I have created an optimized strcmp routine for MIPS and would like to check it in. I verified it by running 'make check' and I also ran 'make bench' to check the performance. This function is slightly slower then the current generic strcmp for strings that are not aligned, but much faster when strings are aligned because it will then load and compare either 2, 4, or 8 bytes at a time. This means it could be loading bytes beyond the end of the strings being compared but it looks like other architecture specific strcmp functions are also doing this optimization and the newlib version of strcmp also does this. OK to checkin? I have attached the original and new bench-strcmp.out files in case anyone wants to compare the old and new strcmp performance results. Steve Ellcey sellcey@mips.com 2013-11-14 Steve Ellcey * sysdeps/mips/strcmp.c: New.