To guarantee the normal operation of next generation portable electronics and wearable devices, together with avoiding electromagnetic wave pollution, it is urgent to find a material possessing flexibility, ultrahigh conductive, and superb electromagnetic interference shielding effectiveness (EMI SE) simultaneously. In this work, inspired by a building bricks toy with the interlock system, we design and fabricate a copper/large flake size graphene (Cu/LG) composite thin film (≈8.8 μm) in the light of high temperature annealing of a large flake size graphene oxide film followed by magnetron sputtering of copper. The obtained Cu/LG thin-film shows ultrahigh thermal conductivity of over 1932.73 (±63.07) W m K and excellent electrical conductivity of 5.88 (±0.29) × 10 S m . Significantly, it also exhibits a remarkably high EMI SE of over 52 dB at the frequency of 1-18 GHz. The largest EMI SE value of 63.29 dB, accorded at 1 GHz, is enough to obstruct and absorb 99.99995% of incident radiation. To the best of knowledge, this is the highest EMI SE performance reported so far in such thin thickness of graphene-based materials. These outstanding properties make Cu/LG film a promising alternative building block for power electronics, microprocessors, and flexible electronics.
Convolutional Neural Networks (CNNs) have begun to permeate all corners of electronic society (from voice recognition to scene generation) due to their high accuracy and machine efficiency per operation. At their core, CNN computations are made up of multi-dimensional dot products between weight and input vectors. This paper studies how weight repetition-when the same weight occurs multiple times in or across weight vectorscan be exploited to save energy and improve performance during CNN inference. This generalizes a popular line of work to improve efficiency from CNN weight sparsity, as reducing computation due to repeated zero weights is a special case of reducing computation due to repeated weights.To exploit weight repetition, this paper proposes a new CNN accelerator called the Unique Weight CNN Accelerator (UCNN). UCNN uses weight repetition to reuse CNN sub-computations (e.g., dot products) and to reduce CNN model size when stored in off-chip DRAM-both of which save energy. UCNN further improves performance by exploiting sparsity in weights. We evaluate UCNN with an accelerator-level cycle and energy model and with an RTL implementation of the UCNN processing element. On three contemporary CNNs, UCNN improves throughputnormalized energy consumption by 1.2× ∼ 4×, relative to a similarly provisioned baseline accelerator that uses Eyeriss-style sparsity optimizations. At the same time, the UCNN processing element adds only 17-24% area overhead relative to the same baseline.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.