GCC Flags used for SPEC ACCELocl submussion by TU Dresden

Optimization Flags

- -m64
- gcc_l, gpp_l, gfortran_l
- -m64\b
- Specify the type of the target processor as 64-bit mode.
- -m32
- gcc_l, gpp_l, gfortran_l
- -m32\b
- Specify the type of the target processor as 32-bit mode.
- -O2
- (?:^|(?<=\s))-O2(?:$[^$]+\))?(?:=\S*)?(?=\s|$)
- -O2 Optimize even more. GCC performs nearly all supported optimizations that do not involve a space-speed tradeoff. The compiler does not perform loop unrolling or function inlining when you specify -O2. As compared to -O, this option increases both compilation time and the performance of the generated code.
- -lOpenCL
- gcc_l, gpp_l, gfortran_l
- -lOpenCL\b
- Link with the OpenCL library
- -I/opt/cuda/5.0.35/include
- gcc_l, gpp_l, gfortran_l
- -I/opt/cuda/5.0.35/include\b
- Include path to NVIDIA OpenCL library header
- -I/opt/intel-ocl/2013-3.2.1-16712/intel/opencl-1.2-3.2.1.16712/include
- gcc_l, gpp_l, gfortran_l
- -I/opt/intel-ocl/2013-3\.2\.1-16712/intel/opencl-1\.2-3\.[12]\.1\.16712/include\b
- Include path to Intel OpenCL library header