GCC 5 To Boast New x86 Optimizations
GCC 5 already boasts an incredible amount of new compiler features as laid out now over dozens of Phoronix articles, but there's even more abound for this major compiler update due out in 2015.
Another feature of GCC 5.0 that we haven't covered to date on Phoronix are x86 optimizations to yield faster code. One of the x86 optimizations is concerning the vectorization of loads/stores groups. Evgeny Stupachenko of Intel wrote a new blog post on the Intel Developer Zone detailing the load/store groups vectorization that should help out workloads like image conversion and software using n-dimensional coordinates and multiplication of vectors by a constant matrix.
Developers wishing to learn more about this optimization to benefit x86 CPUs -- along with Intel's exciting performance results with the change -- can be found at software.intel.com. For one of the tests, with an Intel Core i7 Haswell CPU, the code is three times faster than GCC 4.9.
GCC 5.0 will likely be officially released with its many features around mid-2015.
Another feature of GCC 5.0 that we haven't covered to date on Phoronix are x86 optimizations to yield faster code. One of the x86 optimizations is concerning the vectorization of loads/stores groups. Evgeny Stupachenko of Intel wrote a new blog post on the Intel Developer Zone detailing the load/store groups vectorization that should help out workloads like image conversion and software using n-dimensional coordinates and multiplication of vectors by a constant matrix.
Developers wishing to learn more about this optimization to benefit x86 CPUs -- along with Intel's exciting performance results with the change -- can be found at software.intel.com. For one of the tests, with an Intel Core i7 Haswell CPU, the code is three times faster than GCC 4.9.
GCC 5.0 will likely be officially released with its many features around mid-2015.
7 Comments