations of atmospheric methane from the TROPOMI instrument to estimate total annual methane emissions for 2019-2023 from four large Southeast US landfills with gas collection and control systems. The emissions are on average 6$\times$ higher than the values reported by the landfills to the US Greenhouse Gas Reporting Program (GHGRP) which are used by the US Environmental Protection Agency (EPA) for its national Greenhouse Gas Inventory (GHGI). We find increasing emissions over the 2019-2023 period whereas the GHGRP reports a decrease. The GHGRP requires gas-collecting landfills to estimate their annual emissions either with a recovery-first model (estimating emissions as a function of methane recovered) or a generation-first model (estimating emissions from a first-order-decay applied to waste-in-place). All four landfills choose to use the recovery-first model, which yields emissions that are one-quarter of those from the generation-first model and decreasing over 2019-2023, in contrast with the TROPOMI observations. Our TROPOMI estimates for two of the landfills agree with the generation-first model, with increasing emissions over 2019-2023 due to increasing waste-in-place or decreasing methane recovery, and are still higher than the generation-first model for the other two landfills. Further examination of the GHGRP emissions from all reporting landfills in the US shows that the 19% decrease in landfill emissions reported by the GHGI over 2005-2022 reflects an increasing preference for the recovery-first model by the reporting landfills, rather than an actual emission decrease. The generation-first model would imply an increase in landfill emissions over 2013-2022, and this is more consistent with atmospheric observations.

Topological insulators (TIs) are emergent materials with unique band structure, which allow the study of quantum effect in solids, as well as contribute to high performance quantum devices. To achieve the better performance of TI, here we present a co-doping strategy using synergistic rare-earth Sm and transition-metal Fe dopants in Bi2Se3 single crystals, which combine the advantages of both transition metal doped TI (high ferromagnetic ordering temperature and observed QAHE), and rare-earth doped TI (large magnetic moments and significant spin orbit coupling). In the as-grown single crystals, clear evidences of ferromagnetic ordering were observed. The angle resolve photoemission spectroscopy indicate the ferromagnetism opens a 44 meV band gap at surface Dirac point. Moreover, the carrier mobility at 3 K is ~ 7400 cm2/Vs, and we thus observed an ultra-strong Shubnikov-de Haas oscillation in the longitudinal resistivity, as well as the Hall steps in transverse resistivity below 14 T. Our transport and angular resolved photoemission spectroscopy results suggest that the rare-earth and transition metal co-doping in Bi2Se3 system is a promising avenue implement the quantum anomalous Hall effect, as well as harnessing the massive Dirac fermion in electrical devices., Comment: 5 figures

In the 1960s, it was proposed that in small indirect band-gap materials, excitons can spontaneously form because the density of carriers is too low to screen the attractive Coulomb interaction between electrons and holes. The result is a novel strongly interacting insulating phase known as an excitonic insulator. Here we employ scanning tunnelling microscopy (STM) and spectroscopy (STS) to show that the enhanced Coulomb interaction in quantum-confined elemental Sb nanoflakes drives the system to the excitonic insulator state. The unique feature of the excitonic insulator, a charge density wave (CDW) without periodic lattice distortion, is directly observed. Furthermore, STS shows a gap induced by the CDW near the Fermi surface. Our observations suggest that the Sb(110) nanoflake is an excitonic insulator.

Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges such as frequent hardware failures, intricate parallelization strategies, and imbalanced resource utilization. In this paper, we present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme. Specifically, we investigate discrepancies between LLMs and prior task-specific Deep Learning (DL) workloads, explore resource utilization patterns, and identify the impact of various job failures. Our analysis summarizes hurdles we encountered and uncovers potential opportunities to optimize systems tailored for LLMs. Furthermore, we introduce our system efforts: (1) fault-tolerant pretraining, which enhances fault tolerance through LLM-involved failure diagnosis and automatic recovery. (2) decoupled scheduling for evaluation, which achieves timely performance feedback via trial decomposition and scheduling optimization.

Let $\{X_{i}, i\in J\}$ be a family of locally dependent non-negative integer-valued random variables with finite expectations and variances. We consider the sum $W=\sum_{i\in J}X_i$ and use Stein's method to establish general upper error bounds for the total variation distance $d_{TV}(W, M)$, where $M$ represents a three-parameter random variable. As a direct consequence, we obtain a discretized normal approximation for $W$. As applications, we study in detail four well-known examples, which are counting vertices of all edges point inward, birthday problem, counting monochromatic edges in uniformly colored graphs, and triangles in the Erd\H{o}s-R\'{e}nyi random graph. Through delicate analysis and computations, we obtain sharper upper error bounds than existing results.

The Berry phase is an important concept in solids, correlated to the band topology, axion electrodynamics and potential applications of topological materials. Here, we investigate the magnetotransport and Berry phase of rare earth element Gd doped Bi2Se3 (Gd_Bi2Se3) topological insulator at low temperatures and high magnetic fields. Gd_Bi2Se3 single crystals show Shubnikov-de Haas (SdH) oscillations with nontrivial Berry phase while Bi2Se3 single crystals show zero Berry phase in SdH oscillations. The temperature dependent magnetization curves can be well fitted with the Curie-Weiss law in 3-300 K region, indicating no magnetic ordering in Gd_Bi2Se3 crystals. Moreover, Gd doping has limited influence on the quantum oscillation parameters (e.g., frequency of oscillations, the area of the Fermi surface, effective electron mass, Fermi wave vectors etc.), but has an impact on the Hall mobility, carrier density, and band topology. Our results demonstrate that Gd doping can tune the Berry phase of topological insulators effectively, which may pave a way for the future realization of many predicted exotic transport phenomena of topological origin.

Stoichiometric Cr2Se3 single crystals are particular layer-structured antiferromagnets which possess noncolinear spin configuration, weak ferromagnetic moments, moderate magnetoresistance (MR ~ 14.3%), and bad metallic conductivity below the antiferromagnetic phase transition temperature. Here, we report an interesting >16000% colossal magnetoresistance (CMR) effect in Ti (1.5 atomic percent) lightly-doped Cr2Se3 single crystals. Such a CMR is approximately 1143 times larger than that of the stoichiometric Cr2Se3 crystals and is rarely observed in layered antiferromagnets and is attributed to the frustrated spin configuration. Moreover, the Ti doping not only dramatically changes the electronic conductivity of the Cr2Se3 crystal from a bad metal to a semiconductor with a gap of ~ 15 meV, but also induces a change of the magnetic anisotropy of the Cr2Se3 crystal from strong out-of-plane to weak in plane. Further, magnetotransport measurements reveal that the low-field MR scales with the square of the reduced magnetization, which is a signature of CMR materials. The layered Ti:Cr2Se3 with CMR effect could be used as 2D heterostructure building blocks to provide colossal negative MR in spintronic devices.

As one of the most important n-type thermoelectric (TE) materials, Bi2Te3 has been studied for decades, with efforts to enhance the thermoelectric performance based on element doping, band engineering, etc. In this study, we report a novel bulk-insulating topological material system as a replacement for n-type Bi2Te3 materials: V doped Bi1.08Sn0.02Sb0.9Te2S (V:BSSTS) . The V:BSSTS is a bulk insulator with robust metallic topological surface states. Furthermore, the bulk band gap can be tuned by the doping level of V, which is verified by magnetotransport measurements. Large linear magnetoresistance is observed in all samples. Excellent thermoelectric performance is obtained in the V:BSSTS samples, e.g., the highest figure of merit ZT of ~ 0.8 is achieved in the 2% V doped sample (denoted as V0.02) at 550 K. The high thermoelectric performance of V:BSSTS can be attributed to two synergistic effects: (1) the low conductive secondary phases Sb2S3, and V2S3 are believed to be important scattering centers for phonons, leading to lower lattice thermal conductivity; and (2) the electrical conductivity is increased due to the high-mobility topological surface states at the boundaries. In addition, by replacing one third of costly tellurium with abundant, low-cost, and less-toxic sulfur element, the newly produced BSSTS material is inexpensive but still has comparable TE performance to the traditional Bi2Te3-based materials, which offers a cheaper plan for the electronics and thermoelectric industries. Our results demonstrate that topological materials with unique band structures can provide a new platform in the search for new high performance TE materials.

Spin-orbit interaction (SOI) offers a nonferromagnetic scheme to realize spin polarization through utilizing an electric field. Electrically tunable SOI through electrostatic gates have been investigated, however, the relatively weak and volatile tunability limit its practical applications in spintronics. Here, we demonstrate the nonvolatile electric-field control of SOI via constructing ferroelectric Rashba architectures, i.e., 2D Bi2O2Se/PMN-PT ferroelectric field effect transistors. The experimentally observed weak antilocalization (WAL) cusp in Bi2O2Se films implies the Rashba-type SOI that arises from asymmetric confinement potential. Significantly, taking advantage of the switchable ferroelectric polarization, the WAL-to-weak localization (WL) transition trend reveals the competition between spin relaxation and dephasing process, and the variation of carrier density leads to a reversible and nonvolatile modulation of spin relaxation time and spin splitting energy of Bi2O2Se films by this ferroelectric gating. Our work provides a scheme to achieve nonvolatile control of Rashba SOI with the utilization of ferroelectric remanent polarization.

As more data-intensive tasks with large footprints are deployed in virtual machines (VMs), huge pages are widely used to eliminate the increasing address translation overhead. However, once the huge page mapping is established, all the base page regions in the huge page share a single extended page table (EPT) entry, so that the hypervisor loses awareness of accesses to base page regions. None of the state-of-the-art solutions can obtain access information at base page granularity for huge pages. We observe that this can lead to incorrect decisions by the hypervisor, such as incorrect data placement in a tiered memory system and unshared base page regions when sharing pages. This paper proposes FHPM, a fine-grained huge page management for virtualization without hardware and guest OS modification. FHPM can identify access information at base page granularity, and dynamically promote and demote pages. A key insight of FHPM is to redirect the EPT huge page directory entries (PDEs) to new companion pages so that the MMU can track access information within huge pages. Then, FHPM can promote and demote pages according to the current hot page pressure to balance address translation overhead and memory usage. At the same time, FHPM proposes a VM-friendly page splitting and collapsing mechanism to avoid extra VM-exits. In combination, FHPM minimizes the monitoring and management overhead and ensures that the hypervisor gets fine-grained VM memory accesses to make the proper decision. We apply FHPM to improve tiered memory management (FHPM-TMM) and to promote page sharing (FHPM-Share). FHPM-TMM achieves a performance improvement of up to 33% and 61% over the pure huge page and base page management. FHPM-Share can save 41% more memory than Ingens, a state-of-the-art page sharing solution, with comparable performance.

Topological insulators are emerging materials with insulating bulk and symmetry protected nontrivial surface states. One of the most fascinating transport behaviors in a topological insulator is the quantized anomalous Hall insulator, which has been observed inmagnetic-topological-insulator-based devices. In this work, we report a successful doping of rare earth element Tb into Bi$_{1.08}$Sb$_{0.9}$Te$_2$S topological insulator single crystals, in which the Tb moments are antiferromagnetically ordered below ~10 K. Benefiting from the in-bulk-gap Fermi level, transport behavior dominant by the topological surface states is observed below ~ 150 K. At low temperatures, strong Shubnikov-de Haas oscillations are observed, which exhibit 2D-like behavior. The topological insulator with long range magnetic ordering in rare earth doped Bi$_{1.08}$Sb$_{0.9}$Te$_2$S single crystal provides an ideal platform for quantum transport studies and potential applications., Comment: 15 pages, 3 figures