kernels (K4): withdraw the address helpers; keep only fill_invalid

Horsea's gates showed block_ddf/block_slot change real PTX in
BlockHaloCopy, BlockExplode and BlockExplodeProjected (6/10 modules;
BlockExplodeProjected 38 -> 40 registers) although the results stayed
exact. The stack's bar is byte-identical PTX for naming-only steps, so
those three kernels return to their K3 expressions, the helpers leave
core/layout.cuh, and test_projected_explosion goes back to its K3 form.
fill_invalid stays (its kernels were byte-identical). K4 vs K3 is now
only the NaN-fill helper.

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

src/CelerisLab/lbm/kernels/blocks.cu

@@ -13,6 +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
@@ -20,6 +21,10 @@
 #endif
 #include "streaming/pull_double_buffer.cuh"
 #include "boundary/curved_boundary.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
 #ifndef BLOCK_ROOT_BC
 #error "Blocks require a generated BLOCK_ROOT_BC mode"
 #elif BLOCK_ROOT_BC < 0 || BLOCK_ROOT_BC > 2
@@ -33,13 +38,6 @@
 #include "operators/block_collision.cuh"
 #endif
 
-#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;
-
 // 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)
@@ -169,7 +167,7 @@ extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int hal
     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;
+        fill_invalid(f);
     } else {
         unsigned long j[NQ];
         compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.

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

@@ -2,6 +2,13 @@
 #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.

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
@@ -71,7 +72,7 @@ extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint
     // 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;
+        fill_invalid(f);
     } else {
         unsigned long j[NQ];
         compute_neighbors(x, y, j);  // These interior targets never wrap.

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

@@ -4,6 +4,7 @@
 
 // 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 "../boundary/inlet/common.cuh"
 #include "../boundary/inlet/zou_he_local.cuh"
 #include "../boundary/outlet/pressure_neq.cuh"
@@ -25,7 +26,7 @@ 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);

tests/unit/cpp/channel_root.cpp

@@ -41,7 +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(){