{"doi":"10.1145/3410463.3414634","title":"Mixed-Signal Charge-Domain Acceleration of Deep Neural Networks through Interleaved Bit-Partitioned Arithmetic","abstract":"Albeit low-power, mixed-signal circuitry suffers from significant overhead of Analog to Digital (A/D) conversion, limited range for information encoding, and susceptibility to noise. This paper aims to address these challenges by offering and leveraging the following mathematical insight regarding vector dot-product---the basic operator in Deep Neural Networks (DNNs). This operator can be reformulated as a wide regrouping of spatially parallel low-bitwidth calculations that are interleaved across the bit partitions of multiple elements of the vectors. As such, the computational building block of our accelerator becomes a wide bit-interleaved analog vector unit comprising a collection of low-bitwidth multiply-accumulate modules that operate in the analog domain and share a single A/D converter(ADC). This bit-partitioning results in a lower-resolution ADC while the wide regrouping alleviates the need for A/D conversion per operation, amortizing its cost across multiple bit-partitions of the vector elements. Moreover, the low-bitwidth modules require smaller encoding range and also provide larger margins for noise mitigation. We also utilize the switched-capacitor design for our bit-level reformulation of DNN operations. The proposed switched-capacitor circuitry performs the regrouped multiplications in the charge domain and accumulates the results of the group in its capacitors over multiple cycles. The capacitive accumulation combined with wide bit-partitioned regrouping reduces the rate of A/D conversions, further improving the overall efficiency of the design.","journal":"arXiv (Cornell University)","year":2020,"id":122513,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9632,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":563761,"name":"Hardik Sharma","orcid":"0000-0003-0028-013X","position":1,"is_corresponding":false},{"id":563762,"name":"Sean Kinzer","orcid":"0000-0002-0955-585X","position":2,"is_corresponding":false},{"id":320964,"name":"Amir Yazdanbakhsh","orcid":"0000-0001-8199-7671","position":3,"is_corresponding":false},{"id":564203,"name":"Jongse Park","orcid":null,"position":4,"is_corresponding":false},{"id":563763,"name":"Nam Sung Kim","orcid":"0000-0002-0442-5634","position":5,"is_corresponding":false},{"id":563764,"name":"Doug Burger","orcid":"0009-0006-6588-6596","position":6,"is_corresponding":false},{"id":320965,"name":"Hadi Esmaeilzadeh","orcid":"0000-0002-8548-1039","position":7,"is_corresponding":false},{"id":563760,"name":"Soroush Ghodrati","orcid":"0000-0001-5514-8027","position":0,"is_corresponding":true}],"reference_count":95,"raw_metadata":null,"created_at":"2026-07-18T23:14:51.076430Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}