IceClave: A Trusted Execution Environment for In-Storage Computing

Kang, Luyi; Yang, Xue; Jia, Weiwei; Wang, Xiaohao; Kim, Jongryool; Youn, Changhwan; Joon, Kang, Myeong; Lim, Hyung Jin; Jacob, Bruce; Huang, Jian

doi:10.1145/3466752.3480109

Cited by 17 publications

(9 citation statements)

References 76 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of researchers have identified the need for mechanisms that allow an application hosted in a TEE to securely communicate with I/O devices, such as in-storage processors [20], GPUs [18,38,41], FPGAs [21,28,31,42], and AI accelerators [16,40].…”

Section: Related Workmentioning

confidence: 99%

Confidential Machine Learning within Graphcore IPUs

Vaswani¹,

Volos²,

Fournet³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present IPU Trusted Extensions (ITX), a set of experimental hardware extensions that enable trusted execution environments in Graphcore's AI accelerators.ITX enables the execution of AI workloads with strong confidentiality and integrity guarantees at low performance overheads. ITX isolates workloads from untrusted hosts, and ensures their data and models remain encrypted at all times except within the IPU. ITX includes a hardware root-of-trust that provides attestation capabilities and orchestrates trusted execution, and on-chip programmable cryptographic engines for authenticated encryption of code and data at PCIe bandwidth. We also present software for ITX in the form of compiler and runtime extensions that support multi-party training without requiring a CPU-based TEE.Experimental support for ITX is included in Graphcore's GC200 IPU taped out at TSMC's 7nm technology node. Its evaluation on a development board using standard DNN training workloads suggests that ITX adds less than 5% performance overhead, and delivers up to 17x better performance compared to CPU-based confidential computing systems relying on AMD SEV-SNP.

show abstract

Section: Related Workmentioning

confidence: 99%

Confidential Machine Learning within Graphcore IPUs

Vaswani¹,

Volos²,

Fournet³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…S 2 : Semi-centralized SC with TEE and non-TEE nodes. TEE support goes beyond just CPU nodes as shown in recent proposals for peripheral TEEs [26][27][28][29]. For nodes that are TEE-enabled, we can support the secure isolation of tenants without requiring the SC.…”

Section: Potential Designsmentioning

confidence: 99%

“…Device TEEs. Existing proposals enable TEE on devices such as GPUs [26,[96][97][98][99], FPGAs [29,30,100], SSDs [28], and other accelerators [101]. They focus solely on adding TEEfeatures so as to create hardware-enabled enclaves on the accelerator-either for multi-tenancy or for single-tenancy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Empowering Data Centers for Next Generation Trusted Computing

Dhar¹,

Sridhara²,

Shinde³

et al. 2022

Preprint

View full text Add to dashboard Cite

Modern data centers have grown beyond CPU nodes to provide domain-specific accelerators such as GPUs and FP-GAs to their customers. From a security standpoint, cloud customers want to protect their data. They are willing to pay additional costs for trusted execution environments such as enclaves provided by Intel SGX and AMD SEV. Unfortunately, the customers have to make a critical choice-either use domain-specific accelerators for speed or use CPU-based confidential computing solutions.To bridge this gap, we aim to enable data-center scale confidential computing that expands across CPUs and accelerators. We argue that having wide-scale TEE-support for accelerators presents a technically easier solution, but is far away from being a reality. Instead, our hybrid design provides enclaved execution guarantees for computation distributed over multiple CPU nodes and devices with/without TEE support. Our solution scales gracefully in two dimensions-it can handle a large number of heterogeneous nodes and it can accommodate TEE-enabled devices as and when they are available in the future. We observe marginal overheads of 0.42-8% on real-world AI data center workloads that are independent of the number of nodes in the data center. We add custom TEE support to two accelerators (AI and storage) and integrate it into our solution, thus demonstrating that it can cater to future TEE devices.

show abstract

“…Flash-based SSDs have become an indispensable part in modern storage systems, as they outperform conventional hard-disk drives (HDDs) by orders of magnitude, and their cost is close to that of HDDs [22,30,51,62]. The SSD capacity continues to boost by increasing the number of flash channels and chips with the rapidly shrinking process and manufacturing technology [22,25,41,46].…”

Section: Introductionmentioning

confidence: 99%

LeaFTL: A Learning-Based Flash Translation Layer for Solid-State Drives

Sun¹,

Li²,

Sun³

et al. 2023

Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems,

Self Cite

View full text Add to dashboard Cite

In modern solid-state drives (SSDs), the indexing of flash pages is a critical component in their storage controllers. It not only affects the data access performance, but also determines the efficiency of the precious in-device DRAM resource. A variety of address mapping schemes and optimizations have been proposed. However, most of them were developed with human-driven heuristics.In this paper, we present a learning-based flash translation layer (FTL), named LeaFTL, which learns the address mapping to tolerate dynamic data access patterns via linear regression at runtime. By grouping a large set of mapping entries into a learned segment, it significantly reduces the memory footprint of the address mapping table, which further benefits the data caching in SSD controllers. LeaFTL also employs various optimization techniques, including out-of-band metadata verification to tolerate mispredictions, optimized flash allocation, and dynamic compaction of learned index segments. We implement LeaFTL with both a validated SSD simulator and a real open-channel SSD board. Our evaluation with various storage workloads demonstrates that LeaFTL saves the memory consumption of the mapping table by 2.9× and improves the storage performance by 1.4× on average, in comparison with state-of-the-art FTL schemes.

show abstract

IceClave: A Trusted Execution Environment for In-Storage Computing

Cited by 17 publications

References 76 publications

Confidential Machine Learning within Graphcore IPUs

Confidential Machine Learning within Graphcore IPUs

Empowering Data Centers for Next Generation Trusted Computing

LeaFTL: A Learning-Based Flash Translation Layer for Solid-State Drives

Contact Info

Product

Resources

About