SEARCH · Search NASA

Results for “Compiler Optimizations”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Realistic Cost to Execute Practical Quantum Circuits using Direct Clifford+T Lattice Surgery Compilation

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.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Promise of Graph Sparsification and Decomposition for Noise Reduction in QAOA: Analysis for Trapped-Ion Compilations

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.

Moondra, Jai [Georgia Institute of Technology]↗

DOE OSTI2017

Domain Specific Language Support for Exascale

A multi-institutional project known as D-TEC (short for “Domain- specific Technology for Exascale Computing”) set out to explore technologies to support the construction of Domain Specific Languages (DSLs) to map application programs to exascale architectures. DSLs employ automated code transformation to shift the burden of delivering portable performance from application programmers to compilers. Two chief properties contribute: DSLs permit expression at a high level of abstraction so that a programmer’s intent is clear to a compiler and DSL implementations encapsulate human domain-specific optimization knowledge so that a compiler can be smart enough to achieve good results on specific hardware. Domain specificity is what makes these properties possible in a programming language. If leveraging domain specificity is the key to keep exascale software tractable, a corollary is that many different DSLs will be needed to encompass the full range of exascale computing applications; moreover, a single application may well need to use several different DSLs in conjunction. As a result, developing a general toolkit for building domain-specific languages was a key goal for the D-TEC project. Different aspects of the D-TEC research portfolio were the focus of work at each of the partner institutions in the multi-institutional project. D-TEC research and development work at Rice University focused on on three principal topics: understanding how to automate the tuning of code for complex architectures, research and development of the Rosebud DSL engine, and compiler technology to support complex execution platforms. This report provides a summary of the research and development work on the D-TEC project at Rice University.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Static versioning in the polyhedral model

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.

Meister, Benoit J.↗

DOE OSTI2015

Optimizing Irregular Applications for Energy and Performance on the Tilera Many-core Architecture

Optimizing applications simultaneously for energy and performance is a complex problem. High performance, parallel, irregular applications are notoriously hard to optimize due to their data-dependent memory accesses, lack of structured locality and complex data structures and code patterns. Irregular kernels are growing in importance in applications such as machine learning, graph analytics and combinatorial scientific computing. Performance- and energy-efficient implementation of these kernels on modern, energy efficient, multicore and many-core platforms is therefore an important and challenging problem. We present results from optimizing two irregular applications { the Louvain method for community detection (Grappolo), and high-performance conjugate gradient (HPCCG) { on the Tilera many-core system. We have significantly extended MIT's OpenTuner auto-tuning framework to conduct a detailed study of platform-independent and platform-specific optimizations to improve performance as well as reduce total energy consumption. We explore the optimization design space along three dimensions: memory layout schemes, compiler-based code transformations, and optimization of parallel loop schedules. Using auto-tuning, we demonstrate whole node energy savings of up to 41% relative to a baseline instantiation, and up to 31% relative to manually optimized variants.

irregular applications, energy opttimization, many↗

DOE OSTI2020

Compiler and Runtime Approaches to Enable Large-Scale Irregular Programs. Final report, July 2013 - July 2019

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.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1983

Use of CYBER 203 and CYBER 205 computers for three-dimensional transonic flow calculations

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.

Melson, N. D.↗

NASA NTRS1982

Experiences in using the CYBER 203 for three-dimensional transonic flow calculations

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.

Melson, N. D.↗

NASA NTRS1998

An Atmospheric General Circulation Model with Chemistry for the CRAY T3E: Design, Performance Optimization and Coupling to an Ocean Model

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.

Farrara, John D.↗

NASA NTRS1989

Parallel processing of real-time dynamic systems simulation on OSCAR (Optimally SCheduled Advanced multiprocessoR)

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.

Kasahara, Hironori↗

DOE OSTI2023

A Verified Optimizer for Quantum Circuits

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.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Inference-Engine v0.1.0

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.

Rouson, Damian↗

DOE OSTI2025

A time-parallel multiple-shooting method for large-scale quantum optimal control

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.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2017

Snowflake: A Lightweight Portable Stencil DSL

Stencil computations are not well optimized by general-purpose production compilers and the increased use of multicore, manycore, and accelerator-based systems makes the optimization problem even more challenging. In this paper we present Snowflake, a Domain Specific Language (DSL) for stencils that uses a 'micro-compiler' approach, i.e., small, focused, domain-specific code generators. The approach is similar to that used in image processing stencils, but Snowflake handles the much more complex stencils that arise in scientific computing, including complex boundary conditions, higher-order operators (larger stencils), higher dimensions, variable coefficients, non-unit-stride iteration spaces, and multiple input or output meshes. Snowflake is embedded in the Python language, allowing it to interoperate with popular scientific tools like SciPy and iPython; it also takes advantage of built-in Python libraries for powerful dependence analysis as part of a just-in-time compiler. We demonstrate the power of the Snowflake language and the micro-compiler approach with a complex scientific benchmark, HPGMG, that exercises the generality of stencil support in Snowflake. By generating OpenMP comparable to, and OpenCL within a factor of 2x of hand-optimized HPGMG, Snowflake demonstrates that a micro-compiler can support diverse processor architectures and is performance-competitive whilst preserving a high-level Python implementation.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2016

Kokkos GPU Compiler

The Kokkos Clang compiler is a version of the Clang C++ compiler that has been modified to perform targeted code generation for Kokkos constructs in the goal of generating highly optimized code and to provide semantic (domain) awareness throughout the compilation toolchain of these constructs such as parallel for and parallel reduce. This approach is taken to explore the possibilities of exposing the developer’s intentions to the underlying compiler infrastructure (e.g. optimization and analysis passes within the middle stages of the compiler) instead of relying solely on the restricted capabilities of C++ template metaprogramming. To date our current activities have focused on correct GPU code generation and thus we have not yet focused on improving overall performance. The compiler is implemented by recognizing specific (syntactic) Kokkos constructs in order to bypass normal template expansion mechanisms and instead use the semantic knowledge of Kokkos to directly generate code in the compiler’s intermediate representation (IR); which is then translated into an NVIDIA-centric GPU program and supporting runtime calls. In addition, by capturing and maintaining the higher-level semantics of Kokkos directly within the lower levels of the compiler has the potential for significantly improving the ability of the compiler to communicate with the developer in the terms of their original programming model/semantics.

Moss, Nicholas↗

DOE OSTI2016

Kokkos GPU Compiler

Moss, Nicholas↗

DOE OSTI2023

Accelerating x-ray tracing for exascale systems using Kokkos

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.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

Combining constraint satisfaction and local improvement algorithms to construct anaesthetists' rotas

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.

Smith, Barbara M.↗