2 papers
cs.AR2026
Compiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN Accelerators
Christoph Berganski, Felix Jentzsch, Marco Platzner
Aggressive quantization of neural networks can expose activation functions as bottlenecks for efficient hardware acceleration. Implementing quantized activations as multi-threshold…
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…