Tom Stellard adfd96f742 Fix bitselect for float/double types v2 ...

We need to reinterpret float/double types as uint/ulong in order to
perform the bitwise operations.

This has been tested with piglit, OpenCV, and the ocl conformance tests.

v2:
  - Use vector operations rather than splitting vectors into scalar
    components.

Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 231373

2015-03-05 15:31:05 +00:00

..

async

Implement async_work_group_copy builtin v3

2014-10-03 19:49:39 +00:00

atomic

Remove wrong semi-colons

2014-12-19 09:18:23 +00:00

cl_khr_global_int32_base_atomics

atomic: Add generic atom[ic]_cmpxchg

2014-09-16 22:34:49 +00:00

cl_khr_global_int32_extended_atomics

atomic: Add generic atomic_min implementation

2014-09-16 22:34:41 +00:00

cl_khr_local_int32_base_atomics

atomic: Add generic atom[ic]_cmpxchg

2014-09-16 22:34:49 +00:00

cl_khr_local_int32_extended_atomics

atomic: Add generic atomic_min implementation

2014-09-16 22:34:41 +00:00

common

Move mix from math to common

2015-03-03 21:25:08 +00:00

float

Add several missing double constant definitions

2014-07-17 22:07:35 +00:00

geometric

Add cross for double3 and double4

2014-03-21 16:21:58 +00:00

integer

Implement generic mad_sat

2014-09-02 17:55:02 +00:00

math

Move mix from math to common

2015-03-03 21:25:08 +00:00

relational

Fix bitselect for float/double types v2

2015-03-05 15:31:05 +00:00

shared

…

synchronization

…

workitem

r600: Use llvm intrinsic to read work dimension information

2014-10-15 15:08:06 +00:00

as_type.h

Add missing as_{float,double} functions

2013-10-10 19:08:29 +00:00

clc.h

Move mix from math to common

2015-03-03 21:25:08 +00:00

clcfunc.h

…

clctypes.h

Don't include <stddef.h>

2014-11-18 14:19:27 +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