MétaCan
Menu
Back to cohort
Record W2012591111 · doi:10.1109/icpp.2013.43

Parallel Radix Sort on the AMD Fusion Accelerated Processing Unit

2013· article· en· W2012591111 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicParallel Computing and Optimization Techniques
Canadian institutionsUniversity of Toronto
FundersOntario Centres of ExcellenceAstellas Pharma US
KeywordsComputer scienceParallel computingsortSorting algorithmSortingOverhead (engineering)CopyingVariable (mathematics)Computer hardwareAlgorithmOperating systemDatabase

Abstract

fetched live from OpenAlex

We design, implement and evaluate a parallel radix sort that simultaneously utilizes the CPU and GPU devices on the AMD Fusion APU. The parallel sort, referred to as Fusion Sort, partitions the sort keys between the CPU and GPU devices and utilizes the integrated memory system of the APU to avoid data copying between the devices. We identify three design issues that impact overhead and performance: the granularity of sharing between the two devices, the scheme of data partitioning and the allocation of data in memory regions accessible by each device. We present three variants of Fusion Sort that share data at coarse and fine granularities and with fixed and variable data partitioning schemes. In each variant, data is allocated to minimize the overhead of non-preferred memory accesses of each device. Our evaluation shows that fine-grain sharing with variable data partitioning performs the best. Further, Fusion Sort outperforms CPU-only and GPU-only parallel radix sorts by up to 1.8X and 1.9X respectively. These results demonstrate the viability of the integrated memory system of the APU in the context of sorting.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.941
Threshold uncertainty score0.478

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.047
GPT teacher head0.274
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it