Intel Parallel Studio XE 2016 Update 3 (Linux / MacOSX) | 718 Mb / 3.87 / 1.56 Gb
Intel released a new version of Intel Parallel Studio XE with new features that improve application performance and Big Data analysis. Intel Parallel Studio XE 2016 is a comprehensive suite of software development tools for high-performance computing (HPC) and technical computing applications for the Intel architecture, which includes support for the latest Intel Xeon and Intel Xeon Phi processors and coprocessors.
The new development tool release introduces three new capabilities: the Intel Data Analytics Acceleration Library (DAAL), which boosts the speed of data analytics and machine-learning programs; the Vectorization Advisor, which assists developers in achieving effective vectorization more quickly; and the MPI Performance Snapshot, which improves cluster performance by profiling MPI jobs faster (up to 32K ranks).
The Intel DAAL provides advanced C++ and Java data analytics functions that can be used in all stages of the data analytics workflow, including data acquisition from a data source, pre-processing, transformation, data mining, modeling, validation and decision making.
The library provides building blocks that are pre-optimized and ready to use to reduce overall development time. These building blocks include data mining methods, such as basic statistical moments, Principle Component Analysis, associating rule mining and outlier detection, as well as supervised and unsupervised machine learning methods, such as linear regression, classification, Support Vector Machine and clustering.
The Intel DAAL supports batch, streaming and distributed compute models to cover range of system needs. It also provides tight connections to popular analytics platforms (Hadoop and Spark) and data sources (SQL, non-SQL, files, in-memory) for fast data throughput.
The second new feature, called the Vectorization Advisor, is a vectorization analysis tool that ensures that Fortran and native/managed C++ applications take full advantage of today's Intel processors.
The Vectorization Advisor, part of the Intel Advisor XE 2016 tool, boosts performance by identifying new vectorization opportunities and improvements to existing vectorization. More specifically, it lets developers identify loops that will benefit most from vectorization and identify what is blocking effective vectorization. It also allows developers to explore the benefit of alternative data reorganizations and helps increase confidence that vectorization is safe.
The Vectorization Advisor makes actionable recommendations by highlighting them in the code as well as show estimated performance gains. Overall, the tool allows developers to vectorize effectively in days, instead of months.
The third new feature - MPI Performance Snapshot - is part of the Intel Trace Analyzer and Collector tool, which allows developers to analyze and tune parallel cluster applications for high performance.Intel.Parallel.Studio.XE.2016.with.Update.3.LINUX.ISO-TBE