Use direct momentum in opt-in shifted blocked equilibrium

tests/unit/cpp/semantic_regression.cpp

@@ -34,6 +34,8 @@ inline int obs_torque_index(int,int){return 0;}
 #include "core/descriptors.cuh"
 #include "core/precision.cuh"
 #include "core/layout.cuh"
+// Host round-to-nearest shim; CUDA intrinsic behavior is tested on-device.
+inline float __fdiv_rn(float a, float b) { return a / b; }
 #include "operators/macro.cuh"
 #include "operators/collision_srt.cuh"
 #include "operators/collision_trt.cuh"