Alexandre E. Eichenberger

Compiling ONNX Neural Network Models Using MLIR

Deep neural network models are becoming increasingly popular and have been used in various tasks such as computer vision, speech recognition, and natural language processing. Machine learning...

Serving Deep Learning Models from Relational Databases

The Design of OpenMP Thread Affinity

Early Experiences Porting Three Applications to OpenMP 4.5

Exploiting Fine- and Coarse-Grained Parallelism Using a Directive Based Approach

OMPT: An OpenMP Tools Application Programming Interface for Performance Analysis

A Proposal to OpenMP for Addressing the CPU Oversubscription Challenge

Towards Task-Parallel Reductions in OpenMP

Effective Cluster Assignment for Modulo Scheduling

Register allocation for predicated code

An integrated approach to accelerate data and predicate computations in hyperblocks

Stage scheduling: a technique to reduce the register requirements of a modulo schedule

Minimum register requirements for a modulo schedule

Balance Scheduling: Weighting Branch Tradeoffs in Superblocks

Impact of Load Imbalance on the Design of Software Barriers

Lower Bounds on Precedence-Constrained Scheduling for Parallel Processors

Optimizing Compiler for the CELL Processor

Efficient Edge Profiling for ILP-Processors