Combined On/Off Node Performance Model for SPMV in Multigrid
Explore the source record for details and available documents.
Siefert, Christopher↗
SEARCH · Search NASA
Results for “SpMV”
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.
PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications
Iterative memory-bound solvers commonly occur in HPC codes. Typical GPU implementations have a loop on the host side that invokes the GPU kernel as much as time/algorithm steps there are. The termination of each kernel implicitly acts the barrier required after advancing the solution every time step. We propose an execution model for running memory-bound iterative GPU kernels: PERsistent KernelS (PERKS). In this model, the time loop is moved inside persistent kernel, and device-wide barriers are used for synchronization. We then reduce the traffic to device memory by caching subset of the output in each time step in the unused registers and shared memory. PERKS can be generalized to any iterative solver: they largely independent of the solver's implementation. We explain the design principle of PERKS and demonstrate effectiveness of PERKS for a wide range of iterative 2D/3D stencil benchmarks (geomean speedup of 2.12x for 2D stencils and 1.24x for 3D stencils over state-of-art libraries), and a Krylov subspace conjugate gradient solver (geomean speedup of 4.86x in smaller SpMV datasets from SuiteSparse and 1.43x in larger SpMV datasets over a state-of-art library). All PERKS-based implementations available at: https://github.com/neozhang307/PERKS.
Zhang, Lingqi↗
Large language model evaluation for high–performance computing software development
We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.
97 MATHEMATICS AND COMPUTING↗
Accelerating matrix-centric graph processing on GPUs through bit-level optimizations
Even though it is well known that binary values are common in graph applications (e.g., adjacency matrix), how to leverage the phenomenon for efficiency has not yet been adequately explored. This paper presents a systematic study on how to unlock the potential of the bit-level optimizations of graph computations that involve binary values. It proposes a two-level representation named Bit-Block Compressed Sparse Row (B2SR) and presents a series of optimizations to the graph operations on B2SR by the intrinsics of modern GPUs. It additionally introduces Deep Reinforcement Learning (DRL) as an efficient way to best configure the bit-level optimizations on the fly. Additionally, the DQN-based adaptive tile size selector with dedicated model training can reach 68% prediction accuracy. Evaluations on NVIDIA Pascal and Volta GPUs show that the optimizations bring up to 40× and 6555× for essential GraphBLAS kernels SpMV and SpGEMM, respectively, making GraphBLAS-based BFS accelerate up to 433×, SSSP, PR, and CC up to 35×, and TC up to 52×.
79 ASTRONOMY AND ASTROPHYSICS↗
Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation
We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.
Godoy, William↗
Genetics and Genomics of Pathogen Resistance in Switchgrass (Final Report)
This project was funded by DOE under Grant no. DE-SC0016108. Originally approved for the 2016-2019 period, two no-cost extensions were solicited and approved, which prolonged the lifespan through July 2021. This final report informs on the results obtained so far from the research implemented. The research hinged on integrating genomics (genomic selection, RNAseq, virus-plant interactions) with classical genetics (conventional breeding) to incorporate durable resistance to fungal (rust) and viral (mosaic) diseases in switchgrass (Panicum virgatum) populations being bred for bioenergy. Higher biomass yield, higher quality (low lignin content), and durable disease resistance are key features to make lignocellulosic switchgrass feedstocks economically competitive and sustainable. Genomic selection is being applied on three generations of a switchgrass population derived from crossing two ecotypes (Kanlow as lowland female and Summer as upland male) with differential performance in terms of biomass yield and quality, disease resistance, and winter survivability. Target populations were screened for rust and mosaic in field and/or lab and phenotyped for biomass yield and quality traits. Genetic analyses were applied across generations to capture the joint inheritance of the targeted traits and predict breeding values for parents and progeny with greater accuracy. Parental and a panel of different switchgrass populations were genotyped with the DArTseq technology to develop SNP (0, 1, 2) and in-silico (presence/absence) DArT markers. Rust inoculations techniques were developed and applied successfully on switchgrass. The original populations (Kanlow and Summer) were sequenced with RNAseq to capture the gene expression profiles across sequential time-points and appraise the basis of greater resistance in the Kanlow vs the Summer ecotype. Constructs of PMV and sPMV mosaic virus were assembled and tested first on proso millet to find the best protocol to use later on switchgrass. Results from the preliminary analyses indicate that 1) ample additive genetic variation is available for selection and improving this inter-ecotypic population for yield, quality, and disease traits, 2) significant gains are to be expected with the genetic correlations being favorable between yield and lignin content and between yield and disease ratings, 3) substantial differences exist in the genetic regions controlling rust resistance in the two ecotypes, 4) co-infection with PMV isolates from Nebraska and its satellite from Kansas elicit severe mosaic symptoms, and 5) two different genetic systems are responsible for imparting resistance to rust and virus in switchgrass.
59 BASIC BIOLOGICAL SCIENCES↗
Providing performance portable numerics for Intel GPUs
Summary With discrete Intel GPUs entering the high‐performance computing landscape, there is an urgent need for production‐ready software stacks for these platforms. In this article, we report how we enable the Ginkgo math library to execute on Intel GPUs by developing a kernel backed based on the DPC++ programming environment. We discuss conceptual differences between the CUDA and DPC++ programming models and describe workflows for simplified code conversion. We evaluate the performance of basic and advanced sparse linear algebra routines available in Ginkgo's DPC++ backend in the hardware‐specific performance bounds and compare against routines providing the same functionality that ship with Intel's oneMKL vendor library.
97 MATHEMATICS AND COMPUTING↗