Files
llvm-project/libclc/generic/lib/math/fmax.cl
Tom Stellard 1ded220cc0 Implement fmax using __builtin_fmax
This ensures correct handling of NaNi.

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

llvm-svn: 233713
2015-03-31 16:59:23 +00:00

17 lines
333 B
Common Lisp

#include <clc/clc.h>
#include "../clcmacro.h"
_CLC_DEFINE_BINARY_BUILTIN(float, fmax, __builtin_fmaxf, float, float);
#ifdef cl_khr_fp64
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
_CLC_DEFINE_BINARY_BUILTIN(double, fmax, __builtin_fmax, double, double);
#endif
#define __CLC_BODY <fmax.inc>
#include <clc/math/gentype.inc>