/
LFOSDVVHVXVHUVF HDFWODVFODQJGRHVLW ODQQHGUHOHDVH LLVM IR LFOSDVVHVXVHUVF HDFWODVFODQJGRHVLW ODQQHGUHOHDVH LLVM IR

LFOSDVVHVXVHUVF HDFWODVFODQJGRHVLW ODQQHGUHOHDVH LLVM IR - PDF document

cheryl-pisano
cheryl-pisano . @cheryl-pisano
Follow
385 views
Uploaded On 2015-03-05

LFOSDVVHVXVHUVF HDFWODVFODQJGRHVLW ODQQHGUHOHDVH LLVM IR - PPT Presentation

o cpp aout Open source part Proprietary part brPage 2br Optimization Notice QWHO57526V57347FRPSLOHUV57347PD57347RU57347PD57347QRW57347RSWLPLH57347WR57347WKH57347VDPH57347GHJUHH57347IRU57347QRQ DUH57347QRW57347XQLTXH57347WR57347QWHO57347PLFURSURFHVVRU ID: 41812

cpp aout Open source

Share:

Link:

Embed:

Download Presentation from below link

Download Pdf The PPT/PDF document "LFOSDVVHVXVHUVF HDFWODVFODQJGRHVLW ODQQH..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

OpenMP 4.0 • Implementation available at clang - omp.github.com • Upstreaming to clang trunk under way • Including #pragma omp simd (for vectorizer) • We need your code reviews! Intel® OpenMP Runtime Library • Open - sourced under BSD - like license • Part of LLVM project: openmp.llvm.org • Ported to ARM * , POWER * Cilk tm Plus • Implementation available at cilkplus.github.com • Upstreaming to clang trunk is planned • We welcome your feedback and contributions! Extended Clang C++ front - end • Full compatibility with clang • C / C++ language support • Expressive diagnostics • Support for clang options Intel compiler back - end • Improved performance on IA - 32/Intel64 • OpenMP * 4.0 • Cilk tm Plus • Support for new IA instructions • Intel - specific pragmas • Same back - end as in icc • Support for icc options New C++ compiler for Mac OS X * , combining Clang * C++ front - end with Intel compiler back - end • icl passes user’s *.c / *. cpp file to Clang front - end – exactly as “clang” does it • Latest released Clang front - end, with some extensions (OpenMP 4.0, Cilk tm Plus, pragmas, intrinsics) is employed • Clang front - end produces LLVM IR (in memory) • LLVM IR got converted to Intel compiler IR • Intel compiler back - end optimizes IR, produces object code Intel® Composer XE 2015 Planned release Q3’2014 Beta is available NOW! Andrey Bokhanko (Intel) icl (Intel® Clang - based C++ compiler) Clang (C++ front - end) Intel back - end ld LLVM IR *.o *.cpp a.out • On par with icc • icc and icl employ the same IA - 32/Intel64 back - end, known for performance • For details, including benchmarks and comparisons with other compilers, see http:// software.intel.com/e n - us/intel - composer - xe Open source part Proprietary part *Other names and brands may be claimed as the property of others. Optimization Notice 2 Intel Confidential Optimization Notice Intel’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