MCPcopy Create free account
hub / github.com/ARM-software/ComputeLibrary / fdim

Method fdim

include/half/half.hpp:1337–1344  ·  view source on GitHub ↗

Positive difference implementation. \param x first operand \param y second operand \return Positive difference stored in single-precision

Source from the content-addressed store, hash-verified

1335 /// \param y second operand
1336 /// \return Positive difference stored in single-precision
1337 static expr fdim(float x, float y)
1338 {
1339 #if HALF_ENABLE_CPP11_CMATH
1340 return expr(std::fdim(x, y));
1341 #else
1342 return expr((x<=y) ? 0.0f : (x-y));
1343 #endif
1344 }
1345
1346 /// Fused multiply-add implementation.
1347 /// \param x first operand

Callers

nothing calls this directly

Calls 2

exprClass · 0.85
fdimFunction · 0.85

Tested by

no test coverage detected