Transform Enterprise, HPC & AI, Accelerate Parallel Code

Code Maximized Intel Parallel Studio XE

Just Released: Intel® Parallel Studio XE 2019

Code complexity not only continues to increase, it’s doing so faster and faster. Architectural diversity is the key driver of this phenomenon, with sophisticated computing environments. This requires specialized skills… and advanced tools that deliver more performance more efficiently—with less time and increased developer productivity—to make demanding application workloads hum seamlessly from enterprise to cloud, and HPC to AI.

To make life easier for C/C++, Fortran and Python*developers, Intel just released the new version of its flagship code modernization tool, Intel® Parallel Studio XE 2019. It combines 10+ tools—industry-leading compilers, high-performance libraries, performance profilers, and code analyzers. Developers using this tool suite can confidently build fast, scalable and reliable parallel applications more efficiently using proven techniques like vectorization, multi-threading, multi-node, and memory optimization. Developers work hard, and their code should too—leveraging all the amazing performance and capabilities possible from the power of Intel® processors.

Download Free Trial | Current Users Upgrade Here

Top New Features & Details 

  • Improve application performance on Intel® Xeon® Scalable and Core™ processors with new enhancements in compilers, performance libraries and analysis tools:
    • Vectorize and thread your code using OpenMP* to take advantage of the latest SIMD-enabled hardware, including Intel® Advanced Vector Extensions 512 (Intel® AVX-512)
    • Accelerate diverse workloads across enterprise, cloud, HPC and AI
       
  • Speed machine learning by enabling new high performance Python* capabilities with Scikit-learn: Support Vector Machine (SVM) & K-means prediction, accelerated with Intel® Data Analytics Acceleration Library. Other new features include adding the machine learning XGBoost library (Linux* only), and flexibility for easy command line standalone install.
     
  • Deliver fast, scalable code with Intel® Math Kernel Library's enhanced capabilities for just-in-time (JIT) Small Matrix Multiplication with improved speed of S/DGEMM for Intel® AVX-512 and Intel® AVX2. Solve sparse linear systems, sparse linear least squares and eigenvalue problems, rank and null-space determination, and more. Use highly optimized multinomial random number generator to optimize experiments for finance, geological and biological applications.
     
  • Accelerate image, signal, data processing and cryptography computation tasks with new features in Intel® Integrated Performance Primitives. 
    • Functions for ZFP floating-point data compression to help tackle large data storage challenges, great for oil/gas applications
    • Optimization patch files for the bzip2 source 1.0.6
    • Improved LZ4 compression and decompression performance on high entropy data
    • New color conversion functions for convert RBG images to CIE Lab color models, and vice versa
    • Extended optimization for Intel AVX-512 and Intel AVX2 instruction set
       
  • Intel VTune Amplifier 2019Analyze with the enhanced Application Performance Snapshot to focus on useful data with new data selection and pause options (Linux*) in Intel® VTune™ Amplifier. Analyze CPU utilization of physical cores and preview a new platform profiler for longer, higher level performance analysis. Optimize server and cloud applications with improved JIT profiling. Use a new, more accessible user interface for a simplified profiling workflow. 
     
  • New capabilities in Flow Graph improve concurrency and  heterogeneity through improved task analyzer and  OpenCL* device selection for Threading Building Blocks. Visualize parallelism with rapid visual prototyping environment—interactively build, validate, and visualize parallel algorithms with Flow Graph Analyzer in Intel® Advisor.
     
  • Extend HPC solutions on the path to Exascale—gain greater scalability and reduce latency with next generation Intel® MPI Library.
     
  • Supports industry standards and IDEs—for example:
    • Additional C++17 standard feature support with improvements to lambda and constant expression support, and improved GNU C++ & Microsoft C++ compiler compatibility
    • Standards-driven parallelization for C++ with partial OpenMP* 51 draft support
    • Python including 2.7 and 3.6
  • And more!
Download Free Trial | Current Users Upgrade Here
Expert Help is Available

Developers can get more from their code, overcome performance bottlenecks and development challenges by asking the experts through Intel's Priority Support (included with all paid licenses).Connect privately with Intel engineers for quick answers to technical questions.

Want More Performance? Real Numbers to Help Tell the Story

Intel C++ Compiler 2019 benchmark

Performance results are based on testing as of Aug. 26, 2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure. For more complete information about performance and benchmark results, visit www.intel.com/benchmark. Configuration: Testing by Intel as of Aug. 26, 2018. Linux* hardware: Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz, 384 GB RAM, HyperThreading is on. Software: Intel compilers 19.0, GCC 8.1.0. PGI 18.5, Clang/LLVM 6.0. Linux OS: Red Hat Enterprise Linux Server release 7.4 (Maipo), 3.10.0-693.el7.x86_64. SPEC* Benchmark (www.spec.org). SmartHeap 10 was used for CXX tests when measuring SPECint® benchmarks.SPECint®_rate_base_2017 compiler switches: SmartHeap 10 were used for C++ tests. Intel C/C++ compiler 19.0: -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-mem-layout-trans=3. GCC 8.1.0 -march=znver1 -mfpmath=sse -Ofast -funroll-loops -flto. Clang 6.0: -march=core-avx2 -mfpmath=sse -Ofast -funroll-loops –flto.SPECfp®_rate_base_2017 compiler switches: Intel C/C++ compiler 19.0: -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=3. GCC 8.1.0: -march=skylake-avx512 -mfpmath=sse -Ofast -fno-associative-math -funroll-loops -flto. Clang 6.0: -march=znver1 -mfpmath=sse -Ofast -funroll-loops –flto.SPECint®_speed_base_2017 compiler switches: SmartHeap 10 were used for C++ tests. Intel C/C++ compiler 19.0: -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-mem-layout-trans=3 -qopenmp. GCC 8.1.0 '-march=znver1 -mfpmath=sse -Ofast -funroll-loops -flto -fopenmp. Clang 6.0: -march=core-avx2 -mfpmath=sse -Ofast -funroll-loops -flto -fopenmp=libomp. SPECfp®_speed_base_2017 compiler switches: Intel C/C++ compiler 19.0: -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -ffinite-math-only -qopenmp. GCC 8.1.0: -march=skylake-avx512 -mfpmath=sse -Ofast -fno-associative-math -funroll-loops -flto -fopenmp. Clang 6.0: -march=skylake-avx512 -mfpmath=sse -Ofast -funroll-loops -flto -fopenmp=libomp. See also the Optimization Notice at end of this article.1

 

Intel Fortran Compiler 2019 benchmark

Performance results are based on testing as of Aug. 26, 2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure. For more complete information about performance and benchmark results, visit www.intel.com/benchmark. Configuration: Testing by Intel as of Aug. 26, 2018. Hardware: Intel® Core™ i7-8700K CPU @ 3.70GHz, 64 GB RAM, HyperThreading is on. Software: Intel Fortran Compiler 19.0, PGI Fortran* 18.5, gFortran* 8.1.0. Linux OS: Red Hat Enterprise Linux Server release 7.4 (Maipo), 3.10.0-693.el7.x86_64 Polyhedron Fortran Benchmark (www.fortran.uk). Linux compiler switches: Gfortran: -Ofast -mfpmath=sse -flto -march=haswell -funroll-loops -ftree-parallelize-loops=6. Intel Fortran compiler: -fast -parallel -xCORE-AVX2 -nostandard-realloc-lhs. PGI Fortran: -fast -Mipa=fast,inline -Msmartalloc -Mfprelaxed -Mstack_arrays -Mconcur=bind -tp haswell. See also the Optimization Notice at end of this article.1

 

Intel Python 2019 Benchmark

Performance results are based on testing as of July 9, 2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure. For more complete information about performance and benchmark results, visit www.intel.com/benchmarkConfiguration: Testing by Intel as of July 9, 2018. Stock Python: python 3.6.6 hc3d631a_0 installed from conda, numpy 1.15, numba 0.39.0, llvmlite 0.24.0, scipy 1.1.0, scikit-learn 0.19.2 installed from pip; Intel Python: Intel® Distribution for Python* 2019 Gold: python 3.6.5 intel_11, numpy 1.14.3 intel_py36_5, mkl 2019.0 intel_101, mkl_fft 1.0.2 intel_np114py36_6,mkl_random 1.0.1 intel_np114py36_6, numba 0.39.0 intel_np114py36_0, llvmlite 0.24.0 intel_py36_0, scipy 1.1.0 intel_np114py36_6, scikit-learn 0.19.1 intel_np114py36_35; OS: CentOS Linux 7.3.1611, kernel 3.10.0-514.el7.x86_64; Hardware: Intel(R) Xeon(R) Gold 6140 CPU @ 2.30GHz (2 sockets, 18 cores/socket, HT:off), 256 GB of DDR4 RAM, 16 DIMMs of 16 GB@2666MHz. See also the Optimization Notice at end of this article.1

 

Intel MPI Library 2019 benchmark

Performance results are based on testing as of Sept. 5, 2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure. For more complete information about performance and benchmark results, visit www.intel.com/benchmarkConfiguration: Testing by Intel as of Sept. 5, 2018 Hardware: Intel® Xeon® Gold 6148 CPU @ 2.40GHz; 192 GB RAM. Interconnect: Intel® Omni-Path Host Fabric Interface. Software: RHEL* 7.4; IFS 10.7.0.0.145; Libfabric internal; Intel® MPI Library 2019; Intel® MPI Benchmarks 2019 (built with Intel® C++ Compiler XE 18.0.2.199 for Linux*). See also the Optimization Notice at end of this article.1

 


Sanjiv Shah CVCG DPD

Video: Why Tools Matter More Now Than Ever

In this 10-minute conversation, Sanjiv Shah, Intel vice president and general manager for Intel’s technical, enterprise, and cloud computing software tools group, discusses the Holy Grail of programming.

Advanced development tools (like those found in Intel Parallel Studio XE 2019) are more important than ever for software developers. Watch it.

 

Get Your Code Future-Ready Now with Free Webinars

Intel also offers popular webinars to help developers sharpen their technical skills, save optimization time, and dive into new areas of development. Sign up today for the latest overviews, insights, and how-to’s on today's central topics—AI, DC, HPC, IoT, and other essential acronyms—that you can use right away. Attend Fall Technical Webinar Series.


About Intel Parallel Studio XE

Who Needs It
  • HPC awardTechnical compute developers: HPC and AI software developers, domain specialists, students, and educators
  • Enterprise and cloud application developers: Software developers, business analysts, and data analysts
What It Can Do
  • Optimizes applications for fast code: Boost application performance that scales on current and future Intel platforms
  • Builds code faster: Simplify the process of creating parallel code, shortcut development time

Provides Priority Support: For paid licenses, customers can connect privately direct to Intel engineers for quick answers to technical questions, and receive highly discounted renewal rates.

More Resources 

Intel Parallel Studio XE 2019 site | product brief

 

1Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information, see Performance Benchmark Test DisclosureIntel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice revision #20110804

 
For more complete information about compiler optimizations, see our Optimization Notice.