Session MP2: Distributed coherent communication systems

Anjali Gupta, Muzzammil Hussain

In distributed systems, entities perform the predefined tasks distributively and have to communicate quite frequently. Confidentiality is the primary security requirement in such systems. There should be some secure mechanism whereby a pair of entities can securely communicate with each other. In most of the applications of distributed systems, computational and communication resources are limited and any such mechanism that ensures security of data under transmission should consider these computational and communicational constraints. Symmetric key cryptography emerges as one of the effective mechanisms to secure the data in distributed systems. The security of a symmetric key mechanism purely depends on the secrecy of the session key. In this paper, we have proposed a protocol for the sharing of session key between communicating entities securely. The proposed protocol secures the session through asymmetric key mechanism and once the session key is securely shared, the entities can communicate through the shared session key.

Gary R. Ragsdale

Andrew J. Viterbi

Calum Snowdon, Giuseppe M. J. Barca

Second-order Møller-Plesset perturbation theory (MP2) using the Resolution of the Identity approximation (RI-MP2) is a widely used method for computing molecular energies beyond the Hartree-Fock mean-field approximation. However, its high computational cost and lack of efficient algorithms for modern supercomputing architectures limit its applicability to large molecules. In this paper, we present the first distributed-memory many-GPU RI-MP2 algorithm explicitly designed to utilize hundreds of GPU accelerators for every step of the computation. Our novel algorithm achieves near-peak performance on GPU-based supercomputers through the development of a distributed memory algorithm for forming RI-MP2 intermediate tensors with zero inter-node communication, except for a single O(N^2) asynchronous broadcast, and a distributed memory algorithm for the O(N^5) energy reduction step, capable of sustaining near-peak performance on clusters with several hundred GPUs. Comparative analysis shows our implementation outperforms state-of-the-art quantum chemistry software by over 3.5 times in speed while achieving an eightfold reduction in computational power consumption. Benchmarking on the Perlmutter supercomputer, our algorithm achieves 11.8 PFLOP/s (83% of peak performance) performing and the RI-MP2 energy calculation on a 314-water cluster with 7,850 primary and 30,144 auxiliary basis functions in 4 minutes on 180 nodes and 720 A100 GPUs. This performance represents a substantial improvement over traditional CPU-based methods, demonstrating significant time-to-solution and power consumption benefits of leveraging modern GPU-accelerated computing environments for quantum chemistry calculations.

S. N. Molotkov

Abstract Quantum cryptography systems are systems for extending the initial start key, which is required at the start of the system, to ensure information-theoretic authentication of messages in the classical communication channel. In subsequent sessions, a quantum key is generated, part of which is used for authentication in subsequent sessions. There is a fundamental question for quantum cryptography—how many sessions of quantum key distribution (QKD) can be held until the cryptographic properties of the quantum keys are reached a critical level, after which they can no longer be used for cryptographic purposes, and a new restart of the quantum cryptography system will be required. An explicit expression of the allowable number of sessions of quantum key distribution is obtained. It is shown that for the real parameters of the system, it is possible for the system to work almost indefinitely until the next initialization.

Neeraj Subesh, Rajameenakshi Subramanian, Rajiuddin Sk +1 more