Related papers: Node-Aware Improvements to Allreduce
To recover simultaneous multiple failures in erasure coded storage systems, Patrick Lee et al introduce concurrent repair based minimal storage regenerating codes to reduce repair traffic. The architecture of this approach is simpler and…
Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing…
In the Fully Sharded Data Parallel (FSDP) training pipeline, collective operations can be interleaved to maximize the communication/computation overlap. In this scenario, outstanding operations such as Allgather and Reduce-Scatter can…
We establish lower bounds on the sub-packetization of optimal-access MSR codes in the context of multiple-node failures. These bounds generalize the tight bounds for single-node failure presented by Balaji et al. (IEEE Transactions on…
We resolve the question of optimality for a well-studied packetized implementation of random linear network coding, called PNC. In PNC, in contrast to the classical memoryless setting, nodes store received information in memory to later…
In decentralized optimization, nodes cooperate to minimize an overall objective function that is the sum (or average) of per-node private objective functions. Algorithms interleave local computations with communication among all or a subset…
In many modern AI chips and multicore systems-on-chip, embedded applications exhibit predictable inter-core traffic behavior that can be characterized at design time. For such applications, a variety of design-time traffic management and…
A MapReduce algorithm can be described by a mapping schema, which assigns inputs to a set of reducers, such that for each required output there exists a reducer that receives all the inputs that participate in the computation of this…
As new data and updates are constantly arriving, the results of data mining applications become stale and obsolete over time. Incremental processing is a promising approach to refreshing mining results. It utilizes previously saved states…
Machine learning models made up of millions or billions of parameters are trained and served on large multi-GPU systems. As models grow in size and execute on more GPUs, the collective communications used in these applications become a…
We introduce linear network coding on parallel architecture for multi-source finite acyclic network. In this problem, different messages in diverse time periods are broadcast and every nonsource node in the network decodes and encodes the…
Fully provisioned Message Passing Interface (MPI) parallelism achieves near-optimal wall-clock time for Computational Fluid Dynamics (CFD) solvers. This work addresses a complementary question for shared, cloud-managed clusters: can…
We study the problem of erasure correction (node repair) for regenerating codes defined on graphs wherein the cost of transmitting the information to the failed node depends on the graphical distance from this node to the helper vertices of…
Multi-threaded applications are capable of exploiting the full potential of many-core systems. However, Network-on-Chip (NoC) based inter-core communication in many-core systems is responsible for 60-75% of the miss latency experienced by…
As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…
Good process-to-compute-node mappings can be decisive for well performing HPC applications. A special, important class of process-to-node mapping problems is the problem of mapping processes that communicate in a sparse stencil pattern to…
Multi-antenna precoding effectively mitigates the interference in wireless networks. However, the precoding efficiency can be significantly degraded by the overhead due to the required feedback of channel state information (CSI). This paper…
In this paper, a semantic-aware joint communication and computation resource allocation framework is proposed for mobile edge computing (MEC) systems. In the considered system, each terminal device (TD) has a computation task, which needs…
Data race conditions in multi-tasking software applications are prevented by serializing access to shared memory resources, ensuring data consistency and deterministic behavior. Traditionally tasks acquire and release locks to synchronize…
Generic simulation code for spiking neuronal networks spends the major part of time in the phase where spikes have arrived at a compute node and need to be delivered to their target neurons. These spikes were emitted over the last interval…