aboutsummaryrefslogtreecommitdiff
path: root/include
AgeCommit message (Collapse)AuthorFilesLines
2013-06-12Set/restore rounding mode only when neededSiddhesh Poyarekar1-0/+10
The most common use case of math functions is with default rounding mode, i.e. rounding to nearest. Setting and restoring rounding mode is an unnecessary overhead for this, so I've added support for a context, which does the set/restore only if the FP status needs a change. The code is written such that only x86 uses these. Other architectures should be unaffected by it, but would definitely benefit if the set/restore has as much overhead relative to the rest of the code, as the x86 bits do. Here's a summary of the performance improvement due to these improvements; I've only mentioned functions that use the set/restore and have benchmark inputs for x86_64: Before: cos(): ITERS:4.69335e+08: TOTAL:28884.6Mcy, MAX:4080.28cy, MIN:57.562cy, 16248.6 calls/Mcy exp(): ITERS:4.47604e+08: TOTAL:28796.2Mcy, MAX:207.721cy, MIN:62.385cy, 15543.9 calls/Mcy pow(): ITERS:1.63485e+08: TOTAL:28879.9Mcy, MAX:362.255cy, MIN:172.469cy, 5660.86 calls/Mcy sin(): ITERS:3.89578e+08: TOTAL:28900Mcy, MAX:704.859cy, MIN:47.583cy, 13480.2 calls/Mcy tan(): ITERS:7.0971e+07: TOTAL:28902.2Mcy, MAX:1357.79cy, MIN:388.58cy, 2455.55 calls/Mcy After: cos(): ITERS:6.0014e+08: TOTAL:28875.9Mcy, MAX:364.283cy, MIN:45.716cy, 20783.4 calls/Mcy exp(): ITERS:5.48578e+08: TOTAL:28764.9Mcy, MAX:191.617cy, MIN:51.011cy, 19071.1 calls/Mcy pow(): ITERS:1.70013e+08: TOTAL:28873.6Mcy, MAX:689.522cy, MIN:163.989cy, 5888.18 calls/Mcy sin(): ITERS:4.64079e+08: TOTAL:28891.5Mcy, MAX:6959.3cy, MIN:36.189cy, 16062.8 calls/Mcy tan(): ITERS:7.2354e+07: TOTAL:28898.9Mcy, MAX:1295.57cy, MIN:380.698cy, 2503.7 calls/Mcy So the improvements are: cos: 27.9089% exp: 22.6919% pow: 4.01564% sin: 19.1585% tan: 1.96086% The downside of the change is that it will have an adverse performance impact on non-default rounding modes, but I think the tradeoff is justified.
2013-06-11Fix indentation and add copyright header to time.hSiddhesh Poyarekar1-4/+21
2013-06-11Fix symbol definitions for __clock_* functionsSiddhesh Poyarekar1-0/+1
__clock_gettime and other __clock_* functions could result in an extra PLT reference within libc.so if it actually gets used. None of the code currently uses them, which is why this probably went unnoticed.
2013-06-07Avoid use of "register" as optimization hint.Joseph Myers1-4/+4
2013-06-06Fix leading whitespaces.Ondrej Bilka1-1/+1
2013-05-16Add #include <stdint.h> for uint[32|64]_t usage (except installed headers).Ryan S. Arnold2-1/+2
2013-04-02New <math.h> macro named issignaling to check for a signaling NaN (sNaN).Thomas Schwinge1-0/+3
It is based on draft TS 18661 and currently enabled as a GNU extension.
2013-03-28Avoid unconditional __call_tls_dtors calls in static linking.Roland McGrath1-2/+6
2013-02-18sys/cdefs.h: export __attribute_alloc_size__Mike Frysinger2-5/+3
Since we want to use this in installed headers, move it to the installed sys/cdefs.h. This requires a slight tweaking of the name (add trailing underscores). Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2013-02-18unify xmalloc prototypes & friendsMike Frysinger1-0/+33
These prototypes are duplicated in many places. Add a dedicated header for holding prototypes for program-specific functions to avoid that. Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2013-02-18C++11 thread_local destructors supportSiddhesh Poyarekar2-0/+8
This feature is specifically for the C++ compiler to offload calling thread_local object destructors on thread program exit, to glibc. This is to overcome the possible complication of destructors of thread_local objects getting called after the DSO in which they're defined is unloaded by the dynamic linker. The DSO is marked as 'unloadable' if it has a constructed thread_local object and marked as 'unloadable' again when all the constructed thread_local objects defined in it are destroyed.
2013-02-13Remove __ptrvalue, __bounded and __unbounded.Joseph Myers1-1/+1
2013-02-12Remove redunant "warning: " prefix from stub warnings.Roland McGrath1-2/+1
2013-02-07Remove lots of inline keywords.Roland McGrath1-1/+1
2013-02-04Don't use GLIBC_PRIVATE errno outside of librariesAndreas Schwab2-12/+14
2013-02-02Improve link_map.l_addr comment.Jan Kratochvil1-1/+2
2013-01-17Fix cacos real-part inaccuracy for result real part near 0 (bug 15023).Joseph Myers1-1/+11
2013-01-16Hide reference to mktemp in libpthreadAndreas Schwab1-0/+1
2013-01-11Remove __GLIBC_HAVE_LONG_LONG.Joseph Myers1-8/+0
2013-01-10Remove __USE_ANSI.Joseph Myers1-3/+0
2013-01-02Update copyright notices with scripts/update-copyrights.Joseph Myers17-18/+17
2012-12-24Update version.h and include/features.h for 2.17 release.glibc-2.17David S. Miller1-1/+1
2012-12-07 [BZ #14898]Andreas Schwab1-1/+1
* include/link.h (FORCED_DYNAMIC_TLS_OFFSET) [NO_TLS_OFFSET == 0]: Change to -1.
2012-11-30 * sunrpc/rpc/svc.h (__svc_accept_failed): Move declaration...Siddhesh Poyarekar1-0/+2
* include/rpc/svc.h: ... here.
2012-11-26Cast to __intptr_t before casting pointer to int64H.J. Lu1-0/+16
2012-11-21Check supported DF_1_XXX bitsH.J. Lu1-0/+6
2012-11-20Add recvmmsg and sendmmsg to the generic glibc API.Thomas Schwinge1-0/+4
2012-11-04[BZ #157] Remove include/stub-tag.h for good.Thomas Schwinge1-4/+0
2012-11-03Make fma use of Dekker and Knuth algorithms use round-to-nearest (bug 14796).Joseph Myers1-0/+1
2012-11-02Compile x86 rtld with -mno-sse -mno-mmxH.J. Lu1-0/+4
2012-11-02conformtest: Add test data for fenv.h.Joseph Myers1-0/+2
2012-11-02Test _ISOMAC in include/sys/syslog.h.Joseph Myers1-0/+2
2012-10-24BZ#14743: Move clock_* symbols from librt to libc.Roland McGrath1-1/+5
2012-10-12Avoid PLT references from __get_clockfreq on powerpcAndreas Schwab1-0/+1
2012-10-11Framework to test IFUNC implementations on targetH.J. Lu1-0/+56
2012-10-04Name space hygeine for madvise.Roland McGrath1-2/+3
2012-09-12Make strtod respect the rounding mode (bug 14518).Joseph Myers1-0/+65
2012-08-18add attribute_hidden to __have_{sock_cloexec,pipe2,dup3Mike Frysinger2-4/+4
These internal knobs are not exposed as part of the public ABI, so mark them hidden to avoid generating relocations against them. Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2012-08-18split assume pipe2/dup3/sock_cloexec knobsMike Frysinger1-5/+2
We can't assume sock_cloexec and pipe2 are bound together as the former defines are found in glibc only while the latter are a combo of kernel headers and glibc. So if we do a runtime detection of SOCK_CLOEXEC, but pipe2() is a stub inside of glibc, we hit a problem. For example: main() { getgrnam("portage"); if (!popen("ls", "r")) perror("popen()"); } getgrnam() will detect that the kernel supports SOCK_CLOEXEC and then set both __have_sock_cloexec and __have_pipe2 to true. But if glibc was built against older kernel headers where __NR_pipe2 does not exist, glibc will have a ENOSYS stub for it. So popen() will always fail as glibc assumes pipe2() works. While this isn't too much of an issue for some arches as they added the functionality to the kernel at the same time, not all arches are that lucky. Since the code already has dedicated names for each feature, delete the defines wiring these three features together and make each one a proper dedicated knob. We've been carrying this in Gentoo since glibc-2.9. Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2012-08-17Split sys/param.h out into common file and sysdeps bits/param.h file.Roland McGrath1-0/+1
2012-08-15Declare __getdirentries in internal dirent.h.Roland McGrath1-0/+4
2012-08-13Add explicit acquire/release semantics to atomic_exchange_and_add.Maxim Kuvyrkov1-2/+16
2012-08-02Get rid of ASM_TYPE_DIRECTIVE{,_PREFIX}.Marek Polacek1-33/+20
2012-07-31Clean up stub accept4 definition.Roland McGrath1-2/+2
2012-07-30Fix lots of bitrot for stub configurations.Roland McGrath1-1/+1
2012-07-25Rename __secure_getenv to secure_getenvFlorian Weimer1-1/+2
2012-07-10Get rid of ASM_GLOBAL_DIRECTIVE.Marek Polacek1-15/+11
2012-06-30Release 2.16glibc-2.16.0Carlos O'Donell1-1/+1
Update version.h and include/features.h for 2.16 release.
2012-06-22Fix invalid memory access in do_lookup_x.Andreas Schwab1-4/+4
[BZ #13579] Do not free l_initfini and allow it to be reused on subsequent dl_open calls for the same library. This fixes the invalid memory access in do_lookup_x when the previously free'd l_initfini was accessed through l_searchlist when a library had been opened for the second time.
2012-06-01Remove use of INTDEF/INTUSE in stdio-commonAndreas Schwab1-0/+1
generated by cgit v1.1 at 2024-09-01 05:44:28 +0000