REVIEW 5 cited by
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
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
abstract
Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One technique to limit model size is quantization, which implies using fewer bits to represent weights and biases. Such an approach usually results in a decline in performance. Here, we introduce a method for designing optimally heterogeneously quantized versions of deep neural network models for minimum-energy, high-accuracy, nanosecond inference and fully automated deployment on chip. With a per-layer, per-parameter type automatic quantization procedure, sampling from a wide range of quantizers, model energy consumption and size are minimized while high accuracy is maintained. This is crucial for the event selection procedure in proton-proton collisions at the CERN Large Hadron Collider, where resources are strictly limited and a latency of ${\mathcal O}(1)~\mu$s is required. Nanosecond inference and a resource consumption reduced by a factor of 50 when implemented on field-programmable gate array hardware are achieved.
Forward citations
Cited by 5 Pith papers
-
SparsePixels: Efficient Convolution for Sparse Data on FPGAs
A fixed-budget sparse-convolution FPGA framework runs CNNs on <=20 of ~4000 pixels, achieving 0.665 us inference for MicroBooNE with a 73x speedup and ~2% AUC loss.
-
wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
A new open benchmark with 683,176 synthesized hls4ml designs plus GNN/transformer surrogates that predict FPGA resources/latency accurately in-distribution but poorly on out-of-distribution scientific models.
-
Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation
A framework co-designs approximate printed ternary neural networks and their analog front-ends, claiming up to 17x smaller area and 59x lower power than prior printed classifiers at under 5% accuracy loss.
-
EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Tools
EdgeMark automates and benchmarks embedded AI toolchains, comparing TFLM, Edge Impulse, Ekkono, and Renesas eAI Translator on two microcontroller boards.
-
Neural Architecture Codesign for Fast Physics Applications
An automated two-stage neural architecture search and compression pipeline discovers FPGA-efficient models for Bragg peak finding and jet classification, beating or matching hand-crafted baselines on accuracy, latency...
Discussion (0). Continue with ORCID to comment.