| Feature |
Benefit |
| Supports MMX™ technology through the use of C “intrinsics.” |
Allows developers to use call syntax of C functions instead of manually
coding in assembly language. |
| Supports inline assembly language insertions. |
Allows flexibility for particular performance demands. |
| Provides integrated register allocation. |
Results in increased processing speed. |
| Provides instruction scheduling tailored to the small number of registers. |
Reorders the generated machine instructions so that more than one can execute
in parallel. |
| Provides comprehensive use of the rich addressing modes. |
Reduces the number of instructions in program. |
| Provides support for whole-program compilation. |
Stores information about the entire program before performing multifile
optimizations. |
| Provides profile-guided optimizations. |
Allows the compiler to adjust the flow of the program to achieve
optimum performance based on previous executions with the same data set. |
| Provides loop-intensive data cache transformations. |
Maximizes use of cache. |
| Provides maximum floating-point instruction throughput. |
Allows you to completely use the floating-point stack. |
| Provides a “blended” code optimization switch. |
Allows you to generate code that provides excellent performance with any
Intel Architecture processor, including the Pentium® II processor. |
| Provides processor-specific optimizations. |
Allows you to maximize performance on a specific Intel Architecture processor,
including the Pentium II processor. |
