experiment: isolate full-state regularized west velocity inlet

src/CelerisLab/config.py

@@ -32,6 +32,7 @@ INLET_SCHEME_MAP = {
     "channel_stabilized": 1,
     "equilibrium": 2,
     "regularized": 3,
+    "experimental_regularized_full9": 4,
 }
 OUTLET_MAP = {"neq_extrap": 0, "zero_gradient": 1, "blended": 2}
 Y_WALL_BC_MAP = {"bounce_back": 0, "free_slip": 1, "on_site_velocity": 2}
@@ -162,6 +163,11 @@ class LBMConfig:
             raise ValueError("wall_slot_width requires on_site_velocity and velocity=0")
         if self.top_wall_bc == "reservoir" and (self.y_wall_bc != "on_site_velocity" or self.velocity != 0):
             raise ValueError("reservoir requires on_site_velocity and velocity=0")
+        if self.inlet_scheme == "experimental_regularized_full9":
+            if (not self.is_d2q9 or self.collision != "SRT"
+                    or self.streaming != "double_buffer" or self.store_precision != "FP32"
+                    or self.les_enabled or self.y_wall_bc != "bounce_back"):
+                raise ValueError("experimental_regularized_full9 requires D2Q9/SRT/FP32/double_buffer, bounce_back walls, no LES")
         if self.y_wall_bc == "on_site_velocity":
             if (not self.is_d2q9 or self.collision != "SRT"
                     or self.streaming != "double_buffer" or self.store_precision != "FP32"

src/CelerisLab/lbm/kernels/boundary/inlet/common.cuh

@@ -74,7 +74,7 @@ __device__ __forceinline__ float west_velocity_rho_closure_d3q19(
 
 __device__ __forceinline__ bool inlet_scheme_uses_post_collision_ghost()
 {
-#if INLET_SCHEME == 0
+#if INLET_SCHEME == 0 || INLET_SCHEME == 4
     return true;
 #else
     return false;

src/CelerisLab/lbm/kernels/boundary/inlet/experimental_full9.cuh

@@ -0,0 +1,36 @@
+// Experimental D2Q9 west velocity boundary: full-state stress regularization.
+// Palabos boundaryTemplates::compute_PiNeq / regularized velocity completion.
+// This returns PRE-collision populations. The existing step kernel collides once.
+#ifndef CELERIS_EXPERIMENTAL_FULL9_INLET_CUH
+#define CELERIS_EXPERIMENTAL_FULL9_INLET_CUH
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ inline void apply_experimental_full9_inlet_d2q9(
+    float* __restrict__ f, float ux_target, float uy_target)
+{
+    const float rho = west_velocity_rho_closure_d2q9(f, ux_target);
+    float eq[9];
+    compute_feq(rho, ux_target, uy_target, eq);
+    // Only known pulled directions are read; unknown wrapped q1/5/7 are ignored.
+    // f and eq use the same shifting convention, so weights cancel in K.
+    const float k2 = f[2] - eq[2];
+    const float k3 = f[3] - eq[3];
+    const float k4 = f[4] - eq[4];
+    const float k6 = f[6] - eq[6];
+    const float k8 = f[8] - eq[8];
+    const float pxx = 2.0f * (k2 + k6 + k8);
+    const float pyy = k3 + k4 + 2.0f * (k6 + k8);
+    const float pxy = 2.0f * (k6 - k8);
+    const int cx[9] = {0, 1,-1, 0, 0, 1,-1, 1,-1};
+    const int cy[9] = {0, 0, 0, 1,-1, 1,-1,-1, 1};
+    for (int q = 0; q < 9; ++q) {
+        const float weight = q == 0 ? W0_VAL : (q < 5 ? WS_VAL : WE_VAL);
+        const float stress = weight * (
+            4.5f * (((float)(cx[q]*cx[q]) - 1.0f/3.0f) * pxx
+                  + ((float)(cy[q]*cy[q]) - 1.0f/3.0f) * pyy)
+            + 9.0f * (float)(cx[q]*cy[q]) * pxy);
+        f[q] = eq[q] + stress;
+    }
+}
+#endif
+#endif

src/CelerisLab/lbm/kernels/boundary/inlet_outlet.cuh

@@ -24,6 +24,7 @@
 #include "inlet/channel_stabilized.cuh"
 #include "inlet/equilibrium.cuh"
 #include "inlet/regularized.cuh"
+#include "inlet/experimental_full9.cuh"
 #include "outlet/pressure_neq.cuh"
 
 #if DIM == 2
@@ -45,6 +46,8 @@ __device__ __forceinline__ void apply_inlet_pull_d2q9(
 
 #if INLET_SCHEME == 0
     apply_zou_he_left_velocity_inlet_d2q9(f, u_target, v_target);
+#elif INLET_SCHEME == 4
+    apply_experimental_full9_inlet_d2q9(f, u_target, v_target);
 #elif INLET_SCHEME == 1 || INLET_SCHEME == 3
     float f_neb[NQ];
     const unsigned long k_neb = linear_index(x + 1u, y);
@@ -143,6 +146,8 @@ __device__ __forceinline__ void apply_inlet_esopull_d2q9(
 
 #if INLET_SCHEME == 0
     apply_zou_he_left_velocity_inlet_d2q9(f, u_target, v_target);
+#elif INLET_SCHEME == 4
+    apply_experimental_full9_inlet_d2q9(f, u_target, v_target);
 #elif INLET_SCHEME == 1 || INLET_SCHEME == 3
   #if INLET_SCHEME == 1
     apply_channel_stabilized_inlet_d2q9(f, f_neb, (float)y);