mirror of git://sourceware.org/git/glibc.git
c867597bff
Since the new SSE2/AVX2 memcpy/memmove are faster than the previous ones, we can remove the previous SSE2/AVX2 memcpy/memmove and replace them with the new ones. No change in IFUNC selection if SSE2 and AVX2 memcpy/memmove weren't used before. If SSE2 or AVX2 memcpy/memmove were used, the new SSE2 or AVX2 memcpy/memmove optimized with Enhanced REP MOVSB will be used for processors with ERMS. The new AVX512 memcpy/memmove will be used for processors with AVX512 which prefer vzeroupper. Since the new SSE2 memcpy/memmove are faster than the previous default memcpy/memmove used in libc.a and ld.so, we also remove the previous default memcpy/memmove and make them the default memcpy/memmove, except that non-temporal store isn't used in ld.so. Together, it reduces the size of libc.so by about 6 KB and the size of ld.so by about 2 KB. [BZ #19776] * sysdeps/x86_64/memcpy.S: Make it dummy. * sysdeps/x86_64/mempcpy.S: Likewise. * sysdeps/x86_64/memmove.S: New file. * sysdeps/x86_64/memmove_chk.S: Likewise. * sysdeps/x86_64/multiarch/memmove.S: Likewise. * sysdeps/x86_64/multiarch/memmove_chk.S: Likewise. * sysdeps/x86_64/memmove.c: Removed. * sysdeps/x86_64/multiarch/memcpy-avx-unaligned.S: Likewise. * sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S: Likewise. * sysdeps/x86_64/multiarch/memmove-avx-unaligned.S: Likewise. * sysdeps/x86_64/multiarch/memmove-sse2-unaligned-erms.S: Likewise. * sysdeps/x86_64/multiarch/memmove.c: Likewise. * sysdeps/x86_64/multiarch/memmove_chk.c: Likewise. * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Remove memcpy-sse2-unaligned, memmove-avx-unaligned, memcpy-avx-unaligned and memmove-sse2-unaligned-erms. * sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Replace __memmove_chk_avx512_unaligned_2 with __memmove_chk_avx512_unaligned. Remove __memmove_chk_avx_unaligned_2. Replace __memmove_chk_sse2_unaligned_2 with __memmove_chk_sse2_unaligned. Remove __memmove_chk_sse2 and __memmove_avx_unaligned_2. Replace __memmove_avx512_unaligned_2 with __memmove_avx512_unaligned. Replace __memmove_sse2_unaligned_2 with __memmove_sse2_unaligned. Remove __memmove_sse2. Replace __memcpy_chk_avx512_unaligned_2 with __memcpy_chk_avx512_unaligned. Remove __memcpy_chk_avx_unaligned_2. Replace __memcpy_chk_sse2_unaligned_2 with __memcpy_chk_sse2_unaligned. Remove __memcpy_chk_sse2. Remove __memcpy_avx_unaligned_2. Replace __memcpy_avx512_unaligned_2 with __memcpy_avx512_unaligned. Remove __memcpy_sse2_unaligned_2 and __memcpy_sse2. Replace __mempcpy_chk_avx512_unaligned_2 with __mempcpy_chk_avx512_unaligned. Remove __mempcpy_chk_avx_unaligned_2. Replace __mempcpy_chk_sse2_unaligned_2 with __mempcpy_chk_sse2_unaligned. Remove __mempcpy_chk_sse2. Replace __mempcpy_avx512_unaligned_2 with __mempcpy_avx512_unaligned. Remove __mempcpy_avx_unaligned_2. Replace __mempcpy_sse2_unaligned_2 with __mempcpy_sse2_unaligned. Remove __mempcpy_sse2. * sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Support __memcpy_avx512_unaligned_erms and __memcpy_avx512_unaligned. Use __memcpy_avx_unaligned_erms and __memcpy_sse2_unaligned_erms if processor has ERMS. Default to __memcpy_sse2_unaligned. (ENTRY): Removed. (END): Likewise. (ENTRY_CHK): Likewise. (libc_hidden_builtin_def): Likewise. Don't include ../memcpy.S. * sysdeps/x86_64/multiarch/memcpy_chk.S (__memcpy_chk): Support __memcpy_chk_avx512_unaligned_erms and __memcpy_chk_avx512_unaligned. Use __memcpy_chk_avx_unaligned_erms and __memcpy_chk_sse2_unaligned_erms if if processor has ERMS. Default to __memcpy_chk_sse2_unaligned. * sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S Change function suffix from unaligned_2 to unaligned. * sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Support __mempcpy_avx512_unaligned_erms and __mempcpy_avx512_unaligned. Use __mempcpy_avx_unaligned_erms and __mempcpy_sse2_unaligned_erms if processor has ERMS. Default to __mempcpy_sse2_unaligned. (ENTRY): Removed. (END): Likewise. (ENTRY_CHK): Likewise. (libc_hidden_builtin_def): Likewise. Don't include ../mempcpy.S. (mempcpy): New. Add a weak alias. * sysdeps/x86_64/multiarch/mempcpy_chk.S (__mempcpy_chk): Support __mempcpy_chk_avx512_unaligned_erms and __mempcpy_chk_avx512_unaligned. Use __mempcpy_chk_avx_unaligned_erms and __mempcpy_chk_sse2_unaligned_erms if if processor has ERMS. Default to __mempcpy_chk_sse2_unaligned. |
||
|---|---|---|
| .. | ||
| 64 | ||
| fpu | ||
| multiarch | ||
| nptl | ||
| x32 | ||
| Implies | ||
| Makefile | ||
| Versions | ||
| ____longjmp_chk.S | ||
| __longjmp.S | ||
| _mcount.S | ||
| abort-instr.h | ||
| add_n.S | ||
| addmul_1.S | ||
| atomic-machine.h | ||
| backtrace.c | ||
| bsd-_setjmp.S | ||
| bsd-setjmp.S | ||
| bzero.S | ||
| configure | ||
| configure.ac | ||
| crti.S | ||
| crtn.S | ||
| dl-irel.h | ||
| dl-lookupcfg.h | ||
| dl-machine.h | ||
| dl-procinfo.c | ||
| dl-runtime.c | ||
| dl-tls.h | ||
| dl-tlsdesc.S | ||
| dl-tlsdesc.h | ||
| dl-trampoline.S | ||
| dl-trampoline.h | ||
| ffs.c | ||
| ffsll.c | ||
| hp-timing.h | ||
| htonl.S | ||
| ifuncmain8.c | ||
| ifuncmod8.c | ||
| jmpbuf-offsets.h | ||
| jmpbuf-unwind.h | ||
| l10nflist.c | ||
| ldbl2mpn.c | ||
| ldsodefs.h | ||
| link-defines.sym | ||
| locale-defines.sym | ||
| localplt.data | ||
| lshift.S | ||
| machine-gmon.h | ||
| memchr.S | ||
| memcmp.S | ||
| memcpy.S | ||
| memcpy_chk.S | ||
| memmove.S | ||
| memmove_chk.S | ||
| mempcpy.S | ||
| mempcpy_chk.S | ||
| memrchr.S | ||
| memset.S | ||
| memset_chk.S | ||
| memusage.h | ||
| mp_clz_tab.c | ||
| mul_1.S | ||
| preconfigure | ||
| preconfigure.ac | ||
| rawmemchr.S | ||
| rshift.S | ||
| sched_cpucount.c | ||
| setjmp.S | ||
| stack-aliasing.h | ||
| stackguard-macros.h | ||
| stackinfo.h | ||
| start.S | ||
| stpcpy.S | ||
| strcasecmp.S | ||
| strcasecmp_l-nonascii.c | ||
| strcasecmp_l.S | ||
| strcat.S | ||
| strchr.S | ||
| strchrnul.S | ||
| strcmp.S | ||
| strcpy.S | ||
| strcspn.S | ||
| strlen.S | ||
| strncase.S | ||
| strncase_l-nonascii.c | ||
| strncase_l.S | ||
| strncmp.S | ||
| strnlen.S | ||
| strpbrk.S | ||
| strrchr.S | ||
| strspn.S | ||
| strtok.S | ||
| strtok_r.S | ||
| sub_n.S | ||
| submul_1.S | ||
| sysdep.h | ||
| tls-macros.h | ||
| tlsdesc.c | ||
| tlsdesc.sym | ||
| tst-audit.h | ||
| tst-audit3.c | ||
| tst-audit4-aux.c | ||
| tst-audit4.c | ||
| tst-audit5.c | ||
| tst-audit6.c | ||
| tst-audit7.c | ||
| tst-audit10-aux.c | ||
| tst-audit10.c | ||
| tst-auditmod3a.c | ||
| tst-auditmod3b.c | ||
| tst-auditmod4a.c | ||
| tst-auditmod4b.c | ||
| tst-auditmod5a.c | ||
| tst-auditmod5b.c | ||
| tst-auditmod6a.c | ||
| tst-auditmod6b.c | ||
| tst-auditmod6c.c | ||
| tst-auditmod7a.c | ||
| tst-auditmod7b.c | ||
| tst-auditmod10a.c | ||
| tst-auditmod10b.c | ||
| tst-mallocalign1.c | ||
| tst-quad1.c | ||
| tst-quad1pie.c | ||
| tst-quad2.c | ||
| tst-quad2pie.c | ||
| tst-quadmod1.S | ||
| tst-quadmod1pie.S | ||
| tst-quadmod2.S | ||
| tst-quadmod2pie.S | ||
| tst-split-dynreloc.c | ||
| tst-split-dynreloc.lds | ||
| tst-stack-align.h | ||
| wcschr.S | ||
| wcscmp.S | ||
| wcslen.S | ||
| wcsrchr.S | ||