Characterizing the Performance and Usability of GPU JIT Compilation Interfaces using Proteus
Explore the source record for details and available documents.
Computer science↗
SEARCH · Search NASA
Results for “JIT”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Just-in-Time Compilation and Link-Time Optimization for OpenMP Target Offloading
Following the mass adoption of external accelerators for high performance computing, the overall performance of many applications has become increasingly dependent on relatively small accelerated kernels. As static analysis is fundamentally limited by dynamic values and external definitions, standard ahead-of-time compilation is not always sufficient to achieve the best performance. Furthermore, many users looking to port an existing application to run on an external accelerator will not want to fundamentally restructure their programs. These and other problems can be addressed through both link-time optimization (LTO) and just-in-time (JIT) compilation, but until now had sparse and inconsistent support from the compiler. In this work, we present a new compilation method that enables device-side LTO as well as a transparent JIT compilation tool-chain for OpenMP target offloading. Our contributions include an entirely new device linking and embedding scheme to enable LTO as well as a novel JIT engine to efficiently optimize OpenMP offloading regions at run-time. We also introduce a persistent caching system to improve end-to-end runtime using the JIT engine and minimize kernel launching overheads. We measure the performance of our LTO and JIT implementation via several real-world scientific applications. With our optimizations we observe significant improvements through LTO on large applications as well as significant end-to-end execution time improvement using JIT.
Tian, Shilei↗
Graph-based machine learning improves just-in-time defect prediction
The increasing complexity of today’s software requires the contribution of thousands of developers. This complex collaboration structure makes developers more likely to introduce defect-prone changes that lead to software faults. Determining when these defect-prone changes are introduced has proven challenging, and using traditional machine learning (ML) methods to make these determinations seems to have reached a plateau. In this work, we build contribution graphs consisting of developers and source files to capture the nuanced complexity of changes required to build software. By leveraging these contribution graphs, our research shows the potential of using graph-based ML to improve Just-In-Time (JIT) defect prediction. We hypothesize that features extracted from the contribution graphs may be better predictors of defect-prone changes than intrinsic features derived from software characteristics. We corroborate our hypothesis using graph-based ML for classifying edges that represent defect-prone changes. This new framing of the JIT defect prediction problem leads to remarkably better results. We test our approach on 14 open-source projects and show that our best model can predict whether or not a code change will lead to a defect with an F1 score as high as 77.55% and a Matthews correlation coefficient (MCC) as high as 53.16%. This represents a 152% higher F1 score and a 3% higher MCC over the state-of-the-art JIT defect prediction. We describe limitations, open challenges, and how this method can be used for operational JIT defect prediction.
59 BASIC BIOLOGICAL SCIENCES↗
Improving the Performance of NEML2 with Modern Graph Compilation Backends
NEML2 vectorizes constitutive-model evaluation for large-scale multiphysics simulation, using PyTorch as its tensor backend so that a batch of material-point updates runs on CPU or GPU through a single implementation. In the two prior reports in this series it was a C++-native library, deployed through TorchScript tracing and just-in-time (JIT) compilation; it has since been rewritten from the ground up into a Python-native library deployed through Ahead-of-Time Inductor (AOTInductor), a modern PyTorch graph-compilation backend. The rewrite is driven by a persistent tension, not a language preference: NEML2 composes constitutive models at runtime from a registry of small, independently-authored pieces, and that flexibility is difficult to reconcile with the compile-time knowledge an efficient GPU kernel needs. This report documents the rewrite and the investment that accompanied it: the AOTInductor export pipeline that turns a Python-authored model into a portable, Python-free compiled artifact loadable from pure C++; the eager and compiled runtimes and the new implicit solver layer built on them; a head-to-head benchmark of legacy JIT against AOTInductor; the physics-model catalog and its worked examples; the developer tooling; and the corresponding overhaul of MOOSE’s NEML2 integration that lets MOOSE consume it. A central objective is to examine whether modern PyTorch graph-compilation backends are effective for MOOSE GPU integration. The benchmark answers directly: AOTInductor outperforms legacy JIT on every GPU scenario measured, by 1.0–4.5×. Modern graph-compilation backends are effective for MOOSE GPU integration, and AOTInductor specifically – not compilation in the abstract – is why.
Hu, Gary (Tianchen) [Argonne National Laboratory (↗
Using Numba for GPU acceleration of Neutron Beamline Digital Twins
Digital twins of neutron instruments using Monte Carlo ray tracing have proven to be useful in neutron data analysis and verifying instrument and sample designs. However, these simulations can become quite complex and computationally demanding with tens of billions of neutrons. In this paper, we present a GPU accelerated version of MCViNE using Python and Numba to balance user extensibility with performance. Numba is an open-source just-in-time (JIT) compiler for Python using LLVM to generate efficient machine code for CPUs and GPUs with NVIDIA CUDA. The JIT nature of Numba allowed complex instrument kernels to be generated easily. Initial simulations have shown a speedup between 200-1000x over the original CPU implementation. The performance gain with Numba enables more sophisticated data analysis and impacts neutron scattering science and instrument design.
Kendrick, Coleman↗
SV-Sim: Scalable PGAS-based State Vector Simulation of Quantum Circuits
High-performance quantum circuit simulation in a classic HPC is still imperative in the NISQ era. Observing that the major obstacle of scalable state-vector quantum simulation arises from the massively fine-grained irregular data-exchange with remote nodes, in this paper we present SV-Sim to apply the emerging PGAS-based communication models (i.e., direct peer access for intra-node CPUs/GPUs and SHMEM for inter-node CPU/GPU clusters) for efficient scalable quantum circuit simulation. Through an orchestrated device functional pointer design, SV-Sim is able to abstract the quantum gate sets across various heterogeneous backends, including IBM/Intel/AMD CPUs, NVIDIA /AMD GPUs, and Intel MIC, in a unified framework, but still asserting outstanding performance and tractable interface to higher-level quantum programming environments, such as IBM Qiskit, Microsoft Q\# and Google Cirq. Circumventing the disability of polymorphism in GPUs and leveraging the device-initiated one-sided communication, SV-Sim can process dynamically synthesized quantum circuit in a single GPU/CPU kernel without the need of expensive JIT or runtime branching, significantly improving the performance and simplifying the programming complexity for the emerging variational quantum algorithms. Evaluations on NVIDIA A100-DGX-1, V100-DGX-2, AMD MI100, ALCF Theta, and OLCF Summit HPCs show that SV-Sim can delivery scalable performance on various state-of-the-art HPC platforms, offering a useful tool for quantum algorithm validation and verification.
Li, Ang↗
NAMSA
In NAMSA, we introduce two main solutions to address the limitations of MSA-type algorithms for simulation of electron scattering/microscopy data: just-in-time compilation and work partitioning via MPI and GPU-to-GPU communication. First, the just-in-time (JIT) compilation strategy produces optimally tuned CUDA C++ kernels due to the data layout being perfectly known at runtime and compiled via calls from the Python interpreter. NAMSA automatically optimizes the 2-D FFT planning, and CUDA multi-streams scheduling/launching of probe simulations. With NAMSA, we can simulate electron scattering/microscopy on hundreds to thousands of GPUs, while removing the major limitations of memory and bandwidth from MSA.
Laanait, Nouamane↗
SurFE-XD (Surface curvature-driven Finite Elements model for Diffusion under eXtreme conditions)
SurFE-XD is a mesoscale finite element framework to model surface diffusion under mutliphysics environments. The code uses legacy C++ library dolphin wrapped with python in a FEniCS driven unified form language and just-in-time (JIT) compilation setting. The purpose of the release is to attract wide-ranging usage of the code along with publication supplementation to support reproducibility of scientific data. SurFE-XD has been originally conceived under the LDRD-DR funding for “High-Gradient (C-BAND) Breakdown tolerant accelerator materials project. Currently SrFE-XD support electrostatics and Thermo-elasticity driven surface diffusion kernels. Releasing the code will also enable to include contributions from other physical regimes e.g., plasticity and electrodynamics etc as well portability to GPU-based platforms.
Bagchi, Soumendu↗
Los Alamos National Laboratory Release of Cesium-137 Corrective Action Plan
This Corrective Action Plan (CAP) was developed by a team chartered by John Sarrao, Deputy Director for Science, Technology, and Engineering (DDSTE), to review and respond to the findings of the Joint National Nuclear Security Administration/Triad National Security (NNSA/Triad) Investigation Team (JIT) Joint Investigation Report for the “Sealed Source Recovery at the University of Washington Harborview Training and Research Facility Results in Release of Cesium-137 on May 2, 2019,” dated March 30, 2020. On May 2, 2019, International Isotopes, Inc. (INIS), a subcontractor to Triad National Security, LLC, inadvertently breached a sealed cesium-137 source at the University of Washington (UW), Harborview Medical Center Research and Training (HRT) building in downtown Seattle while attempting to recover the source for the National Nuclear Security Administration (NNSA) Off-Site Source Recovery Program (OSRP). The source breach resulted in contamination of personnel and the HRT building, as well as a release of radioactive material to the environment
07 ISOTOPE AND RADIATION SOURCES↗
Summary of Forensic Examinations in Support of Breach Sealed Source Event at Harborview Medical Facility on 2 May 2019
On May 2, 2019, International Isotopes, Inc. (INIS), a subcontractor to Triad National Security, LLC (contractor for Los Alamos National Laboratory) breached a sealed radioactive source containing ~2800 Ci of the radioactive isotope cesium-137 ( 137 Cs) at the University of Washington Harborview Research and Training (HRT) Building in downtown Seattle while attempting to recover the source for the National Nuclear Security Administration’s (NNSA’s) Off-site Source Recovery Program (OSRP). The breach of the source resulted in the contamination of 13 personnel, all 7 floors of the building, and a release of material to the environment. A summary of root and contributing causes of the event was investigated and published by a joint investigation team (JIT) co-led by NNSA and Triad National Security, LLC. That investigation was supported by forensics examinations provided by Pacific Northwest National Laboratory. This report summarizes the results of those forensic examinations.
61 RADIATION PROTECTION AND DOSIMETRY↗
Embedding Neural Thermal Scattering (NeTS) Modules in SERPENT for Higher Fidelity Advanced Reactor Analysis
When a neutron born in fission thermalizes to the order of $k$ $B$ $T$, it’s de-Broglie wavelength and energy approach the order of inter-atomic spacing and elementary lattice oscillations, respectively. $S$($a,β,t$) or the scattering law, uuantify these temperature-dependent crystallographic contributions to total cross section (or reaction rate). In a Monte Carlo analysis, cumulative distribution functions (CDFs) of $S$($a,β,t$) are loaded to memory from “A Compact ENDF” (ACE) files for stochastically selecting thermal scattered neutron trajectories. In this work, novel neural thermal scattering (NeTS) modules for $S$($a,β,t$) CDFs are designed, trained, serialized and embedded within SERPENT using Python’s limited C-API for on-the-fly deployment of crystalline graphite $S$($a,β,t$) sampling. Torchscript tracing and Numba just-in-time (JIT) compilation streamline neural inference on NVIDIA GPUs with CUDA libraries. Demonstrations of bare sphere thermalization of fast and thermal sources show excellent agreement between embedded NeTS in SERPENT and MCNP. With an explicit model of the reactor, NeTS can predict on-the-fly changes in TREAT neutron spectra as a function of local temperature, which can serve to improve transient and accident predictions in a multiphysics analysis framework. This framework can be further extended to account on-the-fly for changes in local graphitic microstructure to scattering cross sections, and outlines a novel coupling of modern machine learning with state-of-the-art reactor physics methods.
97 MATHEMATICS AND COMPUTING↗
Engineering microscale systems for fully autonomous intracellular neural interfaces
Conventional electrodes and associated positioning systems for intracellular recording from single neurons in vitro and in vivo are large and bulky, which has largely limited their scalability. Further, acquiring successful intracellular recordings is very tedious, requiring a high degree of skill not readily achieved in a typical laboratory. We report here a robotic, MEMS-based intracellular recording system to overcome the above limitations associated with form-factor, scalability and highly skilled and tedious manual operations required for intracellular recordings. This system combines three distinct technologies: 1) novel microscale, glass-polysilicon penetrating electrode for intracellular recording, 2) electrothermal microactuators for precise microscale movement of each electrode and 3) closed-loop control algorithm for autonomous positioning of electrode inside single neurons. Here, we demonstrate the novel, fully integrated system of glass-polysilicon microelectrode, microscale actuators and controller for autonomous intracellular recordings from single neurons in the abdominal ganglion of Aplysia Californica (n = 5 cells). Consistent resting potentials (< –35 mV) and action potentials (> 60 mV) were recorded after each successful penetration attempt with the controller and microactuated glass-polysilicon microelectrodes. The success rate of penetration and quality of intracellular recordings achieved using electrothermal microactuators were comparable to that of conventional positioning systems. The MEMS-based system offers significant advantages: 1) reduction in overall size for potential use in behaving animals, 2) scalable approach to potentially realize multi-channel recordings and 3) a viable method to fully automate measurement of intracellular recordings. Furthermore, this system will be evaluated in vivo in future rodent studies.
42 ENGINEERING↗
Coherent light control of a metastable hidden state
Metastable phases present a promising route to expand the functionality of complex materials. Of particular interest are light-induced metastable phases that are inaccessible under equilibrium conditions, as they often host new, emergent properties switchable on ultrafast timescales. However, the processes governing the trajectories to such hidden phases remain largely unexplored. Here, using time- and angle-resolved photoemission spectroscopy, we investigate the ultrafast dynamics of the formation of a hidden quantum state in the layered dichalcogenide 1T-TaS 2 upon photoexcitation. Our results reveal the nonthermal character of the transition governed by a collective charge-density-wave excitation. Using a double-pulse excitation of the structural mode, we show vibrational coherent control of the phase-transition efficiency. Our demonstration of exceptional control, switching speed, and stability of the hidden state are key for device applications at the nexus of electronics and photonics.
36 MATERIALS SCIENCE↗