Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Subramoney, Sreenivas"'
Non-volatile Memory (NVM) could bridge the gap between memory and storage. However, NVMs are susceptible to data remanence attacks. Thus, multiple security metadata must persist along with the data to protect the confidentiality and integrity of NVM-
Externí odkaz:
http://arxiv.org/abs/2407.09180
Autor:
Bera, Rahul, Ranganathan, Adithya, Rakshit, Joydeep, Mahto, Sujit, Nori, Anant V., Gaur, Jayesh, Olgun, Ataberk, Kanellopoulos, Konstantinos, Sadrosadati, Mohammad, Subramoney, Sreenivas, Mutlu, Onur
Load instructions often limit instruction-level parallelism (ILP) in modern processors due to data and resource dependences they cause. Prior techniques like Load Value Prediction (LVP) and Memory Renaming (MRN) mitigate load data dependence by predi
Externí odkaz:
http://arxiv.org/abs/2406.18786
Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both the speed and length of text generation. Approaches such as Multi-Quer
Externí odkaz:
http://arxiv.org/abs/2406.10247
Memory accounts for 33 - 50% of the total cost of ownership (TCO) in modern data centers. We propose a novel solution to tame memory TCO through the novel creation and judicious management of multiple software-defined compressed memory tiers. As oppo
Externí odkaz:
http://arxiv.org/abs/2404.13886
With the recent growth in demand for large-scale deep neural networks, compute in-memory (CiM) has come up as a prominent solution to alleviate bandwidth and on-chip interconnect bottlenecks that constrain Von-Neuman architectures. However, the const
Externí odkaz:
http://arxiv.org/abs/2402.11780
Data-hungry applications that require terabytes of memory have become widespread in recent years. To meet the memory needs of these applications, data centers are embracing tiered memory architectures with near and far memory tiers. Precise, efficien
Externí odkaz:
http://arxiv.org/abs/2311.10275
Software managed byte-addressable hybrid memory systems consisting of DRAMs and NVMMs offer a lot of flexibility to design efficient large scale data processing applications. Operating systems (OS) play an important role in enabling the applications
Externí odkaz:
http://arxiv.org/abs/2310.03370
Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development, modularity, and iso
Externí odkaz:
http://arxiv.org/abs/2304.07941
Autor:
Jeong, Geonhwa, Damani, Sana, Bambhaniya, Abhimanyu Rajeshkumar, Qin, Eric, Hughes, Christopher J., Subramoney, Sreenivas, Kim, Hyesoon, Krishna, Tushar
Deep Learning (DL) acceleration support in CPUs has recently gained a lot of traction, with several companies (Arm, Intel, IBM) announcing products with specialized matrix engines accessible via GEMM instructions. CPUs are pervasive and need to handl
Externí odkaz:
http://arxiv.org/abs/2302.08687
Autor:
Firtina, Can, Pillai, Kamlesh, Kalsi, Gurpreet S., Suresh, Bharathwaj, Cali, Damla Senol, Kim, Jeremie, Shahroodi, Taha, Cavlak, Meryem Banu, Lindegger, Joel, Alser, Mohammed, Luna, Juan Gómez, Subramoney, Sreenivas, Mutlu, Onur
Profile hidden Markov models (pHMMs) are widely employed in various bioinformatics applications to identify similarities between biological sequences, such as DNA or protein sequences. In pHMMs, sequences are represented as graph structures. These pr
Externí odkaz:
http://arxiv.org/abs/2207.09765