summary refs log tree commit diff
path: root/ChangeLog
Commit message (Collapse)AuthorAgeFilesLines
* Merge commit 'origin/master' into fedora/masterAndreas Schwab2009-09-011-0/+22
|\
| * Fix parse error in bits/mathinline.h with --std=c99Andreas Schwab2009-08-311-0/+4
| |
| * Fix problems with memory allocation in assert.Ulrich Drepper2009-08-311-0/+6
| | | | | | | | | | | | In case the allocator is corrupted and an assert triggers, we shouldn't allocate any more memory. Use a private assert definition which doesn't use malloc.
| * Remove ENABLE_SSSE3_ON_ATOM.H.J. Lu2009-08-281-0/+7
| | | | | | | | | | It turns that SSSE3 isn't slow on Atom. The problem is bsf. This patch removes ENABLE_SSSE3_ON_ATOM.
| * More strto{,u}l{,l} tests.Ulrich Drepper2009-08-281-0/+5
| |
* | Merge commit 'origin/master' into fedora/masterAndreas Schwab2009-08-261-0/+71
|\|
| * Add isinf optimized for 64-bit.Ulrich Drepper2009-08-261-0/+2
| |
| * Optimized isnan for 64-bit machines.Ulrich Drepper2009-08-261-0/+4
| |
| * Make llround an alias for lround on 64-bit machines.Ulrich Drepper2009-08-251-0/+3
| |
| * Optimized nearbyint for 64-bit.Ulrich Drepper2009-08-251-0/+2
| |
| * Optimized rint implementation for x86-64.Ulrich Drepper2009-08-251-0/+2
| |
| * Add 64-bit optimized s_round.Ulrich Drepper2009-08-251-0/+4
| |
| * Optimize out duplicated scalbln code for x86-64.Ulrich Drepper2009-08-251-1/+4
| |
| * Fix generic fdiml.Joseph Myers2009-08-251-0/+4
| |
| * Add 64-bit optimized scalbln.Ulrich Drepper2009-08-251-0/+2
| |
| * Optimized signbit{,f} for x86-64.Ulrich Drepper2009-08-251-0/+3
| |
| * Add 64-bit optimized version lround.Ulrich Drepper2009-08-251-0/+1
| |
| * 64-bit optimized implementation of trunc.Ulrich Drepper2009-08-251-0/+2
| |
| * Handle AVX saving on x86-64 in interrupted smbol lookups.Ulrich Drepper2009-08-251-0/+5
| | | | | | | | | | | | | | | | | | If a signal arrived during a symbol lookup and the signal handler also required a symbol lookup, the end of the lookup in the signal handler reset the flag whether restoring AVX/SSE registers is needed. Resetting means in this case that the tail part of the outer lookup code will try to restore the registers and this can fail miserably. We now restore to the previous value which makes nesting calls possible.
| * Add ceil implementation for 64-bit machines.Ulrich Drepper2009-08-241-0/+7
| | | | | | | | | | | | | | On 64-bit machines we should not split doubles into two 32 bit integer and handle the words separately. We have wide registers. This patch implements a 64-bit ceil version. Ideally all other functions will be converted over time.
| * Optimize float construction/extraction on x86-64.Ulrich Drepper2009-08-241-0/+5
| |
| * Merge branch 'master' of ssh://sources.redhat.com/git/glibcUlrich Drepper2009-08-241-0/+9
| |\
| | * Add sysdeps/unix/syscall-template.S; build syscall stubs with deps and -g ↵Roland McGrath2009-08-241-0/+9
| | | | | | | | | | | | pointing to it.
| * | Fix overflow handling in fdim.Ulrich Drepper2009-08-241-0/+4
| |/
| * Define math_errhandling is possible.Ulrich Drepper2009-08-241-0/+4
| |
| * Optimize x86-64 signbit{,f} a bit.Ulrich Drepper2009-08-241-0/+5
| |
* | Merge commit 'origin/master' into fedora/masterAndreas Schwab2009-08-241-5/+36
|\| | | | | | | | | | | Conflicts: sysdeps/powerpc/powerpc64/____longjmp_chk.S sysdeps/unix/sysv/linux/powerpc/powerpc64/____longjmp_chk.S
| * Add test case for last fixed regex bug.Ulrich Drepper2009-08-231-0/+2
| |
| * Recognize ill-formed { } expressions in regcomp.Ulrich Drepper2009-08-231-0/+3
| |
| * Also correct _POSIX2_* constants in case older standards are selected.Ulrich Drepper2009-08-231-2/+2
| |
| * Define _POSIX_VERSION correctly when older POSIX versions are selected.Ulrich Drepper2009-08-231-0/+3
| |
| * Print sign of NaN values.Ulrich Drepper2009-08-231-0/+5
| |
| * Thread-local locale handling part of XPG7.Ulrich Drepper2009-08-231-0/+5
| | | | | | | | I incorrectly enabled the definitions for XPG6.
| * Add sigstack handling to Linux ____longjmp_chk on powerpc.Andreas Schwab2009-08-221-0/+9
| |
| * Improve backtrace_symbols{,_fd} output when missing symbols. roland/backtrace-symsRoland McGrath2009-08-201-0/+9
| |
* | Merge commit 'origin/master' into fedora/masterAndreas Schwab2009-08-171-2/+18
|\|
| * Fix 64-bit platform handling in test cases for generated headers with constants.Ulrich Drepper2009-08-161-2/+6
| |
| * Improve test-skeleton.c to clean up after dead parent.Ulrich Drepper2009-08-141-0/+7
| |
| * SH: fix clobber list in stdlib/longlong.hSUGIOKA Toshinobu2009-08-101-0/+5
| |
* | Merge commit 'origin/master' into fedora/masterAndreas Schwab2009-08-101-0/+107
|\|
| * Support mixed SSE/AVX audit and check AVX only once.H.J. Lu2009-08-081-0/+28
| | | | | | | | | | | | | | | | | | | | This patch fixes mixed SSE/AVX audit and checks AVX only once in _dl_runtime_profile. When an AVX or SSE register value in pltenter is modified, we have to make sure that the SSE part value is the same in both lr_xmm and lr_vector fields so that pltexit will get the correct value from either lr_xmm or lr_vector fields. AVX-enabled pltenter should update both lr_xmm and lr_vector fields to support stacked AVX/SSE pltenter functions.
| * Use PIC only if SHARED is defined.H.J. Lu2009-08-081-0/+6
| | | | | | | | For ia32, we can avoid PIC in IFUNC functions in static library.
| * Simplify cpuid.h configure test.Jim Meyering2009-08-081-0/+4
| |
| * Move SSE4.2 functions together.Ulrich Drepper2009-08-081-0/+6
| |
| * Add SSSE3-optimized implementation of str{,n}cmp for x86-64.Ulrich Drepper2009-08-071-0/+9
| |
| * Avoid warning through fake initialization.Ulrich Drepper2009-08-071-0/+5
| |
| * Add the missing "; \".H.J. Lu2009-08-071-0/+4
| |
| * Fix expanding STB_GNU_UNIQUE hash table.Andreas Schwab2009-08-071-0/+5
| | | | | | | | | | An invalid symbol name pointer was entered into the hash table while enlarging it.
| * Properly count number of logical processors on Intel CPUs.H.J. Lu2009-08-071-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The meaning of the 25-14 bits in EAX returned from cpuid with EAX = 4 has been changed from "the maximum number of threads sharing the cache" to "the maximum number of addressable IDs for logical processors sharing the cache" if cpuid takes EAX = 11. We need to use results from both EAX = 4 and EAX = 11 to get the number of threads sharing the cache. The 25-14 bits in EAX on Core i7 is 15 although the number of logical processors is 8. Here is a white paper on this: http://software.intel.com/en-us/articles/intel-64-architecture-processor-topology-enumeration/ This patch correctly counts number of logical processors on Intel CPUs with EAX = 11 support on cpuid. Tested on Dinnington, Core i7 and Nehalem EX/EP. It also fixed Pentium Ds workaround since EBX may not have the right value returned from cpuid with EAX = 1.
| * Fix sed expression in TAGS command.Andreas Schwab2009-08-071-0/+5
| | | | | | | | | | The backslash-newline pair is interpreted as the beginning of an address regex.