zou_he inlet无法保障稳定，加入新的inlet模式

README.md

@@ -97,7 +97,7 @@ The on-disk schema matches `src/CelerisLab/configs/config_lbm.json` (nested sect
     "ddf_shifting": false,
     "les": { "enabled": false, "cs": 0.16, "closed_form": true },
     "trt": { "magic_param": 0.1875 },
-    "inlet": { "profile": "parabolic", "trt_neq_damp": 0.5 },
+    "inlet": { "profile": "parabolic", "scheme": "zou_he_local", "trt_neq_damp": 0.5 },
     "outlet": {
       "mode": "neq_extrap",
       "backflow_clamp": true,

src/CelerisLab/common/checkpoint.py

@@ -85,6 +85,7 @@ def save_checkpoint(field, stepper, lbm_cfg, bodies, path=None):
             "les_closed_form": cfg.les_closed_form,
             "trt_magic_param": cfg.trt_magic_param,
             "inlet_profile": cfg.inlet_profile,
+            "inlet_scheme": cfg.inlet_scheme,
             "outlet_mode": cfg.outlet_mode,
             "omega_min": cfg.omega_min, "omega_max": cfg.omega_max,
         }

src/CelerisLab/config.py

@@ -26,6 +26,12 @@ COLLISION_MAP = {"SRT": 0, "TRT": 1, "MRT": 2}
 STREAMING_MAP = {"double_buffer": 0, "esopull": 1}
 PRECISION_MAP = {"FP32": 0, "FP16S": 1, "FP16C": 2}
 INLET_MAP = {"uniform": 0, "parabolic": 1}
+INLET_SCHEME_MAP = {
+    "zou_he_local": 0,
+    "channel_stabilized": 1,
+    "equilibrium": 2,
+    "regularized": 3,
+}
 OUTLET_MAP = {"neq_extrap": 0, "zero_gradient": 1, "blended": 2}
 Y_WALL_BC_MAP = {"bounce_back": 0, "free_slip": 1}
 DTYPE_MAP = {"FP32": "float", "FP64": "double"}
@@ -66,10 +72,12 @@ class LBMConfig:
     les_closed_form: bool = True
     trt_magic_param: float = 0.1875
     inlet_profile: str = "parabolic"
+    inlet_scheme: str = "zou_he_local"
     outlet_mode: str = "neq_extrap"
     outlet_blend_alpha: float = 0.7
     outlet_backflow_clamp: bool = True
     inlet_trt_neq_damp: float = 0.5
+    inlet_regularized_neq_damp: float = 0.5
     outlet_srt_neq_damp: float = 0.5
     y_wall_bc: str = "bounce_back"
     omega_min: float = 0.01
@@ -106,6 +114,8 @@ class LBMConfig:
         assert self.data_type in DTYPE_MAP, f"Unknown data_type: {self.data_type}"
         assert self.store_precision in PRECISION_MAP, (
             f"Unknown store_precision: {self.store_precision}")
+        assert self.inlet_scheme in INLET_SCHEME_MAP, (
+            f"Unknown inlet_scheme: {self.inlet_scheme}")
         if self.store_precision == "FP16C":
             raise ValueError(
                 "store_precision='FP16C' is not supported in the current runtime path. "
@@ -119,6 +129,12 @@ class LBMConfig:
         assert self.nx > 0 and self.ny > 0 and self.nz > 0
         if self.dim == 2:
             assert self.nz == 1, "nz must be 1 for 2D"
+        if not (0.0 <= self.inlet_trt_neq_damp <= 1.0):
+            raise ValueError("method.inlet.trt_neq_damp must lie in [0, 1].")
+        if not (0.0 <= self.inlet_regularized_neq_damp <= 1.0):
+            raise ValueError("method.inlet.regularized_neq_damp must lie in [0, 1].")
+        if not (0.0 <= self.outlet_srt_neq_damp <= 1.0):
+            raise ValueError("method.outlet.srt_neq_damp must lie in [0, 1].")
         if self.dim == 3 and self.y_wall_bc == "free_slip":
             raise ValueError("y_wall_bc='free_slip' is currently supported for D2Q9 only.")
         if self.omega_max >= 2.0:
@@ -156,6 +172,7 @@ class LBMConfig:
             "LES_CS": f"{self.les_cs:.6f}f",
             "LES_CLOSED_FORM": int(self.les_closed_form),
             "INLET_PROFILE": INLET_MAP[self.inlet_profile],
+            "INLET_SCHEME": INLET_SCHEME_MAP[self.inlet_scheme],
             "OUTLET_MODE": OUTLET_MAP[self.outlet_mode],
             "OUTLET_BLEND_ALPHA": f"{self.outlet_blend_alpha:.3f}f",
             "OUTLET_BACKFLOW_CLAMP": int(self.outlet_backflow_clamp),
@@ -164,6 +181,7 @@ class LBMConfig:
             "OMEGA_COLLISION_MAX": f"{self.omega_max:.3f}f",
             "TRT_MAGIC_PARAM": f"{self.trt_magic_param:.6f}f",
             "INLET_TRT_NEQ_DAMP": f"{self.inlet_trt_neq_damp:.4f}f",
+            "INLET_REGULARIZED_NEQ_DAMP": f"{self.inlet_regularized_neq_damp:.4f}f",
             "OUTLET_SRT_NEQ_DAMP": f"{self.outlet_srt_neq_damp:.4f}f",
         }
 
@@ -216,10 +234,12 @@ def load_lbm_config(path: Optional[str] = None) -> LBMConfig:
         les_closed_form=m["les"].get("closed_form", True),
         trt_magic_param=m["trt"]["magic_param"],
         inlet_profile=m["inlet"]["profile"],
+        inlet_scheme=m["inlet"].get("scheme", "zou_he_local"),
         outlet_mode=m["outlet"]["mode"],
         outlet_blend_alpha=m["outlet"]["blend_alpha"],
         outlet_backflow_clamp=m["outlet"]["backflow_clamp"],
         inlet_trt_neq_damp=m["inlet"].get("trt_neq_damp", 0.5),
+        inlet_regularized_neq_damp=m["inlet"].get("regularized_neq_damp", 0.5),
         outlet_srt_neq_damp=m["outlet"].get("srt_neq_damp", 0.5),
         y_wall_bc=m.get("y_wall_bc", "bounce_back"),
         omega_min=m["omega_guard"]["min"],

src/CelerisLab/configs/CONFIG.md

@@ -35,8 +35,10 @@ Python `config.py` 只负责读取和校验，不是配置位置。
 | `les.cs` | float | 0.16 | | Smagorinsky 常数 |
 | `les.closed_form` | bool | true | | 闭合形式 τ_eff（vs 迭代） |
 | `trt.magic_param` | float | 0.1875 | | TRT Λ 参数，高 Re 建议 0.001 |
-| `inlet.profile` | string | `"parabolic"` | `uniform`, `parabolic` | 入口速度剖面 |
-| `inlet.trt_neq_damp` | float | 0.5 | [0, 1] | TRT 入口 NEQ donor 阻尼；更小更平滑、精度略降 |
+| `inlet.profile` | string | `"parabolic"` | `uniform`, `parabolic` | 入口速度剖面（物理目标速度，与 scheme 独立） |
+| `inlet.scheme` | string | `"zou_he_local"` | `zou_he_local`, `channel_stabilized`, `equilibrium`, `regularized` | 入口数值闭合。`zou_he_local` 为本地 Zou-He，适合研究或 MRT 路径；`channel_stabilized` 为 donor NEQ 稳定化入口，适合高阻塞或更保守的量产路径；`equilibrium` 直接写入 `feq` 源态，适合 ghost-source 架构下的稳健 SRT 基线；`regularized` 使用本地宏量加 incoming donor NEQ 阻尼，是介于 `equilibrium` 与 `channel_stabilized` 之间的实验入口 |
+| `inlet.trt_neq_damp` | float | 0.5 | [0, 1] | 仅 `channel_stabilized`：TRT 入口 donor NEQ 阻尼；更小更平滑、精度略降 |
+| `inlet.regularized_neq_damp` | float | 0.5 | [0, 1] | 仅 `regularized`：incoming 方向 donor NEQ 阻尼；0 退化到 unknown 方向仅平衡态，1 为 unknown 方向全 donor NEQ |
 | `outlet.mode` | string | `"neq_extrap"` | `neq_extrap`, `zero_gradient`, `blended` | 出口条件 |
 | `outlet.backflow_clamp` | bool | true | | 出口回流钳位 |
 | `outlet.blend_alpha` | float | 0.7 | | `blended` 下对未知入域方向的混合系数（**所有碰撞模型**共用同一路径） |

src/CelerisLab/configs/config_lbm.json

@@ -33,9 +33,13 @@
         },
         "inlet": {
             "profile": "parabolic",
+            "scheme": "zou_he_local",
             "_profile": "uniform | parabolic",
+            "_scheme": "zou_he_local | channel_stabilized | equilibrium | regularized",
             "trt_neq_damp": 0.5,
-            "_trt_neq_damp": "TRT inlet NEQ donor damping [0,1]. Lower = smoother inlet, less accurate."
+            "_trt_neq_damp": "channel_stabilized only. TRT donor NEQ damping [0,1]. Lower = smoother inlet, less accurate.",
+            "regularized_neq_damp": 0.5,
+            "_regularized_neq_damp": "regularized only. Incoming-direction donor NEQ damping [0,1]. 0 = equilibrium-only on unknowns, 1 = full donor NEQ on unknowns."
         },
         "outlet": {
             "mode": "neq_extrap",

src/CelerisLab/cuda/compiler_v2.py

@@ -115,6 +115,7 @@ def generate_config(cfg: LBMConfig, n_objects: int = 0):
 #define LES_CLOSED_FORM {m['LES_CLOSED_FORM']}
 
 #define INLET_PROFILE        {m['INLET_PROFILE']}
+#define INLET_SCHEME         {m['INLET_SCHEME']}
 #define OUTLET_MODE          {m['OUTLET_MODE']}
 #define OUTLET_BLEND_ALPHA   {m['OUTLET_BLEND_ALPHA']}
 #define OUTLET_BACKFLOW_CLAMP {m['OUTLET_BACKFLOW_CLAMP']}
@@ -125,10 +126,12 @@ def generate_config(cfg: LBMConfig, n_objects: int = 0):
 #define TRT_MAGIC_PARAM     {m['TRT_MAGIC_PARAM']}
 
 // NEQ damping coefficients for inlet/outlet BC reconstruction.
-// TRT inlet: damps donor non-equilibrium to reduce inlet noise at high Re.
-// SRT outlet: damps donor non-equilibrium to suppress checkerboard noise.
-#define INLET_TRT_NEQ_DAMP  {m['INLET_TRT_NEQ_DAMP']}
-#define OUTLET_SRT_NEQ_DAMP {m['OUTLET_SRT_NEQ_DAMP']}
+// TRT inlet: donor damping used by the channel_stabilized inlet.
+// Regularized inlet: damping on incoming-direction donor NEQ.
+// SRT outlet: damped outlet reconstruction to suppress checkerboard noise.
+#define INLET_TRT_NEQ_DAMP         {m['INLET_TRT_NEQ_DAMP']}
+#define INLET_REGULARIZED_NEQ_DAMP {m['INLET_REGULARIZED_NEQ_DAMP']}
+#define OUTLET_SRT_NEQ_DAMP        {m['OUTLET_SRT_NEQ_DAMP']}
 
 #endif
 """)
@@ -219,4 +222,3 @@ def load_module(ptx_path: Optional[str] = None) -> cuda.Module:
 def compile_kernel_v2(arch: str = "sm_70") -> str:
     """Alias for compile_kernel() kept for test-script compatibility."""
     return compile_kernel(arch=arch)
-

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

@@ -0,0 +1,110 @@
+// CelerisLab – boundary/inlet/channel_stabilized.cuh
+// Donor-based west velocity inlet closures designed for robust ghost-source use.
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_INLET_CHANNEL_STABILIZED_CUH
+#define CELERIS_BOUNDARY_INLET_CHANNEL_STABILIZED_CUH
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ inline void apply_channel_stabilized_inlet_d2q9(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb,
+    float y_coord)
+{
+    float rho_neb, u_neb, v_neb;
+    compute_rho_u(f_neb, rho_neb, u_neb, v_neb);
+
+    const float u_target = inlet_target_u(y_coord);
+    const float v_target = 0.0f;
+    const float rho_in = west_velocity_rho_closure_d2q9(f, u_target);
+
+    float feq_tar[9], feq_neb[9];
+    compute_feq(rho_in, u_target, v_target, feq_tar);
+    compute_feq(rho_neb, u_neb, v_neb, feq_neb);
+
+#if COLLISION_MODEL == 1
+    const float beta_n = INLET_TRT_NEQ_DAMP;
+#else
+    const float beta_n = 1.0f;
+#endif
+
+    const float f1_try = feq_tar[1] + beta_n * (f_neb[1] - feq_neb[1]);
+    const float known_sum = f[0] + f[2] + f[3] + f[4] + f[6] + f[8];
+    float pair_diff = rho_in * v_target + (f[4] - f[3]) + (f[6] - f[8]);
+    const float f1_hi = fmaxf(0.0f, rho_in - known_sum - fabsf(pair_diff));
+    const float f1 = fminf(fmaxf(f1_try, 0.0f), f1_hi);
+    float pair_sum = rho_in - known_sum - f1;
+
+    if (fabsf(pair_diff) > pair_sum) {
+        pair_diff = copysignf(pair_sum, pair_diff);
+    }
+
+    f[1] = f1;
+    f[5] = 0.5f * (pair_sum + pair_diff);
+    f[7] = 0.5f * (pair_sum - pair_diff);
+}
+#endif
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+__device__ inline void apply_channel_stabilized_inlet_d3q19(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb,
+    float y_coord)
+{
+    float rho_neb, un, vn, wn;
+    compute_rho_u(f_neb, rho_neb, un, vn, wn);
+
+    const float u_tar = inlet_target_u(y_coord);
+    const float v_tar = 0.0f;
+    const float w_tar = 0.0f;
+    const float rho_in = west_velocity_rho_closure_d3q19(f, u_tar);
+
+    float feq_tar[19], feq_neb[19];
+    compute_feq(rho_in, u_tar, v_tar, w_tar, feq_tar);
+    compute_feq(rho_neb, un, vn, wn, feq_neb);
+
+#if COLLISION_MODEL == 1
+    const float beta_n = INLET_TRT_NEQ_DAMP;
+#else
+    const float beta_n = 1.0f;
+#endif
+
+    const float f1_try = feq_tar[1] + beta_n * (f_neb[1] - feq_neb[1]);
+    const float zsum_try = (feq_tar[9] + feq_tar[15])
+                         + beta_n * ((f_neb[9] - feq_neb[9])
+                                   + (f_neb[15] - feq_neb[15]));
+
+    const float known_sum = f[0] + f[2] + f[3] + f[4] + f[5] + f[6]
+                          + f[8] + f[10] + f[11] + f[12] + f[14]
+                          + f[16] + f[17] + f[18];
+    const float rem_total = rho_in - known_sum;
+
+    float y_diff = rho_in * v_tar
+                 - (f[3] - f[4] - f[8] + f[11] - f[12] + f[14] + f[17] - f[18]);
+    float z_diff = rho_in * w_tar
+                 - (f[5] - f[6] - f[10] + f[11] - f[12] + f[16] + f[18] - f[17]);
+
+    const float f1_hi = fmaxf(0.0f, rem_total - fabsf(y_diff));
+    const float f1 = fminf(fmaxf(f1_try, 0.0f), f1_hi);
+
+    const float zsum_hi = fmaxf(0.0f, rem_total - f1 - fabsf(y_diff));
+    const float z_sum = fminf(fmaxf(zsum_try, 0.0f), zsum_hi);
+    if (fabsf(z_diff) > z_sum) {
+        z_diff = copysignf(z_sum, z_diff);
+    }
+
+    float y_sum = rem_total - f1 - z_sum;
+    y_sum = fmaxf(y_sum, 0.0f);
+    if (fabsf(y_diff) > y_sum) {
+        y_diff = copysignf(y_sum, y_diff);
+    }
+
+    f[1]  = f1;
+    f[9]  = 0.5f * (z_sum + z_diff);
+    f[15] = 0.5f * (z_sum - z_diff);
+    f[7]  = 0.5f * (y_sum + y_diff);
+    f[13] = 0.5f * (y_sum - y_diff);
+}
+#endif
+
+#endif // CELERIS_BOUNDARY_INLET_CHANNEL_STABILIZED_CUH

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

@@ -0,0 +1,72 @@
+// CelerisLab – boundary/inlet/common.cuh
+// Shared helpers for west velocity inlet source-state generation.
+//
+// Important semantic contract in this solver:
+// - x=0 inlet cells are SOLID|BC_INLET ghost source nodes
+// - they generate the state later pulled by the first interior fluid column
+// - inlet methods therefore construct a source state, not a textbook fluid-node
+//   boundary update in isolation
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_INLET_COMMON_CUH
+#define CELERIS_BOUNDARY_INLET_COMMON_CUH
+
+#ifndef INLET_PROFILE
+#define INLET_PROFILE 1
+#endif
+
+#ifndef INLET_SCHEME
+#define INLET_SCHEME 0
+#endif
+
+#ifndef INLET_TRT_NEQ_DAMP
+#define INLET_TRT_NEQ_DAMP 0.50f
+#endif
+
+#ifndef INLET_REGULARIZED_NEQ_DAMP
+#define INLET_REGULARIZED_NEQ_DAMP 0.50f
+#endif
+
+__device__ __forceinline__ float inlet_target_u(float y_coord) {
+#if INLET_PROFILE == 0
+    return U0;
+#else
+    const float y_clamped = fminf((float)(NY - 2), fmaxf(1.0f, y_coord));
+    const float H = fmaxf((float)(NY - 2), 1.0f);
+    const float eta = (y_clamped - 0.5f) / H;
+    const float shape = fmaxf(0.0f, 4.0f * eta * (1.0f - eta));
+    return U0 * 1.5f * shape;
+#endif
+}
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ __forceinline__ float west_velocity_rho_closure_d2q9(
+    const float* __restrict__ f,
+    float ux_target)
+{
+    return (f[0] + f[3] + f[4] + 2.0f * (f[2] + f[6] + f[8]))
+         / (1.0f - ux_target);
+}
+#endif
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+__device__ __forceinline__ float west_velocity_rho_closure_d3q19(
+    const float* __restrict__ f,
+    float ux_target)
+{
+    return (f[0] + f[3] + f[4] + f[5] + f[6] + f[11] + f[12] + f[17] + f[18]
+          + 2.0f * (f[2] + f[8] + f[10] + f[14] + f[16]))
+         / (1.0f - ux_target);
+}
+#endif
+
+__device__ __forceinline__ bool inlet_scheme_uses_post_collision_ghost()
+{
+#if INLET_SCHEME == 0
+    return true;
+#else
+    return false;
+#endif
+}
+
+#endif // CELERIS_BOUNDARY_INLET_COMMON_CUH

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

@@ -0,0 +1,48 @@
+// CelerisLab – boundary/inlet/equilibrium.cuh
+// West velocity inlet source state built from full equilibrium.
+//
+// This method recovers rho from local west-boundary mass closure and then
+// overwrites the full ghost-node state with feq(rho, u_target).
+// It is robust for ghost-source architectures because it injects no boundary
+// non-equilibrium content.
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_INLET_EQUILIBRIUM_CUH
+#define CELERIS_BOUNDARY_INLET_EQUILIBRIUM_CUH
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ inline void apply_equilibrium_left_velocity_inlet_d2q9(
+    float* __restrict__ f,
+    float ux_target,
+    float uy_target)
+{
+    const float rho = west_velocity_rho_closure_d2q9(f, ux_target);
+    float feq[9];
+    compute_feq(rho, ux_target, uy_target, feq);
+
+    #pragma unroll
+    for (int i = 0; i < 9; i++) {
+        f[i] = feq[i];
+    }
+}
+#endif
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+__device__ inline void apply_equilibrium_left_velocity_inlet_d3q19(
+    float* __restrict__ f,
+    float ux_target,
+    float uy_target,
+    float uz_target)
+{
+    const float rho = west_velocity_rho_closure_d3q19(f, ux_target);
+    float feq[19];
+    compute_feq(rho, ux_target, uy_target, uz_target, feq);
+
+    #pragma unroll
+    for (int i = 0; i < 19; i++) {
+        f[i] = feq[i];
+    }
+}
+#endif
+
+#endif // CELERIS_BOUNDARY_INLET_EQUILIBRIUM_CUH

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

@@ -0,0 +1,59 @@
+// CelerisLab – boundary/inlet/regularized.cuh
+// West velocity inlet with local macro state and donor-damped incoming NEQ.
+//
+// This method keeps the target macro state from local west-boundary closure but
+// avoids a full local algebraic source state by injecting only damped donor NEQ
+// on incoming directions.
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_INLET_REGULARIZED_CUH
+#define CELERIS_BOUNDARY_INLET_REGULARIZED_CUH
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ inline void apply_regularized_left_velocity_inlet_d2q9(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb,
+    float ux_target,
+    float uy_target)
+{
+    const float rho = west_velocity_rho_closure_d2q9(f, ux_target);
+    float rho_neb, u_neb, v_neb;
+    compute_rho_u(f_neb, rho_neb, u_neb, v_neb);
+
+    float feq_tar[9], feq_neb[9];
+    compute_feq(rho, ux_target, uy_target, feq_tar);
+    compute_feq(rho_neb, u_neb, v_neb, feq_neb);
+
+    const float beta = INLET_REGULARIZED_NEQ_DAMP;
+    f[1] = feq_tar[1] + beta * (f_neb[1] - feq_neb[1]);
+    f[5] = feq_tar[5] + beta * (f_neb[5] - feq_neb[5]);
+    f[7] = feq_tar[7] + beta * (f_neb[7] - feq_neb[7]);
+}
+#endif
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+__device__ inline void apply_regularized_left_velocity_inlet_d3q19(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb,
+    float ux_target,
+    float uy_target,
+    float uz_target)
+{
+    const float rho = west_velocity_rho_closure_d3q19(f, ux_target);
+    float rho_neb, u_neb, v_neb, w_neb;
+    compute_rho_u(f_neb, rho_neb, u_neb, v_neb, w_neb);
+
+    float feq_tar[19], feq_neb[19];
+    compute_feq(rho, ux_target, uy_target, uz_target, feq_tar);
+    compute_feq(rho_neb, u_neb, v_neb, w_neb, feq_neb);
+
+    const float beta = INLET_REGULARIZED_NEQ_DAMP;
+    f[1]  = feq_tar[1]  + beta * (f_neb[1]  - feq_neb[1]);
+    f[7]  = feq_tar[7]  + beta * (f_neb[7]  - feq_neb[7]);
+    f[9]  = feq_tar[9]  + beta * (f_neb[9]  - feq_neb[9]);
+    f[13] = feq_tar[13] + beta * (f_neb[13] - feq_neb[13]);
+    f[15] = feq_tar[15] + beta * (f_neb[15] - feq_neb[15]);
+}
+#endif
+
+#endif // CELERIS_BOUNDARY_INLET_REGULARIZED_CUH

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

@@ -0,0 +1,90 @@
+// CelerisLab – boundary/inlet/zou_he_local.cuh
+// Local on-site west velocity inlet closures.
+//
+// D2Q9 and D3Q19 variants recover rho from local mass closure and reconstruct
+// unknown incoming populations from local target velocity constraints.
+//
+// In the current ghost-source architecture these reconstructed states are later
+// used as pull sources. Therefore this method requires post-BC ghost collision
+// in the step kernel.
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_INLET_ZOU_HE_LOCAL_CUH
+#define CELERIS_BOUNDARY_INLET_ZOU_HE_LOCAL_CUH
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+
+// Free-slip y-walls: at inlet rows y=1 and y=NY-2, pull can source wall nodes for
+// some known directions. Copy those from stored DDF at (x=1, same y) only.
+__device__ inline void repair_zou_he_west_knowns_d2q9(
+    float* __restrict__ f,
+    const fpxx* __restrict__ fi_in,
+    unsigned int x,
+    unsigned int y)
+{
+    if (x != 0u) return;
+
+    const unsigned long k_int = linear_index(x + 1u, y);
+
+    if (y == 1u) {
+        f[3] = load_ddf(fi_in, index_f(k_int, 3u));
+        f[8] = load_ddf(fi_in, index_f(k_int, 8u));
+    } else if (y == (unsigned int)(NY - 2)) {
+        f[4] = load_ddf(fi_in, index_f(k_int, 4u));
+        f[6] = load_ddf(fi_in, index_f(k_int, 6u));
+    }
+}
+
+__device__ inline void apply_zou_he_left_velocity_inlet_d2q9(
+    float* __restrict__ f,
+    float ux_target,
+    float uy_target)
+{
+    const float rho = west_velocity_rho_closure_d2q9(f, ux_target);
+
+    f[1] = f[2] + (2.0f / 3.0f) * rho * ux_target;
+
+    f[5] = f[6]
+         + 0.5f * (f[4] - f[3])
+         + (1.0f / 6.0f) * rho * ux_target
+         + 0.5f * rho * uy_target;
+
+    f[7] = f[8]
+         + 0.5f * (f[3] - f[4])
+         + (1.0f / 6.0f) * rho * ux_target
+         - 0.5f * rho * uy_target;
+}
+
+#endif // LATTICE_MODEL == LATTICE_D2Q9
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+
+// Hecht-Harting style D3Q19 on-site west velocity closure adapted to the
+// codebase paired ordering:
+//   7  = (+x,+y),  8  = (-x,-y)
+//   13 = (+x,-y), 14 = (-x,+y)
+//   9  = (+x,+z), 10 = (-x,-z)
+//   15 = (+x,-z), 16 = (-x,+z)
+__device__ inline void apply_zou_he_left_velocity_inlet_d3q19(
+    float* __restrict__ f,
+    float ux_target,
+    float uy_target,
+    float uz_target)
+{
+    const float rho = west_velocity_rho_closure_d3q19(f, ux_target);
+
+    const float Nyx = 0.5f * (f[3] + f[11] + f[17] - (f[4] + f[12] + f[18]))
+                    - (1.0f / 3.0f) * rho * uy_target;
+    const float Nzx = 0.5f * (f[5] + f[11] + f[18] - (f[6] + f[17] + f[12]))
+                    - (1.0f / 3.0f) * rho * uz_target;
+
+    f[1]  = f[2]  + (1.0f / 3.0f) * rho * ux_target;
+    f[7]  = f[8]  + (1.0f / 6.0f) * rho * (ux_target + uy_target) - Nyx;
+    f[13] = f[14] + (1.0f / 6.0f) * rho * (ux_target - uy_target) + Nyx;
+    f[9]  = f[10] + (1.0f / 6.0f) * rho * (ux_target + uz_target) - Nzx;
+    f[15] = f[16] + (1.0f / 6.0f) * rho * (ux_target - uz_target) + Nzx;
+}
+
+#endif // LATTICE_MODEL == LATTICE_D3Q19
+
+#endif // CELERIS_BOUNDARY_INLET_ZOU_HE_LOCAL_CUH

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

@@ -1,359 +1,225 @@
 // CelerisLab – boundary/inlet_outlet.cuh
-// Inlet and outlet boundary conditions  (D2Q9).
+// Inlet and outlet dispatch layer.
 //
-// Parabolic inlet (non-equilibrium extrapolation, Zou-He style):
-//   Left wall (x=0): reconstruct cx>0 populations (i=1,5,7)
+// This file contains only profile helpers, method includes, and compile-time
+// switching. Each concrete inlet or outlet implementation lives in its own file
+// under boundary/inlet/ or boundary/outlet/.
 //
-// Pressure outlet (non-equilibrium extrapolation):
-//   Right wall (x=NX-1): reconstruct cx<0 populations (i=2,6,8)
-//
-// New paired D2Q9 ordering:
-//   cx = {0, 1,-1, 0, 0, 1,-1, 1,-1}
-//   cy = {0, 0, 0, 1,-1, 1,-1,-1, 1}
+// Inlet scheme IDs:
+//   0 = zou_he_local
+//   1 = channel_stabilized
+//   2 = equilibrium
+//   3 = regularized
 // ============================================================================
 
 #ifndef CELERIS_BOUNDARY_INLET_OUTLET_CUH
 #define CELERIS_BOUNDARY_INLET_OUTLET_CUH
 
-#ifndef INLET_PROFILE
-#define INLET_PROFILE 1
+#ifndef INLET_SCHEME
+#define INLET_SCHEME 0
 #endif
 
-#ifndef OUTLET_MODE
-#define OUTLET_MODE 0
-#endif
+#include "inlet/common.cuh"
+#include "inlet/zou_he_local.cuh"
+#include "inlet/channel_stabilized.cuh"
+#include "inlet/equilibrium.cuh"
+#include "inlet/regularized.cuh"
+#include "outlet/pressure_neq.cuh"
 
-#ifndef OUTLET_BACKFLOW_CLAMP
-#define OUTLET_BACKFLOW_CLAMP 1
-#endif
-
-#ifndef OUTLET_BLEND_ALPHA
-#define OUTLET_BLEND_ALPHA 0.70f
-#endif
-
-// OUTLET_SRT_NEQ_DAMP and INLET_TRT_NEQ_DAMP are injected by config_method.h.
-// These fallback defaults are only active if building outside the normal
-// Python compile pipeline (e.g. standalone nvcc tests).
-#ifndef OUTLET_SRT_NEQ_DAMP
-#define OUTLET_SRT_NEQ_DAMP 0.50f
-#endif
-
-#ifndef INLET_TRT_NEQ_DAMP
-#define INLET_TRT_NEQ_DAMP 0.50f
-#endif
-
-__device__ __forceinline__ float inlet_target_u(float y_coord) {
-#if INLET_PROFILE == 0
-    // Uniform profile: U0 is the imposed streamwise velocity everywhere on the
-    // inlet fluid band.
-    return U0;
-#else
-    // Parabolic profile on the fluid-node band y in [1, NY-2].
-    //
-    // U0 is treated here as the mean streamwise inlet velocity. The returned
-    // peak centerline velocity is 1.5 * U0, matching the discrete Poiseuille
-    // profile used throughout initialization and boundary reconstruction.
-    // Keep this convention aligned with case setup and validation scripts.
-    const float y_clamped = fminf((float)(NY - 2), fmaxf(1.0f, y_coord));
-    const float H = fmaxf((float)(NY - 2), 1.0f);
-    const float eta = (y_clamped - 0.5f) / H;  // first and last fluid rows map near 0 and 1
-    const float shape = fmaxf(0.0f, 4.0f * eta * (1.0f - eta));
-    return U0 * 1.5f * shape;
-#endif
-}
-
-#if LATTICE_MODEL == LATTICE_D2Q9
-
-// ---------------------------------------------------------------------------
-// Parabolic inlet  (x = 0, non-equilibrium extrapolation)
-//
-// f, f_neb are local DDF arrays:
-//   f      = populations at the boundary node (x=0)
-//   f_neb  = populations at the interior neighbor (x=1)
-//   y      = y-coordinate of the boundary node
-//
-// Reconstructs f[1], f[5], f[7]  (cx > 0 directions in new ordering).
-//
-// Velocity convention:
-//   uniform   -> U0 is the imposed inlet velocity
-//   parabolic -> U0 is the mean inlet velocity, so inlet_target_u() returns a
-//                centerline peak of 1.5 * U0
-//
-// Reconstruction keeps the Zou-He mass closure but does not copy all three
-// unknown-direction NEQ parts from the donor.
-//
-// Why this split form:
-// - In narrow high-blockage channels, the donor diagonals f_neb[5], f_neb[7]
-//   are strongly contaminated by near-wall shear and tend to inject a spurious
-//   negative shift into the first interior column. Empirically this is not just
-//   a corner-node artifact: the whole x=1 profile can be biased low when the
-//   channel becomes very narrow.
-// - Removing NEQ entirely hurts stability, so the streamwise unknown f[1] keeps
-//   donor NEQ information.
-// - The diagonal unknowns are instead reconstructed from local density and
-//   transverse-velocity constraints. A positivity limiter is applied only if
-//   the local constraints are mutually inconsistent, preferring exact rho and
-//   streamwise flux over exact v_target at that node.
-// ---------------------------------------------------------------------------
-__device__ inline void apply_parabolic_inlet(float* __restrict__ f,
-                                             const float* __restrict__ f_neb,
-                                             float y_coord)
+#if DIM == 2
+__device__ __forceinline__ void apply_inlet_pull_d2q9(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    const fpxx* __restrict__ fi_in)
 {
-    // Donor macros from the first interior fluid column.
-    float rho_neb, u_neb, v_neb;
-    compute_rho_u(f_neb, rho_neb, u_neb, v_neb);
-
-    // Target inlet velocity.
-    const float u_target = inlet_target_u(y_coord);
+    const float u_target = inlet_target_u((float)y);
     const float v_target = 0.0f;
 
-    // Zou-He mass closure at the west boundary.
-    // Known (after pull and any wall pre-repair): f[0],f[2],f[3],f[4],f[6],f[8]
-    // Unknown to reconstruct:                         f[1],f[5],f[7]
-    const float rho_in = (f[0] + f[3] + f[4] + 2.0f * (f[2] + f[6] + f[8]))
-                       / (1.0f - u_target);
-
-    float feq_tar[9], feq_neb[9];
-    compute_feq(rho_in, u_target, v_target, feq_tar);
-    compute_feq(rho_neb, u_neb, v_neb, feq_neb);
-
-#if COLLISION_MODEL == 1
-    const float beta_n = INLET_TRT_NEQ_DAMP;
-#else
-    const float beta_n = 1.0f;
+#if INLET_SCHEME == 0
+#if Y_WALL_BC == 1
+    repair_zou_he_west_knowns_d2q9(f, fi_in, x, y);
 #endif
-
-    // Keep donor NEQ only for the streamwise incoming population. This retains
-    // the stabilizing normal-flux information without feeding both diagonal
-    // donor modes back into the inlet every step.
-    const float f1_try = feq_tar[1] + beta_n * (f_neb[1] - feq_neb[1]);
-
-    // Known-part density contribution.
-    const float known_sum = f[0] + f[2] + f[3] + f[4] + f[6] + f[8];
-
-    // From uy = (f3 - f4 + f5 - f6 - f7 + f8) / rho, so with v_target = 0:
-    //   f5 - f7 = rho*v_target + (f4 - f3) + (f6 - f8)
-    float pair_diff = rho_in * v_target + (f[4] - f[3]) + (f[6] - f[8]);
-
-    // Density fixes f5 + f7 once f1 is chosen:
-    //   f5 + f7 = rho - known_sum - f1
-    // To keep both diagonals non-negative we need pair_sum >= |pair_diff|,
-    // hence f1 <= rho - known_sum - |pair_diff|.
-    const float f1_hi = fmaxf(0.0f, rho_in - known_sum - fabsf(pair_diff));
-    const float f1 = fminf(fmaxf(f1_try, 0.0f), f1_hi);
-
-    float pair_sum = rho_in - known_sum - f1;
-
-    // If the local constraints are still inconsistent because of roundoff or an
-    // extremely distorted incoming state, clip the transverse difference rather
-    // than emitting negative diagonal populations.
-    if (fabsf(pair_diff) > pair_sum) {
-        pair_diff = copysignf(pair_sum, pair_diff);
+    apply_zou_he_left_velocity_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);
+    for (int i = 0; i < NQ; i++) {
+        f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
     }
-
-    f[1] = f1;
-    f[5] = 0.5f * (pair_sum + pair_diff);
-    f[7] = 0.5f * (pair_sum - pair_diff);
+  #if INLET_SCHEME == 1
+    apply_channel_stabilized_inlet_d2q9(f, f_neb, (float)y);
+  #else
+    apply_regularized_left_velocity_inlet_d2q9(f, f_neb, u_target, v_target);
+  #endif
+#elif INLET_SCHEME == 2
+    apply_equilibrium_left_velocity_inlet_d2q9(f, u_target, v_target);
+#else
+  #error "Unsupported INLET_SCHEME for D2Q9"
+#endif
 }
 
-// ---------------------------------------------------------------------------
-// Pressure outlet  (x = NX-1, non-equilibrium extrapolation)
-//
-// Reconstructs f[2], f[6], f[8]  (cx < 0 directions in new ordering)
-// p_out = 0 (gauge pressure), uses velocity from neighbor.
-// ---------------------------------------------------------------------------
-__device__ inline void apply_pressure_outlet(float* __restrict__ f,
-                                             const float* __restrict__ f_neb,
-                                             float y_coord)
+__device__ __forceinline__ void apply_outlet_pull_d2q9(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    const fpxx* __restrict__ fi_in)
 {
-    (void)y_coord;
-
-#if OUTLET_MODE == 1
-    // Simple zero-gradient copy for unknown incoming directions at outlet.
-    f[2] = f_neb[2];
-    f[8] = f_neb[8];
-    f[6] = f_neb[6];
-#else
-
-    // Prescribed-pressure outlet: keep neighbor velocity and impose reference
-    // outlet density for NEQ reconstruction.
-    float rho_neb, u_neb, v_neb;
-    compute_rho_u(f_neb, rho_neb, u_neb, v_neb);
-#if OUTLET_BACKFLOW_CLAMP
-    u_neb = fmaxf(u_neb, 0.0f);
-#endif
-    float rho_out = RHO;
-
-    float feq_tar[9], feq_neb[9];
-    compute_feq(rho_out, u_neb, v_neb, feq_tar);
-    compute_feq(rho_neb, u_neb, v_neb, feq_neb);
-
-#if COLLISION_MODEL == 0 || COLLISION_MODEL == 1
-    // SRT and TRT path: use full-population damped NEQ reconstruction at
-    // outlet to suppress checkerboard and boundary-source noise.
-    const float beta = OUTLET_SRT_NEQ_DAMP;
-    #pragma unroll
-    for (int i = 0; i < 9; i++) {
-        const float fneq = f_neb[i] - feq_neb[i];
-        f[i] = feq_tar[i] + beta * fneq;
+    float f_neb[NQ];
+    const unsigned long k_neb = linear_index(x - 1u, y);
+    for (int i = 0; i < NQ; i++) {
+        f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
     }
-#elif OUTLET_MODE == 2
-    const float a = OUTLET_BLEND_ALPHA;
-    f[2] = a * (f_neb[2] - feq_neb[2] + feq_tar[2]) + (1.0f - a) * f_neb[2];
-    f[8] = a * (f_neb[8] - feq_neb[8] + feq_tar[8]) + (1.0f - a) * f_neb[8];
-    f[6] = a * (f_neb[6] - feq_neb[6] + feq_tar[6]) + (1.0f - a) * f_neb[6];
-#else
-    f[2] = f_neb[2] - feq_neb[2] + feq_tar[2];
-    f[8] = f_neb[8] - feq_neb[8] + feq_tar[8];
-    f[6] = f_neb[6] - feq_neb[6] + feq_tar[6];
-#endif
-#endif
+    apply_pressure_outlet_d2q9(f, f_neb);
 }
+#endif
 
-#endif // LATTICE_D2Q9
-
-// ============================================================================
-// D3Q19 inlet / outlet  (non-equilibrium extrapolation)
-//
-// Parabolic inlet (x=0):  reconstruct cx>0 populations i=1,7,9,13,15
-// Pressure outlet (x=NX-1): reconstruct cx<0 populations i=2,8,10,14,16
-//
-// Uses generic feq computation from macro.cuh to avoid hand-expanded formulas.
-// ============================================================================
-#if LATTICE_MODEL == LATTICE_D3Q19
-
-__device__ inline void apply_parabolic_inlet_3d(float* __restrict__ f,
-                                                const float* __restrict__ f_neb,
-                                                float y_coord)
+#if DIM == 3
+__device__ __forceinline__ void apply_inlet_pull_d3q19(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    unsigned int z,
+    const fpxx* __restrict__ fi_in)
 {
-    // Donor macros from the first interior fluid column.
-    float rho_neb, un, vn, wn;
-    compute_rho_u(f_neb, rho_neb, un, vn, wn);
+    const float u_target = inlet_target_u((float)y);
+    const float v_target = 0.0f;
+    const float w_target = 0.0f;
 
-    // Target velocity: parabolic in y, uniform in z.
-    const float u_tar = inlet_target_u(y_coord);
-    const float v_tar = 0.0f;
-    const float w_tar = 0.0f;
-
-    // Zou-He mass balance at the west boundary.
-    // Unknown cx>0 populations are i = 1, 7, 9, 13, 15.
-    const float rho_in = (f[0] + f[3] + f[4] + f[5] + f[6] + f[11] + f[12] + f[17] + f[18]
-                        + 2.0f * (f[2] + f[8] + f[10] + f[14] + f[16]))
-                       / (1.0f - u_tar);
-
-    float feq_tar[19], feq_neb[19];
-    compute_feq(rho_in, u_tar, v_tar, w_tar, feq_tar);
-    compute_feq(rho_neb, un, vn, wn, feq_neb);
-
-#if COLLISION_MODEL == 1
-    const float beta_n = INLET_TRT_NEQ_DAMP;
+#if INLET_SCHEME == 0
+    apply_zou_he_left_velocity_inlet_d3q19(f, u_target, v_target, w_target);
+#elif INLET_SCHEME == 1 || INLET_SCHEME == 3
+    float f_neb[NQ];
+    const unsigned long k_neb = linear_index(x + 1u, y, z);
+    for (int i = 0; i < NQ; i++) {
+        f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
+    }
+  #if INLET_SCHEME == 1
+    apply_channel_stabilized_inlet_d3q19(f, f_neb, (float)y);
+  #else
+    apply_regularized_left_velocity_inlet_d3q19(f, f_neb, u_target, v_target, w_target);
+  #endif
+#elif INLET_SCHEME == 2
+    apply_equilibrium_left_velocity_inlet_d3q19(f, u_target, v_target, w_target);
 #else
-    const float beta_n = 1.0f;
+  #error "Unsupported INLET_SCHEME for D3Q19"
 #endif
-
-    // D3Q19 counterpart of the D2Q9 split strategy:
-    // - keep donor NEQ on the pure streamwise incoming population f[1]
-    // - retain the x-z pair only through its total incoming mass, because the
-    //   present channel setup has y-walls but no z-wall BC path
-    // - reconstruct the y-coupled diagonals from local rho/uy constraints to
-    //   avoid feeding wall-shear contamination back into the inlet every step
-    const float f1_try = feq_tar[1] + beta_n * (f_neb[1] - feq_neb[1]);
-    const float zsum_try = (feq_tar[9] + feq_tar[15])
-                         + beta_n * ((f_neb[9] - feq_neb[9])
-                                   + (f_neb[15] - feq_neb[15]));
-
-    const float known_sum = f[0] + f[2] + f[3] + f[4] + f[5] + f[6]
-                          + f[8] + f[10] + f[11] + f[12] + f[14]
-                          + f[16] + f[17] + f[18];
-    const float rem_total = rho_in - known_sum;
-
-    // uy constraint:
-    // uy = (f3 - f4 + f7 - f8 + f11 - f12 + f14 - f13 + f17 - f18) / rho
-    float y_diff = rho_in * v_tar
-                 - (f[3] - f[4] - f[8] + f[11] - f[12] + f[14] + f[17] - f[18]);
-
-    // uz constraint:
-    // uz = (f5 - f6 + f9 - f10 + f11 - f12 + f16 - f15 + f18 - f17) / rho
-    float z_diff = rho_in * w_tar
-                 - (f[5] - f[6] - f[10] + f[11] - f[12] + f[16] + f[18] - f[17]);
-
-    // Reserve enough total mass for the y-diagonal pair to satisfy positivity.
-    const float f1_hi = fmaxf(0.0f, rem_total - fabsf(y_diff));
-    const float f1 = fminf(fmaxf(f1_try, 0.0f), f1_hi);
-
-    const float zsum_hi = fmaxf(0.0f, rem_total - f1 - fabsf(y_diff));
-    const float z_sum = fminf(fmaxf(zsum_try, 0.0f), zsum_hi);
-    if (fabsf(z_diff) > z_sum) {
-        z_diff = copysignf(z_sum, z_diff);
-    }
-
-    float y_sum = rem_total - f1 - z_sum;
-    y_sum = fmaxf(y_sum, 0.0f);
-    if (fabsf(y_diff) > y_sum) {
-        y_diff = copysignf(y_sum, y_diff);
-    }
-
-    f[1]  = f1;
-    f[9]  = 0.5f * (z_sum + z_diff);
-    f[15] = 0.5f * (z_sum - z_diff);
-    f[7]  = 0.5f * (y_sum + y_diff);
-    f[13] = 0.5f * (y_sum - y_diff);
 }
 
-__device__ inline void apply_pressure_outlet_3d(float* __restrict__ f,
-                                                const float* __restrict__ f_neb,
-                                                float y_coord)
+__device__ __forceinline__ void apply_outlet_pull_d3q19(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    unsigned int z,
+    const fpxx* __restrict__ fi_in)
 {
-    (void)y_coord;
-
-#if OUTLET_MODE == 1
-    // Simple zero-gradient copy for unknown incoming directions at outlet.
-    f[2]  = f_neb[2];
-    f[8]  = f_neb[8];
-    f[10] = f_neb[10];
-    f[14] = f_neb[14];
-    f[16] = f_neb[16];
-#else
-
-    // Neighbor macros
-    float rho_neb, un, vn, wn;
-    compute_rho_u(f_neb, rho_neb, un, vn, wn);
-#if OUTLET_BACKFLOW_CLAMP
-    un = fmaxf(un, 0.0f);
-#endif
-
-    // Prescribed-pressure outlet: keep neighbor velocity and impose reference
-    // outlet density for NEQ reconstruction.
-    float rho_out = RHO;
-    float feq_tar[19], feq_neb[19];
-    compute_feq(rho_out, un, vn, wn, feq_tar);
-    compute_feq(rho_neb, un, vn, wn, feq_neb);
-
-    // Reconstruct cx<0 directions: i = 2, 8, 10, 14, 16
-#if COLLISION_MODEL == 0 || COLLISION_MODEL == 1
-    const float beta = OUTLET_SRT_NEQ_DAMP;
-    #pragma unroll
-    for (int i = 0; i < 19; i++) {
-        const float fneq = f_neb[i] - feq_neb[i];
-        f[i] = feq_tar[i] + beta * fneq;
+    float f_neb[NQ];
+    const unsigned long k_neb = linear_index(x - 1u, y, z);
+    for (int i = 0; i < NQ; i++) {
+        f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
     }
-#elif OUTLET_MODE == 2
-    const float a = OUTLET_BLEND_ALPHA;
-    f[2]  = a * (f_neb[2]  - feq_neb[2]  + feq_tar[2])  + (1.0f - a) * f_neb[2];
-    f[8]  = a * (f_neb[8]  - feq_neb[8]  + feq_tar[8])  + (1.0f - a) * f_neb[8];
-    f[10] = a * (f_neb[10] - feq_neb[10] + feq_tar[10]) + (1.0f - a) * f_neb[10];
-    f[14] = a * (f_neb[14] - feq_neb[14] + feq_tar[14]) + (1.0f - a) * f_neb[14];
-    f[16] = a * (f_neb[16] - feq_neb[16] + feq_tar[16]) + (1.0f - a) * f_neb[16];
-#else
-    f[2]  = f_neb[2]  - feq_neb[2]  + feq_tar[2];
-    f[8]  = f_neb[8]  - feq_neb[8]  + feq_tar[8];
-    f[10] = f_neb[10] - feq_neb[10] + feq_tar[10];
-    f[14] = f_neb[14] - feq_neb[14] + feq_tar[14];
-    f[16] = f_neb[16] - feq_neb[16] + feq_tar[16];
+    apply_pressure_outlet_d3q19(f, f_neb);
+}
 #endif
+
+#if DIM == 2
+__device__ __forceinline__ void apply_inlet_esopull_d2q9(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    const fpxx* __restrict__ fi,
+    unsigned long t)
+{
+    const float u_target = inlet_target_u((float)y);
+    const float v_target = 0.0f;
+
+#if INLET_SCHEME == 0
+#if Y_WALL_BC == 1
+    repair_zou_he_west_knowns_d2q9(f, fi, x, y);
+#endif
+    apply_zou_he_left_velocity_inlet_d2q9(f, u_target, v_target);
+#elif INLET_SCHEME == 1 || INLET_SCHEME == 3
+    const unsigned long k_neb = linear_index(x + 1u, y);
+    unsigned long j_neb[NQ];
+    compute_neighbors(x + 1u, y, j_neb);
+    float f_neb[NQ];
+    load_f_esopull(k_neb, f_neb, fi, j_neb, t);
+  #if INLET_SCHEME == 1
+    apply_channel_stabilized_inlet_d2q9(f, f_neb, (float)y);
+  #else
+    apply_regularized_left_velocity_inlet_d2q9(f, f_neb, u_target, v_target);
+  #endif
+#elif INLET_SCHEME == 2
+    apply_equilibrium_left_velocity_inlet_d2q9(f, u_target, v_target);
+#else
+  #error "Unsupported INLET_SCHEME for D2Q9"
 #endif
 }
 
-#endif // LATTICE_D3Q19
+__device__ __forceinline__ void apply_outlet_esopull_d2q9(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    const fpxx* __restrict__ fi,
+    unsigned long t)
+{
+    const unsigned long k_neb = linear_index(x - 1u, y);
+    unsigned long j_neb[NQ];
+    compute_neighbors(x - 1u, y, j_neb);
+    float f_neb[NQ];
+    load_f_esopull(k_neb, f_neb, fi, j_neb, t);
+    apply_pressure_outlet_d2q9(f, f_neb);
+}
+#endif
+
+#if DIM == 3
+__device__ __forceinline__ void apply_inlet_esopull_d3q19(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    unsigned int z,
+    const fpxx* __restrict__ fi,
+    unsigned long t)
+{
+    const float u_target = inlet_target_u((float)y);
+    const float v_target = 0.0f;
+    const float w_target = 0.0f;
+
+#if INLET_SCHEME == 0
+    apply_zou_he_left_velocity_inlet_d3q19(f, u_target, v_target, w_target);
+#elif INLET_SCHEME == 1 || INLET_SCHEME == 3
+    const unsigned long k_neb = linear_index(x + 1u, y, z);
+    unsigned long j_neb[NQ];
+    compute_neighbors(k_neb, j_neb);
+    float f_neb[NQ];
+    load_f_esopull(k_neb, f_neb, fi, j_neb, t);
+  #if INLET_SCHEME == 1
+    apply_channel_stabilized_inlet_d3q19(f, f_neb, (float)y);
+  #else
+    apply_regularized_left_velocity_inlet_d3q19(f, f_neb, u_target, v_target, w_target);
+  #endif
+#elif INLET_SCHEME == 2
+    apply_equilibrium_left_velocity_inlet_d3q19(f, u_target, v_target, w_target);
+#else
+  #error "Unsupported INLET_SCHEME for D3Q19"
+#endif
+}
+
+__device__ __forceinline__ void apply_outlet_esopull_d3q19(
+    float* __restrict__ f,
+    unsigned int x,
+    unsigned int y,
+    unsigned int z,
+    const fpxx* __restrict__ fi,
+    unsigned long t)
+{
+    const unsigned long k_neb = linear_index(x - 1u, y, z);
+    unsigned long j_neb[NQ];
+    compute_neighbors(k_neb, j_neb);
+    float f_neb[NQ];
+    load_f_esopull(k_neb, f_neb, fi, j_neb, t);
+    apply_pressure_outlet_d3q19(f, f_neb);
+}
+#endif
 
 #endif // CELERIS_BOUNDARY_INLET_OUTLET_CUH

src/CelerisLab/lbm/kernels/boundary/outlet/pressure_neq.cuh

@@ -0,0 +1,114 @@
+// CelerisLab – boundary/outlet/pressure_neq.cuh
+// Pressure outlet and zero-gradient outlet closures.
+// ============================================================================
+
+#ifndef CELERIS_BOUNDARY_OUTLET_PRESSURE_NEQ_CUH
+#define CELERIS_BOUNDARY_OUTLET_PRESSURE_NEQ_CUH
+
+#ifndef OUTLET_MODE
+#define OUTLET_MODE 0
+#endif
+
+#ifndef OUTLET_BACKFLOW_CLAMP
+#define OUTLET_BACKFLOW_CLAMP 1
+#endif
+
+#ifndef OUTLET_BLEND_ALPHA
+#define OUTLET_BLEND_ALPHA 0.70f
+#endif
+
+#ifndef OUTLET_SRT_NEQ_DAMP
+#define OUTLET_SRT_NEQ_DAMP 0.50f
+#endif
+
+#if LATTICE_MODEL == LATTICE_D2Q9
+__device__ inline void apply_pressure_outlet_d2q9(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb)
+{
+#if OUTLET_MODE == 1
+    f[2] = f_neb[2];
+    f[8] = f_neb[8];
+    f[6] = f_neb[6];
+#else
+    float rho_neb, u_neb, v_neb;
+    compute_rho_u(f_neb, rho_neb, u_neb, v_neb);
+#if OUTLET_BACKFLOW_CLAMP
+    u_neb = fmaxf(u_neb, 0.0f);
+#endif
+    const float rho_out = RHO;
+
+    float feq_tar[9], feq_neb[9];
+    compute_feq(rho_out, u_neb, v_neb, feq_tar);
+    compute_feq(rho_neb, u_neb, v_neb, feq_neb);
+
+#if COLLISION_MODEL == 0 || COLLISION_MODEL == 1
+    const float beta = OUTLET_SRT_NEQ_DAMP;
+    #pragma unroll
+    for (int i = 0; i < 9; i++) {
+        const float fneq = f_neb[i] - feq_neb[i];
+        f[i] = feq_tar[i] + beta * fneq;
+    }
+#elif OUTLET_MODE == 2
+    const float a = OUTLET_BLEND_ALPHA;
+    f[2] = a * (f_neb[2] - feq_neb[2] + feq_tar[2]) + (1.0f - a) * f_neb[2];
+    f[8] = a * (f_neb[8] - feq_neb[8] + feq_tar[8]) + (1.0f - a) * f_neb[8];
+    f[6] = a * (f_neb[6] - feq_neb[6] + feq_tar[6]) + (1.0f - a) * f_neb[6];
+#else
+    f[2] = f_neb[2] - feq_neb[2] + feq_tar[2];
+    f[8] = f_neb[8] - feq_neb[8] + feq_tar[8];
+    f[6] = f_neb[6] - feq_neb[6] + feq_tar[6];
+#endif
+#endif
+}
+#endif
+
+#if LATTICE_MODEL == LATTICE_D3Q19
+__device__ inline void apply_pressure_outlet_d3q19(
+    float* __restrict__ f,
+    const float* __restrict__ f_neb)
+{
+#if OUTLET_MODE == 1
+    f[2]  = f_neb[2];
+    f[8]  = f_neb[8];
+    f[10] = f_neb[10];
+    f[14] = f_neb[14];
+    f[16] = f_neb[16];
+#else
+    float rho_neb, un, vn, wn;
+    compute_rho_u(f_neb, rho_neb, un, vn, wn);
+#if OUTLET_BACKFLOW_CLAMP
+    un = fmaxf(un, 0.0f);
+#endif
+    const float rho_out = RHO;
+
+    float feq_tar[19], feq_neb[19];
+    compute_feq(rho_out, un, vn, wn, feq_tar);
+    compute_feq(rho_neb, un, vn, wn, feq_neb);
+
+#if COLLISION_MODEL == 0 || COLLISION_MODEL == 1
+    const float beta = OUTLET_SRT_NEQ_DAMP;
+    #pragma unroll
+    for (int i = 0; i < 19; i++) {
+        const float fneq = f_neb[i] - feq_neb[i];
+        f[i] = feq_tar[i] + beta * fneq;
+    }
+#elif OUTLET_MODE == 2
+    const float a = OUTLET_BLEND_ALPHA;
+    f[2]  = a * (f_neb[2]  - feq_neb[2]  + feq_tar[2])  + (1.0f - a) * f_neb[2];
+    f[8]  = a * (f_neb[8]  - feq_neb[8]  + feq_tar[8])  + (1.0f - a) * f_neb[8];
+    f[10] = a * (f_neb[10] - feq_neb[10] + feq_tar[10]) + (1.0f - a) * f_neb[10];
+    f[14] = a * (f_neb[14] - feq_neb[14] + feq_tar[14]) + (1.0f - a) * f_neb[14];
+    f[16] = a * (f_neb[16] - feq_neb[16] + feq_tar[16]) + (1.0f - a) * f_neb[16];
+#else
+    f[2]  = f_neb[2]  - feq_neb[2]  + feq_tar[2];
+    f[8]  = f_neb[8]  - feq_neb[8]  + feq_tar[8];
+    f[10] = f_neb[10] - feq_neb[10] + feq_tar[10];
+    f[14] = f_neb[14] - feq_neb[14] + feq_tar[14];
+    f[16] = f_neb[16] - feq_neb[16] + feq_tar[16];
+#endif
+#endif
+}
+#endif
+
+#endif // CELERIS_BOUNDARY_OUTLET_PRESSURE_NEQ_CUH

src/CelerisLab/lbm/kernels/config/config_grid.h

@@ -6,8 +6,8 @@
 #define NT   256
 #define MULT_GPU 0
 
-#define NX  1351
-#define NY  601
+#define NX  401
+#define NY  201
 #define NZ  1
 
 // ---- Lattice model (single source of truth) ----

src/CelerisLab/lbm/kernels/config/config_method.h

@@ -13,19 +13,22 @@
 #define LES_CLOSED_FORM 1
 
 #define INLET_PROFILE        0
+#define INLET_SCHEME         3
 #define OUTLET_MODE          0
 #define OUTLET_BLEND_ALPHA   0.700f
 #define OUTLET_BACKFLOW_CLAMP 1
-#define Y_WALL_BC            1
+#define Y_WALL_BC            0
 
 #define OMEGA_COLLISION_MIN 0.01f
 #define OMEGA_COLLISION_MAX 1.960f
 #define TRT_MAGIC_PARAM     0.187500f
 
 // NEQ damping coefficients for inlet/outlet BC reconstruction.
-// TRT inlet: damps donor non-equilibrium to reduce inlet noise at high Re.
-// SRT outlet: damps donor non-equilibrium to suppress checkerboard noise.
-#define INLET_TRT_NEQ_DAMP  0.5000f
-#define OUTLET_SRT_NEQ_DAMP 0.5000f
+// TRT inlet: donor damping used by the channel_stabilized inlet.
+// Regularized inlet: damping on incoming-direction donor NEQ.
+// SRT outlet: damped outlet reconstruction to suppress checkerboard noise.
+#define INLET_TRT_NEQ_DAMP         0.5000f
+#define INLET_REGULARIZED_NEQ_DAMP 0.5000f
+#define OUTLET_SRT_NEQ_DAMP        0.5000f
 
 #endif

src/CelerisLab/lbm/kernels/config/config_objects.h

@@ -3,6 +3,6 @@
 #ifndef CELERIS_CONFIG_OBJECTS_H
 #define CELERIS_CONFIG_OBJECTS_H
 
-#define N_OBJS 1
+#define N_OBJS 0
 
 #endif

src/CelerisLab/lbm/kernels/config/config_physics.h

@@ -4,7 +4,7 @@
 #define CELERIS_CONFIG_PHYSICS_H
 
 #define LBtype float
-#define VIS 0.0056250000
+#define VIS 0.0090000000
 #define RHO 1.0
 #define U0  0.03
 

src/CelerisLab/lbm/kernels/step/one_step_double.cu

@@ -22,18 +22,10 @@ __device__ __forceinline__ void apply_boundary_pull(
     bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
 
     if (is_inlet(fl) && interior_y) {
-        float f_neb[NQ];
-        unsigned long k_neb = linear_index(x + 1u, y);
-        for (int i = 0; i < NQ; i++)
-            f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
-        apply_parabolic_inlet(f, f_neb, (float)y);
+        apply_inlet_pull_d2q9(f, x, y, fi_in);
     }
     else if (is_outlet(fl) && interior_y) {
-        float f_neb[NQ];
-        unsigned long k_neb = linear_index(x - 1u, y);
-        for (int i = 0; i < NQ; i++)
-            f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
-        apply_pressure_outlet(f, f_neb, (float)y);
+        apply_outlet_pull_d2q9(f, x, y, fi_in);
     }
     else {
         bounce_back_swap(f);
@@ -52,18 +44,10 @@ __device__ __forceinline__ void apply_boundary_pull_3d(
     bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
 
     if (is_inlet(fl) && interior_y) {
-        float f_neb[NQ];
-        unsigned long k_neb = linear_index(x + 1u, y, z);
-        for (int i = 0; i < NQ; i++)
-            f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
-        apply_parabolic_inlet_3d(f, f_neb, (float)y);
+        apply_inlet_pull_d3q19(f, x, y, z, fi_in);
     }
     else if (is_outlet(fl) && interior_y) {
-        float f_neb[NQ];
-        unsigned long k_neb = linear_index(x - 1u, y, z);
-        for (int i = 0; i < NQ; i++)
-            f_neb[i] = load_ddf(fi_in, index_f(k_neb, (unsigned int)i));
-        apply_pressure_outlet_3d(f, f_neb, (float)y);
+        apply_outlet_pull_d3q19(f, x, y, z, fi_in);
     }
     else {
         bounce_back_swap(f);
@@ -85,6 +69,7 @@ void OneStep(
 
     uint16_t fl = flag[k];
     unsigned long j[NQ];
+    const bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
     compute_neighbors(x, y, j);
 
     float f[NQ];
@@ -108,8 +93,15 @@ void OneStep(
 #endif
     }
 
-    // Collision (fluid only)
-    if (is_fluid(fl)) {
+    // Collision
+    // Normal path: fluid nodes collide.
+    // Path A repair: when using the local Zou-He inlet, the west inlet nodes are
+    // still tagged SOLID|BC_INLET ghost nodes, but their post-BC state is later
+    // used as a pull source for x=1. Leaving that ghost state uncollided was the
+    // main donor/ghost semantic bug behind the observed inlet blow-ups.
+    const bool collide_inlet_ghost = is_inlet(fl) && interior_y
+                                   && inlet_scheme_uses_post_collision_ghost();
+    if (is_fluid(fl) || collide_inlet_ghost) {
         float rho_n, ux, uy;
         compute_rho_u(f, rho_n, ux, uy);
         collide_dispatch(f, rho_n, ux, uy);
@@ -124,6 +116,7 @@ void OneStep(
 
     uint16_t fl = flag[k];
     unsigned long j[NQ];
+    const bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
     compute_neighbors(k, j);
 
     float f[NQ];
@@ -138,7 +131,9 @@ void OneStep(
     if (is_fluid(fl) && (y == 1u || y == (unsigned int)(NY - 2)))
         apply_wall_bb_d3q19_y_pull(y, f, fi_in, k);
 
-    if (is_fluid(fl)) {
+    const bool collide_inlet_ghost = is_inlet(fl) && interior_y
+                                   && inlet_scheme_uses_post_collision_ghost();
+    if (is_fluid(fl) || collide_inlet_ghost) {
         float rho_n, ux, uy, uz;
         compute_rho_u(f, rho_n, ux, uy, uz);
         collide_dispatch(f, rho_n, ux, uy, uz);

src/CelerisLab/lbm/kernels/step/one_step_esopull.cu

@@ -29,20 +29,10 @@ __device__ __forceinline__ void apply_boundary_esopull(
     bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
 
     if (is_inlet(fl) && interior_y) {
-        unsigned long k_neb = linear_index(x + 1u, y);
-        unsigned long j_neb[NQ];
-        compute_neighbors(x + 1u, y, j_neb);
-        float f_neb[NQ];
-        load_f_esopull(k_neb, f_neb, fi, j_neb, t);
-        apply_parabolic_inlet(f, f_neb, (float)y);
+        apply_inlet_esopull_d2q9(f, x, y, fi, t);
     }
     else if (is_outlet(fl) && interior_y) {
-        unsigned long k_neb = linear_index(x - 1u, y);
-        unsigned long j_neb[NQ];
-        compute_neighbors(x - 1u, y, j_neb);
-        float f_neb[NQ];
-        load_f_esopull(k_neb, f_neb, fi, j_neb, t);
-        apply_pressure_outlet(f, f_neb, (float)y);
+        apply_outlet_esopull_d2q9(f, x, y, fi, t);
     }
     else {
         bounce_back_swap(f);
@@ -62,20 +52,10 @@ __device__ __forceinline__ void apply_boundary_esopull_3d(
     bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
 
     if (is_inlet(fl) && interior_y) {
-        unsigned long k_neb = linear_index(x + 1u, y, z);
-        unsigned long j_neb[NQ];
-        compute_neighbors(k_neb, j_neb);
-        float f_neb[NQ];
-        load_f_esopull(k_neb, f_neb, fi, j_neb, t);
-        apply_parabolic_inlet_3d(f, f_neb, (float)y);
+        apply_inlet_esopull_d3q19(f, x, y, z, fi, t);
     }
     else if (is_outlet(fl) && interior_y) {
-        unsigned long k_neb = linear_index(x - 1u, y, z);
-        unsigned long j_neb[NQ];
-        compute_neighbors(k_neb, j_neb);
-        float f_neb[NQ];
-        load_f_esopull(k_neb, f_neb, fi, j_neb, t);
-        apply_pressure_outlet_3d(f, f_neb, (float)y);
+        apply_outlet_esopull_d3q19(f, x, y, z, fi, t);
     }
     else {
         bounce_back_swap(f);
@@ -99,6 +79,7 @@ void EsoPullStep(
 
     uint16_t fl = flag[k];
     unsigned long j[NQ];
+    const bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
     compute_neighbors(x, y, j);
 
     float f[NQ];
@@ -118,8 +99,13 @@ void EsoPullStep(
     if (is_obstacle(fl) && !is_curved(fl))
         bounce_back_swap(f);
 
-    // Collision (fluid only)
-    if (is_fluid(fl)) {
+    // Collision
+    // Same donor/ghost warning as the double-buffer path: for the local Zou-He
+    // inlet, the ghost-node state must be regularized before the next pull uses
+    // it as the source state for the first interior column.
+    const bool collide_inlet_ghost = is_inlet(fl) && interior_y
+                                   && inlet_scheme_uses_post_collision_ghost();
+    if (is_fluid(fl) || collide_inlet_ghost) {
         float rho_n, ux, uy;
         compute_rho_u(f, rho_n, ux, uy);
         collide_dispatch(f, rho_n, ux, uy);
@@ -134,6 +120,7 @@ void EsoPullStep(
 
     uint16_t fl = flag[k];
     unsigned long j[NQ];
+    const bool interior_y = (y > 0u) && (y < (unsigned int)(NY - 1));
     compute_neighbors(k, j);
 
     float f[NQ];
@@ -151,7 +138,9 @@ void EsoPullStep(
     if (is_obstacle(fl) && !is_curved(fl))
         bounce_back_swap(f);
 
-    if (is_fluid(fl)) {
+    const bool collide_inlet_ghost = is_inlet(fl) && interior_y
+                                   && inlet_scheme_uses_post_collision_ghost();
+    if (is_fluid(fl) || collide_inlet_ghost) {
         float rho_n, ux, uy, uz;
         compute_rho_u(f, rho_n, ux, uy, uz);
         collide_dispatch(f, rho_n, ux, uy, uz);

tests/inlet_plan.md

@@ -0,0 +1,75 @@
+## Inlet module refactor plan
+
+The inlet module should be treated as a source-state generator for west ghost nodes, not as a grab-bag of formulas inside one boundary file. In the current solver, inlet cells are `SOLID | BC_INLET` ghost nodes whose state is later pulled by the first interior column. That semantic should stay explicit in the code structure.
+
+## Current target structure
+
+- `boundary/inlet/common`
+  - shared profile logic such as `inlet_target_u(y)`
+  - shared rho-closure helpers for west velocity inlet
+  - helper stating whether a scheme requires post-BC ghost collision
+- `boundary/inlet/zou_he_local`
+  - local on-site Zou-He source-state reconstruction
+  - D2Q9 and D3Q19 west inlet versions
+- `boundary/inlet/channel_stabilized`
+  - donor-based stabilized inlet for high blockage or conservative production runs
+  - D2Q9 and D3Q19 west inlet versions
+- `boundary/inlet/equilibrium`
+  - full `feq` source-state construction from local rho closure and target velocity
+  - D2Q9 and D3Q19 versions
+- `boundary/inlet/regularized`
+  - local macro state plus damped donor NEQ on incoming directions
+  - D2Q9 and D3Q19 versions
+- `boundary/outlet/pressure_neq`
+  - pressure outlet and zero-gradient outlet implementations
+- `boundary/inlet_outlet`
+  - compile-time dispatch only
+  - no long method bodies
+  - streaming-specific donor assembly and method selection
+
+## Design rule for each inlet scheme
+
+Each scheme should answer the same question:
+
+- given a west ghost node after pull loading, what source state should be stored there for the next interior pull
+
+That makes the interface stable even when methods differ in how much donor information they use.
+
+## Scheme meanings
+
+| Scheme | Main idea | Best fit | Main caution |
+|---|---|---|---|
+| `zou_he_local` | textbook local algebraic closure | MRT, research comparisons, clean local baseline | in ghost-source semantics it requires post-BC ghost collision and can be noisy for high-omega SRT |
+| `channel_stabilized` | donor-based stabilized inlet | high blockage, production robustness, conservative benchmark work | less pure as a local boundary method |
+| `equilibrium` | write full `feq` source state | robust SRT baseline, simple ghost-source compatibility | may suppress inlet NEQ too aggressively for some validation targets |
+| `regularized` | local macro state plus damped incoming donor NEQ | middle ground between `equilibrium` and donor-heavy methods | still an experimental family and may need tuning |
+
+## Collision policy
+
+Post-BC ghost collision must be owned by the scheme, not hard-coded as a general inlet rule.
+
+Current policy:
+
+- `zou_he_local` requires post-BC ghost collision
+- `channel_stabilized` does not
+- `equilibrium` does not
+- `regularized` does not
+
+This should remain encoded through a helper such as `inlet_scheme_uses_post_collision_ghost()` rather than scattered `INLET_SCHEME == ...` checks.
+
+## Why this split matters
+
+The earlier instability work showed that the main difficulty was not a single formula error. The real issue was mixing methods that assume different node semantics:
+
+- local fluid-boundary formulas such as Zou-He
+- ghost-source node architecture in the solver
+- different collision-model tolerances, especially SRT versus MRT
+
+Keeping each inlet method in its own file makes those assumptions visible and lowers the chance of mixing donor and ghost semantics by accident.
+
+## Next cleanups worth doing later
+
+1. Split outlet schemes into separate files as more outlet variants are added.
+2. If inlet junction handling grows, move row-specific or corner-specific logic into dedicated helpers instead of embedding it inside the main schemes.
+3. When validation settles, add a small test matrix document mapping recommended schemes to benchmark families and collision models.
+4. If the solver later moves away from ghost-source inlet nodes, keep this folder layout but replace the per-scheme internals rather than rebuilding the whole dispatch layer.

tests/run_inlet_channel_diagnostic.py

@@ -0,0 +1,574 @@
+# CelerisLab/tests/run_inlet_channel_diagnostic.py
+"""Empty-channel inlet diagnostic: field snapshots and line profiles.
+
+Runs no-cylinder channel flows to isolate inlet / wall / outlet effects before
+adding a body.  See user matrix in module docstring sections A–C.
+
+Usage::
+
+    conda run -n pycuda_3_10 python tests/run_inlet_channel_diagnostic.py --part all
+    conda run -n pycuda_3_10 python tests/run_inlet_channel_diagnostic.py --part a
+    conda run -n pycuda_3_10 python tests/run_inlet_channel_diagnostic.py --part b --nx 401 --ny 201
+
+Output (default ``tests/output/inlet_channel_diag/``)::
+
+    A_baseline/{SRT,MRT}/snapshots/step_XXXXXX.{npz,png}
+    B_matrix/caseNN_.../snapshots/...
+    B_matrix/caseNN_.../lines/ux_lines_stepXXXXXX.png
+    summary.csv
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+import os
+import sys
+import tempfile
+from dataclasses import dataclass
+from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple
+
+import numpy as np
+
+_REPO = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+_DEFAULT_LBM = os.path.join(_REPO, "src", "CelerisLab", "configs", "config_lbm.json")
+
+# Default snapshot steps for parts A and B.
+DEFAULT_SNAPSHOT_STEPS: Tuple[int, ...] = (100, 500, 1000, 1500, 2000)
+
+
+@dataclass(frozen=True)
+class CaseSpec:
+    """One empty-channel configuration."""
+
+    case_id: str
+    label: str
+    inlet_scheme: str
+    y_wall_bc: str
+    outlet_mode: str
+    collision: str = "MRT"
+
+
+def _load_json(path: str) -> dict:
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def _write_json(path: str, payload: dict) -> None:
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(payload, f, indent=2)
+
+
+def vorticity_z(ux: np.ndarray, uy: np.ndarray) -> np.ndarray:
+    """ωz = ∂uy/∂x − ∂ux/∂y on (ny, nx) arrays."""
+    ux = np.asarray(ux, dtype=np.float64)
+    uy = np.asarray(uy, dtype=np.float64)
+    return np.gradient(uy, axis=1) - np.gradient(ux, axis=0)
+
+
+def _line_y_indices(ny: int) -> List[Tuple[int, str]]:
+    return [
+        (1, "y1"),
+        (ny // 2, f"y{ny // 2}"),
+        (ny - 2, f"y{ny - 2}"),
+    ]
+
+
+def _build_cfg(
+    base: dict,
+    *,
+    nx: int,
+    ny: int,
+    collision: str,
+    inlet_scheme: str,
+    inlet_profile: str,
+    y_wall_bc: str,
+    outlet_mode: str,
+    velocity: float,
+    viscosity: float,
+) -> dict:
+    cfg = json.loads(json.dumps(base))
+    cfg["grid"]["nx"] = int(nx)
+    cfg["grid"]["ny"] = int(ny)
+    cfg["grid"]["nz"] = 1
+    cfg["physics"]["velocity"] = float(velocity)
+    cfg["physics"]["viscosity"] = float(viscosity)
+    cfg["physics"]["rho"] = 1.0
+    cfg["method"]["collision"] = str(collision).upper()
+    cfg["method"]["streaming"] = "double_buffer"
+    cfg["method"]["store_precision"] = "FP32"
+    cfg["method"]["les"]["enabled"] = False
+    cfg["method"]["inlet"]["profile"] = str(inlet_profile)
+    cfg["method"]["inlet"]["scheme"] = str(inlet_scheme)
+    cfg["method"]["y_wall_bc"] = str(y_wall_bc)
+    cfg["method"]["outlet"]["mode"] = str(outlet_mode)
+    return cfg
+
+
+def _field_stats(rho: np.ndarray, ux: np.ndarray, vort: np.ndarray) -> Dict[str, float]:
+    def _f(a: np.ndarray) -> float:
+        b = a[np.isfinite(a)]
+        return float("nan") if b.size == 0 else float(np.max(np.abs(b)))
+
+    return {
+        "rho_min": float(np.nanmin(rho)) if np.isfinite(rho).any() else float("nan"),
+        "rho_max": float(np.nanmax(rho)) if np.isfinite(rho).any() else float("nan"),
+        "ux_max": _f(ux),
+        "vort_max": _f(vort),
+        "finite": bool(np.isfinite(rho).all() and np.isfinite(ux).all()),
+    }
+
+
+def _save_snapshot_npz(
+    path: str,
+    *,
+    step: int,
+    rho: np.ndarray,
+    ux: np.ndarray,
+    uy: np.ndarray,
+    vort: np.ndarray,
+    meta: dict,
+) -> None:
+    os.makedirs(os.path.dirname(path), exist_ok=True)
+    np.savez_compressed(
+        path,
+        rho=np.asarray(rho, dtype=np.float32),
+        ux=np.asarray(ux, dtype=np.float32),
+        uy=np.asarray(uy, dtype=np.float32),
+        vort=np.asarray(vort, dtype=np.float32),
+        step=np.int32(step),
+        meta_json=np.asarray(json.dumps(meta)),
+    )
+
+
+def _save_field_pngs(
+    out_dir: str,
+    prefix: str,
+    *,
+    rho: np.ndarray,
+    ux: np.ndarray,
+    vort: np.ndarray,
+    title: str,
+) -> List[str]:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return []
+
+    os.makedirs(out_dir, exist_ok=True)
+    ny, nx = rho.shape
+    extent = (0, nx - 1, 0, ny - 1)
+    paths: List[str] = []
+
+    def _one(arr: np.ndarray, name: str, cmap: str, sym: bool) -> None:
+        a = np.asarray(arr, dtype=np.float64)
+        fin = a[np.isfinite(a)]
+        if fin.size == 0:
+            vmin, vmax = -1.0, 1.0
+        elif sym:
+            v = float(np.percentile(np.abs(fin), 99.5)) or 1.0
+            vmin, vmax = -v, v
+        else:
+            vmin = float(np.percentile(fin, 0.5))
+            vmax = float(np.percentile(fin, 99.5))
+            if vmax <= vmin:
+                vmax = vmin + 1.0
+        fig, ax = plt.subplots(figsize=(min(16.0, max(8.0, nx / 80.0)), min(8.0, max(3.0, ny / 50.0))))
+        im = ax.imshow(a, origin="lower", aspect="auto", cmap=cmap, vmin=vmin, vmax=vmax, extent=extent)
+        ax.set_xlabel("x")
+        ax.set_ylabel("y")
+        ax.set_title(f"{title} — {name}")
+        fig.colorbar(im, ax=ax, fraction=0.046, pad=0.04)
+        fig.tight_layout()
+        p = os.path.join(out_dir, f"{prefix}_{name}.png")
+        fig.savefig(p, dpi=140, bbox_inches="tight")
+        plt.close(fig)
+        paths.append(p)
+
+    _one(rho, "rho", "viridis", sym=False)
+    _one(ux, "ux", "RdBu_r", sym=True)
+    _one(vort, "vort", "RdBu_r", sym=True)
+    return paths
+
+
+def _save_line_plots(
+    path: str,
+    *,
+    rho: np.ndarray,
+    ux: np.ndarray,
+    step: int,
+    case_label: str,
+    y_rows: Sequence[Tuple[int, str]],
+) -> None:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return
+
+    ny, nx = rho.shape
+    x = np.arange(nx, dtype=np.float64)
+
+    fig, axes = plt.subplots(2, 1, figsize=(min(14.0, max(8.0, nx / 60.0)), 7.0), sharex=True)
+    for y_idx, y_lab in y_rows:
+        y_idx = int(np.clip(y_idx, 0, ny - 1))
+        axes[0].plot(x, ux[y_idx, :], label=y_lab, linewidth=1.2)
+        axes[1].plot(x, rho[y_idx, :], label=y_lab, linewidth=1.2)
+
+    axes[0].set_ylabel("u_x")
+    axes[0].legend(loc="best", fontsize=8)
+    axes[0].grid(True, alpha=0.3)
+    axes[1].set_ylabel("rho")
+    axes[1].set_xlabel("x (lattice)")
+    axes[1].legend(loc="best", fontsize=8)
+    axes[1].grid(True, alpha=0.3)
+    fig.suptitle(f"{case_label} — line profiles at step {step}")
+    fig.tight_layout()
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    fig.savefig(path, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+
+
+def _run_channel(
+    case: CaseSpec,
+    *,
+    base_cfg: dict,
+    nx: int,
+    ny: int,
+    velocity: float,
+    viscosity: float,
+    out_root: str,
+    snapshot_steps: Sequence[int],
+    max_step: int,
+    save_png: bool,
+    save_lines: bool,
+    stop_on_nan: bool,
+) -> List[Dict[str, Any]]:
+    """Run one case; write snapshots and optional line plots. Return summary rows."""
+    sys.path.insert(0, os.path.join(_REPO, "src"))
+    from CelerisLab import Simulation  # noqa: WPS433
+
+    cfg = _build_cfg(
+        base_cfg,
+        nx=nx,
+        ny=ny,
+        collision=case.collision,
+        inlet_scheme=case.inlet_scheme,
+        inlet_profile="uniform",
+        y_wall_bc=case.y_wall_bc,
+        outlet_mode=case.outlet_mode,
+        velocity=velocity,
+        viscosity=viscosity,
+    )
+    bdoc = {"objects": []}
+
+    run_dir = os.path.join(out_root, case.case_id)
+    snap_dir = os.path.join(run_dir, "snapshots")
+    line_dir = os.path.join(run_dir, "lines")
+    os.makedirs(snap_dir, exist_ok=True)
+    if save_lines:
+        os.makedirs(line_dir, exist_ok=True)
+
+    tmpd = tempfile.mkdtemp(prefix="inlet_diag_")
+    lbm_tmp = os.path.join(tmpd, "config_lbm.json")
+    body_tmp = os.path.join(tmpd, "config_body.json")
+    _write_json(lbm_tmp, cfg)
+    _write_json(body_tmp, bdoc)
+
+    meta_base = {
+        "case_id": case.case_id,
+        "label": case.label,
+        "nx": nx,
+        "ny": ny,
+        "inlet_scheme": case.inlet_scheme,
+        "inlet_profile": "uniform",
+        "y_wall_bc": case.y_wall_bc,
+        "outlet_mode": case.outlet_mode,
+        "collision": case.collision,
+        "velocity": velocity,
+        "viscosity": viscosity,
+    }
+    _write_json(os.path.join(run_dir, "case_meta.json"), meta_base)
+
+    sim = Simulation(lbm_config_path=lbm_tmp, body_config_path=body_tmp)
+    sim.initialize()
+
+    y_rows = _line_y_indices(ny)
+    want_steps = sorted({int(s) for s in snapshot_steps if 0 < int(s) <= max_step})
+    next_snap = 0
+    rows: List[Dict[str, Any]] = []
+
+    for step in range(1, max_step + 1):
+        sim.step(1)
+        if next_snap < len(want_steps) and step == want_steps[next_snap]:
+            macro = sim.get_macroscopic()
+            rho = np.asarray(macro["rho"], dtype=np.float64)
+            ux = np.asarray(macro["ux"], dtype=np.float64)
+            uy = np.asarray(macro["uy"], dtype=np.float64)
+            vort = vorticity_z(ux, uy)
+            stats = _field_stats(rho, ux, vort)
+            stem = f"step_{step:06d}"
+            meta = {**meta_base, "step": step, **stats}
+            npz_path = os.path.join(snap_dir, f"{stem}.npz")
+            _save_snapshot_npz(
+                npz_path,
+                step=step,
+                rho=rho,
+                ux=ux,
+                uy=uy,
+                vort=vort,
+                meta=meta,
+            )
+            if save_png:
+                _save_field_pngs(
+                    snap_dir,
+                    stem,
+                    rho=rho,
+                    ux=ux,
+                    vort=vort,
+                    title=f"{case.label} step {step}",
+                )
+            if save_lines:
+                line_png = os.path.join(line_dir, f"lines_{stem}.png")
+                _save_line_plots(
+                    line_png,
+                    rho=rho,
+                    ux=ux,
+                    step=step,
+                    case_label=case.label,
+                    y_rows=y_rows,
+                )
+                # Also save raw 1D data for replotting.
+                line_npz = os.path.join(line_dir, f"lines_{stem}.npz")
+                payload = {"x": np.arange(nx, dtype=np.float32)}
+                for y_idx, y_lab in y_rows:
+                    payload[f"ux_{y_lab}"] = ux[y_idx, :].astype(np.float32)
+                    payload[f"rho_{y_lab}"] = rho[y_idx, :].astype(np.float32)
+                payload["step"] = np.int32(step)
+                np.savez_compressed(line_npz, **payload)
+
+            rows.append(
+                {
+                    "case_id": case.case_id,
+                    "label": case.label,
+                    "collision": case.collision,
+                    "inlet_scheme": case.inlet_scheme,
+                    "y_wall_bc": case.y_wall_bc,
+                    "outlet_mode": case.outlet_mode,
+                    "step": step,
+                    **stats,
+                    "npz": npz_path,
+                }
+            )
+            if stop_on_nan and not stats["finite"]:
+                sim.close()
+                rows[-1]["stopped_early"] = True
+                return rows
+            next_snap += 1
+
+    sim.close()
+    return rows
+
+
+def _part_a_cases() -> List[CaseSpec]:
+    # Kan99b-style baseline: zou_he + free_slip + neq_extrap; SRT and MRT.
+    base = CaseSpec(
+        case_id="",
+        label="",
+        inlet_scheme="zou_he_local",
+        y_wall_bc="free_slip",
+        outlet_mode="neq_extrap",
+    )
+    out: List[CaseSpec] = []
+    for coll in ("SRT", "MRT"):
+        cid = f"A_{coll.lower()}_zouhe_fs_neq"
+        out.append(
+            CaseSpec(
+                case_id=cid,
+                label=f"A baseline {coll} zou_he / free_slip / neq_extrap",
+                inlet_scheme=base.inlet_scheme,
+                y_wall_bc=base.y_wall_bc,
+                outlet_mode=base.outlet_mode,
+                collision=coll,
+            )
+        )
+    return out
+
+
+def _part_b_cases() -> List[CaseSpec]:
+    return [
+        CaseSpec(
+            case_id="B_case01_zouhe_fs_neq",
+            label="1 zou_he / free_slip / neq_extrap",
+            inlet_scheme="zou_he_local",
+            y_wall_bc="free_slip",
+            outlet_mode="neq_extrap",
+            collision="MRT",
+        ),
+        CaseSpec(
+            case_id="B_case02_zouhe_bb_neq",
+            label="2 zou_he / bounce_back / neq_extrap",
+            inlet_scheme="zou_he_local",
+            y_wall_bc="bounce_back",
+            outlet_mode="neq_extrap",
+            collision="MRT",
+        ),
+        CaseSpec(
+            case_id="B_case03_zouhe_fs_zgrad",
+            label="3 zou_he / free_slip / zero_gradient",
+            inlet_scheme="zou_he_local",
+            y_wall_bc="free_slip",
+            outlet_mode="zero_gradient",
+            collision="MRT",
+        ),
+        CaseSpec(
+            case_id="B_case04_stab_fs_neq",
+            label="4 channel_stabilized / free_slip / neq_extrap",
+            inlet_scheme="channel_stabilized",
+            y_wall_bc="free_slip",
+            outlet_mode="neq_extrap",
+            collision="MRT",
+        ),
+    ]
+
+
+def _write_summary_csv(path: str, rows: Sequence[Dict[str, Any]]) -> None:
+    if not rows:
+        return
+    keys = [
+        "case_id",
+        "label",
+        "collision",
+        "inlet_scheme",
+        "y_wall_bc",
+        "outlet_mode",
+        "step",
+        "finite",
+        "rho_min",
+        "rho_max",
+        "ux_max",
+        "vort_max",
+        "stopped_early",
+    ]
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    with open(path, "w", encoding="utf-8", newline="") as f:
+        w = csv.DictWriter(f, fieldnames=keys, extrasaction="ignore")
+        w.writeheader()
+        for r in rows:
+            w.writerow(r)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Empty-channel inlet diagnostic (fields + line profiles)")
+    ap.add_argument(
+        "--part",
+        choices=("a", "b", "all"),
+        default="all",
+        help="A=baseline SRT/MRT; B=4-case matrix; all=both",
+    )
+    ap.add_argument("--nx", type=int, default=401, help="Channel length (lattice)")
+    ap.add_argument("--ny", type=int, default=201, help="Channel height (lattice)")
+    ap.add_argument("--velocity", type=float, default=0.03, help="Uniform inlet U0")
+    ap.add_argument("--viscosity", type=float, default=0.009, help="Kinematic viscosity")
+    ap.add_argument(
+        "--out-dir",
+        type=str,
+        default=os.path.join(_REPO, "tests", "output", "inlet_channel_diag"),
+    )
+    ap.add_argument(
+        "--steps",
+        type=str,
+        default="",
+        help="Comma-separated snapshot steps (default: 100,500,1000,1500,2000)",
+    )
+    ap.add_argument("--no-png", action="store_true", help="Skip rho/ux/vort PNG maps")
+    ap.add_argument("--no-lines", action="store_true", help="Skip ux/rho line-profile plots")
+    ap.add_argument(
+        "--continue-on-nan",
+        action="store_true",
+        help="Keep stepping after non-finite fields (default: stop case early)",
+    )
+    args = ap.parse_args()
+
+    if not os.path.isfile(_DEFAULT_LBM):
+        print(f"Missing config: {_DEFAULT_LBM}", file=sys.stderr)
+        return 2
+
+    if args.steps.strip():
+        snap_steps = tuple(int(s.strip()) for s in args.steps.split(",") if s.strip())
+    else:
+        snap_steps = DEFAULT_SNAPSHOT_STEPS
+    max_step = max(snap_steps)
+
+    base_cfg = _load_json(_DEFAULT_LBM)
+    out_dir = os.path.abspath(args.out_dir)
+    os.makedirs(out_dir, exist_ok=True)
+
+    cases: List[CaseSpec] = []
+    if args.part in ("a", "all"):
+        cases.extend(_part_a_cases())
+    if args.part in ("b", "all"):
+        cases.extend(_part_b_cases())
+
+    save_png = not args.no_png
+    # Part A: field maps only; Part B: fields + line plots.
+    all_rows: List[Dict[str, Any]] = []
+
+    for case in cases:
+        part = "A_baseline" if case.case_id.startswith("A_") else "B_matrix"
+        root = os.path.join(out_dir, part)
+        save_lines = not args.no_lines and part == "B_matrix"
+        print(f"--- {case.case_id}: {case.label} ({case.collision}) ---", flush=True)
+        rows = _run_channel(
+            case,
+            base_cfg=base_cfg,
+            nx=args.nx,
+            ny=args.ny,
+            velocity=args.velocity,
+            viscosity=args.viscosity,
+            out_root=root,
+            snapshot_steps=snap_steps,
+            max_step=max_step,
+            save_png=save_png,
+            save_lines=save_lines,
+            stop_on_nan=not args.continue_on_nan,
+        )
+        all_rows.extend(rows)
+        for r in rows:
+            fin = "OK" if r.get("finite") else "NONFINITE"
+            print(
+                f"  step {r['step']:5d}  {fin}  rho=[{r['rho_min']:.4f},{r['rho_max']:.4f}]  "
+                f"ux_max={r['ux_max']:.4f}  vort_max={r['vort_max']:.4f}",
+                flush=True,
+            )
+        if rows and rows[-1].get("stopped_early"):
+            print("  (stopped early: non-finite fields)", flush=True)
+
+    summary_path = os.path.join(out_dir, "summary.csv")
+    _write_summary_csv(summary_path, all_rows)
+    manifest = {
+        "snapshot_steps": list(snap_steps),
+        "nx": args.nx,
+        "ny": args.ny,
+        "velocity": args.velocity,
+        "viscosity": args.viscosity,
+        "line_y_indices": [{"y": y, "label": lab} for y, lab in _line_y_indices(args.ny)],
+        "cases": [c.case_id for c in cases],
+    }
+    _write_json(os.path.join(out_dir, "manifest.json"), manifest)
+
+    print(f"Wrote: {summary_path}", flush=True)
+    print(f"Wrote: {os.path.join(out_dir, 'manifest.json')}", flush=True)
+    print(f"Output root: {out_dir}", flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tests/run_inlet_ghost_timing_experiment.py

@@ -0,0 +1,460 @@
+# CelerisLab/tests/run_inlet_ghost_timing_experiment.py
+"""Minimal ghost-inlet timing experiments (post field-diagnostic).
+
+Experiment 1 — DDF time series at inlet center vs first interior column:
+  (x=0, y=NY/2) and (x=1, y=NY/2), steps 1..N.
+  Populations f1,f2,f5,f6,f7,f8 plus rho, ux (macro and sum f).
+
+Experiment 2 — Same channel with ``inlet.collide=false`` vs ``true``:
+  When collide is on, inlet ghost nodes undergo collision after Zou-He BC.
+  Compare rho_max / ux_max vs step to test ghost-source timing hypothesis.
+
+Usage::
+
+    conda run -n pycuda_3_10 python tests/run_inlet_ghost_timing_experiment.py
+    conda run -n pycuda_3_10 python tests/run_inlet_ghost_timing_experiment.py --exp 1 --steps 50
+    conda run -n pycuda_3_10 python tests/run_inlet_ghost_timing_experiment.py --exp 2 --steps 500
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+import os
+import sys
+import tempfile
+from typing import Any, Dict, List, Optional, Sequence, Tuple
+
+import numpy as np
+
+_REPO = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+_DEFAULT_LBM = os.path.join(_REPO, "src", "CelerisLab", "configs", "config_lbm.json")
+
+# D2Q9 indices logged (see zou_he_velocity.cuh).
+POP_IDX: Tuple[int, ...] = (1, 2, 5, 6, 7, 8)
+POP_NAMES: Tuple[str, ...] = tuple(f"f{i}" for i in POP_IDX)
+
+# cx, cy for macroscopic ux, uy from local f (matches descriptors.cuh D2Q9).
+_CX = np.array([0, 1, -1, 0, 0, 1, -1, 1, -1], dtype=np.float64)
+_CY = np.array([0, 0, 0, 1, -1, 1, -1, -1, 1], dtype=np.float64)
+
+
+def _load_json(path: str) -> dict:
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def _write_json(path: str, payload: dict) -> None:
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(payload, f, indent=2)
+
+
+def _build_cfg(
+    base: dict,
+    *,
+    nx: int,
+    ny: int,
+    collision: str,
+    inlet_collide: bool,
+    velocity: float,
+    viscosity: float,
+) -> dict:
+    cfg = json.loads(json.dumps(base))
+    cfg["grid"]["nx"] = int(nx)
+    cfg["grid"]["ny"] = int(ny)
+    cfg["grid"]["nz"] = 1
+    cfg["physics"]["velocity"] = float(velocity)
+    cfg["physics"]["viscosity"] = float(viscosity)
+    cfg["physics"]["rho"] = 1.0
+    cfg["method"]["collision"] = str(collision).upper()
+    cfg["method"]["streaming"] = "double_buffer"
+    cfg["method"]["store_precision"] = "FP32"
+    cfg["method"]["les"]["enabled"] = False
+    cfg["method"]["inlet"]["profile"] = "uniform"
+    cfg["method"]["inlet"]["scheme"] = "zou_he_local"
+    cfg["method"]["inlet"]["collide"] = bool(inlet_collide)
+    cfg["method"]["y_wall_bc"] = "free_slip"
+    cfg["method"]["outlet"]["mode"] = "neq_extrap"
+    return cfg
+
+
+def _macro_from_f(f: np.ndarray) -> Tuple[float, float, float]:
+    f = np.asarray(f, dtype=np.float64)
+    rho = float(np.sum(f))
+    if abs(rho) < 1e-14:
+        return rho, 0.0, 0.0
+    ux = float(np.dot(f, _CX) / rho)
+    uy = float(np.dot(f, _CY) / rho)
+    return rho, ux, uy
+
+
+def _sample_node(ddf_qnyx: np.ndarray, x: int, y: int) -> Dict[str, float]:
+    f = ddf_qnyx[:, y, x].astype(np.float64)
+    rho_m, ux_m, uy_m = _macro_from_f(f)
+    out: Dict[str, float] = {
+        "rho_sum": rho_m,
+        "ux_macro": ux_m,
+        "uy_macro": uy_m,
+    }
+    for i, name in zip(POP_IDX, POP_NAMES):
+        out[name] = float(f[i])
+    return out
+
+
+def _run_steps(
+    cfg: dict,
+    *,
+    steps: int,
+    y_mid: int,
+    probe_x: Sequence[int] = (0, 1),
+) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
+    sys.path.insert(0, os.path.join(_REPO, "src"))
+    from CelerisLab import Simulation  # noqa: WPS433
+
+    bdoc = {"objects": []}
+    tmpd = tempfile.mkdtemp(prefix="ghost_timing_")
+    lbm_tmp = os.path.join(tmpd, "config_lbm.json")
+    body_tmp = os.path.join(tmpd, "config_body.json")
+    with open(lbm_tmp, "w", encoding="utf-8") as f:
+        json.dump(cfg, f)
+    with open(body_tmp, "w", encoding="utf-8") as f:
+        json.dump(bdoc, f)
+
+    sim = Simulation(lbm_config_path=lbm_tmp, body_config_path=body_tmp)
+    sim.initialize()
+    nx, ny = sim.lbm_cfg.nx, sim.lbm_cfg.ny
+    y_mid = int(np.clip(y_mid, 1, ny - 2))
+
+    rows: List[Dict[str, Any]] = []
+    for step in range(1, int(steps) + 1):
+        sim.step(1)
+        sim.field.download_ddf()
+        farr = sim.field.ddf.reshape(sim.lbm_cfg.nq, ny, nx)
+
+        rec: Dict[str, Any] = {"step": step}
+        for x in probe_x:
+            tag = "inlet" if x == 0 else "interior"
+            s = _sample_node(farr, int(x), y_mid)
+            for k, v in s.items():
+                rec[f"{tag}_{k}"] = v
+
+        # Pull semantics at interior: f[2] is read from stored f[2] at x=0 (same link index).
+        rec["cross_f2_match"] = abs(rec["interior_f2"] - rec["inlet_f2"]) < 1e-5
+        rec["cross_f1_inlet_to_int_pull"] = float(
+            farr[1, y_mid, 1]
+        )  # after step, what x=1 holds in f1
+        rec["delta_inlet_f1"] = (
+            float("nan") if step == 1 else rec["inlet_f1"] - rows[-1]["inlet_f1"]
+        )
+        rec["delta_inlet_ux"] = (
+            float("nan")
+            if step == 1
+            else rec["inlet_ux_macro"] - rows[-1]["inlet_ux_macro"]
+        )
+
+        macro = sim.get_macroscopic()
+        rho_f = np.asarray(macro["rho"], dtype=np.float64)
+        ux_f = np.asarray(macro["ux"], dtype=np.float64)
+        rec["domain_rho_max"] = float(np.nanmax(rho_f))
+        rec["domain_rho_min"] = float(np.nanmin(rho_f))
+        rec["domain_ux_max"] = float(np.nanmax(np.abs(ux_f)))
+        rec["finite"] = bool(np.isfinite(rho_f).all() and np.isfinite(ux_f).all())
+
+        rows.append(rec)
+
+    meta = {
+        "nx": nx,
+        "ny": ny,
+        "y_mid": y_mid,
+        "probe_x": list(probe_x),
+        "inlet_collide": bool(cfg["method"]["inlet"].get("collide", False)),
+        "collision": cfg["method"]["collision"],
+        "inlet_scheme": cfg["method"]["inlet"]["scheme"],
+        "y_wall_bc": cfg["method"]["y_wall_bc"],
+        "outlet_mode": cfg["method"]["outlet"]["mode"],
+        "velocity": cfg["physics"]["velocity"],
+        "viscosity": cfg["physics"]["viscosity"],
+    }
+    sim.close()
+    return rows, meta
+
+
+def _write_csv(path: str, rows: Sequence[Dict[str, Any]]) -> None:
+    if not rows:
+        return
+    keys: List[str] = []
+    for r in rows:
+        for k in r:
+            if k not in keys:
+                keys.append(k)
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    with open(path, "w", encoding="utf-8", newline="") as f:
+        w = csv.DictWriter(f, fieldnames=keys)
+        w.writeheader()
+        w.writerows(rows)
+
+
+def _plot_exp1(out_dir: str, rows: Sequence[Dict[str, Any]], y_mid: int) -> List[str]:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return []
+
+    steps = [int(r["step"]) for r in rows]
+    paths: List[str] = []
+
+    def _ts(key: str, label: str, ax, **kw):
+        ax.plot(steps, [r[key] for r in rows], label=label, **kw)
+
+    # Populations
+    fig, axes = plt.subplots(2, 1, figsize=(11, 7), sharex=True)
+    for name in POP_NAMES:
+        _ts(f"inlet_{name}", f"inlet {name}", axes[0], linewidth=1.0)
+    axes[0].set_ylabel("f at x=0")
+    axes[0].legend(ncol=3, fontsize=7, loc="best")
+    axes[0].grid(True, alpha=0.3)
+    for name in POP_NAMES:
+        _ts(f"interior_{name}", f"int {name}", axes[1], linewidth=1.0)
+    axes[1].set_ylabel("f at x=1")
+    axes[1].set_xlabel("step")
+    axes[1].legend(ncol=3, fontsize=7, loc="best")
+    axes[1].grid(True, alpha=0.3)
+    fig.suptitle(f"Exp1 populations (y={y_mid})")
+    fig.tight_layout()
+    p1 = os.path.join(out_dir, "exp1_populations.png")
+    fig.savefig(p1, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+    paths.append(p1)
+
+    # rho / ux + step-to-step deltas
+    fig, axes = plt.subplots(3, 1, figsize=(11, 8), sharex=True)
+    _ts("inlet_ux_macro", "inlet ux", axes[0])
+    _ts("interior_ux_macro", "interior ux", axes[0])
+    axes[0].axhline(0.03, color="k", ls="--", lw=0.8, label="U0")
+    axes[0].set_ylabel("u_x")
+    axes[0].legend(fontsize=8)
+    axes[0].grid(True, alpha=0.3)
+    _ts("inlet_rho_sum", "inlet rho", axes[1])
+    _ts("interior_rho_sum", "interior rho", axes[1])
+    axes[1].set_ylabel("rho")
+    axes[1].grid(True, alpha=0.3)
+    _ts("delta_inlet_f1", "|Δf1| inlet", axes[2])
+    axes[2].set_ylabel("Δf1")
+    axes[2].set_xlabel("step")
+    axes[2].grid(True, alpha=0.3)
+    fig.suptitle(f"Exp1 macro / inlet f1 increment (y={y_mid})")
+    fig.tight_layout()
+    p2 = os.path.join(out_dir, "exp1_macro_delta.png")
+    fig.savefig(p2, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+    paths.append(p2)
+
+    return paths
+
+
+def _plot_exp2(out_dir: str, rows_a: Sequence[Dict[str, Any]], rows_b: Sequence[Dict[str, Any]]) -> List[str]:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return []
+
+    fig, axes = plt.subplots(2, 1, figsize=(10, 6), sharex=True)
+    for rows, lab, c in (
+        (rows_a, "ghost (no collide)", "C0"),
+        (rows_b, "inlet collide", "C1"),
+    ):
+        steps = [int(r["step"]) for r in rows]
+        axes[0].plot(steps, [r["domain_rho_max"] for r in rows], label=lab, color=c)
+        axes[1].plot(steps, [r["domain_ux_max"] for r in rows], label=lab, color=c)
+    axes[0].set_ylabel("rho_max")
+    axes[0].legend()
+    axes[0].grid(True, alpha=0.3)
+    axes[1].set_ylabel("|ux|_max")
+    axes[1].set_xlabel("step")
+    axes[1].legend()
+    axes[1].grid(True, alpha=0.3)
+    fig.suptitle("Exp2: ghost vs inlet collide")
+    fig.tight_layout()
+    p = os.path.join(out_dir, "exp2_stability_compare.png")
+    fig.savefig(p, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+    return [p]
+
+
+def _oscillation_summary(rows: Sequence[Dict[str, Any]], *, last_n: int = 20) -> Dict[str, float]:
+    """High-frequency proxy: std of inlet f1 and ux over the last *last_n* steps."""
+    if len(rows) < 2:
+        return {}
+    tail = rows[-min(last_n, len(rows)) :]
+    f1 = np.array([r["inlet_f1"] for r in tail], dtype=np.float64)
+    ux = np.array([r["inlet_ux_macro"] for r in tail], dtype=np.float64)
+    d1 = np.array([r["delta_inlet_f1"] for r in tail if np.isfinite(r["delta_inlet_f1"])], dtype=np.float64)
+    return {
+        "std_inlet_f1_last": float(np.std(f1)),
+        "std_inlet_ux_last": float(np.std(ux)),
+        "mean_abs_delta_f1_last": float(np.mean(np.abs(d1))) if d1.size else float("nan"),
+    }
+
+
+def run_exp1(
+    base: dict,
+    *,
+    out_dir: str,
+    nx: int,
+    ny: int,
+    steps: int,
+    collision: str,
+    velocity: float,
+    viscosity: float,
+) -> None:
+    y_mid = ny // 2
+    cfg = _build_cfg(
+        base,
+        nx=nx,
+        ny=ny,
+        collision=collision,
+        inlet_collide=False,
+        velocity=velocity,
+        viscosity=viscosity,
+    )
+    print(f"Exp1: zou_he ghost inlet, y_mid={y_mid}, steps={steps}", flush=True)
+    rows, meta = _run_steps(cfg, steps=steps, y_mid=y_mid)
+    meta["oscillation"] = _oscillation_summary(rows)
+
+    exp_dir = os.path.join(out_dir, "exp1_ddf_timeseries")
+    os.makedirs(exp_dir, exist_ok=True)
+    _write_csv(os.path.join(exp_dir, "timeseries.csv"), rows)
+    _write_json(os.path.join(exp_dir, "meta.json"), meta)
+    plots = _plot_exp1(exp_dir, rows, y_mid)
+    for p in plots:
+        print(f"  plot: {p}", flush=True)
+
+    # Console summary for quick read
+    print("  last 5 steps (inlet center):", flush=True)
+    for r in rows[-5:]:
+        print(
+            f"    step {r['step']:3d}  f1={r['inlet_f1']:.6f}  ux={r['inlet_ux_macro']:.6f}  "
+            f"Δf1={r['delta_inlet_f1']:.2e}  rho_max={r['domain_rho_max']:.4f}  finite={r['finite']}",
+            flush=True,
+        )
+    print(f"  oscillation: {meta['oscillation']}", flush=True)
+    print(f"Wrote: {exp_dir}/timeseries.csv", flush=True)
+
+
+def run_exp2(
+    base: dict,
+    *,
+    out_dir: str,
+    nx: int,
+    ny: int,
+    steps: int,
+    collision: str,
+    velocity: float,
+    viscosity: float,
+) -> None:
+    y_mid = ny // 2
+    exp_dir = os.path.join(out_dir, "exp2_inlet_collide")
+    os.makedirs(exp_dir, exist_ok=True)
+
+    summaries: Dict[str, Any] = {}
+    all_rows: Dict[str, List[Dict[str, Any]]] = {}
+
+    for collide, tag in ((False, "ghost_no_collide"), (True, "ghost_with_collide")):
+        cfg = _build_cfg(
+            base,
+            nx=nx,
+            ny=ny,
+            collision=collision,
+            inlet_collide=collide,
+            velocity=velocity,
+            viscosity=viscosity,
+        )
+        print(f"Exp2 [{tag}]: inlet.collide={collide}, steps={steps}", flush=True)
+        rows, meta = _run_steps(cfg, steps=steps, y_mid=y_mid)
+        all_rows[tag] = rows
+        _write_csv(os.path.join(exp_dir, f"{tag}.csv"), rows)
+
+        last_finite = next(
+            (int(r["step"]) for r in rows if not r.get("finite", True)),
+            None,
+        )
+        summaries[tag] = {
+            **meta,
+            "first_nonfinite_step": last_finite,
+            "final_rho_max": rows[-1]["domain_rho_max"] if rows else None,
+            "final_finite": rows[-1].get("finite") if rows else None,
+            "oscillation": _oscillation_summary(rows),
+        }
+        print(
+            f"  final rho_max={summaries[tag]['final_rho_max']:.4f}  "
+            f"finite={summaries[tag]['final_finite']}  "
+            f"first_nonfinite={summaries[tag]['first_nonfinite_step']}",
+            flush=True,
+        )
+
+    _write_json(os.path.join(exp_dir, "summary.json"), summaries)
+    plots = _plot_exp2(exp_dir, all_rows["ghost_no_collide"], all_rows["ghost_with_collide"])
+    for p in plots:
+        print(f"  plot: {p}", flush=True)
+    print(f"Wrote: {exp_dir}/summary.json", flush=True)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Ghost inlet timing experiments")
+    ap.add_argument("--exp", choices=("1", "2", "all"), default="all")
+    ap.add_argument("--steps", type=int, default=50, help="Steps for exp1 (default 50)")
+    ap.add_argument("--steps2", type=int, default=500, help="Steps for exp2 (default 500)")
+    ap.add_argument("--nx", type=int, default=401)
+    ap.add_argument("--ny", type=int, default=201)
+    ap.add_argument("--collision", default="MRT", choices=("SRT", "TRT", "MRT"))
+    ap.add_argument("--velocity", type=float, default=0.03)
+    ap.add_argument("--viscosity", type=float, default=0.009)
+    ap.add_argument(
+        "--out-dir",
+        default=os.path.join(_REPO, "tests", "output", "inlet_ghost_timing"),
+    )
+    args = ap.parse_args()
+
+    if not os.path.isfile(_DEFAULT_LBM):
+        print(f"Missing {_DEFAULT_LBM}", file=sys.stderr)
+        return 2
+
+    base = _load_json(_DEFAULT_LBM)
+    out_dir = os.path.abspath(args.out_dir)
+    os.makedirs(out_dir, exist_ok=True)
+
+    if args.exp in ("1", "all"):
+        run_exp1(
+            base,
+            out_dir=out_dir,
+            nx=args.nx,
+            ny=args.ny,
+            steps=args.steps,
+            collision=args.collision,
+            velocity=args.velocity,
+            viscosity=args.viscosity,
+        )
+    if args.exp in ("2", "all"):
+        run_exp2(
+            base,
+            out_dir=out_dir,
+            nx=args.nx,
+            ny=args.ny,
+            steps=args.steps2,
+            collision=args.collision,
+            velocity=args.velocity,
+            viscosity=args.viscosity,
+        )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tests/run_inlet_scenario_fields.py

@@ -0,0 +1,587 @@
+# CelerisLab/tests/run_inlet_scenario_fields.py
+"""Three-scenario inlet field export: final or last-stable step at 5000 LBM steps.
+
+Scenarios:
+  - empty_channel: zou_he_local × {SRT,MRT} × {free_slip,bounce_back}
+  - empty_channel_inlet_matrix: all inlet schemes × {SRT,MRT}, bounce_back only
+  - kan99b:        zou_he_local × {SRT,MRT} × {free_slip,bounce_back}, Re=100, domain M
+  - sah04_case9:   channel_stabilized × {SRT,MRT}, high-blockage case 9 geometry
+
+Outputs per run (under ``--out-dir``):
+  fields/final_{rho,ux,vort}.png, fields/final.npz
+  lines/lines_ux_rho.png, lines/lines.npz
+  run_meta.json
+
+Usage::
+
+    conda run -n pycuda_3_10 python tests/run_inlet_scenario_fields.py
+    conda run -n pycuda_3_10 python tests/run_inlet_scenario_fields.py --scenario empty_channel
+    conda run -n pycuda_3_10 python tests/run_inlet_scenario_fields.py --scenario empty_channel_inlet_matrix
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+import os
+import sys
+import tempfile
+from dataclasses import dataclass, replace
+from typing import Any, Dict, List, Optional, Sequence, Tuple
+
+import numpy as np
+
+_REPO = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+_DEFAULT_LBM = os.path.join(_REPO, "src", "CelerisLab", "configs", "config_lbm.json")
+
+# Kan99b lattice contract
+_KAN_U_INF = 0.03
+_KAN_D = 30.0
+_KAN_R = 15.0
+_KAN_RE = 100.0
+_KAN_ALPHA = 1.0
+
+# Sah04 case 9 (high tier)
+_SAH_D = 30
+_SAH_NX = 80 * _SAH_D + 2
+_SAH_NY = 35
+_SAH_CX = 40.0 * _SAH_D + 0.5
+_SAH_CY = 17.0
+_SAH_RE = 200.0
+_SAH_U_MAX = 0.1
+
+
+@dataclass(frozen=True)
+class RunSpec:
+    """One simulation run specification."""
+
+    scenario: str
+    run_id: str
+    label: str
+    nx: int
+    ny: int
+    collision: str
+    inlet_scheme: str
+    inlet_profile: str
+    y_wall_bc: str
+    outlet_mode: str
+    velocity: float
+    viscosity: float
+    steps: int
+    has_cylinder: bool
+    cylinder_center: Tuple[float, float] = (0.0, 0.0)
+    cylinder_radius: float = 0.0
+    cylinder_omega: float = 0.0
+
+
+def _load_json(path: str) -> dict:
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def _write_json(path: str, payload: dict) -> None:
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(payload, f, indent=2)
+
+
+def vorticity_z(ux: np.ndarray, uy: np.ndarray) -> np.ndarray:
+    ux = np.asarray(ux, dtype=np.float64)
+    uy = np.asarray(uy, dtype=np.float64)
+    return np.gradient(uy, axis=1) - np.gradient(ux, axis=0)
+
+
+def _line_y_indices(ny: int) -> List[Tuple[int, str]]:
+    return [(1, "y1"), (ny // 2, f"y{ny // 2}"), (ny - 2, f"y{ny - 2}")]
+
+
+_INLET_SCHEMES = (
+    "zou_he_local",
+    "channel_stabilized",
+    "equilibrium",
+    "regularized",
+)
+
+
+def _empty_channel_inlet_matrix_specs() -> List[RunSpec]:
+    """All inlet schemes on empty channel, bounce_back, SRT/MRT (5000-step field export)."""
+    specs: List[RunSpec] = []
+    for coll in ("SRT", "MRT"):
+        for scheme in _INLET_SCHEMES:
+            run_id = f"{coll.lower()}_{scheme}"
+            specs.append(
+                RunSpec(
+                    scenario="empty_channel_inlet_matrix",
+                    run_id=run_id,
+                    label=f"empty {scheme} {coll} bounce_back",
+                    nx=401,
+                    ny=201,
+                    collision=coll,
+                    inlet_scheme=scheme,
+                    inlet_profile="uniform",
+                    y_wall_bc="bounce_back",
+                    outlet_mode="neq_extrap",
+                    velocity=0.03,
+                    viscosity=0.009,
+                    steps=5000,
+                    has_cylinder=False,
+                )
+            )
+    return specs
+
+
+def _all_specs() -> List[RunSpec]:
+    specs: List[RunSpec] = []
+    for coll in ("SRT", "MRT"):
+        for wall in ("free_slip", "bounce_back"):
+            wid = f"{coll.lower()}_{wall}"
+            specs.append(
+                RunSpec(
+                    scenario="empty_channel",
+                    run_id=wid,
+                    label=f"empty zou_he {coll} {wall}",
+                    nx=401,
+                    ny=201,
+                    collision=coll,
+                    inlet_scheme="zou_he_local",
+                    inlet_profile="uniform",
+                    y_wall_bc=wall,
+                    outlet_mode="neq_extrap",
+                    velocity=0.03,
+                    viscosity=0.009,
+                    steps=5000,
+                    has_cylinder=False,
+                )
+            )
+    dom_m = (1351, 601, (450.0, 300.0))
+    nu_k = _KAN_U_INF * _KAN_D / _KAN_RE
+    omega = 2.0 * _KAN_ALPHA * _KAN_U_INF / _KAN_D
+    for coll in ("SRT", "MRT"):
+        for wall in ("free_slip", "bounce_back"):
+            wid = f"{coll.lower()}_{wall}"
+            specs.append(
+                RunSpec(
+                    scenario="kan99b",
+                    run_id=wid,
+                    label=f"kan99b zou_he {coll} {wall}",
+                    nx=dom_m[0],
+                    ny=dom_m[1],
+                    collision=coll,
+                    inlet_scheme="zou_he_local",
+                    inlet_profile="uniform",
+                    y_wall_bc=wall,
+                    outlet_mode="neq_extrap",
+                    velocity=_KAN_U_INF,
+                    viscosity=nu_k,
+                    steps=5000,
+                    has_cylinder=True,
+                    cylinder_center=dom_m[2],
+                    cylinder_radius=_KAN_R,
+                    cylinder_omega=omega,
+                )
+            )
+    u0_mean = _SAH_U_MAX / 1.5
+    nu_s = _SAH_U_MAX * _SAH_D / _SAH_RE
+    for coll in ("SRT", "MRT"):
+        wid = f"{coll.lower()}_channel_stab"
+        specs.append(
+            RunSpec(
+                scenario="sah04_case9",
+                run_id=wid,
+                label=f"sah04 case9 channel_stab {coll}",
+                nx=_SAH_NX,
+                ny=_SAH_NY,
+                collision=coll,
+                inlet_scheme="channel_stabilized",
+                inlet_profile="parabolic",
+                y_wall_bc="bounce_back",
+                outlet_mode="neq_extrap",
+                velocity=u0_mean,
+                viscosity=nu_s,
+                steps=5000,
+                has_cylinder=True,
+                cylinder_center=(_SAH_CX, _SAH_CY),
+                cylinder_radius=0.5 * _SAH_D,
+                cylinder_omega=0.0,
+            )
+        )
+    return specs
+
+
+def _build_cfg(base: dict, spec: RunSpec) -> dict:
+    cfg = json.loads(json.dumps(base))
+    cfg["grid"]["nx"] = spec.nx
+    cfg["grid"]["ny"] = spec.ny
+    cfg["grid"]["nz"] = 1
+    cfg["physics"]["velocity"] = float(spec.velocity)
+    cfg["physics"]["viscosity"] = float(spec.viscosity)
+    cfg["physics"]["rho"] = 1.0
+    cfg["method"]["collision"] = spec.collision.upper()
+    cfg["method"]["streaming"] = "double_buffer"
+    cfg["method"]["store_precision"] = "FP32"
+    cfg["method"]["les"]["enabled"] = False
+    cfg["method"]["inlet"]["profile"] = spec.inlet_profile
+    cfg["method"]["inlet"]["scheme"] = spec.inlet_scheme
+    cfg["method"]["y_wall_bc"] = spec.y_wall_bc
+    cfg["method"]["outlet"]["mode"] = spec.outlet_mode
+    return cfg
+
+
+def _body_doc(spec: RunSpec) -> dict:
+    if not spec.has_cylinder:
+        return {"objects": []}
+    return {
+        "objects": [
+            {
+                "type": "cylinder",
+                "center": [float(spec.cylinder_center[0]), float(spec.cylinder_center[1])],
+                "radius": float(spec.cylinder_radius),
+                "omega": float(spec.cylinder_omega),
+            }
+        ]
+    }
+
+
+def _save_field_pngs(
+    out_dir: str,
+    prefix: str,
+    *,
+    rho: np.ndarray,
+    ux: np.ndarray,
+    vort: np.ndarray,
+    title: str,
+) -> List[str]:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return []
+
+    os.makedirs(out_dir, exist_ok=True)
+    ny, nx = rho.shape
+    extent = (0, nx - 1, 0, ny - 1)
+    paths: List[str] = []
+
+    def _one(arr: np.ndarray, name: str, cmap: str, sym: bool) -> None:
+        a = np.asarray(arr, dtype=np.float64)
+        fin = a[np.isfinite(a)]
+        if fin.size == 0:
+            vmin, vmax = -1.0, 1.0
+        elif sym:
+            v = float(np.percentile(np.abs(fin), 99.5)) or 1.0
+            vmin, vmax = -v, v
+        else:
+            vmin = float(np.percentile(fin, 0.5))
+            vmax = float(np.percentile(fin, 99.5))
+            if vmax <= vmin:
+                vmax = vmin + 1.0
+        fw = min(18.0, max(8.0, nx / 70.0))
+        fh = min(10.0, max(3.0, ny / 45.0))
+        fig, ax = plt.subplots(figsize=(fw, fh))
+        im = ax.imshow(a, origin="lower", aspect="auto", cmap=cmap, vmin=vmin, vmax=vmax, extent=extent)
+        ax.set_xlabel("x")
+        ax.set_ylabel("y")
+        ax.set_title(f"{title} — {name}")
+        fig.colorbar(im, ax=ax, fraction=0.046, pad=0.04)
+        fig.tight_layout()
+        p = os.path.join(out_dir, f"{prefix}_{name}.png")
+        fig.savefig(p, dpi=150, bbox_inches="tight")
+        plt.close(fig)
+        paths.append(p)
+
+    _one(rho, "rho", "viridis", sym=False)
+    _one(ux, "ux", "RdBu_r", sym=True)
+    _one(vort, "vort", "RdBu_r", sym=True)
+    return paths
+
+
+def _save_line_plots(
+    path: str,
+    *,
+    rho: np.ndarray,
+    ux: np.ndarray,
+    step: int,
+    label: str,
+    y_rows: Sequence[Tuple[int, str]],
+) -> None:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError:
+        return
+
+    ny, nx = rho.shape
+    x = np.arange(nx, dtype=np.float64)
+    fig, axes = plt.subplots(2, 1, figsize=(min(14.0, max(8.0, nx / 55.0)), 7.0), sharex=True)
+    for y_idx, y_lab in y_rows:
+        yi = int(np.clip(y_idx, 0, ny - 1))
+        axes[0].plot(x, ux[yi, :], label=y_lab, linewidth=1.0)
+        axes[1].plot(x, rho[yi, :], label=y_lab, linewidth=1.0)
+    axes[0].set_ylabel("u_x")
+    axes[0].legend(loc="best", fontsize=8)
+    axes[0].grid(True, alpha=0.3)
+    axes[1].set_ylabel("rho")
+    axes[1].set_xlabel("x (lattice)")
+    axes[1].legend(loc="best", fontsize=8)
+    axes[1].grid(True, alpha=0.3)
+    fig.suptitle(f"{label} — ux/rho lines at step {step}")
+    fig.tight_layout()
+    os.makedirs(os.path.dirname(path) or ".", exist_ok=True)
+    fig.savefig(path, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+
+
+def _snapshot_from_sim(sim) -> Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
+    macro = sim.get_macroscopic()
+    rho = np.asarray(macro["rho"], dtype=np.float64)
+    ux = np.asarray(macro["ux"], dtype=np.float64)
+    uy = np.asarray(macro["uy"], dtype=np.float64)
+    vort = vorticity_z(ux, uy)
+    return rho, ux, uy, vort
+
+
+def _is_stable_fields(
+    rho: np.ndarray,
+    ux: np.ndarray,
+    *,
+    rho_lo: float = 0.85,
+    rho_hi: float = 1.25,
+    ux_cap: float = 0.15,
+) -> bool:
+    """Finite fields within a physically plausible band (reject pre-blow-up states)."""
+    if not (np.isfinite(rho).all() and np.isfinite(ux).all()):
+        return False
+    r0 = float(np.min(rho))
+    r1 = float(np.max(rho))
+    umax = float(np.max(np.abs(ux)))
+    return (rho_lo <= r0) and (r1 <= rho_hi) and (umax <= ux_cap)
+
+
+def run_one(spec: RunSpec, base_cfg: dict, out_root: str) -> Dict[str, Any]:
+    sys.path.insert(0, os.path.join(_REPO, "src"))
+    import pycuda.driver as cuda
+    from CelerisLab import Simulation  # noqa: WPS433
+
+    run_dir = os.path.join(out_root, spec.scenario, spec.run_id)
+    field_dir = os.path.join(run_dir, "fields")
+    line_dir = os.path.join(run_dir, "lines")
+    os.makedirs(field_dir, exist_ok=True)
+    os.makedirs(line_dir, exist_ok=True)
+
+    cfg = _build_cfg(base_cfg, spec)
+    tmpd = tempfile.mkdtemp(prefix="inlet_scenario_")
+    lbm_tmp = os.path.join(tmpd, "config_lbm.json")
+    body_tmp = os.path.join(tmpd, "config_body.json")
+    _write_json(lbm_tmp, cfg)
+    _write_json(body_tmp, _body_doc(spec))
+
+    sim = Simulation(lbm_config_path=lbm_tmp, body_config_path=body_tmp)
+    if spec.has_cylinder and spec.cylinder_omega != 0.0:
+        sim.bodies.get(0).state.omega = np.float32(spec.cylinder_omega)
+    sim.initialize()
+
+    stream = cuda.Stream()
+    y_rows = _line_y_indices(spec.ny)
+
+    last_good: Optional[Dict[str, Any]] = None
+    first_bad_step: Optional[int] = None
+    force_bad_step: Optional[int] = None
+
+    print(f"  [{spec.scenario}/{spec.run_id}] {spec.label}  steps={spec.steps}", flush=True)
+
+    for step in range(1, spec.steps + 1):
+        if spec.has_cylinder:
+            sim.bodies.zero_force_segment_async(stream)
+            sim.stepper.step(
+                1,
+                action_gpu=sim.bodies.action_gpu,
+                obs_gpu=sim.bodies.obs_gpu,
+                stream=stream,
+            )
+            if step % 100 == 0 or step == spec.steps:
+                stream.synchronize()
+                sim.bodies.download_obs_full_async(stream)
+                stream.synchronize()
+                fvec = sim.bodies.read_force(0)
+                if not (np.isfinite(fvec[0]) and np.isfinite(fvec[1])):
+                    if force_bad_step is None:
+                        force_bad_step = step
+        else:
+            sim.step(1)
+
+        rho, ux, uy, vort = _snapshot_from_sim(sim)
+        if _is_stable_fields(rho, ux):
+            last_good = {
+                "step": step,
+                "rho": rho.copy(),
+                "ux": ux.copy(),
+                "uy": uy.copy(),
+                "vort": vort.copy(),
+            }
+        elif first_bad_step is None:
+            first_bad_step = step
+
+    sim.close()
+
+    if last_good is None:
+        raise RuntimeError(f"No finite snapshot for {spec.run_id}")
+
+    out_step = int(last_good["step"])
+    rho = last_good["rho"]
+    ux = last_good["ux"]
+    uy = last_good["uy"]
+    vort = last_good["vort"]
+    requested_final = spec.steps
+    used_last_stable = out_step < requested_final
+
+    meta = {
+        "scenario": spec.scenario,
+        "run_id": spec.run_id,
+        "label": spec.label,
+        "nx": spec.nx,
+        "ny": spec.ny,
+        "collision": spec.collision,
+        "inlet_scheme": spec.inlet_scheme,
+        "inlet_profile": spec.inlet_profile,
+        "y_wall_bc": spec.y_wall_bc,
+        "outlet_mode": spec.outlet_mode,
+        "velocity": spec.velocity,
+        "viscosity": spec.viscosity,
+        "requested_steps": requested_final,
+        "output_step": out_step,
+        "used_last_stable": used_last_stable,
+        "first_nonfinite_step": first_bad_step,
+        "first_force_nonfinite_step": force_bad_step,
+        "rho_min": float(np.min(rho)),
+        "rho_max": float(np.max(rho)),
+        "ux_max": float(np.max(np.abs(ux))),
+        "vort_max": float(np.max(np.abs(vort[np.isfinite(vort)]))) if np.isfinite(vort).any() else float("nan"),
+    }
+    _write_json(os.path.join(run_dir, "run_meta.json"), meta)
+
+    stem = f"step_{out_step:06d}"
+    np.savez_compressed(
+        os.path.join(field_dir, "final.npz"),
+        rho=rho.astype(np.float32),
+        ux=ux.astype(np.float32),
+        uy=uy.astype(np.float32),
+        vort=vort.astype(np.float32),
+        step=np.int32(out_step),
+    )
+
+    title = f"{spec.label} (step {out_step}" + (", last stable" if used_last_stable else ", final") + ")"
+    pngs = _save_field_pngs(field_dir, "final", rho=rho, ux=ux, vort=vort, title=title)
+    _save_line_plots(
+        os.path.join(line_dir, "lines_ux_rho.png"),
+        rho=rho,
+        ux=ux,
+        step=out_step,
+        label=spec.label,
+        y_rows=y_rows,
+    )
+    line_payload: Dict[str, Any] = {"x": np.arange(spec.nx, dtype=np.float32), "step": np.int32(out_step)}
+    for y_idx, y_lab in y_rows:
+        yi = int(np.clip(y_idx, 0, spec.ny - 1))
+        line_payload[f"ux_{y_lab}"] = ux[yi, :].astype(np.float32)
+        line_payload[f"rho_{y_lab}"] = rho[yi, :].astype(np.float32)
+    np.savez_compressed(os.path.join(line_dir, "lines.npz"), **line_payload)
+
+    status = "last_stable" if used_last_stable else "final"
+    print(
+        f"    -> {status} step {out_step}  rho=[{meta['rho_min']:.4f},{meta['rho_max']:.4f}]  "
+        f"ux_max={meta['ux_max']:.4f}  force_bad={force_bad_step}",
+        flush=True,
+    )
+    return {**meta, "field_pngs": pngs, "run_dir": run_dir}
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Three-scenario inlet field export (5000 steps)")
+    ap.add_argument(
+        "--scenario",
+        choices=(
+            "empty_channel",
+            "empty_channel_inlet_matrix",
+            "kan99b",
+            "sah04_case9",
+            "all",
+        ),
+        default="all",
+    )
+    ap.add_argument(
+        "--collision",
+        default="",
+        help="Optional filter: SRT or MRT only",
+    )
+    ap.add_argument("--steps", type=int, default=5000)
+    ap.add_argument(
+        "--out-dir",
+        default=os.path.join(_REPO, "tests", "output", "inlet_scenario_fields"),
+    )
+    args = ap.parse_args()
+
+    if not os.path.isfile(_DEFAULT_LBM):
+        print(f"Missing {_DEFAULT_LBM}", file=sys.stderr)
+        return 2
+
+    base = _load_json(_DEFAULT_LBM)
+    if args.scenario == "empty_channel_inlet_matrix":
+        specs = _empty_channel_inlet_matrix_specs()
+    elif args.scenario == "all":
+        specs = _all_specs() + _empty_channel_inlet_matrix_specs()
+    else:
+        specs = _all_specs()
+        if args.scenario != "all":
+            specs = [s for s in specs if s.scenario == args.scenario]
+    if args.collision.strip():
+        coll = args.collision.strip().upper()
+        specs = [s for s in specs if s.collision.upper() == coll]
+    specs = [replace(s, steps=int(args.steps)) for s in specs]
+
+    out_dir = os.path.abspath(args.out_dir)
+    os.makedirs(out_dir, exist_ok=True)
+
+    rows: List[Dict[str, Any]] = []
+    for spec in specs:
+        try:
+            row = run_one(spec, base, out_dir)
+            rows.append(row)
+        except Exception as e:  # noqa: BLE001
+            print(f"  FAILED {spec.scenario}/{spec.run_id}: {e}", flush=True)
+            rows.append(
+                {
+                    "scenario": spec.scenario,
+                    "run_id": spec.run_id,
+                    "label": spec.label,
+                    "error": str(e),
+                }
+            )
+
+    summary_path = os.path.join(out_dir, "summary.csv")
+    if rows:
+        keys: List[str] = []
+        for r in rows:
+            for k in r:
+                if k not in keys and k != "field_pngs":
+                    keys.append(k)
+        with open(summary_path, "w", encoding="utf-8", newline="") as f:
+            w = csv.DictWriter(f, fieldnames=keys, extrasaction="ignore")
+            w.writeheader()
+            w.writerows(rows)
+
+    _write_json(
+        os.path.join(out_dir, "manifest.json"),
+        {"steps": args.steps, "scenario_filter": args.scenario, "runs": [s.run_id for s in specs]},
+    )
+    print(f"Wrote: {summary_path}", flush=True)
+    print(f"Output: {out_dir}", flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tests/run_sah04_st_matrix.py

@@ -46,7 +46,7 @@ from typing import Any, Dict, List, Optional, Sequence, Tuple
 import numpy as np
 import pycuda.driver as cuda
 
-_PKG_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
+_PKG_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 _DEFAULT_LBM = os.path.join(_PKG_ROOT, "src", "CelerisLab", "configs", "config_lbm.json")
 
 # D=30 fixed; Lx_fluid = 80D per Sah04 confined setup