The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction Cost
cs.AR, cs.AI, cs.PF
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (Sep 3rd version)
- Ozaki Scheme II: A GEMM-oriented emulation of floating-point matrix multiplication using an integer modular technique
- Double-Precision Matrix Multiplication Emulation via Ozaki-II Scheme with FP8 Quantization
- Guaranteed DGEMM Accuracy While Using Reduced Precision Tensor Cores Through Extensions of the Ozaki Scheme
Related papers
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
- PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
- Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster
- Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy