תכנון סדר פרציפציות לביצועי השקעה חיבורי במכשירי נייד

תקציר מקורי באנגליתarXiv:2609.14213v1 Announce Type: cross Abstract: Modern mobile inference runs on heterogeneous platforms combining mobile GPUs with multiple CPU core clusters. Existing optimizations typically exploit either inter-operator parallelism, by assigning entire operators to CPU cores or to the GPU, or intra-operator parallelism, by partitioning each operator for CPU-GPU co-execution. We consider these two forms of parallelism together, to improve inference latency of tasks that can be represented by a static DAG of operators with predefined input/output tensor shapes (e.g., CNNs or vision transformers). We define the problem of partition-aware DAG scheduling for mobile heterogeneous inference, illustrating that the best strategy depends on the structure of the inference DAG, thus motivating a j