Transparent Offloading of Computationally Demanding Operations in Microsoft .NET
Bibliographic record
Abstract
For many years, the group of preferred programming languages for writing algorithms meant for large clusters contains among others C/C++ and FORTRAN. However, normally one does not consider the Microsoft .NET programming languages as a part of this group. The reason for this is that only few tools exist that can help programmers simplify the process of writing parallel .NET code besides the official tools from Microsoft i.e. Task Parallel Library (TPL) (Microsoft, n.d.) and HPC Pack. (Microsoft, n.d.) Furthermore, most of the official tools only supports a Microsoft Windows or Microsoft Azure platform and not a mixture of non-virtualized platforms like a Linux machine with Mono (Mono, n.d.) or the decommissioned DotGNU (GNU, n.d.). In addition, some of the most useful tools for writing parallel .NET code does not support multiple machines and as a result, programmers seldom choose .NET as the framework for writing parallel programs. Therefore, this paper presents a .NET tool, which will use well-known parallel tools as inspiration and allow programmers to call a number of methods that can send a job consisting of a user-defined method (code) along with sets of parameters and shared data to a central machine. The central machine will then modify the code and afterwards distributes the work to the connected machines each running one or more workers. By implementing three simple benchmarks, initial tests shows that the benchmarks can achieve linear scaling on a small cluster consisting of Windows machines, and by presenting future design ideas, it is believed that it will be possible to extent the linear scaling to a larger mix-platform cluster consisting of both internal resources (workstations/servers) and external cloud resources.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.009 | 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".