Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization
This work addresses efficiency for resource-constrained CPU deployments, but it is incremental as it builds on existing Tsetlin Machine methods.
The paper tackled the problem of slow Tsetlin Machine inference on CPUs by proposing an optimized software implementation with instruction-level bitwise operations and an early exit mechanism, achieving up to 96.71% reduction in inference time while maintaining code density.
The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on modern CPU architectures. Motivated by this, we propose an efficient software implementation of the TM by leveraging instruction-level bitwise operations for compact model representation and accelerated processing. To further improve inference speed, we introduce an early exit mechanism, which exploits the TM's AND-based clause evaluation to avoid unnecessary computations. Building upon this, we propose a literal Reorder strategy designed to maximize the likelihood of early exits. This strategy is applied during a post-training, pre-inference stage through statistical analysis of all literals and the corresponding actions of their associated Tsetlin Automata (TA), introducing negligible runtime overhead. Experimental results using the gem5 simulator with an ARM processor show that our optimized implementation reduces inference time by up to 96.71% compared to the conventional integer-based TM implementations while maintaining comparable code density.