Age | Commit message (Collapse) | Author |
|
|
|
Backport of d5e0b9bd6e296f3ec5263fa296d39f3fed9b8fa2.
|
|
Pick up dynamic linker fix related to bugzilla 12454 which is:
Inconsistency detected by ld.so: dl-deps.c: 622: _dl_map_object_deps:
Assertion `nlist > 1' failed!
|
|
|
|
39d4957f7d2a3312cf43419a56c95096abaa429e.
|
|
|
|
This commit merges in the following three origin/master changes into a
single commit.
commit 8ff41c4601f8b8d7dfa6682f596dc4071823424d
Author: Will Schmidt <will_schmidt@vnet.ibm.com>
Date: Wed Apr 18 16:44:27 2012 -0500
Have memmove call __builtin_memcopy on PowerPC if src and dest
don't overlap.
commit 6b652f46c3935088082bb5870b6fd9edbaa92125
Author: Will Schmidt <will_schmidt@vnet.ibm.com>
Date: Wed Apr 18 15:34:23 2012 -0500
Further simplify power6 wordcopy by removing switch statements.
This fix replaces switch statements that contain individual
[fwd|bwd]_align_merge (<constant>) calls with a single
[fwd|bwd]_align_merge (align) call.
commit b282631e367f474bbd9e5d92e2aa54b3ce44efe8
Author: Will Schmidt <will_schmidt@vnet.ibm.com>
Date: Wed Apr 18 14:52:25 2012 -0500
Simplify power6 wordcopy by adding [fwd|bwd]_align_merge macros.
|
|
|
|
|
|
|
|
|
|
This patch provides throughput boost for the strcasecmp function
(25% on ppc32 and 40% on ppc64) and strncasecmp (15% on both ppc32
and ppc64) for POWER7. The optimization is done by manually
(strcasecmp) or automatically (strncasecmp) unrolling the test loop
to avoid CPU stalls caused by a test followed by a load.
|
|
This patch provides throughput boost for the nearbyint[f] functions
for POWER. For POWER7, it improves performance for nearbyintf from
5 (ppc32) to 6 times (ppc64) and for nearbyint from 2.5 up to 5
times. For POWER6 it improves nearbyintf up to 2x (ppc64) and
nearbyint up to 4x.
|
|
Backport of commit #ee2aafe08e68c88412b7dcfa4b1e0d11789348f8
|
|
Backport of commit #850fb039cec802072f70ed9763927881bbbf639c
|
|
This patch creates inline assembly functions that use intrinsic PPC
floating point instructions when the platform supports them but rely on
the internal GLIBC functions when the instructions are not implemented
(for instance, on POWER4).
|
|
libm is now somewhat integrated with gcc's -ffinite-math-only option
and lots of the wrapper functions have been optimized.
Backport of commit #0ac5ae2335292908f39031b1ea9fe8edce433c0f
|
|
Backport of commit #edc121be8b53da57950daf6f42a619b5826f30b6
|
|
This patch moves the ppc32 _mcount to libc_shared.a, fixing a
long-standing bug with profiling of secure-plt shared libraries and
PIEs. The problem is that a ppc32 PIC PLT call stub uses r30 (GOT
pointer) to load the function address from the PLT, r30 being set up
in the function prologue, but _mcount is called before the function
prologue. So chances are good that r30 will be pointing to the
executable GOT when trying to call _mcount in a shared lib function.
A similar problem can occur in a PIE if a shared lib calls a function
in the executable.
|
|
This patch addresses some IBM Long Double 128 fmal () test-ldouble.out
and test-ildoubl.out failures. If the ‘x’ and ‘y’ parameters are
finite values and ‘z’ is infinity, the result of fmal () should be ‘z’
not NaN.
|
|
15%. The 32-bit throughput is not notably affected by this change, so
the change to the 32-bit code is done to keep the two files in sync
with each other.
|
|
These POWER optimizations remove most of the FP->INT conversions in
hypot/hypotf and sinf/cosf on POWER making the computation done with
FP operations instead. This eliminates Load-Hit-Store (LHS) stalls,
increasing performance of hypot/hypotf (by about 100% on POWER7 and
12% on POWER6) and sinf/cosf (by 80% on POWER7 and 30% on POWER6).
|
|
Avoid deadcode and remove regressive optimization for POWER[5|6].
Revert git commit 6559b01648c2a08ea862ae923ce7d86c6e8cca45
Trigonometric optimizations for POWER cpus
|
|
|
|
(cherry picked from commit 6b1e7d1992cd89032df431c0e0d1418b97e57cd8)
|
|
(cherry picked from commit 2c3d9ba9a332cecb009b97ebac5bb78a13118c7c)
|
|
(cherry picked from commit ec11dbe1aabbb45d41f5e9c21e315e2496f3b473)
|
|
These optimizations remove most of the FP->INT conversions making
the computation done with FP operations instead. This eliminates
Load-Hit-Store (LHS) stalls on POWER, increasing performance of
hypot/hypotf (about 50% on POWER7, 25% on POWER6, and 30% on POWER5)
and sinf/cosf (30% on POWER7, 15% on POWER6, and 10% on POWER5).
(cherry picked from commit 5939fc0867e1616a537c26d84ca1612b53b0303e)
|
|
(cherry picked from commit 4c559bcdf38d7b655860c1a31c590109f37cc0fe)
|
|
|
|
(cherry picked from commit c1d0e639a95d6d3d3f1c1f70cf97d596bd5a24ec)
|
|
recent versions of GCC to compile GLIBC when altivec is configured.
2009-11-06 Petr Baudis <pasky@suse.cz>
* include/sys/uio.h: Change __vector to __iovec to avoid clash
with altivec.
(cherry picked from commit bcb75669959f740e04208b773e99d87c5342dc34)
|
|
|
|
|
|
|
|
(cherry picked from commit 4bff6e0175ed195871f4e01cc4c4c33274b8f6e3)
|
|
(Cherry picked from commit f2092faf2b6bd491a1891d5d5e393a8bf85d01d7)
|
|
(cherry picked from commit e23fe25b33324a9ea992276c1a4f04127bf9ba4b)
|
|
(cherry picked from commit f12a32e6f02c058c4996a138f16828f772059116)
|
|
(cherry picked from commit 34fe483e121660aff222ec1c15d57804f64191ea)
|
|
(cherry picked from commit 4420675c9d361643d1179ad67e0bb35c8fbdd1ce)
|
|
(cherry picked from commit e6c61494125126d2ba77e5d99f83887a2ed49783)
|
|
(cherry picked from commit ccfe366e6fc64bb81183480bd2ae113041d3c84c)
|
|
2011-05-03 Ryan S. Arnold <rsa@us.ibm.com>
* elf/dynamic-link.h (elf_get_dynamic_info): Remove assert()
around DT_RUNPATH and DT_RPATH which prevents running a dynamic
linker with an embedded RPATH flag, which is what a compiler
modified to embed a non-default INTERP section would do.
|
|
(cherry picked from commit e23fe25b33324a9ea992276c1a4f04127bf9ba4b)
|
|
(cherry picked from commit d55fd7a5573ea7c7c14af95bc37618469cde8a5f)
|
|
(cherry picked from commit 2206397e1c46f69fb20eeb3de1920d3a7014c325)
|
|
We do not track lists of resolved bugs within stable releases.
|
|
(cherry picked from commit 8517b15ee8e39fed11afb784fd0e249d977849f4)
|
|
(cherry picked from commit 10a656fe33d8257531ff3e9a882d3fd7db6ce5b3)
|