From 3d88ebea653dae9325a71da5270240e21bdfc533 Mon Sep 17 00:00:00 2001 From: Filip Leonarski Date: Tue, 17 Nov 2026 16:59:38 +0100 Subject: [PATCH] Refinement on the GPU: the normal matrix's budget counts J's copy in the parameter atoms' order Since the transpose product reads J from a per-atom ordered copy (jt) and each entry's row from row_at, an entry holds two float4 and three int (param, entry, row_at) on the card; row_of stays on the host. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01UqXYdHHZ4cogS1mrGUtfN7 --- image_analysis/structure_refinement/RefinementNewtonGPU.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/image_analysis/structure_refinement/RefinementNewtonGPU.cpp b/image_analysis/structure_refinement/RefinementNewtonGPU.cpp index 149e0e1c4..d9071e74f 100644 --- a/image_analysis/structure_refinement/RefinementNewtonGPU.cpp +++ b/image_analysis/structure_refinement/RefinementNewtonGPU.cpp @@ -37,7 +37,7 @@ size_t RestraintNormalMatrixGPU::DeviceBytes(const RestraintSet &set, size_t n_a return n_atoms * 4 * sizeof(float) // the positions + set.records.size() * (sizeof(RestraintRecord) + sizeof(int)) + set.plane_atoms.size() * sizeof(int) + rows * (sizeof(int) + 2 * sizeof(float)) // row starts, J v - + entries * (4 * sizeof(float) + 3 * sizeof(int)) + params * sizeof(int) // J, its index + + entries * (8 * sizeof(float) + 3 * sizeof(int)) + params * sizeof(int) // J, its transposed copy, index + n * 15 * sizeof(float) // seven vectors, diagonal + n * (2 * sizeof(float) + 2 * sizeof(int)) + 2 * block_atoms.size() * sizeof(int) // h, the blocks + inverse * 2 * sizeof(float) // their inverses