Trash Talk: Accelerating Garbage Collection on Integrated GPUs is Worthless
Bibliographic record
Abstract
Systems integrating heterogeneous processors with unified memory provide seamless integration among these processors with minimal development complexity. These systems integrate accelerators such as GPUs on the same die with CPU cores to accommodate running parallel applications with varying levels of parallelism. Such integration is becoming very common on modern chip architectures, and it places a burden (or opportunity) on application and system programmers to utilize the full potential of such integrated chips. In this paper we evaluate whether we can obtain any performance benefits from running garbage collection on integrated GPU systems, and discuss how difficult it would be to realize these gains for the programmer. Proliferation of garbage-collected languages running on a variety of platforms from handheld mobile devices to data centers makes garbage collection an interesting target to examine on such platforms and can offer valuable lessons for other applications. We present our analysis of running garbage collection on integrated systems and find that the current state of these systems does not provide an advantage for accelerating such a task. We build a framework that allows us to offload garbage collection tasks on integrated GPU systems from within the JVM. We identify dominant phases of garbage collection and study the viability of offloading them to the integrated GPU. We show that performance advantages are limited, partly because an integrated GPU has limited advantage in memory bandwidth over the CPU, and partly because of costly atomic operations.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".