This session focuses on the compiler’s floating-point arithmetic, which is more complicated to handle than an integer or fixed-point arithmetic. There are many performance and precision glitches that a developer can run into and compilers are not as free to optimize the code automatically. For this reason, a software developer must be more aware of the floating-point arithmetic properties to get good performance from the compiler.
Join compiler architect Andy Kaylor for deeper insights, including:

  • Command-line options to control compiler behavior
  • Pragmas to fine-tune controls within your code
  • How the compiler selects math library function implementations
  • The effect of floating-point settings on compiler optimizations
  • Trade-offs between performance, accuracy, and reproducibility

Get the Software

To access the Intel oneAPI DPC++/C++ Compiler and more:

  • Download the Intel oneAPI DPC++/C++ Compiler as part of the Intel® oneAPI Base Toolkit. This is a foundational set of 15 tools and libraries for developing high-performance, data-centric applications across CPUs, GPUs, FPGAs, and other accelerators. Learn More
  • Intel® Parallel Studio XE or Intel® System Studio users can migrate to the next generation of these powerful suites. Each one includes the oneAPI DPC++/C++ Compiler. Learn More

 

 

Intel® oneAPI DPC++/C++ Compiler

Compile ISO C++, Khronos SYCL*, and DPC++ source code across CPUs, GPUs, and FPGAs. Part of the Intel® oneAPI Base Toolkit.

Get It Now   

See All Tools