arXiv subjects

Muthu Annamalai

Publications and source records attributed to Muthu Annamalai.

2 recordsLinked to original sources

arXiv2025

Learned Cost Model for Placement on Reconfigurable Dataflow Hardware

Mapping a dataflow-graph of an ML model onto a reconfigurable system is difficult, as different mappings have different throughputs and consume resource constraints differently. To solve this, a model to evaluate the throughput of mappings is necessary as measuring throughput completely is expensive. Many use a hand-designed analytical model, relying on proxy features or intuition, introducing error. We provide a Learned Approach that predicts throughput 31%-52% more accurately over a variety of graphs. In addition, our approach shows no accuracy degradation after removing performance annotations. We show that using this approach results in 5.6% faster compiled graphs.

cs.DC↗

arXiv2025

Resource Estimation of CGGI and CKKS scheme workloads on FracTLcore Computing Fabric

Cornami Mx2 accelerates of Fully Homomorphic Encryption (FHE) applications, enabled by breakthrough work [1], which are otherwise compute limited. Our processor architecture is based on the systolic array of cores with in-memory compute capability and a network on chip (NoC) processor architecture called the "FracTLcore compute fabric processor" (Mx2). Here, we describe the work to estimate processor resources to compute workload in CGGI (TFHE-rs) or CKKS scheme during construction of our compiler backend for this architecture [2]. These processors are available for running applications in both the TFHE-rs Boolean scheme and CKKS scheme FHE applications.

cs.CR↗