Roman Kaplan
Roman Kaplan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Leonid Yavits
EnICS Labs, Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel
6 shared publications - Ran Ginosar
Technion Israel Institute of Technology Faculty of Electrical Engineering: Technion Israel Institute of Technology The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering
5 shared publications - Harley I. Kornblum
Department of Psychiatry and Human Behavior, University of California, Los Angeles , Los Angeles, CA 90095
1 shared publication - Jeff M. Bronstein
Department of Neurology, David Geffen School of Medicine at UCLA, Los Angeles, USA
1 shared publication Ran Ginosar
1 shared publication- Seema Kaushalya Tiwari-Woodruff
University of California Riverside, Riverside, USA
1 shared publication
Latest Publications
- Open Access
BioSEAL: In-Memory Biological Sequence Alignment Accelerator for Large-Scale Genomic Data
Genome sequences contain hundreds of millions of DNA base pairs. Finding the degree of similarity between two genomes requires executing a compute-intensive dynamic programming algorithm, such as Smith-Waterman. Traditional von Neumann architectures have limited parallelism and cannot provide an efficient solution for large-scale genomic data. Approximate heuristic methods (e.g. BLAST) are commonly used. However, they are suboptimal and still compute-intensive. In this work, we present BioSEAL, a Biological SEquence ALignment accelerator. BioSEAL is a massively parallel non-von Neumann processing-in-memory architecture for large-scale DNA and protein sequence alignment. BioSEAL is based on resistive content addressable memory, capable of energy-efficient and high-performance associative processing. We present an associative processing algorithm for entire database sequence alignment on BioSEAL and compare its performance and power consumption with state-of-art solutions. We show that BioSEAL can achieve up to 57x speedup and 156x better energy efficiency, compared with existing solutions for genome sequence alignment and protein sequence database search.
Open AccessBioSEAL: In-Memory Biological Sequence Alignment Accelerator for Large-Scale Genomic Data
Genome sequences contain hundreds of millions of DNA base pairs. Finding the degree of similarity between two genomes requires executing a compute-intensive dynamic programming algorithm, such as Smith-Waterman. Traditional von Neumann architectures have limited parallelism and cannot provide an efficient solution for large-scale genomic data. Approximate heuristic methods (e.g. BLAST) are commonly used. However, they are suboptimal and still compute-intensive. In this work, we present BioSEAL, a Biological SEquence ALignment accelerator. BioSEAL is a massively parallel non-von Neumann processing-in-memory architecture for large-scale DNA and protein sequence alignment. BioSEAL is based on resistive content addressable memory, capable of energy-efficient and high-performance associative processing. We present an associative processing algorithm for entire database sequence alignment on BioSEAL and compare its performance and power consumption with state-of-art solutions. We show that BioSEAL can achieve up to 57x speedup and 156x better energy efficiency, compared with existing solutions for genome sequence alignment and protein sequence database search.
- 28 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 39 (4) , 44-54
RASSA: Resistive Prealignment Accelerator for Approximate DNA Long Read Mapping
DNA read mapping is a computationally expensive bioinformatics task, required for genome assembly and consensus polishing. It requires to find the best-fitting location for each DNA read on a long reference sequence. A novel resistive approximate similarity search accelerator, RASSA, exploits charge distribution and parallel in-memory processing to reflect a mismatch count between DNA sequences. RASSA implementation of DNA long read pre-alignment outperforms the state-of-art solution, minimap2, by 16-77x with comparable accuracy and provides two orders of magnitude higher throughput than GateKeeper, a short-read pre-alignment hardware architecture implemented in FPGA.
- 28 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 39 (4) , 44-54
RASSA: Resistive Prealignment Accelerator for Approximate DNA Long Read Mapping
DNA read mapping is a computationally expensive bioinformatics task, required for genome assembly and consensus polishing. It requires to find the best-fitting location for each DNA read on a long reference sequence. A novel resistive approximate similarity search accelerator, RASSA, exploits charge distribution and parallel in-memory processing to reflect a mismatch count between DNA sequences. RASSA implementation of DNA long read pre-alignment outperforms the state-of-art solution, minimap2, by 16-77x with comparable accuracy and provides two orders of magnitude higher throughput than GateKeeper, a short-read pre-alignment hardware architecture implemented in FPGA.
- Open Access
AIDA: Associative DNN Inference Accelerator
We propose AIDA, an inference engine for accelerating fully-connected (FC) layers of Deep Neural Network (DNN). AIDA is an associative in-memory processor, where the bulk of data never leaves the confines of the memory arrays, and processing is performed in-situ. AIDA area and energy efficiency strongly benefit from sparsity and lower arithmetic precision. We show that AIDA outperforms the state of art inference accelerator, EIE, by 14.5x (peak performance) and 2.5x (throughput).
Open AccessAIDA: Associative DNN Inference Accelerator
We propose AIDA, an inference engine for accelerating fully-connected (FC) layers of Deep Neural Network (DNN). AIDA is an associative in-memory processor, where the bulk of data never leaves the confines of the memory arrays, and processing is performed in-situ. AIDA area and energy efficiency strongly benefit from sparsity and lower arithmetic precision. We show that AIDA outperforms the state of art inference accelerator, EIE, by 14.5x (peak performance) and 2.5x (throughput).
- 27 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 38 (5) , 32-40
Enabling Full Associativity with Memristive Address Decoder
Address decoders are typically built using regular logic gates. A novel Memristive Perfect Induction gate replaces standard NAND, allowing for storing the address alongside data and comparing it to the input address, thus transforming the address decoder into CAM and enabling fully associative access. Applications include fully associative TLB, cache, and virtually addressable memory.
- 27 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 38 (5) , 32-40
Enabling Full Associativity with Memristive Address Decoder
Address decoders are typically built using regular logic gates. A novel Memristive Perfect Induction gate replaces standard NAND, allowing for storing the address alongside data and comparing it to the input address, thus transforming the address decoder into CAM and enabling fully associative access. Applications include fully associative TLB, cache, and virtually addressable memory.
- 30 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanotechnology
- Vol. 17 (5) , 889-896
PRINS: Processing-in-Storage Acceleration of Machine Learning
Machine learning algorithms have become a major tool in various applications. The high performance requirements on large-scale datasets pose a challenge for traditional von Neumann architectures. We present two machine learning implementations and evaluations on PRINS, a novel processing-in-storage system based on Resistive Content Addressable Memory (ReCAM). PRINS functions simultaneously as a storage and a massively parallel associative processor. PRINS processing-in-storage resolves the bandwidth wall faced by near-data von Neumann architectures, such as 3D DRAM and CPU stack or SSD with embedded CPU, by keeping the computing inside the storage arrays, thus implementing in-data, rather than near-data, processing. We show that PRINS based processing-in-storage architecture may outperform existing in-storage designs and accelerator based designs. Multiple performance comparisons for the ReCAM processing-in-storage implementations of K-means and K-nearest neighbors are performed. Compared platforms include CPU, GPU, FPGA and Automata Processor. We show that PRINS may achieve an order-of-magnitude speedup and improved power efficiency relative to all compared platforms.
- 30 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanotechnology
- Vol. 17 (5) , 889-896
PRINS: Processing-in-Storage Acceleration of Machine Learning
Machine learning algorithms have become a major tool in various applications. The high performance requirements on large-scale datasets pose a challenge for traditional von Neumann architectures. We present two machine learning implementations and evaluations on PRINS, a novel processing-in-storage system based on Resistive Content Addressable Memory (ReCAM). PRINS functions simultaneously as a storage and a massively parallel associative processor. PRINS processing-in-storage resolves the bandwidth wall faced by near-data von Neumann architectures, such as 3D DRAM and CPU stack or SSD with embedded CPU, by keeping the computing inside the storage arrays, thus implementing in-data, rather than near-data, processing. We show that PRINS based processing-in-storage architecture may outperform existing in-storage designs and accelerator based designs. Multiple performance comparisons for the ReCAM processing-in-storage implementations of K-means and K-nearest neighbors are performed. Compared platforms include CPU, GPU, FPGA and Automata Processor. We show that PRINS may achieve an order-of-magnitude speedup and improved power efficiency relative to all compared platforms.
- Open Access
A Resistive CAM Processing-in-Storage Architecture for DNA Sequence Alignment
A novel processing-in-storage (PRinS) architecture based on Resistive CAM (ReCAM) is described and proposed for Smith-Waterman (S-W) sequence alignment. The ReCAM massively-parallel compare operation finds matching base-pairs in a fixed number of cycles, regardless of sequence length. The ReCAM PRinS S-W algorithm is simulated and compared to FPGA, Xeon Phi and GPU-based implementations, showing at least 4.7x higher throughput and at least 15x lower power dissipation.
Open AccessA Resistive CAM Processing-in-Storage Architecture for DNA Sequence Alignment
A novel processing-in-storage (PRinS) architecture based on Resistive CAM (ReCAM) is described and proposed for Smith-Waterman (S-W) sequence alignment. The ReCAM massively-parallel compare operation finds matching base-pairs in a fixed number of cycles, regardless of sequence length. The ReCAM PRinS S-W algorithm is simulated and compared to FPGA, Xeon Phi and GPU-based implementations, showing at least 4.7x higher throughput and at least 15x lower power dissipation.
- 20 May 2004
- Published by Wiley in Journal of Neuroscience Research
- Vol. 77 (2) , 166-173
Developmental expression of OAP‐1/Tspan‐3, a member of the tetraspanin superfamily
OSP/claudin‐11‐associated protein (OAP‐1/Tspan‐3), originally isolated by yeast two‐hybrid screening using OSP/claudin‐11 (oligodendrocyte‐specific protein) as bait, is a member of the tetraspanin superfamily and OAP‐1/Tspan‐3, OSP/claudin‐11, and β1 integrin form a protein complex that seems to be involved in oligodendrocyte proliferation and migration. This study investigated the temporal and regional expression, glycosylation status, and tissue distribution of OAP‐1/Tspan‐3. OAP‐1/Tspan‐3 mRNA was expressed as a single transcript throughout brain development, with high levels of expression in the germinal zones. OAP‐1/Tspan‐3 protein contains N‐terminal glycosylation sites in extracellular loop 2 and deglycosylation studies indicated a decrease in apparent molecular weight of OAP‐1/Tspan‐3, consistent with removal of N‐glycans. Similar to OSP/claudin‐11, OAP‐1/Tspan‐3 is expressed in all stages of oligodendrocyte development and in the myelin sheath. Unlike OSP/claudin‐11, however, it is expressed in all cell types tested in the central nervous system (CNS), including neurons and astrocytes. The association of OAP‐1/Tspan‐3 with OSP/claudin‐11 and β1 integrin, its subcellular distribution as a cell surface, membrane‐spanning glycoprotein, and its widespread distribution supports its potential role in cell migration, proliferation, and interactions between cells and extracellular matrix.
- 20 May 2004
- Published by Wiley in Journal of Neuroscience Research
- Vol. 77 (2) , 166-173
Developmental expression of OAP‐1/Tspan‐3, a member of the tetraspanin superfamily
OSP/claudin‐11‐associated protein (OAP‐1/Tspan‐3), originally isolated by yeast two‐hybrid screening using OSP/claudin‐11 (oligodendrocyte‐specific protein) as bait, is a member of the tetraspanin superfamily and OAP‐1/Tspan‐3, OSP/claudin‐11, and β1 integrin form a protein complex that seems to be involved in oligodendrocyte proliferation and migration. This study investigated the temporal and regional expression, glycosylation status, and tissue distribution of OAP‐1/Tspan‐3. OAP‐1/Tspan‐3 mRNA was expressed as a single transcript throughout brain development, with high levels of expression in the germinal zones. OAP‐1/Tspan‐3 protein contains N‐terminal glycosylation sites in extracellular loop 2 and deglycosylation studies indicated a decrease in apparent molecular weight of OAP‐1/Tspan‐3, consistent with removal of N‐glycans. Similar to OSP/claudin‐11, OAP‐1/Tspan‐3 is expressed in all stages of oligodendrocyte development and in the myelin sheath. Unlike OSP/claudin‐11, however, it is expressed in all cell types tested in the central nervous system (CNS), including neurons and astrocytes. The association of OAP‐1/Tspan‐3 with OSP/claudin‐11 and β1 integrin, its subcellular distribution as a cell surface, membrane‐spanning glycoprotein, and its widespread distribution supports its potential role in cell migration, proliferation, and interactions between cells and extracellular matrix.