Hi Ben, > So you verified that after removing that file, and recompiling all > worked well? Did you also run the testsuite?
Paulus found this bug a long time ago when porting to power3. At the moment we binary edit libc and insert some strategic nops :) > Did this just occur, or has it always been that way? I ask, because I > see no changes to that since 2.2.0 release of glibc. It has always been a problem, memset(,0,) should take into consideration the cacheline size but does not. > If this is the only difference between powerpc and power3, then the > only choice I have is to remove this file for powerpc as a generic > solution (I cannot create two sets of libs for ppc and power3). Ben Herrenschmidt has a fix to export the cacheline size from the kernel using aux entries. Glibc may already have support for this. Anton
