about summary refs log tree commit diff
path: root/sysdeps/powerpc/powerpc32
Commit message (Collapse)AuthorAgeFilesLines
* PowerPC: fix backtrace to handle signal trampolinesAdhemerval Zanella2013-08-201-1/+65
| | | | | | This patch fixes backtrace for PPC32 and PPC64 to correctly handle signal trampolines. The 'debug/tst-backtrace6.c' also check for SA_SIGINFO handling, where is triggers another vDSO symbols for PPC32.
* PowerPC: Enable POWER8 platform sans hwcap bits.Ryan S. Arnold2013-06-241-0/+2
|
* Avoid use of "register" as optimization hint.Joseph Myers2013-06-072-6/+6
|
* Fix leading whitespaces.Ondrej Bilka2013-06-062-2/+2
|
* Remove trailing whitespace.Joseph Myers2013-06-0528-130/+130
|
* Avoid crashing in LD_DEBUG when program name is unavailableSiddhesh Poyarekar2013-05-291-2/+1
| | | | | | | | | Resolves: #15465 The program name may be unavailable if the user application tampers with argc and argv[]. Some parts of the dynamic linker caters for this while others don't, so this patch consolidates the check and fallback into a single macro and updates all users.
* PowerPC: modf optimization fixAdhemerval Zanella2013-04-261-0/+2
| | | | | | | This patch fix the 3c0265394d9ffedff2b0de508602dc52e077ce5c commits by correctly setting minimum architecture for modf PPC optimization to power5+ instead of power5 (since only on power5+ round/ceil will be inline to inline assembly).
* PowerPC: modf optimizationAdhemerval Zanella2013-04-231-0/+2
| | | | | This patch implements modf/modff optimization for POWER by focus on FP operations instead of relying in integer ones.
* PowerPC: remove branch prediction from rint implementationAdhemerval Zanella2013-04-012-6/+6
| | | | | | | | The branch prediction hints is actually hurts performance in this case. The assembly implementation make two assumptions: 1. 'fabs (x) < 2^52' is unlikely and 2. 'x > 0.0' is unlike (if 1. is true). Since it a general floating point function, expected input is not bounded and then it is better to let the hardware handle the branches.
* PowerPC: .eh_frame info in crt1.o isn't useful and triggers gold bug 14675.Alan Modra2013-03-281-0/+7
| | | | | | | The .eh_frame info in crt1.o isn't useful and this patch prevents it from being generated on PowerPC. It triggers the following gold bug: http://sourceware.org/bugzilla/show_bug.cgi?id=14675
* Consolidate copies of mp code in powerpcSiddhesh Poyarekar2013-03-083-221/+2
| | | | | Retain a single copy of the mp code in power4 instead of the two identical copies in powerpc32 and powerpc64.
* Merge powerpc slowexp.c into generic codeSiddhesh Poyarekar2013-03-072-65/+1
|
* Merge powerpc slowpow.c into generic codeSiddhesh Poyarekar2013-03-072-93/+1
|
* Use an intermediate variable to sum exponents in powerpc __mul and __sqrSiddhesh Poyarekar2013-03-071-5/+6
|
* Use generic mpa.c code for everything except __mul and __sqrSiddhesh Poyarekar2013-03-071-628/+4
|
* Remove powerpc32 strncmp comments about bounded pointers.Joseph Myers2013-03-043-9/+0
|
* Remove powerpc32 bounded-pointers code.Joseph Myers2013-02-2844-436/+118
|
* Sync up ppc add_magnitudes and sub_magnitudes with default codeSiddhesh Poyarekar2013-02-281-52/+60
|
* Sync up powerpc __mp_dbl with default codeSiddhesh Poyarekar2013-02-251-3/+1
|
* Mark __inv as static in powerpcSiddhesh Poyarekar2013-02-211-1/+1
|
* Fix whitespace differences between generic and powerpc mpa.cSiddhesh Poyarekar2013-02-211-1/+1
|
* Mark ZERO inputs to __mul as unlikely on powerpcSiddhesh Poyarekar2013-02-211-1/+1
| | | | Syncs up with generic code.
* Copy comment about inner loop from powerpc mpa.c to the default oneSiddhesh Poyarekar2013-02-201-1/+1
|
* Remove redundant return keywordSiddhesh Poyarekar2013-02-141-13/+0
|
* New __sqr function as a faster special case of __mulSiddhesh Poyarekar2013-02-141-0/+100
|
* Remove __ptrvalue, __bounded and __unbounded.Joseph Myers2013-02-131-2/+2
|
* Remove BOUNDED_N and BOUNDED_1.Joseph Myers2013-02-011-3/+1
|
* Remove use of mpa2.hAndreas Schwab2013-01-201-1/+0
|
* Fix code formatting in mpa.cSiddhesh Poyarekar2013-01-141-269/+534
| | | | This includes the overridden mpa.c in power4.
* Remove unnecessary local variable mptwoSiddhesh Poyarekar2013-01-141-4/+0
|
* Update comments in mpa.cSiddhesh Poyarekar2013-01-091-70/+49
| | | | Fixed comment style and clearer wording in some cases.
* Fix spelling errors in sysdeps/powerpc files.Anton Blanchard2013-01-0721-35/+35
|
* Remove unused __cr and __cpymnSiddhesh Poyarekar2013-01-041-47/+0
|
* Fix build failure on power4 processorsSiddhesh Poyarekar2013-01-041-3/+7
| | | | | The power4-specific mpa.c depended on some global variables that were removed by earlier patches. Also, it did not define mpone and mptwo.
* Update copyright notices with scripts/update-copyrights.Joseph Myers2013-01-02133-136/+133
|
* Add script to update copyright notices and reformat some to facilitate its use.Joseph Myers2013-01-016-9/+6
|
* Put __NO_FPRS__ around floating point opcodes in powerpc32/dl-trampoline.S.Sebastan Andrzej Siewior2012-11-011-0/+4
|
* Add missing magic to GLIBC_PROVIDES.Roland McGrath2012-10-091-82/+0
|
* Add versions of wcscpy, wcschr, wcsrchr for power6/power7.Will Schmidt2012-08-223-0/+280
| | | | | | | | | | | | | | Initially based on the versions found in wcsmbs/* ; these files have been changed by hand unrolling, and adding some additional variables to allow some read-ahead to occur, which then relieves some of the wait-for-increment/wait-for-load/wait-for-compare-results pressure that was slowing down every iteration through the while-loop. For 64-bit Power7, These changes give an approx 20% throughput boost for the wcschr and wcsrchr functions; and approx 40% boost for the wcscpy function. 32-bit improvements appear to be slightly better with ~ %30 and ~ %45 respectively. Results for Power6 closely match those for power7.
* [Powerpc] Tune/optimize powerpc{32,64}/power7/memchr.S.Will Schmidt2012-08-211-20/+58
| | | | | | | | | | | | Assorted tweaking, twisting and tuning to squeeze a few additional cycles out of the memchr code. Changes include bypassing the shift pairs (sld,srd) when they are not required, and unrolling the small_loop that handles short and trailing strings. Per scrollpipe data measuring aligned strings for 64-bit, these changes save between five and eight cycles (9-13% overall) for short strings (<32), Longer aligned strings see slight improvement of 1-3% due to bypassing the shifts and the instruction rearranging.
* Get rid of ASM_TYPE_DIRECTIVE{,_PREFIX}.Marek Polacek2012-08-021-9/+9
|
* Move testsuite audit definitions to sysdeps tst-audit.h files.Joseph Myers2012-07-261-0/+25
|
* Split tls-macros.h in sysdeps directories.Adhemerval Zanella2012-07-191-0/+87
| | | | Split PowerPC definitions in PPC32 and PPC64 headers.
* Remove TLS configure checks.Marek Polacek2012-07-172-79/+0
|
* Get rid of ASM_GLOBAL_DIRECTIVE.Marek Polacek2012-07-107-141/+141
|
* Fix missing _mcount@GLIBC_2.0 on powerpc32Andreas Schwab2012-07-063-2/+18
|
* Move __mcount_internal from GLIBC_PRIVATE to GLIBC_2.16Andreas Schwab2012-06-022-0/+20
|
* Fix missing declarationAndreas Schwab2012-05-261-0/+1
|
* Optimize handling of denormals in logb/logbf/logblAndreas Schwab2012-05-262-11/+10
|
* ppc: Pass hwcap to ifuncs.Richard Henderson2012-05-252-4/+5
| | | | | | | | | | * sysdeps/powerpc/powerpc32/dl-irel.h (elf_ifunc_invoke): Pass dl_hwcap to ifunc resolver. * sysdeps/powerpc/powerpc32/dl-machine.h (elf_machine_rela): Use elf_ifunc_invoke. * sysdeps/powerpc/powerpc64/dl-irel.h (elf_ifunc_invoke): Pass dl_hwcap to ifunc resolver. * sysdeps/powerpc/powerpc64/dl-machine.h (resolve_ifunc): Likewise.
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-11-16 18:31:24 +0000