{"title":"Cheddar:适用于 CUDA GPU 的 Swift 全同态加密库","authors":"Jongmin Kim, Wonseok Choi, Jung Ho Ahn","doi":"arxiv-2407.13055","DOIUrl":null,"url":null,"abstract":"Fully homomorphic encryption (FHE) is a cryptographic technology capable of\nresolving security and privacy problems in cloud computing by encrypting data\nin use. However, FHE introduces tremendous computational overhead for\nprocessing encrypted data, causing FHE workloads to become 2-6 orders of\nmagnitude slower than their unencrypted counterparts. To mitigate the overhead,\nwe propose Cheddar, an FHE library for CUDA GPUs, which demonstrates\nsignificantly faster performance compared to prior GPU implementations. We\ndevelop optimized functionalities at various implementation levels ranging from\nefficient low-level primitives to streamlined high-level operational sequences.\nEspecially, we improve major FHE operations, including number-theoretic\ntransform and base conversion, based on efficient kernel designs using a small\nword size of 32 bits. By these means, Cheddar demonstrates 2.9 to 25.6 times\nhigher performance for representative FHE workloads compared to prior GPU\nimplementations.","PeriodicalId":501291,"journal":{"name":"arXiv - CS - Performance","volume":"42 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Cheddar: A Swift Fully Homomorphic Encryption Library for CUDA GPUs\",\"authors\":\"Jongmin Kim, Wonseok Choi, Jung Ho Ahn\",\"doi\":\"arxiv-2407.13055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fully homomorphic encryption (FHE) is a cryptographic technology capable of\\nresolving security and privacy problems in cloud computing by encrypting data\\nin use. However, FHE introduces tremendous computational overhead for\\nprocessing encrypted data, causing FHE workloads to become 2-6 orders of\\nmagnitude slower than their unencrypted counterparts. To mitigate the overhead,\\nwe propose Cheddar, an FHE library for CUDA GPUs, which demonstrates\\nsignificantly faster performance compared to prior GPU implementations. We\\ndevelop optimized functionalities at various implementation levels ranging from\\nefficient low-level primitives to streamlined high-level operational sequences.\\nEspecially, we improve major FHE operations, including number-theoretic\\ntransform and base conversion, based on efficient kernel designs using a small\\nword size of 32 bits. By these means, Cheddar demonstrates 2.9 to 25.6 times\\nhigher performance for representative FHE workloads compared to prior GPU\\nimplementations.\",\"PeriodicalId\":501291,\"journal\":{\"name\":\"arXiv - CS - Performance\",\"volume\":\"42 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Performance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.13055\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Performance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.13055","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Cheddar: A Swift Fully Homomorphic Encryption Library for CUDA GPUs
Fully homomorphic encryption (FHE) is a cryptographic technology capable of
resolving security and privacy problems in cloud computing by encrypting data
in use. However, FHE introduces tremendous computational overhead for
processing encrypted data, causing FHE workloads to become 2-6 orders of
magnitude slower than their unencrypted counterparts. To mitigate the overhead,
we propose Cheddar, an FHE library for CUDA GPUs, which demonstrates
significantly faster performance compared to prior GPU implementations. We
develop optimized functionalities at various implementation levels ranging from
efficient low-level primitives to streamlined high-level operational sequences.
Especially, we improve major FHE operations, including number-theoretic
transform and base conversion, based on efficient kernel designs using a small
word size of 32 bits. By these means, Cheddar demonstrates 2.9 to 25.6 times
higher performance for representative FHE workloads compared to prior GPU
implementations.