Intel® Compiler - How can I generate optimized code to run on any IA-32 or Intel®64 architecture processor?

The compiler's default optimizations, /O2 on Windows* ( -O2 on Linux* or Mac OS* X), generate optimized code for all IA-32 architecture processors with support for SSE2 instructions and for all Intel®64 architecture processors. The option /arch:IA32 on Windows (-mia32 on Linux or Mac OS X) generates code suitable for IA-32 architecture processors without support for SSE2. In addition, /Qipo (inter-procedural optimization or IPO, -ipo on Linux or Mac OS X), /Qprof_use (profile-guided optimization or PGO, -prof_use on Linux or Mac OS X), and /O3 (high-level loop/memory optimizations, -O3 on Linux or Mac OS X) may further improve performance for many types of applications. These options are available for both Intel® and non-Intel microprocessors but they may perform more optimizations for Intel microprocessors than they perform for non-Intel microprocessors. 

The Intel compiler also supports a variety of processor-specific optimizations such as /arch, /Qx and /Qax (-m, -x and -ax on Linux or Mac OS X). For more information about these, please see Intel® compiler options for SSE generation and processor-specific optimizations.
For a broader summary of optimzation options, see the Quick Reference Guide to Optimization with Intel Compilers.
For more detail, see the main Compiler User and Reference Guide.

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