LP-GEMM decomposes GEMM operations to propagate packing layouts across dependent calls, cutting redundant data movement while keeping full BLAS compatibility.
Towards optimized tensor code generation for deep learning on sunway many-core processor
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
-
LP-GEMM: Integrating Layout Propagation into GEMM Operations
LP-GEMM decomposes GEMM operations to propagate packing layouts across dependent calls, cutting redundant data movement while keeping full BLAS compatibility.