Search

Genome analysis has revolutionized fields such as personalized medicine and forensics. Modern sequencing machines generate vast amounts of fragmented strings of genome data called reads. The alignment of these reads into a complete DNA sequence of an organism (the read mapping process) requires extensive data transfer between processing units and memory, leading to execution bottlenecks. Prior studies have primarily focused on accelerating specific stages of the read-mapping task. Conversely, this paper introduces a holistic framework called DART-PIM that accelerates the entire read-mapping process. DART-PIM facilitates digital processing-in-memory (PIM) for an end-to-end acceleration of the entire read-mapping process, from indexing using a unique data organization schema to filtering and read alignment with an optimized Wagner Fischer algorithm. A comprehensive performance evaluation with real genomic data shows that DART-PIM achieves a 5.7x and 257x improvement in throughput and a 92x and 27x energy efficiency enhancement compared to state-of-the-art GPU and PIM implementations, respectively.

The emerging field of DNA storage employs strands of DNA bases (A/T/C/G) as a storage medium for digital information to enable massive density and durability. The DNA storage pipeline includes: (1) encoding the raw data into sequences of DNA bases; (2) synthesizing the sequences as DNA \textit{strands} that are stored over time as an unordered set; (3) sequencing the DNA strands to generate DNA \textit{reads}; and (4) deducing the original data. The DNA synthesis and sequencing stages each generate several independent error-prone duplicates of each strand which are then utilized in the final stage to reconstruct the best estimate for the original strand. Specifically, the reads are first \textit{clustered} into groups likely originating from the same strand (based on their similarity to each other), and then each group approximates the strand that led to the reads of that group. This work improves the DNA clustering stage by embedding it as part of the DNA sequencing. Traditional DNA storage solutions begin after the DNA sequencing process generates discrete DNA reads (A/T/C/G), yet we identify that there is untapped potential in using the raw signals generated by the Nanopore DNA sequencing machine before they are discretized into bases, a process known as \textit{basecalling}, which is done using a deep neural network. We propose a deep neural network that clusters these signals directly, demonstrating superior accuracy, and reduced computation times compared to current approaches that cluster after basecalling.

This paper presents a novel approach to address the constrained coding challenge of generating almost-balanced sequences. While strictly balanced sequences have been well studied in the past, the problem of designing efficient algorithms with small redundancy, preferably constant or even a single bit, for almost balanced sequences has remained unsolved. A sequence is $\varepsilon(n)$-almost balanced if its Hamming weight is between $0.5n\pm \varepsilon(n)$. It is known that for any algorithm with a constant number of bits, $\varepsilon(n)$ has to be in the order of $\Theta(\sqrt{n})$, with $O(n)$ average time complexity. However, prior solutions with a single redundancy bit required $\varepsilon(n)$ to be a linear shift from $n/2$. Employing an iterative method and arithmetic coding, our emphasis lies in constructing almost balanced codes with a single redundancy bit. Notably, our method surpasses previous approaches by achieving the optimal balanced order of $\Theta(\sqrt{n})$. Additionally, we extend our method to the non-binary case considering $q$-ary almost polarity-balanced sequences for even $q$, and almost symbol-balanced for $q=4$. Our work marks the first asymptotically optimal solutions for almost-balanced sequences, for both, binary and non-binary alphabet., Comment: Accepted to The IEEE International Symposium on Information Theory (ISIT) 2024

The execution of deep neural network (DNN) algorithms suffers from significant bottlenecks due to the separation of the processing and memory units in traditional computer systems. Emerging memristive computing systems introduce an in situ approach that overcomes this bottleneck. The non-volatility of memristive devices, however, may expose the DNN weights stored in memristive crossbars to potential theft attacks. Therefore, this paper proposes a two-dimensional permutation-based protection (TDPP) method that thwarts such attacks. We first introduce the underlying concept that motivates the TDPP method: permuting both the rows and columns of the DNN weight matrices. This contrasts with previous methods, which focused solely on permuting a single dimension of the weight matrices, either the rows or columns. While it's possible for an adversary to access the matrix values, the original arrangement of rows and columns in the matrices remains concealed. As a result, the extracted DNN model from the accessed matrix values would fail to operate correctly. We consider two different memristive computing systems (designed for layer-by-layer and layer-parallel processing, respectively) and demonstrate the design of the TDPP method that could be embedded into the two systems. Finally, we present a security analysis. Our experiments demonstrate that TDPP can achieve comparable effectiveness to prior approaches, with a high level of security when appropriately parameterized. In addition, TDPP is more scalable than previous methods and results in reduced area and power overheads. The area and power are reduced by, respectively, 1218$\times$ and 2815$\times$ for the layer-by-layer system and by 178$\times$ and 203$\times$ for the layer-parallel system compared to prior works., Comment: 14 pages, 11 figures

Digital processing-in-memory (PIM) architectures mitigate the memory wall problem by facilitating parallel bitwise operations directly within the memory. Recent works have demonstrated their algorithmic potential for accelerating data-intensive applications; however, there remains a significant gap in the programming model and microarchitectural design. This is further exacerbated by aspects unique to memristive PIM such as partitions and operations across both directions of the memory array. To address this gap, this paper provides an end-to-end architectural integration of digital memristive PIM from a high-level Python library for tensor operations (similar to NumPy and PyTorch) to the low-level microarchitectural design. We begin by proposing an efficient microarchitecture and instruction set architecture (ISA) that bridge the gap between the low-level control periphery and an abstraction of PIM parallelism. We subsequently propose a PIM development library that converts high-level Python to ISA instructions and a PIM driver that translates ISA instructions into PIM micro-operations. We evaluate PyPIM via a cycle-accurate simulator on a wide variety of benchmarks that both demonstrate the versatility of the Python library and the performance compared to theoretical PIM bounds. Overall, PyPIM drastically simplifies the development of PIM applications and enables the conversion of existing tensor-oriented Python programs to PIM with ease., Comment: Accepted to the 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)

Binary compositions of surface ligands are known to improve the colloidal stability and fluorescence quantum yield of nanocrystals (NCs), due to ligand-ligand interactions and surface organization. Herein, we follow the thermodynamics of a ligand exchange reaction of CdSe NCs with alkylthiols mixtures. The effects of ligand polarity and length difference on ligand packing were investigated using isothermal titration calorimetry (ITC). The thermodynamic signature of the formation of mixed ligand shells was observed. Correlating the experimental results with thermodynamic mixing models has allowed us to calculate the inter-chain interactions and infer the final ligand shell configuration. Our findings demonstrate that the small dimensions of the NCs and the subsequent increased interfacial region between dissimilar ligands, in contrast to macroscopic surfaces, allow the formation of a myriad of clustering patterns, controlled by the inter-ligand interactions. This work provides a fundamental understanding of the parameters determining the ligand shell structure and should help guide smart surface design toward NC-based applications., Comment: 28 pages, 4 figures; combines with SI file 24 pages, 14 figures, 9 tables

Processing-in-memory (PIM) architectures are emerging to reduce data movement in data-intensive applications. These architectures seek to exploit the same physical devices for both information storage and logic, thereby dwarfing the required data transfer and utilizing the full internal memory bandwidth. Whereas analog PIM utilizes the inherent connectivity of crossbar arrays for approximate matrix-vector multiplication in the analog domain, digital PIM architectures enable bitwise logic operations with massive parallelism across columns of data within memory arrays. Several recent works have extended the computational capabilities of digital PIM architectures towards the full-precision (single-precision floating-point) acceleration of convolutional neural networks (CNNs); yet, they lack a comprehensive comparison to GPUs. In this paper, we examine the potential of digital PIM for CNN acceleration through an updated quantitative comparison with GPUs, supplemented with an analysis of the overall limitations of digital PIM. We begin by investigating the different PIM architectures from a theoretical perspective to understand the underlying performance limitations and improvements compared to state-of-the-art hardware. We then uncover the tradeoffs between the different strategies through a series of benchmarks ranging from memory-bound vectored arithmetic to CNN acceleration. We conclude with insights into the general performance of digital PIM architectures for different data-intensive applications.

The Discrete Fourier Transform (DFT) is essential for various applications ranging from signal processing to convolution and polynomial multiplication. The groundbreaking Fast Fourier Transform (FFT) algorithm reduces DFT time complexity from the naive O(n^2) to O(n log n), and recent works have sought further acceleration through parallel architectures such as GPUs. Unfortunately, accelerators such as GPUs cannot exploit their full computing capabilities as memory access becomes the bottleneck. Therefore, this paper accelerates the FFT algorithm using digital Processing-in-Memory (PIM) architectures that shift computation into the memory by exploiting physical devices capable of storage and logic (e.g., memristors). We propose an O(log n) in-memory FFT algorithm that can also be performed in parallel across multiple arrays for high-throughput batched execution, supporting both fixed-point and floating-point numbers. Through the convolution theorem, we extend this algorithm to O(log n) polynomial multiplication - a fundamental task for applications such as cryptography. We evaluate FourierPIM on a publicly-available cycle-accurate simulator that verifies both correctness and performance, and demonstrate 5-15x throughput and 4-13x energy improvement over the NVIDIA cuFFT library on state-of-the-art GPUs for FFT and polynomial multiplication.

Constrained coding is a fundamental field in coding theory that tackles efficient communication through constrained channels. While channels with fixed constraints have a general optimal solution, there is increasing demand for parametric constraints that are dependent on the message length. Several works have tackled such parametric constraints through iterative algorithms, yet they require complex constructions specific to each constraint to guarantee convergence through monotonic progression. In this paper, we propose a universal framework for tackling any parametric constrained-channel problem through a novel simple iterative algorithm. By reducing an execution of this iterative algorithm to an acyclic graph traversal, we prove a surprising result that guarantees convergence with efficient average time complexity even without requiring any monotonic progression. We demonstrate the effectiveness of this universal framework by applying it to a variety of both local and global channel constraints. We begin by exploring the local constraints involving illegal substrings of variable length, where the universal construction essentially iteratively replaces forbidden windows. We apply this local algorithm to the minimal periodicity, minimal Hamming weight, local almost-balanced Hamming weight and the previously-unsolved minimal palindrome constraints. We then continue by exploring global constraints, and demonstrate the effectiveness of the proposed construction on the repeat-free encoding, reverse-complement encoding, and the open problem of global almost-balanced encoding. For reverse-complement, we also tackle a previously-unsolved version of the constraint that addresses overlapping windows. Overall, the proposed framework generates state-of-the-art constructions with significant ease while also enabling the simultaneous integration of multiple constraints for the first time.

DNA sequence classification is a fundamental task in computational biology with vast implications for applications such as disease prevention and drug design. Therefore, fast high-quality sequence classifiers are significantly important. This paper introduces ClaPIM, a scalable DNA sequence classification architecture based on the emerging concept of hybrid in-crossbar and near-crossbar memristive processing-in-memory (PIM). We enable efficient and high-quality classification by uniting the filter and search stages within a single algorithm. Specifically, we propose a custom filtering technique that drastically narrows the search space and a search approach that facilitates approximate string matching through a distance function. ClaPIM is the first PIM architecture for scalable approximate string matching that benefits from the high density of memristive crossbar arrays and the massive computational parallelism of PIM. Compared with Kraken2, a state-of-the-art software classifier, ClaPIM provides significantly higher classification quality (up to 20x improvement in F1 score) and also demonstrates a 1.8x throughput improvement. Compared with EDAM, a recently-proposed SRAM-based accelerator that is restricted to small datasets, we observe both a 30.4x improvement in normalized throughput per area and a 7% increase in classification precision.

It has been previously shown (Phys. Rev. E 66, 066305, 2002) that a non-rotating turbulent convection with nonuniform large-scale flows contributes to the turbulent heat flux. As a result, the turbulent heat flux depends explicitly not only on the gradients of the large-scale temperature, but it also depends on the gradients of the large-scale velocity. This is because the nonuniform large-scale flows produce anisotropic velocity fluctuations which modify the turbulent heat flux. This effect causes an excitation of a convective-wind instability and formation of large-scale semi-organised coherent structures (large-scale convective cells). We perform mean-field numerical simulations of shear-free convection which take into account the modification of the turbulent heat flux by nonuniform large-scale flows. The redistribution of the turbulent heat flux by the nonuniform large-scale motions in turbulent convection plays a crucial role in the formation of the large-scale semi-organised coherent structures. This effect results in a strong reduction of the critical effective Rayleigh number (based on the eddy viscosity and turbulent temperature diffusivity) required for the formation of the large-scale convective cells. The convective-wind instability is excited when the scale separation ratio between the height of the convective layer and the integral turbulence scale is large. The level of the mean kinetic energy at saturation increases with the scale separation ratio. Inside the large-scale convective cells, there are local regions with the positive vertical gradient of the potential temperature which implies that these regions are stably stratified., Comment: 13 pages, 14 figures, revtex4-2

The emerging memristive Memory Processing Unit (mMPU) overcomes the memory wall through memristive devices that unite storage and logic for real processing-in-memory (PIM) systems. At the core of the mMPU is stateful logic, which is accelerated with memristive partitions to enable logic with massive inherent parallelism within crossbar arrays. This paper vastly accelerates the fundamental operations of matrix-vector multiplication and convolution in the mMPU, with either full-precision or binary elements. These proposed algorithms establish an efficient foundation for large-scale mMPU applications such as neural-networks, image processing, and numerical methods. We overcome the inherent asymmetry limitation in the previous in-memory full-precision matrix-vector multiplication solutions by utilizing techniques from block matrix multiplication and reduction. We present the first fast in-memory binary matrix-vector multiplication algorithm by utilizing memristive partitions with a tree-based popcount reduction (39x faster than previous work). For convolution, we present a novel in-memory input-parallel concept which we utilize for a full-precision algorithm that overcomes the asymmetry limitation in convolution, while also improving latency (2x faster than previous work), and the first fast binary algorithm (12x faster than previous work).

Digital processing-in-memory (PIM) architectures are rapidly emerging to overcome the memory-wall bottleneck by integrating logic within memory elements. Such architectures provide vast computational power within the memory itself in the form of parallel bitwise logic operations. We develop novel algorithmic techniques for PIM that, combined with new perspectives on computer arithmetic, extend this bitwise parallelism to the four fundamental arithmetic operations (addition, subtraction, multiplication, and division), for both fixed-point and floating-point numbers, and using both bit-serial and bit-parallel approaches. We propose a state-of-the-art suite of arithmetic algorithms, demonstrating the first algorithm in the literature of digital PIM for a majority of cases - including cases previously considered impossible for digital PIM, such as floating-point addition. Through a case study on memristive PIM, we compare the proposed algorithms to an NVIDIA RTX 3070 GPU and demonstrate significant throughput and energy improvements., Comment: Accepted to IEEE Transactions on Emerging Topics in Computing (TETC)

Digital memristive processing-in-memory overcomes the memory wall through a fundamental storage device capable of stateful logic within crossbar arrays. Dynamically dividing the crossbar arrays by adding memristive partitions further increases parallelism, thereby overcoming an inherent trade-off in memristive processing-in-memory. The algorithmic topology of partitions is highly unique, and was recently exploited to accelerate multiplication (11x with 32 partitions) and sorting (14x with 16 partitions). Yet, the physical implementation of memristive partitions, such as the peripheral decoders and the control message, has never been considered and may lead to vast impracticality. This paper overcomes that challenge with several novel techniques, presenting efficient practical designs of memristive partitions. We begin by formalizing the algorithmic properties of memristive partitions into serial, parallel, and semi-parallel operations. Peripheral overhead is addressed via a novel technique of half-gates that enables efficient decoding with negligible overhead. Control overhead is addressed by carefully reducing the operation set of memristive partitions, while resulting in negligible performance impact, by utilizing techniques such as shared indices and pattern generators. Ultimately, these efficient practical solutions, combined with the vast algorithmic potential, may revolutionize digital memristive processing-in-memory.

Aligning the entire genome of an organism is a compute-intensive task. Pre-alignment filters substantially reduce computation complexity by filtering potential alignment locations. The base-count filter successfully removes over 68% of the potential locations through a histogram-based heuristic. This paper presents FiltPIM, an efficient design of the basecount filter that is based on memristive processing-in-memory. The in-memory design reduces CPU-to-memory data transfer and utilizes both intra-crossbar and inter-crossbar memristive stateful-logic parallelism. The reduction in data transfer and the efficient stateful-logic computation together improve filtering time by 100x compared to a CPU implementation of the filter., Comment: Published in 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS)

Recent research has sought to accelerate cryptographic hash functions as they are at the core of modern cryptography. Traditional designs, however, suffer from the von Neumann bottleneck that originates from the separation of processing and memory units. An emerging solution to overcome this bottleneck is processing-in-memory (PIM): performing logic within the same devices responsible for memory to eliminate data-transfer and simultaneously provide massive computational parallelism. In this paper, we seek to vastly accelerate the state-of-the-art SHA-3 cryptographic function using the memristive memory processing unit (mMPU), a general-purpose memristive PIM architecture. To that end, we propose a novel in-memory algorithm for variable rotation, and utilize an efficient mapping of the SHA-3 state vector for memristive crossbar arrays to efficiently exploit PIM parallelism. We demonstrate a massive energy efficiency of 1,422 Gbps/W, improving a state-of-the-art memristive SHA-3 accelerator (SHINE-2) by 4.6x., Comment: Accepted to International Conference on Modern Circuits and Systems Technologies (MOCAST) 2022

Reliability is an inherent challenge for the emerging nonvolatile technology of racetrack memories, and there exists a fundamental relationship between codes designed for racetrack memories and codes with constrained periodicity. Previous works have sought to construct codes that avoid periodicity in windows, yet have either only provided existence proofs or required high redundancy. This paper provides the first constructions for avoiding periodicity that are both efficient (average-linear time) and with low redundancy (near the lower bound). The proposed algorithms are based on iteratively repairing windows which contain periodicity until all the windows are valid. Intuitively, such algorithms should not converge as there is no monotonic progression; yet, we prove convergence with average-linear time complexity by exploiting subtle properties of the encoder. Overall, we both provide constructions that avoid periodicity in all windows, and we also study the cardinality of such constraints., Comment: Accepted to The International Symposium on Information Theory and Its Applications (ISITA) 2022