vecmathlib - vecmathlib forked from https://bitbucket.org/eschnett/vecmathlib for POWER8 improvements

	Commit message (Collapse)	Author	Age	Files	Lines
...
*	Add more tests for type conversions and rounding	Erik Schnetter	2013-03-21	2	-4/+53
\|
*	Correct rounding and conversion functions	Erik Schnetter	2013-03-21	5	-64/+69
\|
*	Remove typeinfo work-around that is not necessary any more	Erik Schnetter	2013-03-21	1	-13/+3
\|
*	Disable GNU extensions	Erik Schnetter	2013-03-21	2	-8/+8
\|
*	Simplify remainder() and fmod()	Erik Schnetter	2013-03-21	1	-4/+8
\|
*	Don't use typeinfo	Erik Schnetter	2013-03-21	4	-18/+22
\|
*	Merged in visit0r/vecmathlib (pull request #3)	Erik Schnetter	2013-03-21	5	-7/+23
\|\ \| \| \| \|	Fixes to make it build with Clang++ 3.2 using libstdc++ from Debian 6.0.
\| *	Didn't mean to commit that :)	Pekka Jääskeläinen	2013-03-21	1	-4/+0
\| \|
\| *	Fixes to make it build with Clang++ 3.2 using libstdc++ from Debian 6.0.	Pekka Jääskeläinen	2013-03-21	5	-7/+27
\|/
*	Update list of pocl functions (remove temporarily disabled "clamp")	Erik Schnetter	2013-03-20	1	-1/+1
\|
*	Output configuration settings	Erik Schnetter	2013-03-20	1	-0/+21
\|
*	Add _cl_ prefix to some functions	Erik Schnetter	2013-03-19	1	-20/+54
\|
*	Disable clamp, since vecmathlib only provides the floating-point version	Erik Schnetter	2013-03-19	1	-2/+3
\|
*	Remove __vml_ prefix for pocl wrappers	Erik Schnetter	2013-03-15	1	-17/+18
\|
*	Remove explicit "inline" declarations	Erik Schnetter	2013-03-15	8	-8/+8
\|
*	Improve fdim	Erik Schnetter	2013-03-15	1	-1/+1
\|
*	Introduce "builtin" vectors (still disabled)	Erik Schnetter	2013-03-15	5	-6/+1178
\|
*	Provide vector types with 8 and 16 bit precision	Erik Schnetter	2013-02-19	6	-31/+1373
\| \| \| \|	Use non-functional dummy float types fp8 and fp16.
*	Beautify code	Erik Schnetter	2013-02-19	2	-2/+2
\|
*	Improve lsr() implementation	Erik Schnetter	2013-02-19	1	-12/+2
\|
*	Correct definitions of lsr, >>, and << for vector shift arguments	Erik Schnetter	2013-02-19	4	-99/+75
\|
*	Define all() and any() inside class	Erik Schnetter	2013-02-19	4	-96/+72
\|
*	Increase output precision when tests fail	Erik Schnetter	2013-02-19	1	-5/+7
\|
*	Output absolute error when a test fails	Erik Schnetter	2013-02-19	1	-0/+2
\|
*	Rename makefile variable for clarity	Erik Schnetter	2013-02-19	1	-3/+3
\|
*	Use double2 instead of float1 as example	Erik Schnetter	2013-02-19	1	-2/+2
\|
*	Instantiate operator[] and set_elt()	Erik Schnetter	2013-02-19	1	-0/+31
\|
*	Turn instantiations into a library	Erik Schnetter	2013-02-19	2	-6/+2
\|
*	Delegate implementing operator[] and set_elt to the compiler	Erik Schnetter	2013-02-19	4	-149/+17
\|
*	Add rint(), correct round()	Erik Schnetter	2013-02-19	14	-27/+93
\|
*	Implement pocl functions that take pointer arguments	Erik Schnetter	2013-02-18	3	-158/+199
\|
*	Generate pocl-compatible OpenCL math function bindings	Erik Schnetter	2013-02-17	13	-358/+922
\|
*	Create libvecmathlib.a containing implementations of most math functions	Erik Schnetter	2013-02-16	2	-0/+359
\|
*	Add cbrt, hypot, trunc; rename scalbn to ldexp	Erik Schnetter	2013-02-16	17	-95/+237
\|
*	Replace assert(0) by __builtin_unreachable()	Erik Schnetter	2013-02-15	4	-11/+11
\|
*	Change order of tests	Erik Schnetter	2013-02-15	1	-4/+5
\|
*	Replace all assert() by VML_ASSERT()	Erik Schnetter	2013-02-15	14	-22/+8
\|
*	Examine log() machine code	Erik Schnetter	2013-02-15	1	-0/+3
\|
*	Optimize log() more	Erik Schnetter	2013-02-15	1	-6/+9
\|
*	Optimize log()	Erik Schnetter	2013-02-15	3	-183/+179
\|
*	Update README	Erik Schnetter	2013-02-15	1	-1/+2
\|
*	Look at exp() code	Erik Schnetter	2013-02-15	1	-0/+3
\|
*	Speed up exp()	Erik Schnetter	2013-02-15	1	-3/+21
\|
*	Use optimised coefficients for exp()	Erik Schnetter	2013-02-14	1	-18/+31
\|
*	Update sin() coefficients	Erik Schnetter	2013-02-14	1	-18/+16
\|
*	Update scripts and coefficients	Erik Schnetter	2013-02-14	2	-1088/+1091
\|
*	Add Mathematica script to generate optimised polynomial coefficients	Erik Schnetter	2013-02-14	2	-0/+1535
\| \| \| \|	Also add script output with these coefficients.
*	Add "instantiations.cc" to look at generated machine code	Erik Schnetter	2013-02-14	3	-0/+37
\|
*	Clean up vector classes	Erik Schnetter	2013-02-14	6	-132/+1561
\| \| \| \| \| \|	realvec<T,N>: machine-specific, optimised implementations realpseudovec<T,N>: scalarised implementation based on libm (for benchmark comparisons) realtestvec<T,N>: scalarised implementation without libm, using only vecmathlib's algorithms (for correctness testing)
*	Correct sum() implementation	Erik Schnetter	2013-02-14	1	-1/+1
\|