Jeroen Ketema 575fb84cc3 OpenCL 1.1 does not define CL_VERSION_1_2 so use hardcoded number instead ... Otherwise the test evaluates to true on OpenCL 1.1 and earlier. Since we therefore cannot use the CL_VERSION_?_? macros move them to the proper position in the top-level header. llvm-svn: 211787		2014-06-26 15:26:38 +00:00
..
atomic	Add atomic_sub and atomic_dec builtin functions	2013-09-06 20:20:21 +00:00
cl_khr_global_int32_base_atomics	Fix a C&P error in r195021 (65a950abab3cb8435ccb2646ac4773986c995c81)	2013-11-28 00:17:29 +00:00
common	Implement sign() builtin	2013-10-10 19:08:56 +00:00
float	OpenCL 1.1 does not define CL_VERSION_1_2 so use hardcoded number instead	2014-06-26 15:26:38 +00:00
geometric	Add cross for double3 and double4	2014-03-21 16:21:58 +00:00
integer	Parenthesize arguments for mad_hi	2013-09-09 14:36:21 +00:00
math	Add exp10	2014-06-25 10:06:35 +00:00
relational	relational: Implement signbit	2014-06-25 13:29:23 +00:00
shared	Add __CLC_ prefix to all macro definitions in headers	2013-07-08 17:27:02 +00:00
synchronization	…
workitem	…
as_type.h	Add missing as_{float,double} functions	2013-10-10 19:08:29 +00:00
clc.h	OpenCL 1.1 does not define CL_VERSION_1_2 so use hardcoded number instead	2014-06-26 15:26:38 +00:00
clcfunc.h	…
clctypes.h	Revert "clctypes.h: Don't rely on stddef.h for size_t and ptrdiff_t"	2014-06-16 20:21:19 +00:00
clcversion.h	Introduce CLC_VERSION macros v2	2014-06-24 09:46:52 +00:00
convert.h	Port pocl's gen_convert.py script to libclc	2013-10-10 19:09:01 +00:00