اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFrom Physics Model to Results: An Optimizing Framework for Cross-Architecture Code Generation
138
0
0.0
(
0
)
تأليف
Marek Blazewicz
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute architectures. Chemora extends the capabilities of Cactus, facilitating the usage of large-scale CPU/GPU systems in an efficient manner for complex applications, without low-level code tuning. Chemora achieves parallelism through MPI and multi-threading, combining OpenMP and CUDA. Optimizations include high-level code transformations, efficient loop traversal strategies, dynamically selected data and instruction cache usage strategies, and JIT compilation of GPU code tailored to the problem characteristics. The discretization is based on higher-order finite differences on multi-block domains. Chemoras capabilities are demonstrated by simulations of black hole collisions. This problem provides an acid test of the framework, as the Einstein equations contain hundreds of variables and thousands of terms.
قيم البحث
اقرأ أيضاً
Despite the recent advancement in NLP research, cross-lingual transfer for natural language generation is relatively understudied. In this work, we transfer supervision from high resource language (HRL) to multiple low-resource languages (LRLs) for n
atural language generation (NLG). We consider four NLG tasks (text summarization, question generation, news headline generation, and distractor generation) and three syntactically diverse languages, i.e., English, Hindi, and Japanese. We propose an unsupervised cross-lingual language generation framework (called ZmBART) that does not use any parallel or pseudo-parallel/back-translated data. In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages. The objective function of the auxiliary task is close to the target tasks which enriches the multi-lingual latent representation of mBART and provides good initialization for target tasks. Then, this model is fine-tuned with task-specific supervised English data and directly evaluated with low-resource languages in the Zero-shot setting. To overcome catastrophic forgetting and spurious correlation issues, we applied freezing model component and data argumentation approaches respectively. This simple modeling approach gave us promising results.We experimented with few-shot training (with 1000 supervised data points) which boosted the model performance further. We performed several ablations and cross-lingual transferability analyses to demonstrate the robustness of ZmBART.
Computational physics problems often have a common set of aspects to them that any particular numerical code will have to address. Because these aspects are common to many problems, having a framework already designed and ready to use will not only s
peed the development of new codes, but also enhance compatibility between codes. Some of the most common aspects of computational physics problems are: a grid, a clock which tracks the flow of the simulation, and a set of models describing the dynamics of various quantities on the grid. Having a framework that could deal with these basic aspects of the simulation in a common way could provide great value to computational scientists by solving various numerical and class design issues that routinely arise. This paper describes the newly developed computational framework that we have built for rapidly prototyping new physics codes. This framework, called turboPy, is a lightweight physics modeling framework based on the design of the particle-in-cell code turboWAVE. It implements a class (called Simulation) which drives the simulation and manages communication between physics modules, a class (called PhysicsModule) which handles the details of the dynamics of the various parts of the problem, and some additional classes such as a Grid class and a Diagnostic class to handle various ancillary issues that commonly arise.
Given a closed-source program, such as most of proprietary software and viruses, binary code analysis is indispensable for many tasks, such as code plagiarism detection and malware analysis. Today, source code is very often compiled for various archi
tectures, making cross-architecture binary code analysis increasingly important. A binary, after being disassembled, is expressed in an assembly languages. Thus, recent work starts exploring Natural Language Processing (NLP) inspired binary code analysis. In NLP, words are usually represented in high-dimensional vectors (i.e., embeddings) to facilitate further processing, which is one of the most common and critical steps in many NLP tasks. We regard instructions as words in NLP-inspired binary code analysis, and aim to represent instructions as embeddings as well. To facilitate cross-architecture binary code analysis, our goal is that similar instructions, regardless of their architectures, have embeddings close to each other. To this end, we propose a joint learning approach to generating instruction embeddings that capture not only the semantics of instructions within an architecture, but also their semantic relationships across architectures. To the best of our knowledge, this is the first work on building cross-architecture instruction embedding model. As a showcase, we apply the model to resolving one of the most fundamental problems for binary code similarity comparison---semantics-based basic block comparison, and the solution outperforms the code statistics based approach. It demonstrates that it is promising to apply the model to other cross-architecture binary code analysis tasks.
OpenSBLI is an open-source code-generation system for compressible fluid dynamics (CFD) on heterogeneous computing architectures. Written in Python, OpenSBLI is an explicit high-order finite-difference solver on structured curvilinear meshes. Shock-c
apturing is performed by a choice of high-order Weighted Essentially Non-Oscillatory (WENO) or Targeted Essentially Non-Oscillatory (TENO) schemes. OpenSBLI generates a complete CFD solver in the Oxford Parallel Structured (OPS) domain specific language. The OPS library is embedded in C code, enabling massively-parallel execution of the code on a variety of high-performance-computing architectures, including GPUs. The present paper presents a code base that has been completely rewritten from the earlier proof of concept (Jacobs et al, JoCS 18 (2017), 12-23), allowing shock capturing, coordinate transformations for complex geometries, and a wide range of boundary conditions, including solid walls with and without heat transfer. A suite of validation and verification cases are presented, plus demonstration of a large-scale Direct Numerical Simulation (DNS) of a transitional Shockwave Boundary Layer Interaction (SBLI). The code is shown to have good weak and strong scaling on multi-GPU clusters. We demonstrate that code-generation and domain specific languages are suitable for performing efficient large-scale simulations of complex fluid flows on emerging computing architectures.
This paper describes the Jas4pp framework for exploring physics cases and for detector-performance studies of future particle collision experiments. Jas4pp is a multi-platform Java program for numeric calculations, scientific visualization in 2D and
3D, storing data in various file formats and displaying collision events and detector geometries. It also includes complex data-analysis algorithms for function minimisation, regression analysis, event reconstruction (such as jet reconstruction), limit settings and other libraries widely used in particle physics. The framework can be used with several scripting languages, such as Python/Jython, Groovy and JShell. Several benchmark tests discussed in the paper illustrate significant improvements in the performance of the Groovy and JShell scripting languages compared to the standard Python implementation in C. The improvements for numeric computations in Java are attributed to recent enhancements in the Java Virtual Machine.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
