3 papers
cs.AR2026
Arithmetic Packing on Wide Integer Datapaths in DSP Primitives of Modern FPGA Devices
Titus Bornträger, Shane Fleming, Philipp Holzinger +3
Deep Neural Networks increasingly employ low-precision quantization to reduce computational requirements. While FPGAs are well suited for workloads with heterogeneous precisions, t…
cs.AR2025
SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators
Yaman Umuroglu, Christoph Berganski, Felix Jentzsch +8
While neural network quantization effectively reduces the cost of matrix multiplications, aggressive quantization can expose non-matrix-multiply operations as significant performan…
cs.LG2025
FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs
Shashwat Khandelwal, Jakoba Petri-Koenig, Thomas B. PreuÃer +2
Recurrent neural networks (RNNs), particularly LSTMs, are effective for time-series tasks like sentiment analysis and short-term stock prediction. However, their computational comp…