Just-in-time Length Specialization of Dynamic Vector Code

Accelerating program performance via short SIMD vector units is very common in modern processors, as evidenced by the use of SSE, MMX, and AltiVec SIMD instructions in multimedia, scientific, and embedded applications. To take full advantage of the vector capabilities, a compiler needs to generate efficient vector code automatically. However, most commercial and open-source compilers still fall short of using the full potential of vector units, and only generate vector code for simple loop nests. In this poster, we present the design and implementation of an auto-vectorization framework in the back-end of a dynamic compiler that not only generates optimized vector code but is also well integrated with the instruction scheduler and register allocator. Additionally, we describe a vector instruction selection algorithm based on dynamic programming. Our results obtained in JikesRVM dynamic compilation environment show performance improvement of up to 57.71% on an Intel Xeon processor, compared to non-vectorized execution.

Code optimization is an intricate task that is getting more complex as computing systems evolve. Managing the program optimization process, including the implementation and evaluation of code variants, is tedious, inefficient, and errors are likely to be introduced in the process. Moreover, because each platform typically requires a different sequence of transformations to fully harness its computing power, the optimization process complexity grows as new platforms are adopted. To address these issues, systems and frameworks have been proposed to automate the code optimization process. They, however, have not been widely adopted and are primarily used by experts with deep knowledge about underlying architecture and compiler intricacies. This article describes the requirements that we believe necessary for making automatic performance tuning more broadly used, especially in complex, long-lived high-performance computing applications. Besides discussing limitations of current systems and strategies to overcome these, we describe the design of a system that is able to semi-automatically generate efficient platform-specific code. In the proposed system, the code optimization is programmer-guided, separately from application code, on an external file in what we call optimization programming. The language to program the optimization process is able to represent complex collections of transformations and, as a result, generate efficient platform-specific code. A database manages different optimized versions of code regions, providing a pragmatic approach to performance portability, and the framework itself has separate components, allowing the optimized code to be used on systems without installing all of the modules required for the code generation. We present experiments on two different platforms to illustrate the generation of efficient platform-specific code that performs comparable to hand-optimized, vendor-provided code.

Bit-serial processing-in-memory (PIM) architectures have been extensively studied, yet a standardized tool for generating efficient bit-serial code is lacking, hindering fair comparisons. We present a fully automated compiler framework, PIMsynth, for bit-serial PIM architectures, targeting both digital and analog substrates. The compiler takes Verilog as input and generates optimized micro-operation code for programmable bit-serial PIM backends. Our flow integrates logic synthesis, optimization steps, instruction scheduling, and backend code generation into a unified toolchain. With the compiler, we provide a bit-serial compilation benchmark suite designed for efficient bit-serial code generation. To enable correctness and performance validation, we extend an existing PIM simulator to support compiler-generated micro-op-level workloads. Preliminary results demonstrate that the compiler generates competitive bit-serial code within <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1.08\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1.54\times$</tex-math></inline-formula> of hand-optimized digital and analog PIM baselines. Our code is publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/UVA-LavaLab/PIMsynth</uri>.

Integrating user knowledge with information from parallelisation tools to facilitate the automatic generation of efficient parallel FORTRAN code

BackgroundThe distribution of resources can affect animal range sizes, which in turn may alter infectious disease dynamics in heterogenous environments. The risk of pathogen exposure or the spatial extent of outbreaks may vary with host range size. This study examined the range sizes of herbivorous anthrax host species in two ecosystems and relationships between spatial movement behavior and patterns of disease outbreaks for a multi-host environmentally transmitted pathogen.MethodsWe examined range sizes for seven host species and the spatial extent of anthrax outbreaks in Etosha National Park, Namibia and Kruger National Park, South Africa, where the main host species and outbreak sizes differ. We evaluated host range sizes using the local convex hull method at different temporal scales, within-individual temporal range overlap, and relationships between ranging behavior and species contributions to anthrax cases in each park. We estimated the spatial extent of annual anthrax mortalities and evaluated whether the extent was correlated with case numbers of a given host species.ResultsRange size differences among species were not linearly related to anthrax case numbers. In Kruger the main host species had small range sizes and high range overlap, which may heighten exposure when outbreaks occur within their ranges. However, different patterns were observed in Etosha, where the main host species had large range sizes and relatively little overlap. The spatial extent of anthrax mortalities was similar between parks but less variable in Etosha than Kruger. In Kruger outbreaks varied from small local clusters to large areas and the spatial extent correlated with case numbers and species affected. Secondary host species contributed relatively few cases to outbreaks; however, for these species with large range sizes, case numbers positively correlated with outbreak extent.ConclusionsOur results provide new information on the spatiotemporal structuring of ranging movements of anthrax host species in two ecosystems. The results linking anthrax dynamics to host space use are correlative, yet suggest that, though partial and proximate, host range size and overlap may be contributing factors in outbreak characteristics for environmentally transmitted pathogens.

Deep learning (DL) model training must address the memory bottleneck to continue scaling. Processing-in-memory approaches can be a viable solution as they move computations near or into the memory, reducing substantial data movement. However, to deploy applications on such hardware, end-to-end software support is crucial for efficient computation mapping and scheduling as well as extensible code generation, but no consideration has been made for DL training workloads. In this paper, we propose XLA-NDP, a compiler and runtime solution for NDPX, a near-data processing (NDP) architecture integrated with an existing DL training framework. XLA-NDP offloads NDPX kernels and schedules them to overlap with GPU kernels to maximize parallelism based on GPU and NDPX costs, while providing a template-based code generator with low-level optimizations. The experiments showed that XLA-NDP provides up to 1.41x speedup (1.24x on average) over the GPU baseline for four DL model training.

The source transformation tool for automatic differentiation of Fortran programs ADIFOR uses a preaccumulation technique to speed up tangent-linear codes significantly compared to the standard forward mode. Reverse mode automatic differentiation is applied to all scalar assignments to generate efficient code for the computation of local gradients. It has been well known for some time that reverse mode is not necessarily the optimal choice for the computation of these statement-level gradients as it does not minimize the number of operations required. This article presents an efficient algorithm for the solution of this combinatorial optimization problem. The corresponding software is freely available for downloading on our website. Developers of software for automatic differentiation are invited to integrate the algorithm into their tools. Gradients of scalar multivariate functions can be computed by elimination methods on the linearized computational graph. The combinatorial optimization problem that aims to minimize the number of arithmetic operations performed by the elimination algorithm is known to be NP-complete. In this article we present a polynomial algorithm for solving a relevant subclass of this problem's instances. The proposed method relies on the ability to compute vertex covers in bipartite graphs in polynomial time. A simplified version of this graph algorithm is used in a research prototype of the differentiation-enabled NAGWare Fortran compiler for the preaccumulation of local gradients of scalar assignments in the context of automatic generation of efficient tangent-linear code for numerical programs.

Predictions of realised fecundity and spawning time in Norwegian spring-spawning herring ( Clupea harengus)

Recent simulations have shown that the lack of resolution to be found in taxonomic relative to phylogenetic classification systems only slightly inflates the probability of Type 1 error (inappropriately rejecting the null hypothesis) in evolutionary comparative studies that take relatedness into account. Thus, on this basis, taxonomies may be expected to organize the data adequately for such studies when phylogenies are not available. However, phylogenies instigate particular rearrangements in plant classification that are not easily addressed by simulation, and an analysis of specific variables is used here to gain insight into the consistency of results when a large dataset is organized prior to analysis first with a taxonomy, and then with a phylogeny. This study examines commonness and rarity as it is measured by plant range size of species drawn from the floras of the islands of Great Britain and Crete. The data were restricted to native species of the main island of each group. Using a taxonomic classification of the data, both floras were investigated for the effect of range size on woodiness versus non-woodiness, and tree versus shrub life form. The flora of Great Britain was further examined for possible differences in range size due to overall plant size, and pollination and dispersal types. Using a phylogeny to organize the data, all of the same comparisons of growth form and mutualistic interactions were made for the flora of Great Britain, plus comparisons of cloning versus non-cloning, vining versus non-vining and reproductive schedule (annual, biennial and perennial). Although a phylogeny is the preferred tool for organizing that data, the results suggest that analyses using a taxonomy can lead to conclusions reliable across classification schemes. With either organizational system, trees had larger range sizes than shrubs, and wind-pollinated species had larger range sizes than related non-wind-pollinated species. Additional analyses also indicated that non-clonal plants are more widespread than related clonal species. Changes in the relative position and number of contrasts within comparisons indicate that the exact effect of using a phylogeny versus a taxonomy will depend on the distribution within the phylogeny of the trait being studied.

The purpose of this study was to determine and analyze the effect of workload and motivation on the performance of population and civil registration service employees in Makassar City. The type of research used is a quantitative descriptive research method, with 54 respondents. Data collection techniques used in this study were observation, questionnaires, and documentation. The data analysis technique used was statistical calculations through the Statistical for the Social Science (SPSS) version 22 application. This can be seen from the results of SPSS data processing where the workload variable (X1) has a t count of 1.868 while the t table is 1.675 and a sig value of 0.05. This shows that t count &gt; t table (1.868 &gt; 1.675) and sig value of 0.068 &gt; 0.05. This means that the workload variable has a positive but insignificant effect on employee performance. The motivation variable (X2) has a t count of 5.088 while the t table is 1.675 and a sig value of 0.05. This shows that the t count test &gt; t table (5.088 &gt; 1.675) and a sig value of 0.00 &lt; 0.05. This means that the motivation variable has a positive and significant effect on employee performance.

BackgroundA large language model is a type of artificial intelligence (AI) model that opens up great possibilities for health care practice, research, and education, although scholars have emphasized the need to proactively address the issue of unvalidated and inaccurate information regarding its use. One of the best-known large language models is ChatGPT (OpenAI). It is believed to be of great help to medical research, as it facilitates more efficient data set analysis, code generation, and literature review, allowing researchers to focus on experimental design as well as drug discovery and development.ObjectiveThis study aims to explore the potential of ChatGPT as a real-time literature search tool for systematic reviews and clinical decision support systems, to enhance their efficiency and accuracy in health care settings.MethodsThe search results of a published systematic review by human experts on the treatment of Peyronie disease were selected as a benchmark, and the literature search formula of the study was applied to ChatGPT and Microsoft Bing AI as a comparison to human researchers. Peyronie disease typically presents with discomfort, curvature, or deformity of the penis in association with palpable plaques and erectile dysfunction. To evaluate the quality of individual studies derived from AI answers, we created a structured rating system based on bibliographic information related to the publications. We classified its answers into 4 grades if the title existed: A, B, C, and F. No grade was given for a fake title or no answer.ResultsFrom ChatGPT, 7 (0.5%) out of 1287 identified studies were directly relevant, whereas Bing AI resulted in 19 (40%) relevant studies out of 48, compared to the human benchmark of 24 studies. In the qualitative evaluation, ChatGPT had 7 grade A, 18 grade B, 167 grade C, and 211 grade F studies, and Bing AI had 19 grade A and 28 grade C studies.ConclusionsThis is the first study to compare AI and conventional human systematic review methods as a real-time literature collection tool for evidence-based medicine. The results suggest that the use of ChatGPT as a tool for real-time evidence generation is not yet accurate and feasible. Therefore, researchers should be cautious about using such AI. The limitations of this study using the generative pre-trained transformer model are that the search for research topics was not diverse and that it did not prevent the hallucination of generative AI. However, this study will serve as a standard for future studies by providing an index to verify the reliability and consistency of generative AI from a user’s point of view. If the reliability and consistency of AI literature search services are verified, then the use of these technologies will help medical research greatly.

Abstract. We present a semantics for the statechart variant implemented in the Statemate product of i-Logix. Our semantics enables distributed code generation for Statemate models in the context of rapid prototyping for embedded control applications. We argue that it seems impossible to efficiently generate distributed code using the original Statemate semantics. The new, distributed semantics has the advantages that, first, it enables the generation of efficient distributed code, second, it preserves many aspects of the original semantics for those parts of a model that are not distributed, and third, the changes made regarding the interaction of distributed model parts are similar to the interaction between the model and its environment in the original semantics, thus giving designers a familiar execution model. The semantics has been implemented in Grace, a framework for rapid prototyping code generation for embedded control applications.

Modeling languages propose convenient abstractions and transformations to handle the complexity of today’s embedded systems. Based on the formalism of the Hierarchical State Machine, they enable the expression of hierarchical control parallelism. However, they face two important challenges when it comes to modeling data-intensive applications: no unified approach that also accounts for data-parallel actions and no effective code optimization and generation flows. We propose a modeling language extended with parallel action semantics and hierarchical indexed-state machines suitable for computationally intensive applications. Together with its formal semantics, we present an optimizing model compiler aiming for the generation of efficient data-parallel implementations.

This chapter considers a number of major issues that a telecom system house like Alcatel faces as a result of the trend towards DSP systems-on-chip using DSP-cores : the choice of the DSP-core architecture, the decision to use an off-the-shelf core or to develop an in-house core, the selection of the formalism in which the DSP software is developed, and the required tool support. In this analysis, an important focus of attention is whether the selected architecture and design-entry formalism allow efficient code generation in the near future, because these issues determine the success or failure of the introduction of a high-level language based methodology of DSP systems-on-chip. In addition, we present our view on the code generation problem itself.

Abiotic stress tolerance can explain range size and filling in temperate woody plants