Performance without Compromise

If your application could use a boost of performance, incorporate the Intel® C++ Compiler into your development cycle. For better performance, it is optimized to take advantage of advanced processor features like multiple cores and wider vector registers, including Intel® Advanced Vector Extensions 512 (Intel® AVX-512) instructions. The compiler is a drop-in addition for C and C++ development and has broad support for current and previous C and C++ standards with full C++14 and C99 support. Initial C++17 support is also available.

Benchmark results were obtained prior to implementation of recent software patches and firmware updates that are intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system.

Configuration: Linux* hardware: 2x Intel® Xeon® processor Gold 6148 at 2.40 GHz, 192 GB RAM, HyperThreading is on. Software: Compilers from Intel 18.0, GCC 7.1.0. PGI 15.10, Clang/LLVM 4.0. Linux operating system: Red Hat Enterprise* for Linux server, release 7.2 (Maipo), kernel 3.10.0-514.el7.x86_64. SPEC* Benchmark (www.spec.org). SmartHeap 10 was used for CXX tests when measuring SPECint* benchmarks.

SPECint _rate_base_2006 compiler switches: SmartHeap 10 were used for C++ tests. Intel C and Intel C++ Compilers 18.0: -m32 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -qopt-mem-layout-trans=3 C++ code adds option –static. GCC 7.1.0: -m32 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. Clang 4.0: -m32 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops C++ code adds option –fno-fast-math.

SPECfp*_rate_base_2006 compiler switches: Intel C and Intel C++ Compilers 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -qopt-mem-layout-trans=3 -auto-p32. C code adds option –static. Intel® Fortran 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -qopt-mem-layout-trans=3 –static. GCC 7.1.0: -m64 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. Clang 4.0: -m64 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops

SPECint_speed_base_2006 compiler switches: SmartHeap 10 were used for C++ tests. Intel C and Intel C++ Compilers 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -auto-p32. C code adds options –static –parallel. GCC 7.1.0: -m64 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. C code adds options –ftree-parallelize-loops=40. Clang 4.0: -m64 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops. C++ code adds options -fno-fast-math -fno-fast-math.

SPECfp_speed_base_2006 compiler switches: Intel C and Intel C++ Compilers 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -static -auto-p32. C code adds option –parallel. Intel Fortran 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -static -parallel. GCC 7.1.0: -m64 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. C code adds option -ftree-parallelize-loops=40. Clang 4.0: -m64 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops

Benchmark source: Intel Corporation

See below for further notes and disclaimers.1


Benchmark results were obtained prior to implementation of recent software patches and firmware updates that are intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system.

Configuration: Linux hardware: Intel Xeon processor Gold 6148 at 2.40 GHz, 192 GB RAM, HyperThreading is on. Software: Compilers from Intel 18.0, GCC 7.1.0. PGI 15.10, Clang/LLVM 4.0. Linux operating system: Red Hat Enterprise, Linux Server release 7.2 (Maipo), kernel 3.10.0-514.el7.x86_64. SPEC* Benchmark (www.spec.org). SmartHeap libs 11.3 for Visual C++* and compilers from Intel was used for SPECint benchmarks. SPECint_speed_base_2006 compiler switches: SmartHeap 10 were used for C++ tests. Intel C and Intel C++ Compilers 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -auto-p32. C code adds options –static –parallel. GCC 7.1.0: -m64 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. C code adds options –ftree-parallelize-loops=40. Clang 4.0: -m64 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops. C++ code adds options -fno-fast-math -fno-fast-math. SPECfp_speed_base_2006 compiler switches: Intel C and Intel C++ Compilers 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -static -auto-p32. C code adds option –parallel. Intel Fortran 18.0: -m64 -xCORE-AVX512 -ipo -O3 -no-prec-div -qopt-prefetch -static -parallel. GCC 7.1.0: -m64 -Ofast -flto -march=core-avx2 -mfpmath=sse -funroll-loops. C code adds option -ftree-parallelize-loops=40. Clang 4.0: -m64 -Ofast -march=core-avx2 -flto -mfpmath=sse -funroll-loops

Benchmark source: Intel Corporation

See below for further notes and disclaimers.1

Outstanding support

Confidential Support and One Year of Updates Included
Every paid version of our software products automatically gives you access to the Online Service Center for at least a year from the date of purchase, and you can extend it for additional time at a reduced rate. This includes:

  • Free access to all new product updates, and continued access to and support for older versions of the product.
  • The ability to interact directly and privately with our product engineers by submitting confidential inquiries and code samples.
  • Responsiveness to your product needs (older and newer versions) and technical questions—a key reason for our customer satisfaction.
  • Community product forums covering all of our software development products.
  • Access to a vast library of self-help documents that are built off of the decades of experience our community has in using our software products.

Optimization Notice: Intel® compilers may or may not optimize to the same degree for third-party 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