[Libclc-dev] [PATCH 1/2] Implement fmin using __builtin_fmin

[Tom Stellard]

This ensures correct handling of NaN / INF.

This has been tested with piglit, OpenCV, and the ocl conformance tests.
---
 generic/include/clc/math/fmin.h |  5 +----
 generic/lib/math/fmin.cl        | 13 +++++++++----
 generic/lib/math/fmin.inc       | 18 ++++++++++++++++++
 3 files changed, 28 insertions(+), 8 deletions(-)
 create mode 100644 generic/lib/math/fmin.inc

diff --git a/generic/include/clc/math/fmin.h b/generic/include/clc/math/fmin.h
index 5588ba9..d45f572 100644
--- a/generic/include/clc/math/fmin.h
+++ b/generic/include/clc/math/fmin.h
@@ -1,8 +1,5 @@
-#undef fmin
-#define fmin __clc_fmin
-
 #define __CLC_BODY <clc/math/binary_decl.inc>
-#define __CLC_FUNCTION __clc_fmin
+#define __CLC_FUNCTION fmin
 
 #include <clc/math/gentype.inc>
 
diff --git a/generic/lib/math/fmin.cl b/generic/lib/math/fmin.cl
index a61ad47..28c7d01 100644
--- a/generic/lib/math/fmin.cl
+++ b/generic/lib/math/fmin.cl
@@ -1,11 +1,16 @@
 #include <clc/clc.h>
 
+#include "../clcmacro.h"
+
+_CLC_DEFINE_BINARY_BUILTIN(float, fmin, __builtin_fminf, float, float);
+
 #ifdef cl_khr_fp64
+
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
-#endif
 
-#define FUNCTION __clc_fmin
-#define FUNCTION_IMPL(x, y) ((y) < (x) ? (y) : (x))
+_CLC_DEFINE_BINARY_BUILTIN(double, fmin, __builtin_fmin, double, double);
+
+#endif
 
-#define __CLC_BODY <binary_impl.inc>
+#define __CLC_BODY <fmin.inc>
 #include <clc/math/gentype.inc>
diff --git a/generic/lib/math/fmin.inc b/generic/lib/math/fmin.inc
new file mode 100644
index 0000000..d4b5ac2
--- /dev/null
+++ b/generic/lib/math/fmin.inc
@@ -0,0 +1,18 @@
+
+#if !defined(__CLC_SCALAR)
+
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE fmin(__CLC_GENTYPE x, float y) {
+  return fmin(x, (__CLC_GENTYPE)((__CLC_SCALAR_GENTYPE)y));
+}
+
+#ifdef cl_khr_fp64
+
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE fmin(__CLC_GENTYPE x, double y) {
+  return fmin(x, (__CLC_GENTYPE)((__CLC_SCALAR_GENTYPE)y));
+}
+
+#endif // ifdef cl_khr_fp64
+
+#endif // !defined(__CLC_SCALAR)
-- 
2.0.4