1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
|
#include <clc/clc.h>
#include "../../../generic/lib/clcmacro.h"
_CLC_DEF _CLC_OVERLOAD float fmax(float x, float y)
{
/* fcanonicalize removes sNaNs and flushes denormals if not enabled.
* Otherwise fmax instruction flushes the values for comparison,
* but outputs original denormal */
x = __builtin_canonicalizef(x);
y = __builtin_canonicalizef(y);
return __builtin_fmaxf(x, y);
}
_CLC_BINARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, float, fmax, float, float)
#ifdef cl_khr_fp64
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
_CLC_DEF _CLC_OVERLOAD double fmax(double x, double y)
{
x = __builtin_canonicalize(x);
y = __builtin_canonicalize(y);
return __builtin_fmax(x, y);
}
_CLC_BINARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, double, fmax, double, double)
#endif
#ifdef cl_khr_fp16
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
_CLC_DEF _CLC_OVERLOAD half fmax(half x, half y)
{
if (isnan(x))
return y;
if (isnan(y))
return x;
return (y < x) ? x : y;
}
_CLC_BINARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, half, fmax, half, half)
#endif
#define __CLC_BODY <../../../generic/lib/math/fmax.inc>
#include <clc/math/gentype.inc>
|
