Merge pull request #614 from ROCm-Developer-Tools/fma

Add overloading resolution functions for fma

[ROCm/hip commit: 3d67c9f952]

projects/hip/include/hip/hcc_detail/math_functions.h

@@ -1166,6 +1166,16 @@ long long llabs(long long x)
 #endif
 // END INTEGER
 
+__DEVICE__
+inline _Float16 fma(_Float16 x, _Float16 y, _Float16 z) {
+    return __ocml_fma_f16(x, y, z);
+}
+
+__DEVICE__
+inline float fma(float x, float y, float z) {
+    return fmaf(x, y, z);
+}
+
 #pragma push_macro("__DEF_FLOAT_FUN")
 #pragma push_macro("__DEF_FLOAT_FUN2")
 #pragma push_macro("__DEF_FLOAT_FUN2I")