A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC
This addresses data transmission challenges for particle physics experiments like CMS at CERN, offering a flexible, configurable solution for high-granularity calorimeters, though it is incremental as it applies existing neural network methods to a new hardware context.
The paper tackles the data transmission bottleneck from detector front-ends to off-detector trigger systems at the HL-LHC by implementing a neural network autoencoder in a radiation-tolerant ASIC for lossy compression, achieving a total area of 3.6 mm², power consumption of 95 mW, and 2.4 nJ per inference.
Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network autoencoder model can be implemented in a radiation tolerant ASIC to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the CMS experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the neural network weights, a unique data compression algorithm can be deployed for each sensor in different detector regions, and changing detector or collider conditions. To meet area, performance, and power constraints, we perform a quantization-aware training to create an optimized neural network hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework, and was processed through synthesis and physical layout flows based on a LP CMOS 65 nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates, and reports a total area of 3.6 mm^2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. This is the first radiation tolerant on-detector ASIC implementation of a neural network that has been designed for particle physics applications.