In this paper, we propose a low complexity turbo receiver for high frequency (HF) skywave massive multiple-input multiple-output (MIMO) systems. We first introduce the beam based channel model (BBCM) with uniform sampling for directional cosine. By leveraging the BBCM, we reveal the interference sparsity of HF skywave massive MIMO systems, which is defined as the asymptotic sparsity of the channel Gram matrix. Exploiting the interference sparsity, we provide a condition of extracting sufficient observation for signal detection. Motivated by this condition, we construct the interference user terminal (UT) set (IUS) and extract the observation vector from the received signal after matched filtering (MF) for each UT. Then, a low-dimensional interference sparsity-aware detector (ISD) is separately designed for each UT by minimizing the mean-squared error (MSE), and the interference sparsity-aware turbo receiver (ISTR) is subsequently formulated using ISDs. Under a relaxed version of the condition for sufficient observation selection, we prove the optimality of the ISTR. Further, we develop an efficient implementation of the ISTR, involving approximate computation of the ISD, the signal reconstructed by ISD and the channel Gram matrix. Moreover, an efficient construction of IUS using the statistical channel state information (CSI) is also proposed. Simulation results confirm that the proposed ISTR achieves excellent performance with relatively low complexity.

Scaling Large Language Model (LLM) training relies on multidimensional parallelism, where High-Bandwidth Domains (HBDs) are critical for communication-intensive parallelism like Tensor Parallelism. However, existing HBD architectures face fundamental limitations in scalability, cost, and fault resiliency: switch-centric HBDs (e.g., NVL-72) incur prohibitive scaling costs, while GPU-centric HBDs (e.g., TPUv3/Dojo) suffer from severe fault propagation. Switch-GPU hybrid HBDs (e.g., TPUv4) take a middle-ground approach, but the fault explosion radius remains large.