Non-Bijunctive Permutation Collapse: AltiVec vec_perm Enables Single-Cycle Attention Path Selection for LLM Inference
Non-Bijunctive Permutation Collapse: AltiVec vec_perm Enables Single-Cycle Attention Path Selection for LLM Inference
We demonstrate that IBM AltiVec's vec_perm instruction performs non-bijective permutations — operations architecturally impossible on modern x86 (AVX-512) and ARM (NEON) SIMD units, which enforce bijective shuffles. Key results: 27–96x operation advantage over x86/ARM for combined prune+amplify attention operations 8.81x inference speedup (16.74 to 147.54 t/s) on IBM POWER8 S824 with TinyLlama 1.1B 30+ permutation patterns benchmarked: hierarchical collapse, multi-head attention, sparse pruning, fractal transforms Hebbian learning connection: hardware-native winner-take-all path selection Integrated into llama.cpp. POWER8's 128 vector registers and SMT8 (128 threads) make it uniquely capable for non-bijunctive AI inference.
Priority: November 2024 (initial vec_perm research), December 2025 (POWER8 integration). Predates DeepSeek Engram (arXiv:2601.07372) by 27+ days. Source code: https://github.com/Scottcjn/ram-coffers Video evidence: https://youtu.be/T_o39s7r0iE (Dec 17, 2025)
POWER8, information collapse, vec_perm, transformer optimization, LLM inference, non-bijective permutation, attention mechanism, Hebbian learning, AltiVec, SIMD architecture, non-bijunctive, sparse attention
POWER8, information collapse, vec_perm, transformer optimization, LLM inference, non-bijective permutation, attention mechanism, Hebbian learning, AltiVec, SIMD architecture, non-bijunctive, sparse attention
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!