SEARCH · Engineering Papers
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.
Compiler organization is discussed, including overall compiler structure, internal data transfer, compiler development, and code optimization. The user, system, and SDL interfaces are described, along with compiler system requirements. Run-time software support package and restrictions and dependencies are also considered of the HAL/S-FC system.
Many proposals to scale quantum technology rely on modular or distributed designs wherein individual quantum processors, called nodes, are linked together to form one large multinode quantum computer (MNQC). One scalable method to construct an MNQC is using superconducting quantum systems with optical interconnects. However, internode gates in these systems may be two to three orders of magnitude noisier and slower than local operations. Surmounting the limitations of internode gates will require improvements in entanglement generation, use of entanglement distillation, and optimized software and compilers. Still, it remains unclear what performance is possible with current hardware and what performance algorithms require. In this article, we employ a systems analysis approach to quantify overall MNQC performance in terms of hardware models of internode links, entanglement distillation, and local architecture. We show how to navigate tradeoffs in entanglement generation and distillation in the context of algorithm performance, lay out how compilers and software should balance between local and internode gates, and discuss when noisy quantum internode links have an advantage over purely classical links. Here, we find that a factor of 10–100× better link performance is required and introduce a research roadmap for the co-design of hardware and software towards the realization of early MNQCs. While we focus on superconducting devices with optical interconnects, our approach is general across MNQC implementations.
Near-term intermediate scale quantum (NISQ) computers are likely to have very restricted hardware resources, where precisely controllable qubits are expensive, error-prone, and scarce. Programmers of such computers must therefore balance trade-offs among a large number of (potentially heterogeneous) factors specific to the targeted application and quantum hardware. To assist them, we propose Meta Quantum Circuits with Constraints (MQCC), a meta-programming framework for quantum programs. Programmers express their application as a succinct collection of normal quantum circuits stitched together by a set of (manually or automatically) added meta-level choice variables, whose values are constrained according to a programmable set of quantitative optimization criteria. MQCC’s compiler generates the appropriate constraints and solves them via an SMT solver, producing an optimized, runnable program. We showcase a few MQCC’s applications for its generality including an automatic generation of efficient error syndrome extraction schemes for fault-tolerant quantum error correction with heterogeneous qubits and an approach to writing approximate quantum Fourier transformation and quantum phase estimation that smoothly trades off accuracy and resource use. We also illustrate that MQCC can easily encode prior one-off NISQ application designs-–multi-programming (MP), crosstalk mitigation (CM)—as well as a combination of their optimization goals (i.e., a combined MP-CM).
We report a resource estimation pipeline that explicitly compiles quantum circuits expressed using the Clifford+T gate set into a surface code lattice surgery instruction set. The cadence of magic state requests from the compiled circuit enables the optimization of magic state distillation and storage requirements in a post-hoc analysis. To compile logical circuits into lattice surgery operations, we build upon the open-source Lattice Surgery Compiler. The revised compiler operates in two stages: the first translates logical gates into an abstract, layout-independent instruction set; the second compiles these into local lattice surgery instructions that are allocated to hardware tiles according to a specified resource layout. The second stage retains logical parallelism while avoiding resource contention in the fault-tolerant layer, aiding realism. Additionally, users can specify dedicated tiles at which magic states are replenished, enabling resource costs from the logical computation to be considered independently from magic state distillation and storage. We demonstrate the applicability of our pipeline to large practical quantum circuits by providing resource estimates for the ground state estimation of molecules. Finally, we find that variable magic state consumption rates in real circuits can cause the resource costs of magic state storage to dominate unless production is varied to suit.
We develop new approximate compilation schemes that significantly reduce the expense of compiling the Quantum Approximate Optimization Algorithm (QAOA) for solving the Max-Cut problem. Our main focus is on compilation with trapped-ion simulators using Pauli-X operations and all-to-all Ising Hamiltonian HIsing evolution generated by Molmer-Sorensen or optical dipole force interactions, though some of our results also apply to standard gate-based compilations. Our results are based on principles of graph sparsification and decomposition; the former reduces the number of edges in a graph while maintaining its cut structure, while the latter breaks a weighted graph into a small number of unweighted graphs. Though these techniques have been used as heuristics in various hybrid quantum algorithms, there have been no guarantees on their performance, to the best of our knowledge. This work provides the first provable guarantees using sparsification and decomposition to improve quantum noise resilience and reduce quantum circuit complexity. For quantum hardware that uses edge-by-edge QAOA compilations, sparsification leads to a direct reduction in circuit complexity. For trapped-ion quantum simulators implementing all-to-all HIsing pulses, we show that for a (1−ϵ) factor loss in the Max-Cut approximation (ϵ>0), our compilations improve the (worst-case) number of HIsing pulses from O(n2) to O(nlog(n/ϵ)) and the (worst-case) number of Pauli-X bit flips from O(n2) to O(nlog(n/ϵ)ϵ2) for n-node graphs. This is an asymptotic improvement for any constant ϵ>0. We demonstrate that significant improvements to the approximation ratio are obtained using decomposition in simulated trapped-ion experiments with dephasing noise. We further present a generic argument showing that sparsification results in an exponentially improved circuit fidelity lower bound in digital computing schemes based on one- and two-qubit gates, which are relevant to a wide variety of hardwares such as superconducting qubits and certain neutral atom or trapped ion setups, and more sophisticated noise models. We anticipate these approximate compilation techniques will be useful tools in a variety of future quantum computing experiments.
An approach is presented to enhancing the optimization process in a polyhedral compiler by introducing compile-time versioning, i.e., the production of several versions of optimized code under varying assumptions on its run-time parameters. We illustrate this process by enabling versioning in the polyhedral processor placement pass. We propose an efficient code generation method and validate that versioning can be useful in a polyhedral compiler by performing benchmarking on a small set of deep learning layers defined for dynamically-sized tensors.
While regular algorithms, characterized by operations on dense matrices and arrays, have long been the mainstay of scientific, high-performance computing, irregular algorithms, which feature unpredictable accesses to pointer-based data structures, are becoming increasingly common in high performance computing, arising in graph analysis, data mining and visualization, among other domains. Unfortunately, the defining characteristics of irregular applications, their dynamic, unpredictable, data-dependent access patterns and data layouts, make achieving high performance on large scale systems difficult. Scaling applications to peta- and exa-scale requires carefully controlling communication and data movement and placement, an inherently difficult task when access patterns and data layouts are unpredictable! Most irregular applications that attain high performance must be painstakingly hand-written and hand-tuned, with few common principles or paradigms uniting various implementations and easing future development. Despite the increasing importance of irregular applications, there is little programmer knowledge, and even less compiler ability, devoted to optimizing them. This project aims to solve these problems. By allowing programmers to write irregular applications in high level forms, with at most a few annotations highlighting key structural properties, programmers can focus on developing their algorithms and methods. The compiler and run-time system can take on the tedious task of optimizing the application for execution at large scales, and can automatically provide efficient implementations. This will provide portability and ease maintenance for existing irregular applications, but, more importantly, open up whole new domains of computational science to large-scale, high-performance simulation codes.
Experiences are discussed for modifying two three-dimensional transonic flow computer programs (FLO 22 and FLO 27) for use on the CDC CYBER 203 computer system. Both programs were originally written for use on serial machines. Several methods were attempted to optimize the execution of the two programs on the vector machine: leaving the program in a scalar form (i.e., serial computation) with compiler software used to optimize and vectorize the program, vectorizing parts of the existing algorithm in the program, and incorporating a vectorizable algorithm (ZEBRA I or ZEBRA II) in the program. Comparison runs of the programs were made on CDC CYBER 175. CYBER 203, and two pipe CDC CYBER 205 computer systems.
In this paper, the authors report on some of their experiences modifying two three-dimensional transonic flow programs (FLO22 and FLO27) for use on the NASA Langley Research Center CYBER 203. Both of the programs discussed were originally written for use on serial machines. Several methods were attempted to optimize the execution of the two programs on the vector machine, including: (1) leaving the program in a scalar form (i.e., serial computation) with compiler software used to optimize and vectorize the program, (2) vectorizing parts of the existing algorithm in the program, and (3) incorporating a new vectorizable algorithm (ZEBRA I or ZEBRA II) in the program.
The design, implementation and performance optimization on the CRAY T3E of an atmospheric general circulation model (AGCM) which includes the transport of, and chemical reactions among, an arbitrary number of constituents is reviewed. The parallel implementation is based on a two-dimensional (longitude and latitude) data domain decomposition. Initial optimization efforts centered on minimizing the impact of substantial static and weakly-dynamic load imbalances among processors through load redistribution schemes. Recent optimization efforts have centered on single-node optimization. Strategies employed include loop unrolling, both manually and through the compiler, the use of an optimized assembler-code library for special function calls, and restructuring of parts of the code to improve data locality. Data exchanges and synchronizations involved in coupling different data-distributed models can account for a significant fraction of the running time. Therefore, the required scattering and gathering of data must be optimized. In systems such as the T3E, there is much more aggregate bandwidth in the total system than in any particular processor. This suggests a distributed design. The design and implementation of a such distributed 'Data Broker' as a means to efficiently couple the components of our climate system model is described.
Parallel processing of real-time dynamic systems simulation on a multiprocessor system named OSCAR is presented. In the simulation of dynamic systems, generally, the same calculation are repeated every time step. However, we cannot apply to Do-all or the Do-across techniques for parallel processing of the simulation since there exist data dependencies from the end of an iteration to the beginning of the next iteration and furthermore data-input and data-output are required every sampling time period. Therefore, parallelism inside the calculation required for a single time step, or a large basic block which consists of arithmetic assignment statements, must be used. In the proposed method, near fine grain tasks, each of which consists of one or more floating point operations, are generated to extract the parallelism from the calculation and assigned to processors by using optimal static scheduling at compile time in order to reduce large run time overhead caused by the use of near fine grain tasks. The practicality of the scheme is demonstrated on OSCAR (Optimally SCheduled Advanced multiprocessoR) which has been developed to extract advantageous features of static scheduling algorithms to the maximum extent.
We present VOQC, the first verified optimizer for quantum circuits, written using the Coq proof assistant. Quantum circuits are expressed as programs in a simple, low-level language called SQIR, a small quantum intermediate representation, which is deeply embedded in Coq. Optimizations and other transformations are expressed as Coq functions, which are proved correct with respect to a semantics of SQIR programs. SQIR programs denote complex-valued matrices, as is standard in quantum computation, but we treat matrices symbolically to reason about programs that use an arbitrary number of quantum bits. SQIR’s careful design and our provided automation make it possible to write and verify a broad range of optimizations in VOQC, including full-circuit transformations from cutting-edge optimizers.
Given a pre-trained neural network, Inference-Engine performs maps network inputs to outputs by executing the forward pass through the provided network. Although the predominant programming language for machine-learning is Python, most high-performance computing (HPC) applications are written in Fortran, C, or C++. Inference-Engine aims to support HPC programs and is written in Fortran, a language with a large feature set supporting interoperability with C. This software exposes concurrency in a portable way by using standard language features that some modern Fortran compilers can exploit with various optimizations, including offloading computation to a Graphics Processing Unit (GPU). In particular, this software makes extensive use of Fortran's "do concurrent" parallel loop construct, implicitly parallel array statements, and pure procedures that can be invoked inside "do concurrent" blocks. Inference-Engine also supports dynamic choice of inference methods at runtime. Two current options include one method that uses Fortran's "dot_product" intrinsic function inside "do concurrent" blocks and another method that instead uses Fortran' "matmul" array intrinsic function. We plan to investigate automatic compiler offloading of "do concurrent" calculations to GPUs and compile-time substitution of optimized libraries such as the Basic Linear Algebra Library (BLAS) for "matmul" invocations. We also envision the potential for the choice of which method to use could happen at program launch based on in situ performance measurements on any given platform.
Quantum optimal control plays a crucial role in quantum computing by providing the interface between compiler and hardware. Solving the optimal control problem is particularly challenging for multi-qubit gates, due to the exponential growth in computational complexity with the system's dimensionality and the deterioration of optimization convergence. To ameliorate the computational complexity of time-integration, this paper introduces a multiple-shooting approach in which the time domain is divided into multiple windows and the intermediate states at window boundaries are treated as additional optimization variables. Further, this enables parallel computation of state evolution across time-windows, significantly accelerating objective function and gradient evaluations. Since the initial state matrix in each window is only guaranteed to be unitary upon convergence of the optimization algorithm, the conventional gate trace infidelity is replaced by a generalized infidelity that is convex for non-unitary state matrices. Continuity of the state across window boundaries is enforced by equality constraints. A quadratic penalty optimization method is used to solve the constrained optimal control problem, and an efficient adjoint technique is employed to calculate the gradients in each iteration. We demonstrate the effectiveness of the proposed method through numerical experiments on quantum Fourier transform gates in systems with 2, 3, and 4 qubits, noting a speedup of 80x for evaluating the gradient in the 4-qubit case, highlighting the method's potential for optimizing control pulses in multi-qubit quantum systems.
The upcoming exascale computing systems Frontier and Aurora will draw much of their computing power from GPU accelerators. The hardware for these systems will be provided by AMD and Intel, respectively, each supporting their own GPU programming model. The challenge for applications that harness one of these exascale systems will be to avoid lock-in and to preserve performance portability. We report here on our results of using Kokkos to accelerate a real-world application on NERSC's Perlmutter Phase 1 (using NVIDIA A100 accelerators) and Crusher, the testbed system for OLCF's Frontier (using AMD MI250X). By porting to Kokkos, we successfully ran the same X-ray tracing code on both systems and achieved speed-ups between 13 % and 66 % compared to the original CUDA code. Finally, these results are a highly encouraging demonstration of using Kokkos to accelerate production science code.
A system is described which was built to compile weekly rotas for the anaesthetists in a large hospital. The rota compilation problem is an optimization problem (the number of tasks which cannot be assigned to an anaesthetist must be minimized) and was formulated as a constraint satisfaction problem (CSP). The forward checking algorithm is used to find a feasible rota, but because of the size of the problem, it cannot find an optimal (or even a good enough) solution in an acceptable time. Instead, an algorithm was devised which makes local improvements to a feasible solution. The algorithm makes use of the constraints as expressed in the CSP to ensure that feasibility is maintained, and produces very good rotas which are being used by the hospital involved in the project. It is argued that formulation as a constraint satisfaction problem may be a good approach to solving discrete optimization problems, even if the resulting CSP is too large to be solved exactly in an acceptable time. A CSP algorithm may be able to produce a feasible solution which can then be improved, giving a good, if not provably optimal, solution.
Explore the source record for details and available documents.
OpenARC is an open-sourced, very High-Level Intermediate Representation (HLIR)-based, extensible compiler framework, where various performance optimizations, traceability mechanisms, fault tolerance techniques, etc., can be built for better debuggability/performance/resilience on the complex accelerator computing. OpenARC is the first OpenACC compiler supporting Altera FPGAs, in addition to NVIDIA GPUs, AMD GPUs, and Intel Xeon Phis.