This patch adds a dispatcher for 128-bit wide vector functions in the quad library.

This patch adds a dispatcher for the scalar functions in the quad library.

This patch adds quad-precision ldexp, ilogb, fma and hypot.

Co-authored-by: shibatch <shibatch.sf.net@gmail.com>

This patch updates copyright notice.

Co-authored-by: shibatch <shibatch.sf.net@gmail.com>

This patch replaces Horner method which was used to evaluate polynomials with Estrin's method( https://en.wikipedia.org/wiki/Estrin%27s_scheme ) that allows more parallel computations with out-of-order execution.
This patch also introducing a new reduction method to tan.
With this patch, mainly computation for double-precision functions becomes faster, and the effect is like a few percent to 20 percent. For example, the ratio between execution time of the following functions before and after applying this patch is shown below.

Sleef_atan2d4_u35 : 1.21
Sleef_powd4_u10 : 1.17
Sleef_sind4_u35 : 1.10
Sleef_tand4_u10 : 1.04
Sleef_tand4_u35 : 1.17

* This patch updates the documentation.

* It also changes minor version numbers in DLL, and update files related to debian packaging.

* SPECIFICATION file is removed. This was now redundant since the accuracy specification is described in the xhtml files.

* Entered the release date.

* [CI] Add build status from travis-ci.

* [travis] Use gcc-6 compiler.

* [travis] Use gcc-7 o enable AVX512 compilation.

* [travis] Revert to gcc-6.

* [travis] Disable 128-bit float for the build.

* [travis] Adapt build system to travis environment.

The tester.c sources have been modified to pass the shell environemt
variable to the executable that is invoked with `execvpe`.

A new target "test" have been added to the root Makefile to run the
"iut" tests.

* [travis] Use -lrt for linking clock_gettime.

* [travis] Add -ltr for old gcc.

* [travis] Add a missing -ltr for iutavx build.

* [travis] Fix compilation failure.

It is -lrt, not -ltr...

* [travis] Use travis default behaviour.

* [travis] Revert ENABLEFLOAT128 support for gcc >= 5.

The following patch enables SLEEF to use the Advanced SIMD vector
extension for the AArch64 execution mode of the A64 instruction set on
ARMv8 (AArch64 AdvSIMD hereafter).

The suffix "advsimd" is consistently used across the sources and the
build and test systems to identify this extension.

The patch have been tested on native hardware for single and double
precision for the following cases:

* iut: scalar
* iutadvsimd: AArch64 AdvSIMD
* iutcevext: clang vector extentions on AArch64

The patch includes also the following minor changes:

* the copyright notice in the README file has been changed to assign
  copyright to other contributors;
* libsleef-dft has been temporarly disabled for AArch64 builds;
* set some shell scripts permission to executable.

Suggestion to add affirmative statement regarding license for contributions.  
You may also want to add "and contributors" for the copyright notice or some other way to acknowledge copyright is held by multiple people or organizations.