feat: opt-in MRT collision for blocked/refined stepping

Additive compile-time COLLISION_MODEL == 2 branches in BlockStep,
BlockChannelStep and patch_collide repeat the uniform collide_dispatch
MRT sequence (zero forcing, omega clamp, collide_mrt_no_force). SRT
statements, including the shifted retained-delta/direct-momentum path,
are unchanged under the alternate branch. Guards accept SRT or MRT only;
TRT, LES, non-FP32, non-double-buffer and shifted dense/mixed refinement
stay rejected. Transfers, subcycling, BFL, raw ledgers, channel closures,
shifted-Jet SRT guard and PeriodicBlockStepper are untouched. Existing
MRT operator, shifted representation and fixed kinetic rates are reused.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ClaudeandClaude Opus 5.5 committed 2026-10-18 10:26:55 +00:00
1 parent 9805383f9c
commit 00d7a54829
8 files changed
+168 -10

No files matched your search

+12 -2
View File
@@ -11,6 +11,9 @@
#include "core/obs.cuh"
#include "operators/macro.cuh"
#include "operators/collision_srt.cuh"
#if COLLISION_MODEL == 2
#include "operators/collision_mrt.cuh"
#endif
#include "streaming/pull_double_buffer.cuh"
#include "boundary/planar_velocity.cuh"
#include "boundary/curved_boundary.cuh"
@@ -19,8 +22,8 @@ extern "C" {
#include "step/curved_double.cu"
}
#if DIM != 2 || NQ != 9 || COLLISION_MODEL != 0 || STORE_PRECISION != 0 || USE_DDF_SHIFTING || USE_LES || STREAMING_MODEL != 0
#error "Refinement requires unshifted FP32 D2Q9 SRT double buffers without LES"
#if DIM != 2 || NQ != 9 || (COLLISION_MODEL != 0 && COLLISION_MODEL != 2) || STORE_PRECISION != 0 || USE_DDF_SHIFTING || USE_LES || STREAMING_MODEL != 0
#error "Refinement requires unshifted FP32 D2Q9 SRT or MRT double buffers without LES"
#endif
// Enabled only in the validation build; no diagnostic arrays in normal builds.
@@ -33,10 +36,17 @@ __device__ unsigned int incoming_counts[NQ * TOTAL_CELLS];
#endif
__device__ __forceinline__ void patch_collide(float* f, unsigned long k) {
#if COLLISION_MODEL == 2
float rho, ux, uy;
compute_rho_u(f, rho, ux, uy);
collide_mrt_no_force(f, rho, ux, uy,
fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega)));
#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