Use direct momentum in opt-in shifted blocked equilibrium

tests/unit/cpp/collision_regression.cpp

@@ -13,6 +13,8 @@
 #define OMEGA_COLLISION_MAX 1.99f
 struct Params {float omega, fx, fy, fz;} d_params;
 #include "core/descriptors.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"