Pith. sign in

REVIEW 2 cited by

Memory Planning for Deep Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.00448 v1 pith:IS42M7XT submitted 2022-02-23 cs.LG cs.PF

classification cs.LGcs.PF
keywords memorytextttallocationmemomalloccomponentcontentioncontextdeep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study memory allocation patterns in DNNs during inference, in the context of large-scale systems. We observe that such memory allocation patterns, in the context of multi-threading, are subject to high latencies, due to \texttt{mutex} contention in the system memory allocator. Latencies incurred due to such \texttt{mutex} contention produce undesirable bottlenecks in user-facing services. Thus, we propose a "memorization" based technique, \texttt{MemoMalloc}, for optimizing overall latency, with only moderate increases in peak memory usage. Specifically, our technique consists of a runtime component, which captures all allocations and uniquely associates them with their high-level source operation, and a static analysis component, which constructs an efficient allocation "plan". We present an implementation of \texttt{MemoMalloc} in the PyTorch deep learning framework and evaluate memory consumption and execution performance on a wide range of DNN architectures. We find that \texttt{MemoMalloc} outperforms state-of-the-art general purpose memory allocators, with respect to DNN inference latency, by as much as 40\%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LATTICE: Constraint-Directed Scheduling, Memory Planning, and Pipeline Refinement for NPUs

    cs.NI 2026-07 conditional novelty 6.0 of 10

    LATTICE is a three-stage NPU compiler pipeline that schedules with memory pressure in mind, materializes a fixed on-chip memory plan, and refines timing while preserving that plan, beating four baselines on all 24 mod...

  2. Xema: Efficient Diffusion Serving through Fine-Grained Memory Management and Auto-Configuration

    cs.DC 2026-07 conditional novelty 6.0 of 10

    Trace-guided fine-grained memory control and offline joint planning raise diffusion serving SLO attainment by up to 3.7× while cutting configuration search from hours to minutes.

Pith tools