{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:21:41Z","timestamp":1772695301878,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"United States National Science Foundation","doi-asserted-by":"publisher","award":["2530705"],"award-info":[{"award-number":["2530705"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408484","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-13","source":"Crossref","is-referenced-by-count":0,"title":["HERO-Sign: Hierarchical Tuning and Efficient Compiler-Time GPU Optimizations for SPHINCS+ Signature Generation"],"prefix":"10.1109","author":[{"given":"Yaoyun","family":"Zhou","sequence":"first","affiliation":[{"name":"University of California,Department of EECS,Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical Engineering,Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Alter","year":"2021","journal-title":"Optimizing the nist post quantum candidate sphincs+ using avx-512"},{"issue":"1","key":"ref2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.46586\/tches.v2018.i1.18-39","article-title":"FPGA-based accelerator for post-quantum signature scheme SPHINCS-256","volume":"2018","author":"Amiet","year":"2018","journal-title":"IACR Transactions on Cryptographic Hardware and Embedded Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DSD51259.2020.00046"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1113479"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363229"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature23474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2018.2888987"},{"key":"ref10","volume-title":"Cuda shared memory access mechanism with vectorized instructions","author":"Code","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3728469"},{"key":"ref12","volume-title":"Evaluating post-quantum cryptography on embedded systems: A performance analysis","author":"Dong","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276712"},{"key":"ref14","article-title":"Optimization for sphincs+ using intel secure hash algorithm extensions","volume-title":"Cryptology ePrint Archive","author":"Hanson","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref16","volume-title":"Taskflow: A general-purpose parallel and heterogeneous task programming system","author":"Huang","year":"2023"},{"key":"ref17","year":"2023","journal-title":"Ibm quantum roadmap to 2033"},{"key":"ref18","volume-title":"Intel oneapi dpc++ compiler","year":"2023"},{"issue":"99","key":"ref19","first-page":"1","article-title":"Parallel implementation of sphincs+ with gpus","author":"Kim","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems I: Regular Papers"},{"key":"ref20","volume-title":"Mlir: Multi-level intermediate representation - linalg dialect and task dag","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707270"},{"key":"ref22","first-page":"2021","article-title":"Nist pqc standardization update","author":"Moody","year":"2021","journal-title":"National Institute of Standards and Technology"},{"key":"ref23","year":"2022","journal-title":"Cuda graphs"},{"key":"ref24","volume-title":"CUDA C Programming Guide","author":"Corporation","year":"2023"},{"key":"ref25","volume-title":"NVIDIA Nsight Compute","year":"2025"},{"key":"ref26","volume-title":"How to understand the bank conflict of shared memory?","year":"2023"},{"key":"ref27","year":"2025","journal-title":"NIST Selects HQC as Fifth Algorithm for Post-Quantum Encryption"},{"key":"ref28","volume-title":"liboqs: C library for prototyping and experimenting with quantum-resistant cryptography","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.22331\/q-2018-08-06-79"},{"issue":"1","key":"ref30","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.32604\/cmc.2023.033910","article-title":"Accelerating falcon postquantum digital signature algorithm on graphic processing units","volume":"75","author":"Seog","year":"2023","journal-title":"Computers, Materials & Continua"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/42190.42277"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3453289"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1994.365700"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2995562"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/sc.2014.21"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1007\/978-3-031-17143-7_25","article-title":"A novel high-performance implementation ofnbsp;crystalskyber withnbsp;ai accelerator","volume-title":"Computer Security - ESORICS 2022: 27th European Symposium on Research in Computer Security, Copenhagen, Denmark, September 26\u201330, 2022, Proceedings, Part III","author":"Wan","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3457736"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3585558"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED65160.2025.11014474"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408484.pdf?arnumber=11408484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:50:25Z","timestamp":1772693425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408484","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}