Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/David Kaeli

David Kaeli

3 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Distributed×2Architecture×1Prog. Lang.×1Crypto×1Algorithms×1ML×1Performance×1

Frequent co-authors

José Cano2×
Sana Taghipour Anvari1×
Elam Cohavi1×
Nicolas Bohm Agostini1×
Jude Haris1×
Antonino Tumeo1×

Research Timeline

2026
GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs

The paper proposes a novel, optimized sparse matrix multiplication method for fully homomorphic encrypted deep neural networks, achieving up to a 3.0x speedup on AMD GPUs compared to CPU implementations.

Defeat the Heap: Zero-Copy Data Movement in AXI4MLIR

This paper optimizes data transfer between host and accelerator in machine learning workloads by eliminating redundant staging operations.

DRIFT: Direct Reduced Fourier Transforms for Distributed Spectral Neural Operators

This paper introduces the Distributed Truncated Spectral Transform (DTST) for Fourier Neural Operators (FNOs), achieving significant speedups in distributed computing.

Highlighted terms show continued research focus across papers

Papers

cs.DCEmpiricalRecentJul 15, 2026

DRIFT: Direct Reduced Fourier Transforms for Distributed Spectral Neural Operators

Sana Taghipour Anvari, David Kaeli

This paper introduces the Distributed Truncated Spectral Transform (DTST) for Fourier Neural Operators (FNOs), achieving significant speedups in distributed computing.

View →
cs.ARcs.PLEmpiricalRecent
Jun 9, 2026

Defeat the Heap: Zero-Copy Data Movement in AXI4MLIR

Elam Cohavi, Nicolas Bohm Agostini, Jude Haris, Antonino Tumeo +2 more

This paper optimizes data transfer between host and accelerator in machine learning workloads by eliminating redundant staging operations.

View →
cs.CRcs.DCcs.DSApr 13, 2026

GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs

Lara D'Agata, Carlos Agulló-Domingo, Óscar Vera-López, Kaustubh Shivdikar +6 more

The paper proposes a novel, optimized sparse matrix multiplication method for fully homomorphic encrypted deep neural networks, achieving up to a 3.0x speedup on AMD GPUs compared to CPU implementatio…

View →