Space-filling curves enable platform- and shape-oblivious communication-avoiding matrix multiplication that outperforms vendor libraries by up to 5.5x on CPUs while also accelerating LLM prefill and distributed workloads.
Libxsmm: accelerating small matrix multiplications by runtime code generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple
Space-filling curves enable platform- and shape-oblivious communication-avoiding matrix multiplication that outperforms vendor libraries by up to 5.5x on CPUs while also accelerating LLM prefill and distributed workloads.