Search

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE underutilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9x speedup and 20.3-37.7x energy efficiency boost compared to powerful GPUs. It also rivals the related accelerators by 2.2-3.7x energy efficiency improvement while providing pioneering support for MSDeformAttn., Comment: Accepted to DAC 2024

Non-volatile flip-flops (NVFFs) using power gating techniques promise to overcome the soaring leakage power consumption issue with the scaling of CMOS technology. Magnetic tunnel junction (MTJ) is a good candidate for constructing the NVFF thanks to its low power, high speed, good CMOS compatibility, etc. In this paper, we propose a novel magnetic NVFF based on an emerging memory device called NAND-SPIN. The data writing of NAND-SPIN is achieved by successively applying two unidirectional currents, which respectively generate the spin orbit torque (SOT) and spin transfer torque (STT) for erase and programming operations. This characteristic allows us to design an erase-hidden and drivability-improved magnetic NVFF. Furthermore, more design flexibility could be obtained since the backup operation of the proposed NVFF is not limited by the inherent slave latch. Simulation results show that our proposed NVFF achieves performance improvement in terms of power, delay and area, compared with conventional slave-latch-driven SOT-NVFF designs., Comment: This article has been accepted in a future issue of IEEE Transactions on Nanotechnology: Regular Papers

Lithium metal batteries (LMB) are vital devices for high-energy-density energy storage, but Li metal anode is highly reactive with electrolyte and forms uncontrolled dendrite that can cause undesirable parasitic reactions thus poor cycling stability and raise safety concerns. Despite remarkable progress made to partly solve these issues, the Li metal still plate at the electrode/electrolyte interface where the parasitic reactions and dendrite formation invariably occur. Here we demonstrate the inward-growth plating of Li into a metal foil while avoiding surface deposition, which is driven by the reversible solid-solution based alloy phase change. Lithiation of the solid solution alloy phase facilitates the freshly generated Li atoms at the surface to sink into the foil, while the reversible alloy phase change is companied by the dealloying reaction during delithiation, which extracts Li atoms from inside of the foil. The yielded dendrite free Li anode produces an enhanced Coulombic efficiency of 99.5 plus or minus 0.2% with a reversible capacity of 1660 mA h $g^{-1}$ (3.3 mA h cm$^{-2}$)., Comment: 21 pages, 4 figures

There are two main parts in this manuscript. First, for a Jacobian pair $(f, g)$, with the concept of final major roots and final minor roots, we obtain equations and inequalities for intersection numbers ${\rm I}(f_\xi, g)$ and ${\rm I}(f_\xi, f_y)$ respectively, here, $\xi$ is a generic element of the base field and $f_\xi=f-\xi$ and discuss usage of them in some special cases. Second, we discuss all possibilities of the splits of principle minor roots for the case of degree (99, 66) with help of Abhyankar-Moh planar semigroup, find an unknown possible split and suggest case (99, 66) is open., Comment: 14 pages

The condition of plane polynomial curve to be a line in well-known Abhyankar-Moh Theorem is replaced by weaker ones. A criterion of embedded line is obtained from this strong theorem: Two polynomials can generate the entire polynomial ring iff their derivatives can be generated., Comment: 4 pages