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/lbm/kernels/blocks.cu

@@ -38,153 +38,12 @@
 #include "operators/block_collision.cuh"
 #endif
 
-// 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];
-}
-
+// 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
-// 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);
-}
-
-#endif
-
-// Root channel is a replacement full step, selected once by the host.
-#if BLOCK_ROOT_BC == 2
+#include "step/block_step.cu"
+#else
 #include "step/block_channel.cu"
 #endif

src/CelerisLab/lbm/kernels/refinement.cu

@@ -36,93 +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]))) {
-        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);
-}
+// 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_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);
+}

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

@@ -22,12 +22,12 @@ 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()
         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()
+        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);"):