Intel® Parallel Studio XE 2017 Beta is brings together exciting new technologies along with improvements to Intel’s existing software development tools. Registration gets you early access to the Intel® Parallel Studio XE 2017 products and the opportunity to provide feedback to help make our products better.
Here are some of the highlights:
- Enhanced Big Data Analytics – Easily Build IA Optimized Data Analytics Application
Intel® Data Analytics Acceleration Library (Intel® DAAL) Beta will help data scientists speed through big data challenges with optimized IA functions. New features include: Python APIs, Neural Network layer support, extended support for data sources, new normalization functions, new optimization algorithms and new activation functions.
- Boost Speed of Machine Learning Applications
Intel® Math Kernel Library 2017 Beta introduces machine learning support using DNN (Deep Neural Networks) primitives. Some of the new capabilities include extended TBB threading layer support, extended Sparse BLAS functionality, optimizations and usage models on second generation of Intel® Xeon Phi™, expanded online samples and C++ & Fortran separation for install.
- Faster performance from Python packages powered by Intel® Math Kernel Library
Intel® Distribution for Python* 2017 Beta adds new Python packages like scikit-learn, mpi4py, numba, conda, tbb (Python interfaces to Intel® Threading Building Blocks) and pyDAAL (Python interfaces to Intel® Data Analytics Acceleration Library). The Beta also delivers performance improvements for NumPy/SciPy through linking with performance libraries like Intel® MKL, Intel® MPI Library, Intel® TBB and Intel® DAAL.
- Profile mixed Python, Go + native code
Intel® VTune™ Amplifier XE Beta, unlike pure Python profilers, can now profile mixed Python + native C, C++ or Fortran code. Find the real performance bottleneck in your Python or Go application even if it does call native code.
- Storage & HPC analysis & easier configuration.
Intel® VTune™ Amplifier XE Beta introduces new Storage analysis feature to help you find unbalanced disk I/O and compute. Storage accesses are attributed to the source code. HPC Performance Characterization Analysis monitors utilization of the CPU, memory, and FPU for a compute-intensive or throughput application. This makes it easier to identify floating point operation and memory optimization opportunities. EBS analysis configuration for MPI applications has been simplified and remote Linux target now has automated configuration from UI.
- Discover Untapped Performance Faster
Intel® VTune™ Amplifier XE Beta introduces two new performance snapshots for a quick and easy way to prioritize performance projects based on data instead of guesswork. Application Performance Snapshot shows the potential benefit of code modernization. Storage Snapshot (coming soon in the beta update) shows if faster storage may improve performance.
- Expanded Compiler Features – Scaling Development Efforts Forward
Intel® C++ and Fortran Compiler 17.0 Beta compilers continue supporting the latest language standards and features – OpenMP* 4.0 and most of OpenMP* 4.5, C++11 and C++14, as well as Fortran 2008. Several enhancements improve your performance and vectorization capabilities – enjoy a significant boost in Coarray Fortran performance, vectorize your C++ code using the new Intel SIMD Data Layout Template, or tune your code for the latest Intel® Xeon Phi coprocessors. More informative optimization reports and a tighter integration with Intel® Advisor boost your productivity and efficiency.
- Easier Vectorization – Faster Code Faster
Intel® Advisor 2017 Beta introduces several new features: Gather/Scatter profiling, Optimize for AVX-512 even without Hardware, Loop Analytics improvements, Detection of heap allocated variables in MAP, MPI flow improvements, Multi-ISA improvements and SDLT recommendation.
- Advanced cluster diagnostic expert system in a tool
Intel® Cluster Checker 2017 Beta simplifies diagnosis of issues to improve cluster functionality and performance. It provides rapid reassurance to execute on a fully working cluster environment, which can be easily integrated into other software (using the Intel® Cluster Checker API). Its comprehensive cluster environment checking can be easily extended with custom tests.
For more details and information about this beta program, check out the Intel® Parallel Studio XE 2017 Beta page, which includes additional information in the FAQ and What’s New documents.
Intel® Parallel Studio XE Beta Articles and References: