Bibliographic record
Abstract
The uniform grid is a well-known acceleration structure for ray tracing. It is fast to build, but slow to traverse. In this paper, we propose a novel micro 64-tree structure to speed up grid traversals on a GPU. A micro 64-tree is a compact 64-way full tree that summarizes the occupancy of an underlying uniform grid in a hierarchy. A node of the tree stands for a voxel, whose occupancy is represented by a single bit. A node is subdivided into a 64-subgrid that is stored in a 64-bit word. The micro 64-tree is built on the top of a uniform grid. We improve the GPU grid construction algorithm by computing precise triangle-cell intersections and precluding non-overlapping triangle-cell pairs before sorting. The micro 64-tree is then built bottom-up from the uniform grid by reductions in parallel. The top levels of the micro 64-tree are pre-loaded into the shared memory of a GPU, which support on-chip traversals across the coarse levels. The traversal algorithm navigates the ray through the 64-subgrids at different levels, with a concise context for each level stored in the GPU's registers to facilitate vertical moves. With a small overhead in memory and a small overhead in building time, the micro 64-tree can reduce traversal steps, decrease memory bandwidth consumption, and hence significantly improve the efficiency of ray tracing on a GPU.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.015 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".