Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Memory benchmark”

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.

At least 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

CLOMP v1.5

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading. For simplicity, it does not use MPI by default but it is expected to be run on the resources a threaded MPI task would use (e.g., a portion of a shared memory compute node). Compiling with -DWITH_MPI allows packing one or more nodes with CLOMP tasks and having CLOMP report OpenMP performance for the slowest MPI task. On current systems, the strong scaling performance results for 4, 8, or 16 threads are of the most interest. Suggested weak scaling inputs are provided for evaluating future systems. Since MPI is often used to place at least one MPI task per coherence or NUMA domain, it is recommended to focus OpenMP runtime measurements on a subset of node hardware where it is most possible to have low OpenMP overheads (e.g., within one coherence domain or NUMA domain).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Investigation of the OECD/NEA PWR MOX/UO{sub 2} core transient benchmark using a coupled whole core pin-by-pin route in WIMS

This paper investigates the new CAMELOT coupling route developed in WIMS, which uses prepared tabulated cross-sections combined with the flux solver MERLIN module and the integrated sub-channel thermal hydraulics solver ARTHUR module to solve for the coupled core state. This coupling route is applied to the OECD/NEA pressurized water reactor (PWR) core transient benchmark exercise, involving 3-D neutronics and thermal-hydraulics analysis of a full-sized PWR core featuring MOX fuel at various core states, as well as simulating a control rod ejection transient. Analysis of the results for each part of the benchmark demonstrate that the high-resolution pin-by-pin analysis used in WIMS closely matches the other participants in the benchmark, with differences of between 20-200 pcm for k-effective, 1-2.5% RMS difference for assembly-averaged powers, 2-8% difference in rod worth calculations, < 200 ppm for calculations of critical boron concentration, zero difference in delayed neutron fraction calculation and a very close match for power response to the rod ejection transient. This is the first application of the WIMS-CAMELOT approach for the transient analysis of a full-sized reactor and as such further improvements such as reducing computational cost through parallelization, optimisation and memory reduction, are currently in active development. This paper demonstrates the accuracy and flexibility of the CAMELOT coupling route, providing a straightforward and consistent user image that can be easily used for a variety of modelling problems involving coupled neutronics and thermal-hydraulics. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Pre-conditioned BFGS-based uncertainty quantification in elastic full-waveform inversion

SUMMARY Full-waveform inversion has become an essential technique for mapping geophysical subsurface structures. However, proper uncertainty quantification is often lacking in current applications. In theory, uncertainty quantification is related to the inverse Hessian (or the posterior covariance matrix). Even for common geophysical inverse problems its calculation is beyond the computational and storage capacities of the largest high-performance computing systems. In this study, we amend the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm to perform uncertainty quantification for large-scale applications. For seismic inverse problems, the limited-memory BFGS (L-BFGS) method prevails as the most efficient quasi-Newton method. We aim to augment it further to obtain an approximate inverse Hessian for uncertainty quantification in FWI. To facilitate retrieval of the inverse Hessian, we combine BFGS (essentially a full-history L-BFGS) with randomized singular value decomposition to determine a low-rank approximation of the inverse Hessian. Setting the rank number equal to the number of iterations makes this solution efficient and memory-affordable even for large-scale problems. Furthermore, based on the Gauss–Newton method, we formulate different initial, diagonal Hessian matrices as pre-conditioners for the inverse scheme and compare their performances in elastic FWI applications. We highlight our approach with the elastic Marmousi benchmark model, demonstrating the applicability of pre-conditioned BFGS for large-scale FWI and uncertainty quantification.

58 GEOSCIENCES↗
DOE OSTI2019

PPT-GPU: Scalable GPU Performance Modeling

Performance modeling is a challenging problem due to the complexities of hardware architectures. In this paper, we present PPT-GPU, a scalable and accurate simulation framework that enables GPU code developers and architects to predict the performance of applications in a fast, and accurate manner on different GPU architectures. PPT-GPU is part of the open source project, Performance Prediction Toolkit (PPT) developed at the Los Alamos National Laboratory. We extend the old GPU model in PPT that predict the runtimes of computational physics codes to offer better prediction accuracy, for which, we add models for different memory hierarchies found in GPUs and latencies for different instructions. To further show the utility of PPT-GPU, we compare our model against real GPU device(s) and the widely used cycle-accurate simulator, GPGPU-Sim using different workloads from RODINIA and Parboil benchmarks. The results indicate that the predicted performance of PPT-GPU is within a 10% error compared to the real device(s). In addition, PPT-GPU is highly scalable, where it is up to 450x faster than GPGPU-Sim with more accurate results.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Speed and Memory Improvements to MCNP6 Delayed-Gamma Line Treatment

The delayed-gamma (DG) line-emission (line) sampling was first introduced into MCNPX in 2005. At the time, storage demands for problems with large numbers of DG lines was a major concern. In order to accommodate large amounts of line data while keeping the memory footprint of such a problem from exceeding memory limits, complicated logic was included to sift through various storage options. In mid-2015 concerns arose over the adequacy of the MCNP6 DG source option (inherited from MCNPX) with line sampling for modeling high-fidelity problems. One indication that there was a problem came when studying the MCNP6 produced DG spectra of U-238 and its progeny using high-fidelity spectroscopic tallies when compared to DG line amplitudes directly from ENDF/B-VII.1 emission data. Despite producing a correct integral number of gammas, the comparison to ENDF data showed a broadening in the energy lines and a reduction in the amplitude of more prominent lines. It was later found that the cause of this broadening was one of the memory-saving techniques used to store DG line data when problems required many DG lines. Specifically, the DG lines were integrated into fine energy bins for sampling. When a DG line was to be sampled, a random number would be used to choose which energy bin to sample based on emission probability. Once chosen, a second random number was used to perform nearest-line sampling in that bin. The integration of lines led to an oversampling of low-probability lines, especially when in close proximity to high-probability lines. This treatment also caused a similar issue with the time-dependent behavior of DG line emission which occurred when low-probability lines were sampled near high probability lines with the former decay constant being used. The effect on time-dependent gamma production was demonstrated in analytic benchmarks performed by Weldon et al.. To address these issues a new gamma line storage and sampling treatment was introduced in 2015. This new treatment, stores gamma emission data in a line-by-line CDF which is sampled directly, thereby resolving both the line-broadening issue, and the time-dependence issue as was demonstrated by Tutt el al.. In addition, the new DG sampling treatment was written to use dynamically dimensioned storage arrays as opposed to large fixed-dimensioned arrays, as in the former treatment, and also makes more efficient use of line data that is stored by reducing or eliminating repeated data. As a result, storage arrays are generated only for DG data relevant to the problem being executed. The result should be a reduction in both memory requirements and runtime. However, these reductions could not be realized until the logic for the old treatment could be removed. This paper provides an update on recent work which has focused on the removal of the old DG sampling logic and attempts to quantify the memory reduction and speed up of selected problems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Uncertainty-Guided Prediction Horizon of Phase-Resolved Ocean Wave Forecasting Under Data Sparsity: Experimental and Numerical Evaluation

Accurate short-term wave forecasting is critical for the safe and efficient operation of marine structures that rely on real-time, phase-resolved ocean wave information for control and monitoring purposes (e.g., digital twins). These systems often depend on environmental sensors (e.g., waverider buoys, wave-sensing LIDAR). Challenges arise when upstream sensor data are missing, sparse, or phase-shifted due to drift. This study investigates the performance of two machine learning models, time-series dense encoder (TiDE) and long short-term memory (LSTM), for forecasting phase-resolved ocean surface elevations under varying degrees of data degradation. We introduce the τ-trimming algorithm, which adapts the prediction horizon based on uncertainty thresholds derived from historical forecasts. Numerical wave tank (NWT) and wave basin experiments are used to benchmark model performance under short- and long-term data masking, spatially coarse sensor grids, and upstream phase shifts. Results show under a 50% probability of upstream data loss, the τ-trimmed TiDE model achieves a 46% reduction in error at the most upstream target, compared to 22% for LSTM. Furthermore, phase misalignment in upstream data introduces a near-linear increase in forecast error. Under moderate model settings, a ±3 s misalignment increases the mean absolute error by approximately 0.5 m, while the same error is accumulated at ±4 s using the more conservative approach. These findings inform the design of resilient, uncertainty-aware wave forecasting systems suited for realistic offshore sensing environments.

42 ENGINEERING↗
DOE OSTI2023

Quantum Logic Enhanced Sensing in Solid-State Spin Ensembles

We demonstrate quantum logic enhanced sensitivity for a macroscopic ensemble of solid-state, hybrid two-qubit sensors. We achieve over a factor of 30 improvement in the single-shot signal-to-noise ratio, translating to an ac magnetic field sensitivity enhancement exceeding an order of magnitude for time-averaged measurements. Using the electronic spins of nitrogen vacancy (NV) centers in diamond as sensors, we leverage the on-site nitrogen nuclear spins of the NV centers as memory qubits, in combination with homogeneous and stable bias and control fields, ensuring that all of the ~10 9 two-qubit sensors are sufficiently identical to permit global control of the NV ensemble spin states. We find quantum logic sensitivity enhancement for multiple measurement protocols with varying optimal sensing intervals, including XY8 and DROID-60 dynamical decoupling, as well as correlation spectroscopy, using an applied ac magnetic field signal. The results are independent of the nature of the target signal and broadly applicable to measurements using NV centers and other solid-state spin ensembles. Furthermore, this work provides a benchmark for macroscopic ensembles of quantum sensors that employ quantum logic or quantum error correction algorithms for enhanced sensitivity.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2005

Parallelization of Lower-Upper Symmetric Gauss-Seidel Method for Chemically Reacting Flow

Development of technologies for exploration of the solar system has revived an interest in computational simulation of chemically reacting flows since planetary probe vehicles exhibit non-equilibrium phenomena during the atmospheric entry of a planet or a moon as well as the reentry to the Earth. Stability in combustion is essential for new propulsion systems. Numerical solution of real-gas flows often increases computational work by an order-of-magnitude compared to perfect gas flow partly because of the increased complexity of equations to solve. Recently, as part of Project Columbia, NASA has integrated a cluster of interconnected SGI Altix systems to provide a ten-fold increase in current supercomputing capacity that includes an SGI Origin system. Both the new and existing machines are based on cache coherent non-uniform memory access architecture. Lower-Upper Symmetric Gauss-Seidel (LU-SGS) relaxation method has been implemented into both perfect and real gas flow codes including Real-Gas Aerodynamic Simulator (RGAS). However, the vectorized RGAS code runs inefficiently on cache-based shared-memory machines such as SGI system. Parallelization of a Gauss-Seidel method is nontrivial due to its sequential nature. The LU-SGS method has been vectorized on an oblique plane in INS3D-LU code that has been one of the base codes for NAS Parallel benchmarks. The oblique plane has been called a hyperplane by computer scientists. It is straightforward to parallelize a Gauss-Seidel method by partitioning the hyperplanes once they are formed. Another way of parallelization is to schedule processors like a pipeline using software. Both hyperplane and pipeline methods have been implemented using openMP directives. The present paper reports the performance of the parallelized RGAS code on SGI Origin and Altix systems.

Yoon, Seokkwan↗
NASA NTRS1996

I/O-Efficient Scientific Computation Using TPIE

In recent years, input/output (I/O)-efficient algorithms for a wide variety of problems have appeared in the literature. However, systems specifically designed to assist programmers in implementing such algorithms have remained scarce. TPIE is a system designed to support I/O-efficient paradigms for problems from a variety of domains, including computational geometry, graph algorithms, and scientific computation. The TPIE interface frees programmers from having to deal not only with explicit read and write calls, but also the complex memory management that must be performed for I/O-efficient computation. In this paper we discuss applications of TPIE to problems in scientific computation. We discuss algorithmic issues underlying the design and implementation of the relevant components of TPIE and present performance results of programs written to solve a series of benchmark problems using our current TPIE prototype. Some of the benchmarks we present are based on the NAS parallel benchmarks while others are of our own creation. We demonstrate that the central processing unit (CPU) overhead required to manage I/O is small and that even with just a single disk, the I/O overhead of I/O-efficient computation ranges from negligible to the same order of magnitude as CPU time. We conjecture that if we use a number of disks in parallel this overhead can be all but eliminated.

Vengroff, Darren Erik↗
NASA NTRS2004

Validation of CFD/Heat Transfer Software for Turbine Blade Analysis

I am an intern in the Turbine Branch of the Turbomachinery and Propulsion Systems Division. The division is primarily concerned with experimental and computational methods of calculating heat transfer effects of turbine blades during operation in jet engines and land-based power systems. These include modeling flow in internal cooling passages and film cooling, as well as calculating heat flux and peak temperatures to ensure safe and efficient operation. The branch is research-oriented, emphasizing the development of tools that may be used by gas turbine designers in industry. The branch has been developing a computational fluid dynamics (CFD) and heat transfer code called GlennHT to achieve the computational end of this analysis. The code was originally written in FORTRAN 77 and run on Silicon Graphics machines. However the code has been rewritten and compiled in FORTRAN 90 to take advantage of more modem computer memory systems. In addition the branch has made a switch in system architectures from SGI's to Linux PC's. The newly modified code therefore needs to be tested and validated. This is the primary goal of my internship. To validate the GlennHT code, it must be run using benchmark fluid mechanics and heat transfer test cases, for which there are either analytical solutions or widely accepted experimental data. From the solutions generated by the code, comparisons can be made to the correct solutions to establish the accuracy of the code. To design and create these test cases, there are many steps and programs that must be used. Before a test case can be run, pre-processing steps must be accomplished. These include generating a grid to describe the geometry, using a software package called GridPro. Also various files required by the GlennHT code must be created including a boundary condition file, a file for multi-processor computing, and a file to describe problem and algorithm parameters. A good deal of this internship will be to become familiar with these programs and the structure of the GlennHT code. Additional information is included in the original extended abstract.

Kiefer, Walter D.↗
DOE OSTI2017

Deploy Nalu/Kokkos algorithmic infrastructure with performance benchmarking.

The former Nalu interior heterogeneous algorithm design, which was originally designed to manage matrix assembly operations over all elemental topology types, has been modified to operate over homogeneous collections of mesh entities. This newly templated kernel design allows for removal of workset variable resize operations that were formerly required at each loop over a Sierra ToolKit (STK) bucket (nominally, 512 entities in size). Extensive usage of the Standard Template Library (STL) std::vector has been removed in favor of intrinsic Kokkos memory views. In this milestone effort, the transition to Kokkos as the underlying infrastructure to support performance and portability on many-core architectures has been deployed for key matrix algorithmic kernels. A unit-test driven design effort has developed a homogeneous entity algorithm that employs a team-based thread parallelism construct. The STK Single Instruction Multiple Data (SIMD) infrastructure is used to interleave data for improved vectorization. The collective algorithm design, which allows for concurrent threading and SIMD management, has been deployed for the core low-Mach element- based algorithm. Several tests to ascertain SIMD performance on Intel KNL and Haswell architectures have been carried out. The performance test matrix includes evaluation of both low- and higher-order methods. The higher-order low-Mach methodology builds on polynomial promotion of the core low-order control volume nite element method (CVFEM). Performance testing of the Kokkos-view/SIMD design indicates low-order matrix assembly kernel speed-up ranging between two and four times depending on mesh loading and node count. Better speedups are observed for higher-order meshes (currently only P=2 has been tested) especially on KNL. The increased workload per element on higher-order meshes bene ts from the wide SIMD width on KNL machines. Combining multiple threads with SIMD on KNL achieves a 4.6x speedup over the baseline, with assembly timings faster than that observed on Haswell architecture. The computational workload of higher-order meshes, therefore, seems ideally suited for the many-core architecture and justi es further exploration of higher-order on NGP platforms. A Trilinos/Tpetra-based multi-threaded GMRES preconditioned by symmetric Gauss Seidel (SGS) represents the core solver infrastructure for the low-Mach advection/diffusion implicit solves. The threaded solver stack has been tested on small problems on NREL's Peregrine system using the newly developed and deployed Kokkos-view/SIMD kernels. fforts are underway to deploy the Tpetra-based solver stack on NERSC Cori system to benchmark its performance at scale on KNL machines.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1994

High Performance Programming Using Explicit Shared Memory Model on the Cray T3D

The Cray T3D is the first-phase system in Cray Research Inc.'s (CRI) three-phase massively parallel processing program. In this report we describe the architecture of the T3D, as well as the CRAFT (Cray Research Adaptive Fortran) programming model, and contrast it with PVM, which is also supported on the T3D We present some performance data based on the NAS Parallel Benchmarks to illustrate both architectural and software features of the T3D.

Saini, Subhash↗
DOE OSTI2025

Atomic Structure, Dynamics, Changes in Chemical Bonding and Semiconductor-Metal Transition in Sb 2 Se 3 : A Remarkable Material for Quantum Networks and Energy Applications

Antimony sesquiselenide has become an outstanding functional material for photovoltaics, energy storage and transformation, memory and photonic applications. Sb 2 Se 3 is one of the most successful emerging solar light absorbers and has also been identified as a highly promising ultralow-loss phase-change material (PCM) for next-generation coherent nanophotonic processors, photonic tensor cores, quantum and neuromorphic networks. Unlike benchmark telluride PCMs, Sb 2 Se 3 features a quasi-one-dimensional (1D) crystalline structure consisting of (Sb 4 Se 6 ) ∞ ribbons, lacks the typical PCM chemical bonding, and undergoes an extended semiconductor-metal transition above the melting point. Consequently, the origin of high optical contrast between crystalline (SET) and amorphous (RESET) logic states remains elusive and presents a significant challenge. Using high-energy X-ray diffraction and Raman spectroscopy over a wide temperature range, supported by first-principles simulations and complemented by thermal, optical and electrical measurements, as well as by 121 Sb-Mossbauer spectroscopy, the quasi-1D network of orthorhombic antimony sesquiselenide was found to undergo significant evolution in amorphous and supercooled Sb 2 Se 3 , leading to lower coordination, shorter interatomic distances and a higher p-electron density on antimony, indicating changes in chemical bonding. The observed novel Sb 2 Se 3 nanocrystalline polymorph, characterized by trigonal antimony coordination and more isolated Sb-Se ribbons, could help reduce multiple trapping defect states in the bandgap, which are typical of orthorhombic Sb 2 Se 3 , thereby enhancing the power-conversion efficiency of photovoltaic devices. Semimetallic and metallic liquid Sb 2 Se 3 exhibit a gradual transformation into a denser 2D and/or 3D network with higher antimony coordination. Localized electron states in the pseudogap are becoming extended, leading to an increase in electronic conductivity σ following the relationship σ ∝ N(E F ) 2 . Liquid Sb 2 Se 3 also appears to be strongly fragile, with a nonmonotonic change in viscosity and higher atomic mobility in the metallic liquid. Furthermore, these results explain extraordinary functionalities of Sb 2 Se 3 for photonic and energy applications.

antimony↗
DOE OSTI2017

Block-Parallel Data Analysis with DIY2

DIY2 is a programming model and runtime for block-parallel analytics on distributed-memory machines. Its main abstraction is block-structured data parallelism: data are decomposed into blocks; blocks are assigned to processing elements (processes or threads); computation is described as iterations over these blocks, and communication between blocks is defined by reusable patterns. By expressing computation in this general form, the DIY2 runtime is free to optimize the movement of blocks between slow and fast memories (disk and flash vs. DRAM) and to concurrently execute blocks residing in memory with multiple threads. This enables the same program to execute in-core, out-of-core, serial, parallel, single-threaded, multithreaded, or combinations thereof. This paper describes the implementation of the main features of the DIY2 programming model and optimizations to improve performance. DIY2 is evaluated on benchmark test cases to establish baseline performance for several common patterns and on larger complete analysis codes running on large-scale HPC machines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for the monsoon region. We develop a deep neural network composed of a convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against the GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including (1) quantile mapping, (2) the support vector machine, and (3) the convolutional neural network. To test the robustness of the model and its applicability in practical forecasting, we apply the trained network for precipitation prediction forced by retrospective forecasts from the ECMWF model. Compared to the ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead times from 1 day up to 2 weeks. This superiority decreases with the forecast lead time, as the GCM’s skill in predicting atmospheric dynamics is diminished by the chaotic effect. Finally, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is only slightly worse than the observed precipitation forced simulation (NSE = 0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Rapid Memory Footprint Access Diagnostics

Footprint and reuse distance measure temporal locality and therefore do not capture the significance of access patterns (spacial locality). A strided access pattern has the largest possible footprint but usually has the best performance. To highlight exposed memory latency, we separate footprint into strided (prefetchable) and irregular (non-prefetchable) access components and calculate the growth rate of each. To rapidly compute these footprint access diagnostics, we present two methods, whole-program and precise. Current footprint analyses can cause 200× or more slowdown with realistic inputs and are therefore impractical. Our whole-program method reduces the overhead to 10% by computing upper bounds, but still yields inter-procedural insight through a call path profile. Our precise method uses additional static analysis and profiling to refine the upper bounds for intra-procedural loop nests. We evaluate our approaches using benchmarks that vary access patterns (strided \vs unpredictable), sparsity (all words in a cache line \vs some), and reuse (varying and repeated accesses per element). Notably, for loop nests with unpredictable accesses, the precise method's accuracy is within 10% of ideal. The whole-program method has sufficient accuracy to diagnose bottlenecks.

data locality, memory footprint, footprint access ↗