kernels (K10): refinement.cu becomes an include-only entry; patch kernels under step/

refinement.cu keeps its header, includes, the curved_double.cu entry
block, the #error guard and the optional CELERIS_REFINEMENT_AUDIT
counters, then includes step/patch_step.cu, which holds patch_collide,
PatchExplode, PatchFineStep and PatchCoarseStep moved verbatim (checked
against the previous refinement.cu) in the same order.
test_refinement_mrt reads refinement.cu + step/patch_step.cu; its
assertions are unchanged. The audit-build tests include refinement.cu
from the build root, so step/patch_step.cu still resolves.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/CelerisLab/cuda/compiler_v2.py

@@ -54,14 +54,18 @@ def _write(path: str, content: str):
 
 
 def generate_config(cfg: LBMConfig, n_objects: int = 0,
-                    *, build_root: Optional[str] = None) -> str:
+                    *, build_root: Optional[str] = None, block_root_bc: int = 0) -> str:
     """Snapshot kernels and render headers in a fresh private directory.
 
     Returns its path. Pass it explicitly to compile_kernel for interleaved
     builds. Legacy generate_config(); compile_kernel() remains context-local.
     The caller owns cleanup_build_dir() once the loaded module is no longer
     needed for recompilation/debugging. No package files are changed.
+    block_root_bc specializes a blocked root module; fine/dense builds use 0.
     """
+    if (isinstance(block_root_bc, bool) or not isinstance(block_root_bc, int)
+            or block_root_bc not in (0, 1, 2)):
+        raise ValueError("block_root_bc must be an integer mode 0, 1 or 2")
     macros = cfg.to_macros()
     if isinstance(n_objects, bool) or not isinstance(n_objects, int) or n_objects < 0:
         raise ValueError("n_objects must be a nonnegative integer")
@@ -71,14 +75,15 @@ def generate_config(cfg: LBMConfig, n_objects: int = 0,
     try:
         shutil.copytree(_KERNEL_DIR, build_dir, dirs_exist_ok=True,
                         ignore=shutil.ignore_patterns("*.ptx", "*.cubin", "*.tmp"))
-        _render_config(macros, n_objects, os.path.join(build_dir, "config"))
+        _render_config(macros, n_objects, os.path.join(build_dir, "config"),
+                       block_root_bc=block_root_bc)
         digest = hashlib.sha256()
         for path in sorted(Path(build_dir).rglob("*")):
             if path.is_file():
                 digest.update(str(path.relative_to(build_dir)).encode())
                 digest.update(path.read_bytes())
         metadata = {"source_sha256": digest.hexdigest(), "config": asdict(cfg),
-                    "n_objects": n_objects}
+                    "n_objects": n_objects, "block_root_bc": block_root_bc}
         _write(os.path.join(build_dir, ".celeris-build"), json.dumps(metadata, sort_keys=True))
     except BaseException:
         shutil.rmtree(build_dir)
@@ -101,7 +106,7 @@ def cleanup_build_dir(build_dir: Optional[str]) -> None:
         _last_ptx_path.set(None)
 
 
-def _render_config(m: dict, n_objects: int, cdir: str):
+def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0):
     _write(os.path.join(cdir, "config_grid.h"), f"""{_HEADER}\
 // Layer: Global / Grid
 #ifndef CELERIS_CONFIG_GRID_H
@@ -165,6 +170,9 @@ def _render_config(m: dict, n_objects: int, cdir: str):
 #define STORE_PRECISION  {m['STORE_PRECISION']}
 #define USE_DDF_SHIFTING {m['USE_DDF_SHIFTING']}
 
+// Internal blocked root mode: 0=periodic/fine, 1=slot/reservoir, 2=channel.
+#define BLOCK_ROOT_BC {block_root_bc}
+
 #define USE_LES {m['USE_LES']}
 #define LES_CS  {m['LES_CS']}
 #define LES_CLOSED_FORM {m['LES_CLOSED_FORM']}

src/CelerisLab/lbm/kernels/blocks.cu

@@ -1,5 +1,6 @@
 // CelerisLab/lbm/kernels/blocks.cu
-// One periodic level of fixed-size blocks (lbm/blocks.py layout). Separate
+// One fixed-size blocked level (lbm/blocks.py layout), specialized at compile
+// time for periodic/fine, slot/reservoir or channel stepping. Separate
 // compilation entry: NX, NY are the block window including halo, so index_f
 // and linear_index address one block; blockIdx.z selects the block, whose
 // populations start at b*NQ*TOTAL_CELLS (block-contiguous, Q-major inside).
@@ -12,6 +13,7 @@
 #include "core/params.cuh"
 #include "core/flags.cuh"
 #include "core/obs.cuh"
+#include "core/cell_kind.cuh"
 #include "operators/macro.cuh"
 #include "operators/collision_srt.cuh"
 #if COLLISION_MODEL == 2
@@ -19,182 +21,29 @@
 #endif
 #include "streaming/pull_double_buffer.cuh"
 #include "boundary/curved_boundary.cuh"
-#include "boundary/planar_velocity.cuh"
 
 #if DIM != 2 || NQ != 9 || (COLLISION_MODEL != 0 && COLLISION_MODEL != 2) || STORE_PRECISION != 0 || USE_LES || STREAMING_MODEL != 0
 #error "Blocks require FP32 D2Q9 SRT or MRT double buffers without LES"
 #endif
-
-// Fixed-patch cell kinds, matching refinement.py ACTIVE/INNER_GHOST/OUTER_GHOST.
-constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;
-
-// Zero-initialized for ordinary blocks/fine levels. Set only for parent walls;
-// NX/NY remain local storage strides, never physical wall coordinates.
-struct BlockWall { unsigned int nx, ny, slot_width; float amplitude; };
-extern "C" { __constant__ BlockWall d_block_wall; }
-
-// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
-extern "C" __global__ void BlockHaloCopy(
-    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t d = dst[row], s = src[row];
-    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
-}
-
-// Fixed-patch explosion into blocked fine storage: target = owner block cell
-// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
-// storage is the one-window case with coarse_cells = full domain size.
-extern "C" __global__ void BlockExplode(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const uint64_t d = donor[row];
-    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
-}
-
-// Experimental Schornbaum--Ruede (arXiv:1508.07982, Algorithm 2)
-// and Chen et al. (doi:10.1016/j.physa.2005.09.036) population interpolation.
-// Independent implementation of the mathematical stencil; no upstream source copied.
-// Stencil cells are owner cores; a disabled axis repeats its center twice.
-extern "C" __global__ void BlockExplodeProjected(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells,
-    const uint64_t* neighbors, const float* offsets)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row], d = donor[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q) {
-        float v[4];
-        for (unsigned int a = 0; a < 4; ++a) {
-            const uint64_t n = neighbors[4ul * row + a];
-            v[a] = coarse[(n / coarse_cells) * NQ * coarse_cells
-                          + q * coarse_cells + n % coarse_cells];
-        }
-        float gx = .5f * (v[1] - v[0]), gy = .5f * (v[3] - v[2]);
-        const float ex = d_cx[q], ey = d_cy[q];
-        if (q != 0) {
-            const float along = (ex * gx + ey * gy) / (ex * ex + ey * ey);
-            gx -= ex * along;
-            gy -= ey * along;
-        }
-        to[index_f(t % TOTAL_CELLS, q)] =
-            coarse[(d / coarse_cells) * NQ * coarse_cells + q * coarse_cells + d % coarse_cells]
-            + offsets[2ul * row] * gx + offsets[2ul * row + 1] * gy;
-    }
-}
-
-// Targets are receiver-local SOURCE slots for the immediately following pull.
-// Keep child summation order identical to PatchCoarseStep; no collision here.
-extern "C" __global__ void BlockCoalesce(
-    const fpxx* fine, fpxx* coarse, const uint64_t* target, const uint64_t* children,
-    unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t* s = children + 4ul * row;
-    coarse[target[row]] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
-}
-
-// Static cut links, receiver-local staging: cell is the receiver's local core
-// cell, so the existing BFL writes the solid-source window image that this
-// block's next pull reads (no halo copy between this kernel and BlockStep).
-// surface_velocity (nullable, 2 floats per link): prescribed fluid velocity on
-// fixed geometry, same convention as CurvedBoundaryKernel. Optional raw rows
-// (jx,jy,torque,dm) are unique physical links, never body-observation slots.
-extern "C" __global__ void BlockCurvedBoundary(
-    fpxx* f, const uint32_t* block, const uint32_t* cell, const unsigned char* dir,
-    const float* q, const unsigned char* fallback, unsigned int count,
-    const float* surface_velocity, const float* rx, const float* ry, float* raw)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    float Uw = 0.0f, Vw = 0.0f;
-    if (surface_velocity != nullptr) {
-        const float u = surface_velocity[2 * row], v = surface_velocity[2 * row + 1];
-        if (u != 0.0f || v != 0.0f) { Uw = u; Vw = v; }
-    }
-    apply_bouzidi_link(dir[row], q[row], cell[row], f + (unsigned long)block[row] * NQ * TOTAL_CELLS,
-                       Uw, Vw, rx ? rx[row] : 0.0f, ry ? ry[row] : 0.0f,
-                       fallback[row], nullptr, -1, raw ? raw + 4ul * row : nullptr,
-                       raw ? raw + 4ul * row + 3 : nullptr);
-}
-
-// Same-stream BFL -> this row-owned accumulation -> pull step. No atomics,
-// no cross-row reduction and no history allocation proportional to substeps.
-extern "C" __global__ void BlockAccumulateExchange(
-    const float* raw, double* integral, unsigned int count, double h, double dt)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const unsigned long k = 4ul * row;
-    const double impulse = h * dt;
-    integral[k] += impulse * (double)raw[k];
-    integral[k + 1] += impulse * (double)raw[k + 1];
-    integral[k + 2] += h * impulse * (double)raw[k + 2];
-    integral[k + 3] += h * h * (double)raw[k + 3];
-}
-
-// Pull/collide/store core cells only; halo cells of out are left untouched.
-// flags (block cell ids, nullable): solid cores store NaN and never collide.
-// kind (block cell ids, nullable = all ACTIVE): OUTER skips the pull and
-// stores NaN, INNER pulls without collision, ACTIVE pulls and collides.
-extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int halo,
-                                     const uint16_t* flags, const unsigned char* kind) {
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
-    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
-    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
-    const unsigned char cell_kind = kind != nullptr ? kind[cell] : KIND_ACTIVE;
-    float f[NQ];
-    if (cell_kind == KIND_OUTER || (flags != nullptr && is_solid(flags[cell]))) {
-        for (int q = 0; q < NQ; ++q) f[q] = NAN;
-    } else {
-        unsigned long j[NQ];
-        compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.
-        stream_pull_load(k, f, in + base, j);
-        if (cell_kind == KIND_ACTIVE) {
-            if (d_block_wall.nx != 0) {
-                unsigned int gx, gy;
-                block_global_xy(x, y, halo, d_block_wall.nx, gx, gy);
-                if (gy == 1)
-                    reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(
-                        gx, d_block_wall.nx, d_block_wall.slot_width, d_block_wall.amplitude));
-                else if (gy == d_block_wall.ny - 2) reconstruct_top_reservoir(f, RHO);
-            }
-#if COLLISION_MODEL == 2
-            collide_mrt_unforced(f);  // SRT path below unchanged.
-#else
-            float rho, ux, uy, feq[NQ];
-            compute_rho_u(f, rho, ux, uy);
-#if USE_DDF_SHIFTING
-            // Preserve the density perturbation before adding the unit reference.
-            const float drho = f[0]+f[1]+f[2]+f[3]+f[4]+f[5]+f[6]+f[7]+f[8];
-            const float jx = f[1]-f[2]+f[5]-f[6]+f[7]-f[8];
-            const float jy = f[3]-f[4]+f[5]-f[6]-f[7]+f[8];
-            compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);
-#else
-            compute_feq(rho, ux, uy, feq);
+#ifndef BLOCK_ROOT_BC
+#error "Blocks require a generated BLOCK_ROOT_BC mode"
+#elif BLOCK_ROOT_BC < 0 || BLOCK_ROOT_BC > 2
+#error "BLOCK_ROOT_BC must be 0, 1 or 2"
 #endif
-            collide_srt_no_force(f, feq, d_params.omega);
-#endif
-        }
-    }
-    stream_pull_store(k, f, out + base);
-}
 
-// Root channel closure; fine and periodic levels keep BlockStep.
+#if BLOCK_ROOT_BC == 1
+#include "boundary/block_wall.cuh"
+#endif
+#if BLOCK_ROOT_BC != 2
+#include "operators/block_collision.cuh"
+#endif
+
+// Kernels, in definition order: transfers, boundary staging, then the one full
+// step selected for this module (BlockStep, or BlockChannelStep for a channel root).
+#include "step/block_transfer.cu"
+#include "step/block_boundary.cu"
+#if BLOCK_ROOT_BC != 2
+#include "step/block_step.cu"
+#else
 #include "step/block_channel.cu"
+#endif

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

@@ -0,0 +1,20 @@
+// Physical parent walls; NX/NY remain local storage strides.
+#ifndef CELERIS_BOUNDARY_BLOCK_WALL_CUH
+#define CELERIS_BOUNDARY_BLOCK_WALL_CUH
+
+#include "planar_velocity.cuh"
+
+struct BlockWall { unsigned int nx, ny, slot_width; float amplitude; };
+extern "C" { __constant__ BlockWall d_block_wall; }
+
+__device__ __forceinline__ void block_wall(float* f, unsigned int x, unsigned int y,
+                                         unsigned int halo) {
+    unsigned int gx, gy;
+    block_global_xy(x, y, halo, d_block_wall.nx, gx, gy);
+    if (gy == 1)
+        reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(
+            gx, d_block_wall.nx, d_block_wall.slot_width, d_block_wall.amplitude));
+    else if (gy == d_block_wall.ny - 2) reconstruct_top_reservoir(f, RHO);
+}
+
+#endif

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

@@ -15,10 +15,13 @@
 // D2Q9 y-wall half-way bounce-back for pull double-buffer streaming.
 // ---------------------------------------------------------------------------
 #if LATTICE_MODEL == LATTICE_D2Q9
-__device__ inline void apply_wall_bb_d2q9_y_pull(unsigned int y,
-                                                  float* __restrict__ f,
-                                                  const fpxx* __restrict__ fi_in,
-                                                  unsigned long k)
+// Rows 1 and top_row (= physical ny - 2) next to walls at rows 0 and ny - 1.
+// y is the physical row; k addresses the node in fi_in (a block window may
+// have NX/NY strides different from the physical extent).
+__device__ inline void apply_wall_bb_d2q9_rows(unsigned int y, unsigned int top_row,
+                                               float* __restrict__ f,
+                                               const fpxx* __restrict__ fi_in,
+                                               unsigned long k)
 {
     if (y == 1) {
         // Directions sourced from y=0 wall in pull step: +y, +x+y, -x+y.
@@ -26,14 +29,22 @@ __device__ inline void apply_wall_bb_d2q9_y_pull(unsigned int y,
         f[5] = load_ddf(fi_in, index_f(k, 6u));
         f[8] = load_ddf(fi_in, index_f(k, 7u));
     }
-    else if (y == (unsigned int)(NY - 2)) {
-        // Directions sourced from y=NY-1 wall in pull step: -y, -x-y, +x-y.
+    else if (y == top_row) {
+        // Directions sourced from the y = ny - 1 wall in pull step: -y, -x-y, +x-y.
         f[4] = load_ddf(fi_in, index_f(k, 3u));
         f[6] = load_ddf(fi_in, index_f(k, 5u));
         f[7] = load_ddf(fi_in, index_f(k, 8u));
     }
 }
 
+__device__ inline void apply_wall_bb_d2q9_y_pull(unsigned int y,
+                                                  float* __restrict__ f,
+                                                  const fpxx* __restrict__ fi_in,
+                                                  unsigned long k)
+{
+    apply_wall_bb_d2q9_rows(y, (unsigned int)(NY - 2), f, fi_in, k);
+}
+
 // ---------------------------------------------------------------------------
 // D2Q9 y-wall free-slip (specular reflection) for pull double-buffer streaming.
 //

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

@@ -8,6 +8,9 @@
 #define STORE_PRECISION  0
 #define USE_DDF_SHIFTING 0
 
+// Internal blocked root mode: 0=periodic/fine, 1=slot/reservoir, 2=channel.
+#define BLOCK_ROOT_BC 0
+
 #define USE_LES 0
 #define LES_CS  0.160000f
 #define LES_CLOSED_FORM 1

src/CelerisLab/lbm/kernels/core/cell_kind.cuh

@@ -0,0 +1,16 @@
+// CelerisLab – core/cell_kind.cuh
+// Fixed-patch cell kinds stored per block cell, matching lbm/refinement.py
+// ACTIVE/INNER_GHOST/OUTER_GHOST: OUTER is invalid (stores NaN, no pull),
+// INNER streams without collision, ACTIVE pulls and collides.
+#ifndef CELERIS_CORE_CELL_KIND_CUH
+#define CELERIS_CORE_CELL_KIND_CUH
+
+constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;
+
+// NaN populations mark a cell without valid state (OUTER ghost or solid core).
+__device__ __forceinline__ void fill_invalid(float* f)
+{
+    for (int q = 0; q < NQ; ++q) f[q] = NAN;
+}
+
+#endif

src/CelerisLab/lbm/kernels/operators/block_collision.cuh

@@ -0,0 +1,31 @@
+// Collision used by periodic/fine and slot/reservoir BlockStep.
+#ifndef CELERIS_OPERATORS_BLOCK_COLLISION_CUH
+#define CELERIS_OPERATORS_BLOCK_COLLISION_CUH
+
+#include "../core/params.cuh"
+#include "macro.cuh"
+#include "collision_srt.cuh"
+#if COLLISION_MODEL == 2
+#include "collision_mrt.cuh"
+#endif
+
+__device__ __forceinline__ void block_collide(float* f) {
+#if COLLISION_MODEL == 2
+    collide_mrt_unforced(f);  // SRT path below unchanged.
+#else
+    float rho, ux, uy, feq[NQ];
+    compute_rho_u(f, rho, ux, uy);
+#if USE_DDF_SHIFTING
+    // Preserve the density perturbation before adding the unit reference.
+    const float drho = f[0]+f[1]+f[2]+f[3]+f[4]+f[5]+f[6]+f[7]+f[8];
+    const float jx = f[1]-f[2]+f[5]-f[6]+f[7]-f[8];
+    const float jy = f[3]-f[4]+f[5]-f[6]-f[7]+f[8];
+    compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);
+#else
+    compute_feq(rho, ux, uy, feq);
+#endif
+    collide_srt_no_force(f, feq, d_params.omega);
+#endif
+}
+
+#endif

src/CelerisLab/lbm/kernels/operators/bounce_back_swap.cuh

@@ -0,0 +1,14 @@
+// CelerisLab – operators/bounce_back_swap.cuh
+// Full-way bounce-back at a wall node: swap every opposite pair (paired
+// order q, q+1). Needs only NQ; shared by the uniform and blocked steps.
+#ifndef CELERIS_OPERATORS_BOUNCE_BACK_SWAP_CUH
+#define CELERIS_OPERATORS_BOUNCE_BACK_SWAP_CUH
+
+__device__ __forceinline__ void bounce_back_swap(float* f) {
+    #pragma unroll
+    for (int i = 1; i < NQ; i += 2) {
+        float t = f[i]; f[i] = f[i+1]; f[i+1] = t;
+    }
+}
+
+#endif

src/CelerisLab/lbm/kernels/operators/helpers.cuh

@@ -5,12 +5,7 @@
 #ifndef CELERIS_OPERATORS_HELPERS_CUH
 #define CELERIS_OPERATORS_HELPERS_CUH
 
-__device__ __forceinline__ void bounce_back_swap(float* f) {
-    #pragma unroll
-    for (int i = 1; i < NQ; i += 2) {
-        float t = f[i]; f[i] = f[i+1]; f[i+1] = t;
-    }
-}
+#include "bounce_back_swap.cuh"
 
 __device__ __forceinline__ void collide_dispatch(
     float* f, float rho_n,

src/CelerisLab/lbm/kernels/refinement.cu

@@ -9,6 +9,7 @@
 #include "core/params.cuh"
 #include "core/flags.cuh"
 #include "core/obs.cuh"
+#include "core/cell_kind.cuh"
 #include "operators/macro.cuh"
 #include "operators/collision_srt.cuh"
 #if COLLISION_MODEL == 2
@@ -35,93 +36,5 @@ __device__ unsigned int incoming_counts[NQ * TOTAL_CELLS];
 }
 #endif
 
-__device__ __forceinline__ void patch_collide(float* f, unsigned long k) {
-#if COLLISION_MODEL == 2
-    collide_mrt_unforced(f);
-#else
-    float rho, ux, uy, feq[NQ];
-    compute_rho_u(f, rho, ux, uy);
-    compute_feq(rho, ux, uy, feq);
-    collide_srt_no_force(f, feq, d_params.omega);
-#endif
-#ifdef CELERIS_REFINEMENT_AUDIT
-    ++collision_counts[k];
-#endif
-}
-
-extern "C" __global__ void PatchExplode(
-    const float* coarse, float* fine, const uint32_t* targets,
-    const uint32_t* donors, unsigned int count, unsigned long coarse_cells)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    for (unsigned int q = 0; q < NQ; ++q)
-        fine[index_f(targets[row], q)] = coarse[q * coarse_cells + donors[row]];
-#ifdef CELERIS_REFINEMENT_AUDIT
-    ++explosion_counts[targets[row]];
-#endif
-}
-
-extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint16_t* flags) {
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x >= NX || y >= NY) return;
-    float f[NQ];
-    // Outer halo is invalid after EACH hop, including when reusing the buffer
-    // that held explosion data. Inner halo only streams; it never collides.
-    if (x < 2 || y < 2 || x >= NX - 2 || y >= NY - 2
-            || (flags != nullptr && is_solid(flags[k]))) {
-        for (int q = 0; q < NQ; ++q) f[q] = NAN;
-    } else {
-        unsigned long j[NQ];
-        compute_neighbors(x, y, j);  // These interior targets never wrap.
-        stream_pull_load(k, f, in, j);
-        if (x >= 4 && y >= 4 && x < NX - 4 && y < NY - 4)
-            patch_collide(f, k);
-    }
-    stream_pull_store(k, f, out);
-}
-
-extern "C" __global__ void PatchCoarseStep(
-    const float* in, float* out, const float* fine,
-    const uint64_t* targets, const uint64_t* children, unsigned int count,
-    unsigned int x0, unsigned int y0, unsigned int x1, unsigned int y1,
-    unsigned int wall_aware)
-{
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x >= NX || y >= NY) return;
-    // Both buffers were poisoned at initialization; covered cells stay invalid.
-    if (x >= x0 && x < x1 && y >= y0 && y < y1) return;
-    if (wall_aware && (y == 0 || y == NY - 1)) return;
-    unsigned long j[NQ];
-    compute_neighbors(x, y, j);
-    float f[NQ];
-    stream_pull_load(k, f, in, j);
-    if (x >= x0 - 1 && x <= x1 && y >= y0 - 1 && y <= y1) {
-        for (unsigned int q = 1; q < NQ; ++q) {
-            uint64_t slot = index_f(k, q);
-            unsigned int lo = 0, hi = count;
-            while (lo < hi) {
-                unsigned int mid = lo + (hi - lo) / 2;
-                if (targets[mid] < slot) lo = mid + 1;
-                else hi = mid;
-            }
-            if (lo < count && targets[lo] == slot) {
-                const uint64_t* s = children + 4ul * lo;
-                f[q] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
-#ifdef CELERIS_REFINEMENT_AUDIT
-                ++incoming_counts[slot];
-#endif
-            }
-        }
-    }
-    // Includes the eight grazing-corner links with UNCOVERED coarse donors.
-    // All replacement arrivals must be in place before computing rho/u.
-    if (wall_aware) {
-        if (y == 1) reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(x));
-        else if (y == NY - 2) reconstruct_top_reservoir(f, RHO);
-    }
-    patch_collide(f, k);
-    stream_pull_store(k, f, out);
-}
+// Kernels: patch collision helper, PatchExplode, PatchFineStep, PatchCoarseStep.
+#include "step/patch_step.cu"

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

@@ -0,0 +1,42 @@
+// CelerisLab/lbm/kernels/step/block_boundary.cu
+// Receiver-local curved-boundary staging and its raw-exchange accumulation.
+// Part of the blocks.cu compilation entry; relies on its includes and guards.
+
+// Static cut links, receiver-local staging: cell is the receiver's local core
+// cell, so the existing BFL writes the solid-source window image that this
+// block's next pull reads (no halo copy between this kernel and BlockStep).
+// surface_velocity (nullable, 2 floats per link): prescribed fluid velocity on
+// fixed geometry, same convention as CurvedBoundaryKernel. Optional raw rows
+// (jx,jy,torque,dm) are unique physical links, never body-observation slots.
+extern "C" __global__ void BlockCurvedBoundary(
+    fpxx* f, const uint32_t* block, const uint32_t* cell, const unsigned char* dir,
+    const float* q, const unsigned char* fallback, unsigned int count,
+    const float* surface_velocity, const float* rx, const float* ry, float* raw)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    float Uw = 0.0f, Vw = 0.0f;
+    if (surface_velocity != nullptr) {
+        const float u = surface_velocity[2 * row], v = surface_velocity[2 * row + 1];
+        if (u != 0.0f || v != 0.0f) { Uw = u; Vw = v; }
+    }
+    apply_bouzidi_link(dir[row], q[row], cell[row], f + (unsigned long)block[row] * NQ * TOTAL_CELLS,
+                       Uw, Vw, rx ? rx[row] : 0.0f, ry ? ry[row] : 0.0f,
+                       fallback[row], nullptr, -1, raw ? raw + 4ul * row : nullptr,
+                       raw ? raw + 4ul * row + 3 : nullptr);
+}
+
+// Same-stream BFL -> this row-owned accumulation -> pull step. No atomics,
+// no cross-row reduction and no history allocation proportional to substeps.
+extern "C" __global__ void BlockAccumulateExchange(
+    const float* raw, double* integral, unsigned int count, double h, double dt)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const unsigned long k = 4ul * row;
+    const double impulse = h * dt;
+    integral[k] += impulse * (double)raw[k];
+    integral[k + 1] += impulse * (double)raw[k + 1];
+    integral[k + 2] += h * impulse * (double)raw[k + 2];
+    integral[k + 3] += h * h * (double)raw[k + 3];
+}

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

@@ -1,5 +1,12 @@
+#if BLOCK_ROOT_BC != 2
+#error "BlockChannelStep requires BLOCK_ROOT_BC == 2"
+#endif
+
 // Root-only blocked counterpart of OneStep's D2Q9/SRT channel closure.
 // NX/NY are LOCAL strides; all physical boundary decisions use global coordinates.
+#include "../core/cell_kind.cuh"
+#include "../operators/bounce_back_swap.cuh"
+#include "../boundary/bounce_back.cuh"
 #include "../boundary/inlet/common.cuh"
 #include "../boundary/inlet/zou_he_local.cuh"
 #include "../boundary/outlet/pressure_neq.cuh"
@@ -21,7 +28,7 @@ extern "C" __global__ void BlockChannelStep(
     const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
     float f[NQ];
     if (kind != nullptr && kind[cell] == KIND_OUTER) {
-        for (int q = 0; q < NQ; ++q) f[q] = NAN;
+        fill_invalid(f);
     } else {
         unsigned long j[NQ];
         compute_neighbors(x, y, j);
@@ -29,27 +36,17 @@ extern "C" __global__ void BlockChannelStep(
         const bool wall = gy == 0 || gy == d_block_channel.ny - 1;
         const bool outlet = gx == d_block_channel.nx - 1;
         if (wall) {
-            // Wall owns all four corners. Ghosts pull and swap, never collide.
-            for (int q = 1; q < NQ; q += 2) {
-                const float t = f[q]; f[q] = f[q + 1]; f[q + 1] = t;
-            }
+            bounce_back_swap(f);  // Wall owns all four corners; ghosts never collide.
         } else if (gx == 0) {
             apply_zou_he_left_velocity_inlet_d2q9(
                 f, inlet_target_u((float)gy, d_block_channel.ny, d_block_channel.velocity), 0.0f);
         } else if (outlet) {
             // Immutable input donor, receiver-local (also valid across a block seam).
             float donor[NQ];
-            for (int q = 0; q < NQ; ++q)
-                donor[q] = load_ddf(in + base, index_f(k - 1, q));
+            load_node(in + base, k - 1, donor);
             apply_pressure_outlet_d2q9(f, donor);
-        } else if (gy == 1) {
-            f[3] = load_ddf(in + base, index_f(k, 4));
-            f[5] = load_ddf(in + base, index_f(k, 6));
-            f[8] = load_ddf(in + base, index_f(k, 7));
-        } else if (gy == d_block_channel.ny - 2) {
-            f[4] = load_ddf(in + base, index_f(k, 3));
-            f[6] = load_ddf(in + base, index_f(k, 5));
-            f[7] = load_ddf(in + base, index_f(k, 8));
+        } else {
+            apply_wall_bb_d2q9_rows(gy, d_block_channel.ny - 2, f, in + base, k);
         }
         if (!wall && !outlet) {
 #if COLLISION_MODEL == 2

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

@@ -0,0 +1,35 @@
+// CelerisLab/lbm/kernels/step/block_step.cu
+// Generic blocked pull/collide/store for periodic/fine and slot/reservoir levels.
+// Part of the blocks.cu compilation entry; relies on its includes and guards.
+#if BLOCK_ROOT_BC == 2
+#error "BlockStep is not built for the channel root (BLOCK_ROOT_BC == 2)"
+#endif
+
+// Pull/collide/store core cells only; halo cells of out are left untouched.
+// flags (block cell ids, nullable): solid cores store NaN and never collide.
+// kind (block cell ids, nullable = all ACTIVE): OUTER skips the pull and
+// stores NaN, INNER pulls without collision, ACTIVE pulls and collides.
+extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int halo,
+                                     const uint16_t* flags, const unsigned char* kind) {
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
+    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
+    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
+    const unsigned char cell_kind = kind != nullptr ? kind[cell] : KIND_ACTIVE;
+    float f[NQ];
+    if (cell_kind == KIND_OUTER || (flags != nullptr && is_solid(flags[cell]))) {
+        fill_invalid(f);
+    } else {
+        unsigned long j[NQ];
+        compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.
+        stream_pull_load(k, f, in + base, j);
+        if (cell_kind == KIND_ACTIVE) {
+#if BLOCK_ROOT_BC == 1
+            block_wall(f, x, y, halo);
+#endif
+            block_collide(f);
+        }
+    }
+    stream_pull_store(k, f, out + base);
+}

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

@@ -0,0 +1,78 @@
+// CelerisLab/lbm/kernels/step/block_transfer.cu
+// Same-level halo refresh and 2:1 explosion/coalescence between blocked levels.
+// Part of the blocks.cu compilation entry; relies on its includes and guards.
+
+// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
+extern "C" __global__ void BlockHaloCopy(
+    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t d = dst[row], s = src[row];
+    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
+}
+
+// Fixed-patch explosion into blocked fine storage: target = owner block cell
+// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
+// storage is the one-window case with coarse_cells = full domain size.
+extern "C" __global__ void BlockExplode(
+    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
+    unsigned int count, unsigned long coarse_cells)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t t = target[row];
+    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const uint64_t d = donor[row];
+    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
+}
+
+// Experimental Schornbaum--Ruede (arXiv:1508.07982, Algorithm 2)
+// and Chen et al. (doi:10.1016/j.physa.2005.09.036) population interpolation.
+// Independent implementation of the mathematical stencil; no upstream source copied.
+// Stencil cells are owner cores; a disabled axis repeats its center twice.
+extern "C" __global__ void BlockExplodeProjected(
+    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
+    unsigned int count, unsigned long coarse_cells,
+    const uint64_t* neighbors, const float* offsets)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t t = target[row], d = donor[row];
+    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    for (unsigned int q = 0; q < NQ; ++q) {
+        float v[4];
+        for (unsigned int a = 0; a < 4; ++a) {
+            const uint64_t n = neighbors[4ul * row + a];
+            v[a] = coarse[(n / coarse_cells) * NQ * coarse_cells
+                          + q * coarse_cells + n % coarse_cells];
+        }
+        float gx = .5f * (v[1] - v[0]), gy = .5f * (v[3] - v[2]);
+        const float ex = d_cx[q], ey = d_cy[q];
+        if (q != 0) {
+            const float along = (ex * gx + ey * gy) / (ex * ex + ey * ey);
+            gx -= ex * along;
+            gy -= ey * along;
+        }
+        to[index_f(t % TOTAL_CELLS, q)] =
+            coarse[(d / coarse_cells) * NQ * coarse_cells + q * coarse_cells + d % coarse_cells]
+            + offsets[2ul * row] * gx + offsets[2ul * row + 1] * gy;
+    }
+}
+
+// Targets are receiver-local SOURCE slots for the immediately following pull.
+// Keep child summation order identical to PatchCoarseStep; no collision here.
+extern "C" __global__ void BlockCoalesce(
+    const fpxx* fine, fpxx* coarse, const uint64_t* target, const uint64_t* children,
+    unsigned int count)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t* s = children + 4ul * row;
+    coarse[target[row]] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
+}

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

@@ -0,0 +1,95 @@
+// CelerisLab/lbm/kernels/step/patch_step.cu
+// Dense fixed-patch collision, explosion and the fine/coarse steps.
+// Part of the refinement.cu compilation entry; relies on its includes, guards
+// and the optional CELERIS_REFINEMENT_AUDIT counters declared there.
+
+__device__ __forceinline__ void patch_collide(float* f, unsigned long k) {
+#if COLLISION_MODEL == 2
+    collide_mrt_unforced(f);
+#else
+    float rho, ux, uy, feq[NQ];
+    compute_rho_u(f, rho, ux, uy);
+    compute_feq(rho, ux, uy, feq);
+    collide_srt_no_force(f, feq, d_params.omega);
+#endif
+#ifdef CELERIS_REFINEMENT_AUDIT
+    ++collision_counts[k];
+#endif
+}
+
+extern "C" __global__ void PatchExplode(
+    const float* coarse, float* fine, const uint32_t* targets,
+    const uint32_t* donors, unsigned int count, unsigned long coarse_cells)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    for (unsigned int q = 0; q < NQ; ++q)
+        fine[index_f(targets[row], q)] = coarse[q * coarse_cells + donors[row]];
+#ifdef CELERIS_REFINEMENT_AUDIT
+    ++explosion_counts[targets[row]];
+#endif
+}
+
+extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint16_t* flags) {
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x >= NX || y >= NY) return;
+    float f[NQ];
+    // Outer halo is invalid after EACH hop, including when reusing the buffer
+    // that held explosion data. Inner halo only streams; it never collides.
+    if (x < 2 || y < 2 || x >= NX - 2 || y >= NY - 2
+            || (flags != nullptr && is_solid(flags[k]))) {
+        fill_invalid(f);
+    } else {
+        unsigned long j[NQ];
+        compute_neighbors(x, y, j);  // These interior targets never wrap.
+        stream_pull_load(k, f, in, j);
+        if (x >= 4 && y >= 4 && x < NX - 4 && y < NY - 4)
+            patch_collide(f, k);
+    }
+    stream_pull_store(k, f, out);
+}
+
+extern "C" __global__ void PatchCoarseStep(
+    const float* in, float* out, const float* fine,
+    const uint64_t* targets, const uint64_t* children, unsigned int count,
+    unsigned int x0, unsigned int y0, unsigned int x1, unsigned int y1,
+    unsigned int wall_aware)
+{
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x >= NX || y >= NY) return;
+    // Both buffers were poisoned at initialization; covered cells stay invalid.
+    if (x >= x0 && x < x1 && y >= y0 && y < y1) return;
+    if (wall_aware && (y == 0 || y == NY - 1)) return;
+    unsigned long j[NQ];
+    compute_neighbors(x, y, j);
+    float f[NQ];
+    stream_pull_load(k, f, in, j);
+    if (x >= x0 - 1 && x <= x1 && y >= y0 - 1 && y <= y1) {
+        for (unsigned int q = 1; q < NQ; ++q) {
+            uint64_t slot = index_f(k, q);
+            unsigned int lo = 0, hi = count;
+            while (lo < hi) {
+                unsigned int mid = lo + (hi - lo) / 2;
+                if (targets[mid] < slot) lo = mid + 1;
+                else hi = mid;
+            }
+            if (lo < count && targets[lo] == slot) {
+                const uint64_t* s = children + 4ul * lo;
+                f[q] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
+#ifdef CELERIS_REFINEMENT_AUDIT
+                ++incoming_counts[slot];
+#endif
+            }
+        }
+    }
+    // Includes the eight grazing-corner links with UNCOVERED coarse donors.
+    // All replacement arrivals must be in place before computing rho/u.
+    if (wall_aware) {
+        if (y == 1) reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(x));
+        else if (y == NY - 2) reconstruct_top_reservoir(f, RHO);
+    }
+    patch_collide(f, k);
+    stream_pull_store(k, f, out);
+}

src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh

@@ -21,6 +21,14 @@
 //   i.e. the population traveling in direction i at node n
 //   arrived from the node at n - c_i  = neighbor in direction opp(i)
 // ---------------------------------------------------------------------------
+// load_node: all NQ populations of node n as stored (no streaming).
+__device__ __forceinline__ void load_node(const fpxx* __restrict__ fi, unsigned long n,
+                                          float* __restrict__ f)
+{
+    for (int q = 0; q < NQ; ++q)
+        f[q] = load_ddf(fi, index_f(n, q));
+}
+
 __device__ __forceinline__ void stream_pull_load(unsigned long n,
                                                  float* __restrict__ f,
                                                  const fpxx* __restrict__ fi,

src/CelerisLab/lbm/refinement_stepper.py

@@ -362,7 +362,10 @@ class FixedPatchStepper:
             raise RuntimeError("level omega/tau mismatch")
         host = self._boundary_hosts[index]
         n_objects = len(host.objects) if name == "PatchFineStep" and host is not None else 0
-        build = compiler.generate_config(config, n_objects=n_objects)
+        block_root_bc = 0
+        if index == 0 and layout is not None:
+            block_root_bc = 2 if self._channel else 1 if self._wall_aware else 0
+        build = compiler.generate_config(config, n_objects=n_objects, block_root_bc=block_root_bc)
         try:
             ptx = compiler.compile_kernel(self.ctx.sm_arch, source=source, build_dir=build)
             module = compiler.load_module(ptx)

tests/unit/cpp/channel_root.cpp

@@ -16,6 +16,7 @@
 #define NZ 1
 #define NT 1
 #define COLLISION_MODEL 0
+#define BLOCK_ROOT_BC 2
 #define USE_LES 0
 #define RHO 1.f
 #define U0 .025f
@@ -40,7 +41,7 @@ inline float __fdiv_rn(float a,float b){return a/b;}
 #include "boundary/inlet_outlet.cuh"
 #include "step/one_step_double.cu"
 #else
-constexpr unsigned char KIND_OUTER=2;
+#include "core/cell_kind.cuh"
 #include "step/block_channel.cu"
 #endif
 int main(){

tests/unit/test_build_contracts.py

@@ -83,6 +83,32 @@ assert abs(sum(compute_feq_d2q9(1.,0.,0.)) - 1.) < 1e-6
 
 
 class BuildContracts(unittest.TestCase):
+    def test_block_root_modes_are_rendered_and_recorded(self):
+        with tempfile.TemporaryDirectory() as root:
+            for mode in (0, 1, 2):
+                with self.subTest(mode=mode):
+                    build = compiler.generate_config(LBMConfig(), build_root=root, block_root_bc=mode)
+                    try:
+                        method = Path(build, "config/config_method.h").read_text()
+                        self.assertIn(f"#define BLOCK_ROOT_BC {mode}\n", method)
+                        metadata = json.loads(Path(build, ".celeris-build").read_text())
+                        self.assertEqual(metadata["block_root_bc"], mode)
+                        self.assertNotIn("block_root_bc", metadata["config"])
+                    finally:
+                        compiler.cleanup_build_dir(build)
+            build = compiler.generate_config(LBMConfig(), build_root=root)
+            try:
+                self.assertEqual(json.loads(Path(build, ".celeris-build").read_text())["block_root_bc"], 0)
+            finally:
+                compiler.cleanup_build_dir(build)
+
+    def test_invalid_block_root_mode_fails_before_snapshot(self):
+        for mode in (-1, 3, True, False, 1.0, "1", None):
+            with self.subTest(mode=mode), patch.object(compiler.tempfile, "mkdtemp") as allocate:
+                with self.assertRaisesRegex(ValueError, "block_root_bc"):
+                    compiler.generate_config(LBMConfig(), block_root_bc=mode)
+                allocate.assert_not_called()
+
     @staticmethod
     def fake_compile(command, check):
         source = Path(command[-3])

tests/unit/test_channel_root.py

@@ -97,5 +97,6 @@ def test_evolved_ghost_snapshot_and_physical_download():
         with pytest.raises(ValueError, match="finite"):
             backend.initialize(*arrays)
         assert backend._levels[0].kernel == host.compiler.load_module.return_value.get_function("BlockChannelStep")
+        assert [call.kwargs["block_root_bc"] for call in host.compiler.generate_config.call_args_list] == [2, 0]
     finally:
         backend.close()

tests/unit/test_projected_explosion.py

@@ -162,7 +162,7 @@ class ProjectedKernelTests(unittest.TestCase):
         targets = child.owner.ravel()[p.ghost_fine]
         donors = parent.owner.ravel()[p.ghost_coarse]
         source = (Path(__file__).resolve().parents[2] /
-                  "src/CelerisLab/lbm/kernels/blocks.cu").read_text()
+                  "src/CelerisLab/lbm/kernels/step/block_transfer.cu").read_text()
         kernel = source.split('extern "C" __global__ void BlockExplodeProjected(',1)[1]
         kernel = 'void BlockExplodeProjected(' + kernel.split('// Targets are receiver-local SOURCE slots',1)[0]
         def array(name, values, kind):

tests/unit/test_refinement_mrt.py

@@ -22,13 +22,16 @@ class RefinementMRTHost(unittest.TestCase):
 
     def test_srt_statements_and_guards_preserved(self):
         """MRT is an additive compile-time branch; SRT statements and other guards remain."""
-        blocks = (KERNELS / "blocks.cu").read_text()
+        blocks = (KERNELS / "blocks.cu").read_text() + (KERNELS / "step/block_step.cu").read_text()
         channel = (KERNELS / "step/block_channel.cu").read_text()
-        refinement = (KERNELS / "refinement.cu").read_text()
+        block_collision = (KERNELS / "operators/block_collision.cuh").read_text()
+        self.assertIn('#include "operators/block_collision.cuh"', blocks)
+        self.assertEqual(blocks.count("block_collide(f);"), 1)
+        refinement = (KERNELS / "refinement.cu").read_text() + (KERNELS / "step/patch_step.cu").read_text()
         for text in ("compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);",
                      "compute_feq(rho, ux, uy, feq);",
                      "collide_srt_no_force(f, feq, d_params.omega);"):
-            self.assertIn(text, blocks)
+            self.assertIn(text, block_collision)
         self.assertIn("collide_srt(f, feq, forcing, omega);", channel)
         self.assertIn("collide_srt_no_force(f, feq, d_params.omega);", refinement)
         for source in (blocks, refinement):
@@ -40,10 +43,11 @@ class RefinementMRTHost(unittest.TestCase):
         # One shared unforced MRT body; each blocked/patch path calls it exactly once.
         mrt = (KERNELS / "operators/collision_mrt.cuh").read_text()
         self.assertEqual(mrt.count("void collide_mrt_unforced("), 1)
-        for source in (blocks, channel, refinement):
+        for source in (blocks + "\n" + block_collision, channel, refinement):
             self.assertEqual(source.count("collide_mrt_unforced(f);"), 1)
             self.assertNotIn("collide_mrt_no_force(", source)
             self.assertNotIn("compute_rho_u(f, rho, ux, uy);\n            collide_mrt", source)
+            self.assertNotRegex(source, r"compute_rho_u\(f, rho, ux, uy\);\s*collide_mrt")
 
 
 if __name__ == "__main__": unittest.main()

tests/validation/multigrid/test_channel_root_gpu.py

@@ -27,7 +27,7 @@ def state(ny, nx):
 
 def compile_module(cfg, context, source):
     cfg.validate()
-    build = compiler.generate_config(cfg)
+    build = compiler.generate_config(cfg, block_root_bc=2 if source == "blocks.cu" else 0)
     try:
         module = compiler.load_module(compiler.compile_kernel(context.sm_arch, source=source, build_dir=build))
     finally:

tests/validation/multigrid/test_refinement_blocked_base.py

@@ -223,6 +223,8 @@ class BlockedBaseCPU(unittest.TestCase):
                     self.assertIs(collide[4], coarse.kind)
                 walls = [a for ptr, a in m["uploads"] if isinstance(ptr, str) and ptr == "d_block_wall"]
                 self.assertEqual(len(walls), 1)
+                self.assertEqual([call.kwargs["block_root_bc"] for call in
+                                  compiler.generate_config.call_args_list], [1, 0])
                 width, height, slot, speed = struct.unpack("=IIIf", walls[0])
                 self.assertEqual((width, height, slot), (NX, NY, 8))
                 self.assertAlmostEqual(speed, .001)

tests/validation/taylor_green/test_projected_pairs.py

@@ -249,35 +249,41 @@ class ProjectedPairsTests(unittest.TestCase):
         self.assertFalse(assess(incomplete)["comparisons"][3]["passed"])
 
     def test_pinned_build_sources_match_host_generated_inputs(self):
-        """The pinned fingerprints are what today's compiler generates from the qualified
-        NUMERICAL_REVISION kernels; the current kernels may legitimately differ."""
+        """Check the pinned fingerprints using NUMERICAL_REVISION's renderer and kernels.
+        The imported LBMConfig is unchanged from that revision; this is a host
+        build-input check, not a reconstruction of the historical CUDA toolchain."""
+        import importlib.util
         import tarfile
-        from CelerisLab.cuda import compiler_v2
 
         kernels = "src/CelerisLab/lbm/kernels"
+        renderer = "src/CelerisLab/cuda/compiler_v2.py"
         if subprocess.run(["git", "-C", str(REPO), "cat-file", "-e",
                            f"{NUMERICAL_REVISION}^{{commit}}"], capture_output=True).returncode:
             self.fail(f"{NUMERICAL_REVISION} is not in this clone; the pinned build "
                       "sources cannot be checked")
         archive = subprocess.run(["git", "-C", str(REPO), "archive", "--format=tar",
-                                  NUMERICAL_REVISION, kernels],
+                                  NUMERICAL_REVISION, kernels, renderer],
                                  capture_output=True, check=True).stdout
         with tempfile.TemporaryDirectory() as snapshot:
             with tarfile.open(fileobj=io.BytesIO(archive)) as tar:
                 tar.extractall(snapshot)
-            with patch.object(compiler_v2, "_KERNEL_DIR", str(Path(snapshot) / kernels)):
+            spec = importlib.util.spec_from_file_location(
+                "CelerisLab.cuda._compiler_a135252", Path(snapshot) / renderer)
+            compiler = importlib.util.module_from_spec(spec)
+            spec.loader.exec_module(compiler)
+            with patch.object(compiler, "_KERNEL_DIR", str(Path(snapshot) / kernels)):
                 for size in (128, 256):
                     with self.subTest(size=size):
                         cfg = replace(run_case.config(size, 100), nx=10, ny=10)
                         cfg.validate()
-                        root = compiler_v2.generate_config(cfg)
+                        root = compiler.generate_config(cfg)
                         try:
                             actual = json.loads((Path(root) / ".celeris-build").read_text())
                             expected = build_metadata(size)
                             self.assertEqual(actual, {key: expected[key] for key in
                                                       ("source_sha256", "config", "n_objects")})
                         finally:
-                            compiler_v2.cleanup_build_dir(root)
+                            compiler.cleanup_build_dir(root)
 
     def test_source_preflight_requires_clean_exact_revision_and_tree(self):
         import oracle