MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / fma

Function fma

samples/common/half.h:2956–2959  ·  view source on GitHub ↗

Fused multiply add. \param x first operand \param y second operand \param z third operand \return ( \a x * \a y ) + \a z rounded as one operation. template typename enable ::type fma(T x, U y, V z) { return functions::fma(x, y, z); }

Source from the content-addressed store, hash-verified

2954// template<typename T,typename U,typename V> typename enable<expr,T,U,V>::type fma(T x, U y, V z) { return
2955// functions::fma(x, y, z); }
2956inline expr fma(half x, half y, half z)
2957{
2958 return functions::fma(x, y, z);
2959}
2960inline expr fma(half x, half y, expr z)
2961{
2962 return functions::fma(x, y, z);

Callers 1

fmaMethod · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected