Frank14f/CelerisLab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

kernels: shared block-window to global coordinate helper

Browse Source 
BlockStep (slot-reservoir wall rows) and BlockChannelStep computed the
global cell of a block-window cell with the same four lines.
block_global_xy (core/layout.cuh, 2D, __forceinline__) now holds them;
both kernels call it with their own domain width. Same integer
operations: no numerical, ABI or scheduling change. The slot-reservoir
kernel layout is unchanged (no split).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Claude
2026-10-21 01:24:27 +00:00
co-authored by Claude Opus 5.5
parent 781333407e
commit 1fa498c7d7
3 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/CelerisLab/lbm/kernels/blocks.cu
+2 -4
View File
@@ -168,10 +168,8 @@ extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int hal
stream_pull_load(k, f, in + base, j);
if (cell_kind == KIND_ACTIVE) {
if (d_block_wall.nx != 0) {
const unsigned int bx = NX - 2 * halo, by = NY - 2 * halo;
const unsigned int nbx = d_block_wall.nx / bx;
const unsigned int gx = (blockIdx.z % nbx) * bx + x - halo;
const unsigned int gy = (blockIdx.z / nbx) * by + y - 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));
src/CelerisLab/lbm/kernels/core/layout.cuh
+12
View File
@@ -53,6 +53,18 @@ __device__ __forceinline__ void index_from_thread(unsigned int& x,
k = (unsigned long)y * NX + x;
}
// Global cell of window cell (x, y) in block blockIdx.z of a row-major,
// full-domain block layout domain_nx cells wide. NX/NY are the local strides.
__device__ __forceinline__ void block_global_xy(unsigned int x, unsigned int y,
unsigned int halo, unsigned int domain_nx,
unsigned int& gx, unsigned int& gy)
{
const unsigned int bx = NX - 2 * halo, by = NY - 2 * halo;
const unsigned int nbx = domain_nx / bx;
gx = (blockIdx.z % nbx) * bx + x - halo;
gy = (blockIdx.z / nbx) * by + y - halo;
}
// ---------------------------------------------------------------------------
// Neighbor list (periodic BCs via modular arithmetic)
// ---------------------------------------------------------------------------
src/CelerisLab/lbm/kernels/step/block_channel.cu
+2 -4
View File
@@ -15,10 +15,8 @@ extern "C" __global__ void BlockChannelStep(
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 int bx = NX - 2 * halo, by = NY - 2 * halo;
const unsigned int nbx = d_block_channel.nx / bx;
const unsigned int gx = (blockIdx.z % nbx) * bx + x - halo;
const unsigned int gy = (blockIdx.z / nbx) * by + y - halo;
unsigned int gx, gy;
block_global_xy(x, y, halo, d_block_channel.nx, gx, gy);
const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
float f[NQ];