arXiv (All)
open access
Silent Failures at the $2^{32}$ Boundary: A Technical Report on Large-Tensor Matrix Multiplication in PyTorch's Apple MPS Backend
Apple Silicon machines with 192GB or more of unified memory make it routine to place tensors with more than $2^{32}$ elements on a desktop GPU. We show that PyTorch's Metal Performance Shaders (MPS) backend silently returns wrong results for batched matrix multiplication at this scale. On macOS 27.0
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Silent Failures at the $2^{32}$ Boundary: A Technical Report on Large-Tensor Matrix Multiplication in PyTorch's Apple MPS Backend#1028668
- ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts#386840
- From Routing Delay Shifts to Silent Data Corruption: Neutron-Induced SEU Effects in AXI-Based Zynq UltraScale+ MPSoCs#1104737
- On the Limitations of Non-GPU AI Accelerators for Large-Model Inference: A Field Study of MoE and Multimodal Serving on Huawei Ascend#353032
- WingSpan: Concurrency and Dependence for Sparse and Structured Tensor Compilers#677649
Record · ID 1048386
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive