Reconfigurable Supercomputing with Scalable Systolic Arrays and In-Stream Control for Wavefront Genomics Processing

Size: px
Start display at page:

Download "Reconfigurable Supercomputing with Scalable Systolic Arrays and In-Stream Control for Wavefront Genomics Processing"

Transcription

1 Reconfigurable Supercomputing with Scalable Systolic rrays and In-Stream ontrol for Wavefront enomics Processing SP 1 uesday, July 13, 21. Pascoe (speaker),. Lawande,. Lam,. eorge NSF enter for igh-performance Reconfigurable omputing (RE), University of Florida Y. Sun, W. Farmerie Interdisciplinary enter for Biotechnology Research (IBR), University of Florida M. erbordt epartment of Electrical and omputer Engineering, Boston University

2 Motivation Impending roadblock in health-sciences research urrent-generation sequencing technology capable of producing millions of sequences per day Next-generation sequencing instruments poised to increase production more than 1-fold onventional sequence-analysis processing has not kept pace with raw sequence production Objective: evelop sustainable solution for increasing performance of sequence-analysis applications pproach: evelop in-stream control approach for systolic array to maximize hardware acceleration apitalize on reconfigurable computing at scale to achieve sustainable supercomputing performance 2

3 Presentation Outline Background Sequential Score alculation Backtrack to Produce String Representation Sequence-lignment cceleration ommon ardware cceleration echniques Sequence-lignment cceleration Issues Scalable Systolic rrays with In-Stream ontrol emonstration of In-Stream ontrol: ase Studies Needleman-Wunsch (NW) Smith-Waterman (SW) Needle-istance (N) Novo- System rchitecture iel PROStar-III Boards NW/SW/N Performance Evaluation on Novo- onclusions Q& 3

4 Background: Sequence-lignment Example Sequence S 1 : Sequence S 2 : Want to quantify similarity between S 1 and S 2 Use NW or SW or other algorithms to align sequences S( i, j) max S( i 1, j S( i ( i 1) Sub( i, 1, j) eog 1, j) e j) ( i, ( i, j) j) max max S( i ( i S( i, ( i, j j 1, j) 1, j) 1) 1) og eg og eg S( i, j ( i, j 1) 1) eog e S(, i) (, i) S( i,) ( i,) og og i eg for 1 i imax, 1 j jmax Sub( i, j) penalty matrix Needleman-Wunsch Equations 4

5 5 Sequential Score alculation Score alculation --- match = 5, mismatch =, ogap =, egap = S1 S2

6 6 Backtrack to Produce String Representation _ S1 S2

7 7 Sequence-lignment cceleration S1 S2 Score alculation --- match = 5, mismatch =, ogap =, egap = -.5

8 ommon ardware cceleration echniques onstruct systolic array of processing elements (PEs) to exploit parallelism Each PE responsible for calculating single column of scoring matrix O(X Y) time complexity in software reduced to O(X+Y) in hardware S(i max,) S(i-1,j-1) + Sub(i,j) S(i-1,j) + eog Max (i-1,j) + e S(,j max ) omputation of ell Score S(i max,j max ) } } S(i,j-1) + eog Exploit Parallelism along nti-diagonal (i,j-1) + e } 8

9 Sequence-lignment cceleration Issues Maximum possible performance directly proportional to: Number of PEs Operating clock frequency (e.g. 1 PEs x 1Mz = 1 UPS) iga ell Updates Per Second chieved performance can be much less due to overhead: Input data manipulation Input data transfer to FP FP initialization and setup atapath initialization PE configuration esign goals: Eliminate or overlap overhead with useful work Pipeline latency andshaking control between FP/PU Output data transfer to PU Output data manipulation Others Minimizing PE area to maximize the number of PEs per FP 9

10 Scalable Systolic rrays with In-Stream ontrol Worst-case Performance Low-area Overhead N (setup time + pipeline latency + PU/FP handshake + PE configuration time + time to record results + time to process streamed sequence) Best-case Performance igh-area Overhead pipeline latency + N (time to process streamed sequence) With In-Stream ontrol Near-best-case Performance Low-area Overhead pipeline latency + M (PE configuration + 2 clock cycles) + N (time to process streamed sequence + 2 clock cycles) Replace complex state machines and other supporting logic with control data inserted directly into data stream Signal state transitions rigger complex actions on application data Limit wasted cycles Reduce PE area Increase hardware utilization ssuming N successive alignments and M PE reconfigurations omplex-controller performance with simple-controller overhead 1

11 In-Stream ontrol: Needleman-Wunsch Needleman-Wunsch (NW) used for global sequence alignment onventional systolic-array architecture With simple PEs and simple control Input sequences consist of standard nucleotide alphabet (,,,, N) 3-bit encoding: dd 3 additional control characters (total of 8 characters): (L) load query, (R) reset to initial conditions, (P) push results Special 2-character sequence PN used to signal end of stream 11

12 In-Stream ontrol for NW: Simple Example Example set of short sequences: {,, N, N} ssume it is desired to perform NW between each unique sequence pair in set: (i.e. 1-2, 1-3, 1, 2-3, 2, and 3) Stream encoding LRPRNPRNPLR NPRNPLNRNPN fter (5 + pipeline length) FP clock cycles, the six results are ready for retrieval when PU has free cycles 12

13 In-Stream ontrol for NW: Summary Introduces notion of local control ontrol characters used as framing characters for each loaded or streamed sequence Simultaneously: PEs in pipeline between an L and R can be reconfiguring Earlier group of PEs between an R and P can be processing a query Even earlier group is doing something else Simplifies control: Meaningful outputs result from correct sequence of characters passing through systolic array No need for control signals from controller and PU Benefit: ost? Limits PE idle periods Reduces configuration overhead between runs Reduces PE area Only two additional clock cycles of overhead per sequence to process framing characters 13

14 In-Stream ontrol: Smith-Waterman From Prev. FP o FIFO Input Buffer Input FIFO Interface PE(1) PE(2) PE(N) Output Buffer Output FIFO Interface FIFO o Next FP SRM (atabase) Optimized for Short Sequences vs. Large atabase Smith-Waterman (SW) used for local sequence alignment Use NW control structure as basis then modify to add functionalities Switching between query and database stream Requires overloaded L character to toggle between streams Loading multiple queries against a single streamed database Introduce concept of push window and add extra bit to PU stream encoding for controlling query start and query extend modes Providing traceback (string representation of alignment) No changes to encoding scheme, modification to supporting software control Extending queries across multiple FPs No changes to encoding scheme, modification to supporting software control 14

15 In-Stream ontrol for SW: Simple Example Example set of short sequences: {,, N, N} ssume it is desired to perform SW between each sequence and a large database atabase Stream (3bit) Encoding: R PPPPL Query Stream (4bit) Encoding: (L)(1)()()()(1)()()(1)()(N) ()(1)(N)()()(R)(L)(P)(N) fter (2 + database length + pipeline length) FP clock cycles, the 4 results are ready for retrieval when PU has free cycles From Prev. FP o FIFO Input Buffer Input FIFO Interface SRM (atabase) PE(1) PE(2) PE(N) Output Buffer Output FIFO Interface FIFO o Next FP 15

16 In-Stream ontrol: Needle-istance Needle-istance (N) used for calculating optimal pairwise distance Original Software: 1. alculate NW score 2. enerate string representation 3. alculate custom normalized edit distance ardware: Score and distance calculations performed in parallel Eliminate computation of string representation Edit distance: = 2 otal distance: = 1 Normalized edit distance: 2/1 =.2 N PEs implemented by adding distance calculation modules to PEs of NW 16

17 Novo- System rchitecture 24+1 Linux servers in cluster 24 compute servers (2 boards/server) 1 head-node server for management 2 b/s non-blocking InfiniBand 1 b/s Ethernet 26 (24+2) quad-core Xeons Max. system power of ~8 KW 48 quad-fp boards iel PIe x8 PROStar-III Embedded-style boards, for both PE- & P-oriented research 4¼ B R2 attached to each FP ~ 1 B total RM in Novo- 192 Stratix-III E26 FPs Each ltera FP with x18 multipliers, 254K logic elements, 24K registers, & max. power ~18W Novo is Latin, "to make anew, refresh, revive, change, alter," essence of R; is for enesis or reen. 17

18 iel PROStar-III Board (one of 48) J for Signalap debug 2 2B = 4B R2 RM per FP 12.8 mm PIe x8 interface (4B/s) iel PROStarIII Board ypical frequencies 1-325Mz M channels 32 R2 module slots 8 NOE: iel developed multiboard interconnect; stream apps 312 across mm multiple PS-III boards within servers ltera Stratix-III E26 FP 254,4 Logic Elements 768 multipliers (18 18) 14,688 Kbits of embedded memory 5% less power than Stratix-II 65nm technology 18

19 Speedup verage Sequence Length (Nucleotides) Needleman-Wunsch Performance Evaluation on Novo- NW PEs/FP Baseline: , length 85 Sequence omparisons Software Runtime: 11,26 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 47, ,14 3, , , (est.) ,13 Scaling performance with varying number of FPs under optimal input conditions K 4K 16K 256K 1M 4M Number of Sequence omparisons Performance of single FP under varying input conditions 16M 32M NW UPS chieved/max 17,24/2,4 = 85% 19

20 Speedup atabase Length (Nucleotides) Speedup vg. Sequence Length (Nucleotides) SW/N Performance Evaluation on Novo- SW 65 PEs/FP 45 PEs/FP N verage Sequence Length (Nucleotides) 1K 64M 4M 256K 16K K 4K 16K 64K 256K 1M 4M 16M Number of Sequence omparisons Baseline: uman X hromosome v 192, length 65 Seqs Software Runtime: 5,481 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 23, ,966 3, , , (est.) ,366 SW UPS chieved/max 15,158/15,6 = 97% 2 Baseline: , length 45 istance alculations Software Runtime: 11,673 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 13,522 3,18 4 3,429 12, , , (est.) ,751 N UPS chieved/max 8,471/1,8 = 78%

21 onclusions eveloped in-stream control approach for systolic array to maximize hardware acceleration apitalized on reconfigurable computing at scale to achieve sustainable supercomputing performance emonstrated performance and sustainability results on Novo-: Baseline: , length 85 Sequence omparisons Software Runtime: 11,26 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 47, ,14 3, , , (est.) ,13 Baseline: uman X hromosome v 192, length 65 Seqs Software Runtime: 5,481 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 23, ,966 3, , , (est.) ,366 Baseline: , length 45 istance alculations Software Runtime: 11,673 PU hours on 2.4z Opteron # FPs Runtime (sec) Speedup 1 13,522 3,18 4 3,429 12, , , (est.) ,751 Results on Novo- for NW (left), SW (enter), and N (Right). Each table shows scaling performance with varying number of FPs under optimal input conditions. Estimated performance on Novo- comparable or better than biggest supercomputers on ORNL: 224,162 cores 2.4 z exacore Opterons; 6.95 MW Novo- Power LNL: 122,4 cores 3.2 z ells + 1.8z Opterons; 2.35 MW } 8 KW Max. 21

22 hanks for listening! Questions Questions? 22

23 References [1] W. Pearson and W. Miller, "ynamic programming algorithms for biological sequence comparison, Methods Enzymol. 21: 5751, [2] Y. Sun, Y. ai, L. Liu, F. Yu, M.L. Farrell, W. McKendree, W. Farmerie, ESPRI: Estimating Species Richness Using Large ollections of 16S rrn Pyrosequences, Nucleic cids Research, vol. 37, no. 1 e76, May 29. PMI: PM [3] S. Lloyd and Q. Snell, ardware ccelerated Sequence lignment with raceback, Int. Journal of R, vol. 29, rticle I [4] O. Storaasli, W. Yu,. Strenski, J. Maltby, Performance Evaluation of FP-Based Biological pplications, Proc. ray Users roup, Seattle, W, May 27. [5] K. Benkrid, Y. Liu, and. Benkrid, ighly Parameterized and Efficient FP-Based Skeleton for Pairwise Biological Sequence lignment, IEEE rans. LSI Systems, vol. 17, pp , 29. [6] Novo- architecture overview, [7] ESPRI download, plaza.ufl.edu/sunyijun/espri.htm 23

Software Implementation of Smith-Waterman Algorithm in FPGA

Software Implementation of Smith-Waterman Algorithm in FPGA Software Implementation of Smith-Waterman lgorithm in FP NUR FRH IN SLIMN, NUR DLILH HMD SBRI, SYED BDUL MULIB L JUNID, ZULKIFLI BD MJID, BDUL KRIMI HLIM Faculty of Electrical Engineering Universiti eknologi

More information

Sequence Comparison: Dynamic Programming. Genome 373 Genomic Informatics Elhanan Borenstein

Sequence Comparison: Dynamic Programming. Genome 373 Genomic Informatics Elhanan Borenstein Sequence omparison: Dynamic Programming Genome 373 Genomic Informatics Elhanan Borenstein quick review: hallenges Find the best global alignment of two sequences Find the best global alignment of multiple

More information

SEQUENCE alignment is one of the most widely used operations

SEQUENCE alignment is one of the most widely used operations A parallel FPGA design of the Smith-Waterman traceback Zubair Nawaz #1, Muhammad Nadeem #2, Hans van Someren 3, Koen Bertels #4 # Computer Engineering Lab, Delft University of Technology The Netherlands

More information

Outline. Sequence Alignment. Types of Sequence Alignment. Genomics & Computational Biology. Section 2. How Computers Store Information

Outline. Sequence Alignment. Types of Sequence Alignment. Genomics & Computational Biology. Section 2. How Computers Store Information enomics & omputational Biology Section Lan Zhang Sep. th, Outline How omputers Store Information Sequence lignment Dot Matrix nalysis Dynamic programming lobal: NeedlemanWunsch lgorithm Local: SmithWaterman

More information

A 135mW Fully Integrated Data Processor for

A 135mW Fully Integrated Data Processor for 5mW Fully Integrated Data Processor for Next-eneration Sequencing Yi-hung Wu, Jui-Hung Hung, hia-hsiang Yang, National aiwan University, National hiao ung University 7 IEEE 4.8: 5mW Fully Integrated Data

More information

Accelerating Smith Waterman (SW) Algorithm on Altera Cyclone II Field Programmable Gate Array

Accelerating Smith Waterman (SW) Algorithm on Altera Cyclone II Field Programmable Gate Array Accelerating Smith Waterman (SW) Algorithm on Altera yclone II Field Programmable Gate Array NUR DALILAH AHMAD SABRI, NUR FARAH AIN SALIMAN, SYED ABDUL MUALIB AL JUNID, ABDUL KARIMI HALIM Faculty Electrical

More information

OPEN MP-BASED PARALLEL AND SCALABLE GENETIC SEQUENCE ALIGNMENT

OPEN MP-BASED PARALLEL AND SCALABLE GENETIC SEQUENCE ALIGNMENT OPEN MP-BASED PARALLEL AND SCALABLE GENETIC SEQUENCE ALIGNMENT Asif Ali Khan*, Laiq Hassan*, Salim Ullah* ABSTRACT: In bioinformatics, sequence alignment is a common and insistent task. Biologists align

More information

An FPGA-Based Web Server for High Performance Biological Sequence Alignment

An FPGA-Based Web Server for High Performance Biological Sequence Alignment 2009 NS/ES onference on daptive Hardware and Systems n FPG-Based Web Server for High Performance Biological Sequence lignment Ying Liu 1, Khaled Benkrid 1, bdsamad Benkrid 2 and Server Kasap 1 1 Institute

More information

Accelerating the Smith-Waterman Algorithm for Bio-sequence Matching on GPU

Accelerating the Smith-Waterman Algorithm for Bio-sequence Matching on GPU ccelerating the Smith-Waterman lgorithm for Bio-sequence Matching on GPU Qianghua Zhu, Fei Xia, and Guoqing Jin Electronic Engineering ollege, Naval University of Engineering, Wuhan, P. R. hina, 430033

More information

Sequence Alignment with Traceback on Reconfigurable Hardware

Sequence Alignment with Traceback on Reconfigurable Hardware 2008 International Conference on Reconfigurable Computing and FPGs Sequence lignment with Traceback on Reconfigurable Hardware Scott Lloyd and Quinn O. Snell Brigham Young University, Dept. of Computer

More information

Practical Methods for Constructing Suffix Trees. Advisor: Jignesh M. Patel Yuanyuan Tian

Practical Methods for Constructing Suffix Trees. Advisor: Jignesh M. Patel Yuanyuan Tian Practical Methods for onstructing Suffix rees dvisor: Jignesh M. Patel Yuanyuan ian 1 Roadmap Background & Motivation Our pproaches op-down Disk-Based lgorithm (DD) Merge-Based lgorithm (S-Merge) Experiments

More information

Solving the Longest Common Subsequence (LCS) problem using the Associative ASC Processors with Reconfigurable 2D Mesh

Solving the Longest Common Subsequence (LCS) problem using the Associative ASC Processors with Reconfigurable 2D Mesh Solving the Longest ommon Subsequence (LS) problem using the ssociative S Processors with Virdi Sabegh Singh (dvisor Dr. Robert. Walker) omputer Science Department Kent State University Presentation Outline

More information

Scalable Accelerator Architecture for Local Alignment of DNA Sequences

Scalable Accelerator Architecture for Local Alignment of DNA Sequences Scalable Accelerator Architecture for Local Alignment of DNA Sequences Nuno Sebastião, Nuno Roma, Paulo Flores INESC-ID / IST-TU Lisbon Rua Alves Redol, 9, Lisboa PORTUGAL {Nuno.Sebastiao, Nuno.Roma, Paulo.Flores}

More information

Pairwise Sequence Alignment: Dynamic Programming Algorithms. COMP Spring 2015 Luay Nakhleh, Rice University

Pairwise Sequence Alignment: Dynamic Programming Algorithms. COMP Spring 2015 Luay Nakhleh, Rice University Pairwise Sequence Alignment: Dynamic Programming Algorithms COMP 571 - Spring 2015 Luay Nakhleh, Rice University DP Algorithms for Pairwise Alignment The number of all possible pairwise alignments (if

More information

Biology 644: Bioinformatics

Biology 644: Bioinformatics Find the best alignment between 2 sequences with lengths n and m, respectively Best alignment is very dependent upon the substitution matrix and gap penalties The Global Alignment Problem tries to find

More information

Sequence Alignment (chapter 6) p The biological problem p Global alignment p Local alignment p Multiple alignment

Sequence Alignment (chapter 6) p The biological problem p Global alignment p Local alignment p Multiple alignment Sequence lignment (chapter 6) p The biological problem p lobal alignment p Local alignment p Multiple alignment Local alignment: rationale p Otherwise dissimilar proteins may have local regions of similarity

More information

A BANDED SMITH-WATERMAN FPGA ACCELERATOR FOR MERCURY BLASTP

A BANDED SMITH-WATERMAN FPGA ACCELERATOR FOR MERCURY BLASTP A BANDED SITH-WATERAN FPGA ACCELERATOR FOR ERCURY BLASTP Brandon Harris*, Arpith C. Jacob*, Joseph. Lancaster*, Jeremy Buhler*, Roger D. Chamberlain* *Dept. of Computer Science and Engineering, Washington

More information

Alignment and clustering tools for sequence analysis. Omar Abudayyeh Presentation December 9, 2015

Alignment and clustering tools for sequence analysis. Omar Abudayyeh Presentation December 9, 2015 Alignment and clustering tools for sequence analysis Omar Abudayyeh 18.337 Presentation December 9, 2015 Introduction Sequence comparison is critical for inferring biological relationships within large

More information

Speeding Up Ray Tracing. Optimisations. Ray Tracing Acceleration

Speeding Up Ray Tracing. Optimisations. Ray Tracing Acceleration Speeding Up Ray Tracing nthony Steed 1999, eline Loscos 2005, Jan Kautz 2007-2009 Optimisations Limit the number of rays Make the ray test faster for shadow rays the main drain on resources if there are

More information

CMSC423: Bioinformatic Algorithms, Databases and Tools Lecture 8. Note

CMSC423: Bioinformatic Algorithms, Databases and Tools Lecture 8. Note MS: Bioinformatic lgorithms, Databases and ools Lecture 8 Sequence alignment: inexact alignment dynamic programming, gapped alignment Note Lecture 7 suffix trees and suffix arrays will be rescheduled Exact

More information

Pairwise Sequence Alignment: Dynamic Programming Algorithms COMP 571 Luay Nakhleh, Rice University

Pairwise Sequence Alignment: Dynamic Programming Algorithms COMP 571 Luay Nakhleh, Rice University 1 Pairwise Sequence Alignment: Dynamic Programming Algorithms COMP 571 Luay Nakhleh, Rice University DP Algorithms for Pairwise Alignment 2 The number of all possible pairwise alignments (if gaps are allowed)

More information

A Parallel Hardware Architecture for Information-Theoretic Adaptive Filtering

A Parallel Hardware Architecture for Information-Theoretic Adaptive Filtering A Parallel Hardware Architecture for Information-Theoretic Adaptive Filtering HPRCTA 2010 Stefan Craciun Dr. Alan D. George Dr. Herman Lam Dr. Jose C. Principe November 14, 2010 NSF CHREC Center ECE Department,

More information

Big Data Meets High-Performance Reconfigurable Computing

Big Data Meets High-Performance Reconfigurable Computing Big Data Meets High-Performance Reconfigurable Computing UF Workshop on Dense, Intense, and Complex Data Alan George CHREC Center Director Herman Lam CHREC Center Associate Director June 19, 2013 What

More information

AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-based Multi- and Many-core Processors

AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-based Multi- and Many-core Processors AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-based Multi- and Many-core Processors Kaixi Hou, Hao Wang, Wu-chun Feng {kaixihou,hwang121,wfeng}@vt.edu Pairwise Sequence Alignment Algorithms

More information

Acceleration of Algorithm of Smith-Waterman Using Recursive Variable Expansion.

Acceleration of Algorithm of Smith-Waterman Using Recursive Variable Expansion. www.ijarcet.org 54 Acceleration of Algorithm of Smith-Waterman Using Recursive Variable Expansion. Hassan Kehinde Bello and Kazeem Alagbe Gbolagade Abstract Biological sequence alignment is becoming popular

More information

SGI s Approach to Multi-paradigm Computing Ron Renwick Product Manager Reconfigurable Computing

SGI s Approach to Multi-paradigm Computing Ron Renwick Product Manager Reconfigurable Computing Silicon Graphics, Inc. SGI s pproach to Multi-paradigm omputing Ron Renwick Product Manager Reconfigurable omputing SGI Scalable ccnum rchitecture Basic Node Structure and Interconnect PU PU PU PU hip

More information

Sequence analysis Pairwise sequence alignment

Sequence analysis Pairwise sequence alignment UMF11 Introduction to bioinformatics, 25 Sequence analysis Pairwise sequence alignment 1. Sequence alignment Lecturer: Marina lexandersson 12 September, 25 here are two types of sequence alignments, global

More information

Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014

Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014 Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014 Dynamic programming is a group of mathematical methods used to sequentially split a complicated problem into

More information

Dynamic Programming Part I: Examples. Bioinfo I (Institut Pasteur de Montevideo) Dynamic Programming -class4- July 25th, / 77

Dynamic Programming Part I: Examples. Bioinfo I (Institut Pasteur de Montevideo) Dynamic Programming -class4- July 25th, / 77 Dynamic Programming Part I: Examples Bioinfo I (Institut Pasteur de Montevideo) Dynamic Programming -class4- July 25th, 2011 1 / 77 Dynamic Programming Recall: the Change Problem Other problems: Manhattan

More information

Integrated Accelerator Architecture for DNA Sequences Alignment with Enhanced Traceback Phase

Integrated Accelerator Architecture for DNA Sequences Alignment with Enhanced Traceback Phase Integrated Accelerator Architecture for DNA Sequences Alignment with Enhanced Traceback Phase Nuno Sebastião Tiago Dias Nuno Roma Paulo Flores INESC-ID INESC-ID / IST INESC-ID INESC-ID IST-TU Lisbon ISEL-PI

More information

Accelerating Genomic Sequence Alignment Workload with Scalable Vector Architecture

Accelerating Genomic Sequence Alignment Workload with Scalable Vector Architecture Accelerating Genomic Sequence Alignment Workload with Scalable Vector Architecture Dong-hyeon Park, Jon Beaumont, Trevor Mudge University of Michigan, Ann Arbor Genomics Past Weeks ~$3 billion Human Genome

More information

Outline. MAC (Medium Access Control) General MAC Requirements. Typical MAC protocols. Typical MAC protocols

Outline. MAC (Medium Access Control) General MAC Requirements. Typical MAC protocols. Typical MAC protocols Outline Medium ccess ontrol With oordinated daptive Sleeping for Wireless Sensor Networks Presented by: rik rooks Introduction to M S-M Overview S-M Evaluation ritique omparison to MW Washington University

More information

High Performance Systolic Array Core Architecture Design for DNA Sequencer

High Performance Systolic Array Core Architecture Design for DNA Sequencer High Performance Systolic Array Core Architecture Design for DNA Sequencer Dayana Saiful Nurdin 1, Mohd. Nazrin Md. Isa 1,* Rizalafande Che Ismail 1 and Muhammad Imran Ahmad 2 1 The Integrated Circuits

More information

An Analysis of Pairwise Sequence Alignment Algorithm Complexities: Needleman-Wunsch, Smith-Waterman, FASTA, BLAST and Gapped BLAST

An Analysis of Pairwise Sequence Alignment Algorithm Complexities: Needleman-Wunsch, Smith-Waterman, FASTA, BLAST and Gapped BLAST An Analysis of Pairwise Sequence Alignment Algorithm Complexities: Needleman-Wunsch, Smith-Waterman, FASTA, BLAST and Gapped BLAST Alexander Chan 5075504 Biochemistry 218 Final Project An Analysis of Pairwise

More information

Efficient Rectilinear Steiner Tree Construction with Rectangular Obstacles

Efficient Rectilinear Steiner Tree Construction with Rectangular Obstacles Proceedings of the th WSES Int. onf. on IRUITS, SYSTEMS, ELETRONIS, ONTROL & SIGNL PROESSING, allas, US, November 1-3, 2006 204 Efficient Rectilinear Steiner Tree onstruction with Rectangular Obstacles

More information

Highly Scalable and Accurate Seeds for Subsequence Alignment

Highly Scalable and Accurate Seeds for Subsequence Alignment Highly Scalable and Accurate Seeds for Subsequence Alignment Abhijit Pol Tamer Kahveci Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL, USA, 32611

More information

A Design of a Hybrid System for DNA Sequence Alignment

A Design of a Hybrid System for DNA Sequence Alignment IMECS 2008, 9-2 March, 2008, Hong Kong A Design of a Hybrid System for DNA Sequence Alignment Heba Khaled, Hossam M. Faheem, Tayseer Hasan, Saeed Ghoneimy Abstract This paper describes a parallel algorithm

More information

Multiple Sequence Alignment Theory and Applications

Multiple Sequence Alignment Theory and Applications Mahidol University Objectives SMI512 Molecular Sequence alysis Multiple Sequence lignment Theory and pplications Lecture 3 Pravech jawatanawong, Ph.. e-mail: pravech.aja@mahidol.edu epartment of Microbiology

More information

Sequence comparison: Local alignment

Sequence comparison: Local alignment Sequence comparison: Local alignment Genome 559: Introuction to Statistical an Computational Genomics Prof. James H. Thomas http://faculty.washington.eu/jht/gs559_217/ Review global alignment en traceback

More information

Harnessing Associative Computing for Sequence Alignment with Parallel Accelerators

Harnessing Associative Computing for Sequence Alignment with Parallel Accelerators Harnessing Associative Computing for Sequence Alignment with Parallel Accelerators Shannon I. Steinfadt Doctoral Research Showcase III Room 17 A / B 4:00-4:15 International Conference for High Performance

More information

Hardware Accelerated Sequence Alignment with Traceback

Hardware Accelerated Sequence Alignment with Traceback Brigham Young University BYU Scholarsrchive ll Faculty Publications 2009-01-01 Hardware ccelerated Sequence lignment with raceback Scott Lloyd Quinn O. Snell snell@cs.byu.edu Follow this and additional

More information

Darwin-WGA. A Co-processor Provides Increased Sensitivity in Whole Genome Alignments with High Speedup

Darwin-WGA. A Co-processor Provides Increased Sensitivity in Whole Genome Alignments with High Speedup Darwin-WGA A Co-processor Provides Increased Sensitivity in Whole Genome Alignments with High Speedup Yatish Turakhia*, Sneha D. Goenka*, Prof. Gill Bejerano, Prof. William J. Dally * Equal contribution

More information

Rapid: A Configurable Architecture for Compute-Intensive Applications

Rapid: A Configurable Architecture for Compute-Intensive Applications Rapid: Configurable rchitecture for Compute-Intensive pplications Carl Ebeling Dept. of Computer Science and Engineering niversity of Washington lternatives for High-Performance Systems SIC se application-specific

More information

Bioinformatics for Biologists

Bioinformatics for Biologists Bioinformatics for Biologists Sequence Analysis: Part I. Pairwise alignment and database searching Fran Lewitter, Ph.D. Director Bioinformatics & Research Computing Whitehead Institute Topics to Cover

More information

As of August 15, 2008, GenBank contained bases from reported sequences. The search procedure should be

As of August 15, 2008, GenBank contained bases from reported sequences. The search procedure should be 48 Bioinformatics I, WS 09-10, S. Henz (script by D. Huson) November 26, 2009 4 BLAST and BLAT Outline of the chapter: 1. Heuristics for the pairwise local alignment of two sequences 2. BLAST: search and

More information

Jyoti Lakhani 1, Ajay Khunteta 2, Dharmesh Harwani *3 1 Poornima University, Jaipur & Maharaja Ganga Singh University, Bikaner, Rajasthan, India

Jyoti Lakhani 1, Ajay Khunteta 2, Dharmesh Harwani *3 1 Poornima University, Jaipur & Maharaja Ganga Singh University, Bikaner, Rajasthan, India International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2017 IJSRCSEIT Volume 2 Issue 6 ISSN : 2456-3307 Improvisation of Global Pairwise Sequence Alignment

More information

GPU Accelerated Smith-Waterman

GPU Accelerated Smith-Waterman GPU Accelerated Smith-Waterman Yang Liu 1,WayneHuang 1,2, John Johnson 1, and Sheila Vaidya 1 1 Lawrence Livermore National Laboratory 2 DOE Joint Genome Institute, UCRL-CONF-218814 {liu24, whuang, jjohnson,

More information

Darwin: A Genomic Co-processor gives up to 15,000X speedup on long read assembly (To appear in ASPLOS 2018)

Darwin: A Genomic Co-processor gives up to 15,000X speedup on long read assembly (To appear in ASPLOS 2018) Darwin: A Genomic Co-processor gives up to 15,000X speedup on long read assembly (To appear in ASPLOS 2018) Yatish Turakhia EE PhD candidate Stanford University Prof. Bill Dally (Electrical Engineering

More information

Center Extreme Scale CS Research

Center Extreme Scale CS Research Center Extreme Scale CS Research Center for Compressible Multiphase Turbulence University of Florida Sanjay Ranka Herman Lam Outline 10 6 10 7 10 8 10 9 cores Parallelization and UQ of Rocfun and CMT-Nek

More information

Flexible Architecture Research Machine (FARM)

Flexible Architecture Research Machine (FARM) Flexible Architecture Research Machine (FARM) RAMP Retreat June 25, 2009 Jared Casper, Tayo Oguntebi, Sungpack Hong, Nathan Bronson Christos Kozyrakis, Kunle Olukotun Motivation Why CPUs + FPGAs make sense

More information

Acceleration of the Smith-Waterman algorithm for DNA sequence alignment using an FPGA platform

Acceleration of the Smith-Waterman algorithm for DNA sequence alignment using an FPGA platform Acceleration of the Smith-Waterman algorithm for DNA sequence alignment using an FPGA platform Barry Strengholt Matthijs Brobbel Delft University of Technology Faculty of Electrical Engineering, Mathematics

More information

34 Bioinformatics I, WS 12/13, D. Huson, November 11, 2012

34 Bioinformatics I, WS 12/13, D. Huson, November 11, 2012 34 Bioinformatics I, WS 12/13, D. Huson, November 11, 2012 4 Multiple Sequence lignment Sources for this lecture: R. Durbin, S. Eddy,. Krogh und. Mitchison, Biological sequence analysis, ambridge, 1998

More information

Lecture 10. Sequence alignments

Lecture 10. Sequence alignments Lecture 10 Sequence alignments Alignment algorithms: Overview Given a scoring system, we need to have an algorithm for finding an optimal alignment for a pair of sequences. We want to maximize the score

More information

Smith-Waterman Algorithm Traceback Optimization using Structural Modelling Technique

Smith-Waterman Algorithm Traceback Optimization using Structural Modelling Technique Smith-Waterman Algorithm Traceback Optimization using Structural Modelling Technique Nur Farah Ain Saliman*, Nur Dalilah Ahmad Sabri, Syed Abdul Mutalib Al Junid, Nooritawati Md Tahir, Zulkifli Abd Majid

More information

Lecture Overview. Sequence search & alignment. Searching sequence databases. Sequence Alignment & Search. Goals: Motivations:

Lecture Overview. Sequence search & alignment. Searching sequence databases. Sequence Alignment & Search. Goals: Motivations: Lecture Overview Sequence Alignment & Search Karin Verspoor, Ph.D. Faculty, Computational Bioscience Program University of Colorado School of Medicine With credit and thanks to Larry Hunter for creating

More information

CUDAlign 4.0: Incremental Speculative Traceback for Exact Chromosome-Wide Alignment in GPU Clusters

CUDAlign 4.0: Incremental Speculative Traceback for Exact Chromosome-Wide Alignment in GPU Clusters 216 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising

More information

Keywords -Bioinformatics, sequence alignment, Smith- waterman (SW) algorithm, GPU, CUDA

Keywords -Bioinformatics, sequence alignment, Smith- waterman (SW) algorithm, GPU, CUDA Volume 5, Issue 5, May 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Accelerating Smith-Waterman

More information

Sequence Alignment & Search

Sequence Alignment & Search Sequence Alignment & Search Karin Verspoor, Ph.D. Faculty, Computational Bioscience Program University of Colorado School of Medicine With credit and thanks to Larry Hunter for creating the first version

More information

Algorithmic Approaches for Biological Data, Lecture #20

Algorithmic Approaches for Biological Data, Lecture #20 Algorithmic Approaches for Biological Data, Lecture #20 Katherine St. John City University of New York American Museum of Natural History 20 April 2016 Outline Aligning with Gaps and Substitution Matrices

More information

Mouse, Human, Chimpanzee

Mouse, Human, Chimpanzee More Alignments 1 Mouse, Human, Chimpanzee Mouse to Human Chimpanzee to Human 2 Mouse v.s. Human Chromosome X of Mouse to Human 3 Local Alignment Given: two sequences S and T Find: substrings of S and

More information

Id Question Microprocessor is the example of architecture. A Princeton B Von Neumann C Rockwell D Harvard Answer A Marks 1 Unit 1

Id Question Microprocessor is the example of architecture. A Princeton B Von Neumann C Rockwell D Harvard Answer A Marks 1 Unit 1 Question Microprocessor is the example of architecture. Princeton Von Neumann Rockwell Harvard nswer Question bus is unidirectional. ata ddress ontrol None of these nswer Question Use of isolates PU form

More information

Developing Applications for HPRCs

Developing Applications for HPRCs Developing Applications for HPRCs Esam El-Araby The George Washington University Acknowledgement Prof.\ Tarek El-Ghazawi Mohamed Taher ARSC SRC SGI Cray 2 Outline Background Methodology A Case Studies

More information

Programmable Forwarding Planes at Terabit/s Speeds

Programmable Forwarding Planes at Terabit/s Speeds Programmable Forwarding Planes at Terabit/s Speeds Patrick Bosshart HIEF TEHNOLOGY OFFIER, BREFOOT NETWORKS nd the entire Barefoot Networks team Hot hips 30, ugust 21, 2018 Barefoot Tofino : Domain Specific

More information

Algorithmic Paradigms. Chapter 6 Dynamic Programming. Steps in Dynamic Programming. Dynamic Programming. Dynamic Programming Applications

Algorithmic Paradigms. Chapter 6 Dynamic Programming. Steps in Dynamic Programming. Dynamic Programming. Dynamic Programming Applications lgorithmic Paradigms reed. Build up a solution incrementally, only optimizing some local criterion. hapter Dynamic Programming Divide-and-conquer. Break up a problem into two sub-problems, solve each sub-problem

More information

Co-synthesis and Accelerator based Embedded System Design

Co-synthesis and Accelerator based Embedded System Design Co-synthesis and Accelerator based Embedded System Design COE838: Embedded Computer System http://www.ee.ryerson.ca/~courses/coe838/ Dr. Gul N. Khan http://www.ee.ryerson.ca/~gnkhan Electrical and Computer

More information

CS 284A: Algorithms for Computational Biology Notes on Lecture: BLAST. The statistics of alignment scores.

CS 284A: Algorithms for Computational Biology Notes on Lecture: BLAST. The statistics of alignment scores. CS 284A: Algorithms for Computational Biology Notes on Lecture: BLAST. The statistics of alignment scores. prepared by Oleksii Kuchaiev, based on presentation by Xiaohui Xie on February 20th. 1 Introduction

More information

Computational Genomics and Molecular Biology, Fall

Computational Genomics and Molecular Biology, Fall Computational Genomics and Molecular Biology, Fall 2015 1 Sequence Alignment Dannie Durand Pairwise Sequence Alignment The goal of pairwise sequence alignment is to establish a correspondence between the

More information

A Scalable Coprocessor for Bioinformatic Sequence Alignments

A Scalable Coprocessor for Bioinformatic Sequence Alignments A Scalable Coprocessor for Bioinformatic Sequence Alignments Scott F. Smith Department of Electrical and Computer Engineering Boise State University Boise, ID, U.S.A. Abstract A hardware coprocessor for

More information

Fast Sequence Alignment Method Using CUDA-enabled GPU

Fast Sequence Alignment Method Using CUDA-enabled GPU Fast Sequence Alignment Method Using CUDA-enabled GPU Yeim-Kuan Chang Department of Computer Science and Information Engineering National Cheng Kung University Tainan, Taiwan ykchang@mail.ncku.edu.tw De-Yu

More information

A CAM(Content Addressable Memory)-based architecture for molecular sequence matching

A CAM(Content Addressable Memory)-based architecture for molecular sequence matching A CAM(Content Addressable Memory)-based architecture for molecular sequence matching P.K. Lala 1 and J.P. Parkerson 2 1 Department Electrical Engineering, Texas A&M University, Texarkana, Texas, USA 2

More information

Today s Lecture. Edit graph & alignment algorithms. Local vs global Computational complexity of pairwise alignment Multiple sequence alignment

Today s Lecture. Edit graph & alignment algorithms. Local vs global Computational complexity of pairwise alignment Multiple sequence alignment Today s Lecture Edit graph & alignment algorithms Smith-Waterman algorithm Needleman-Wunsch algorithm Local vs global Computational complexity of pairwise alignment Multiple sequence alignment 1 Sequence

More information

High Speed Asynchronous Data Transfers on the Cray XT3

High Speed Asynchronous Data Transfers on the Cray XT3 High Speed Asynchronous Data Transfers on the Cray XT3 Ciprian Docan, Manish Parashar and Scott Klasky The Applied Software System Laboratory Rutgers, The State University of New Jersey CUG 2007, Seattle,

More information

Scalable Hardware Accelerator for Comparing DNA and Protein Sequences

Scalable Hardware Accelerator for Comparing DNA and Protein Sequences Scalable Hardware Accelerator for Comparing DNA and Protein Sequences Philippe Faes, Bram Minnaert, Mark Christiaens, Eric Bonnet, Yvan Saeys, Dirk Stroobandt, Yves Van de Peer Abstract Comparing genetic

More information

An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware

An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware Tao Chen, Shreesha Srinath Christopher Batten, G. Edward Suh Computer Systems Laboratory School of Electrical

More information

Fundamentals of Quantitative Design and Analysis

Fundamentals of Quantitative Design and Analysis Fundamentals of Quantitative Design and Analysis Dr. Jiang Li Adapted from the slides provided by the authors Computer Technology Performance improvements: Improvements in semiconductor technology Feature

More information

CBMF W4761 Final Project Report

CBMF W4761 Final Project Report CBMF W4761 Final Project Report Christopher Fenton CBMF W4761 8/16/09 Introduction Performing large scale database searches of genomic data is one of the largest problems in computational genomics. When

More information

Comparative Analysis of Protein Alignment Algorithms in Parallel environment using CUDA

Comparative Analysis of Protein Alignment Algorithms in Parallel environment using CUDA Comparative Analysis of Protein Alignment Algorithms in Parallel environment using BLAST versus Smith-Waterman Shadman Fahim shadmanbracu09@gmail.com Shehabul Hossain rudrozzal@gmail.com Gulshan Jubaed

More information

System of Systems Complexity Identification and Control

System of Systems Complexity Identification and Control System of Systems Identification and ontrol Joseph J. Simpson Systems oncepts nd ve NW # Seattle, W jjs-sbw@eskimo.com Mary J. Simpson Systems oncepts nd ve NW # Seattle, W mjs-sbw@eskimo.com bstract System

More information

HIGH LEVEL SYNTHESIS OF SMITH-WATERMAN DATAFLOW IMPLEMENTATIONS

HIGH LEVEL SYNTHESIS OF SMITH-WATERMAN DATAFLOW IMPLEMENTATIONS HIGH LEVEL SYNTHESIS OF SMITH-WATERMAN DATAFLOW IMPLEMENTATIONS S. Casale-Brunet 1, E. Bezati 1, M. Mattavelli 2 1 Swiss Institute of Bioinformatics, Lausanne, Switzerland 2 École Polytechnique Fédérale

More information

Distributed Protein Sequence Alignment

Distributed Protein Sequence Alignment Distributed Protein Sequence Alignment ABSTRACT J. Michael Meehan meehan@wwu.edu James Hearne hearne@wwu.edu Given the explosive growth of biological sequence databases and the computational complexity

More information

Regular Expression Constrained Sequence Alignment

Regular Expression Constrained Sequence Alignment Regular Expression Constrained Sequence Alignment By Abdullah N. Arslan Department of Computer science University of Vermont Presented by Tomer Heber & Raz Nissim otivation When comparing two proteins,

More information

Novo-G: A View at the HPC Crossroads for Scientific Computing

Novo-G: A View at the HPC Crossroads for Scientific Computing Novo-G: A View at the HPC Crossroads for Scientific Computing ERSA Keynote for Reconfigurable Supercomputing Panel A. George, H. Lam, C. Pascoe, A. Lawande, G. Stitt NSF Center for High-Performance Reconfigurable

More information

Let s say I give you a homework assignment today with 100 problems. Each problem takes 2 hours to solve. The homework is due tomorrow.

Let s say I give you a homework assignment today with 100 problems. Each problem takes 2 hours to solve. The homework is due tomorrow. Let s say I give you a homework assignment today with 100 problems. Each problem takes 2 hours to solve. The homework is due tomorrow. Big problems and Very Big problems in Science How do we live Protein

More information

WITH the advent of the Next-Generation Sequencing

WITH the advent of the Next-Generation Sequencing 1262 IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, VOL. 20, NO. 7, JULY 2012 Integrated Hardware Architecture for Efficient Computation of the n-best Bio-Sequence Local Alignments in

More information

Single Pass, BLAST-like, Approximate String Matching on FPGAs*

Single Pass, BLAST-like, Approximate String Matching on FPGAs* Single Pass, BLAST-like, Approximate String Matching on FPGAs* Martin Herbordt Josh Model Yongfeng Gu Bharat Sukhwani Tom VanCourt Computer Architecture and Automated Design Laboratory Department of Electrical

More information

Searching Biological Sequence Databases Using Distributed Adaptive Computing

Searching Biological Sequence Databases Using Distributed Adaptive Computing Searching Biological Sequence Databases Using Distributed Adaptive Computing Nicholas P. Pappas Thesis submitted to the Faculty of the Virginia Polytechnic Institute and State University in partial fulfillment

More information

Tradeoff Analysis and Architecture Design of a Hybrid Hardware/Software Sorter

Tradeoff Analysis and Architecture Design of a Hybrid Hardware/Software Sorter Tradeoff Analysis and Architecture Design of a Hybrid Hardware/Software Sorter M. Bednara, O. Beyer, J. Teich, R. Wanka Paderborn University D-33095 Paderborn, Germany bednara,beyer,teich @date.upb.de,

More information

Compares a sequence of protein to another sequence or database of a protein, or a sequence of DNA to another sequence or library of DNA.

Compares a sequence of protein to another sequence or database of a protein, or a sequence of DNA to another sequence or library of DNA. Compares a sequence of protein to another sequence or database of a protein, or a sequence of DNA to another sequence or library of DNA. Fasta is used to compare a protein or DNA sequence to all of the

More information

Algorithms and Tools for Bioinformatics on GPUs. Bertil SCHMIDT

Algorithms and Tools for Bioinformatics on GPUs. Bertil SCHMIDT Algorithms and Tools for Bioinformatics on GPUs Bertil SCHMIDT Contents Motivation Pairwise Sequence Alignment Multiple Sequence Alignment Short Read Error Correction using CUDA Some other CUDA-enabled

More information

Flexible wireless communication architectures

Flexible wireless communication architectures Flexible wireless communication architectures Sridhar Rajagopal Department of Electrical and Computer Engineering Rice University, Houston TX Faculty Candidate Seminar Southern Methodist University April

More information

Third Generation Routers

Third Generation Routers IP orwarding 5-5- omputer Networking 5- Lecture : Routing Peter Steenkiste all www.cs.cmu.edu/~prs/5-- The Story So ar IP addresses are structured to reflect Internet structure IP packet headers carry

More information

Metropolitan Road Traffic Simulation on FPGAs

Metropolitan Road Traffic Simulation on FPGAs Metropolitan Road Traffic Simulation on FPGAs Justin L. Tripp, Henning S. Mortveit, Anders Å. Hansson, Maya Gokhale Los Alamos National Laboratory Los Alamos, NM 85745 Overview Background Goals Using the

More information

Local Alignment & Gap Penalties CMSC 423

Local Alignment & Gap Penalties CMSC 423 Local Alignment & ap Penalties CMSC 423 lobal, Semi-global, Local Alignments Last time, we saw a dynamic programming algorithm for global alignment: both strings s and t must be completely matched: s t

More information

Sequence Alignment. part 2

Sequence Alignment. part 2 Sequence Alignment part 2 Dynamic programming with more realistic scoring scheme Using the same initial sequences, we ll look at a dynamic programming example with a scoring scheme that selects for matches

More information

Efficient Smith-Waterman on multi-core with FastFlow

Efficient Smith-Waterman on multi-core with FastFlow BioBITs Euromicro PDP 2010 - Pisa Italy - 17th Feb 2010 Efficient Smith-Waterman on multi-core with FastFlow Marco Aldinucci Computer Science Dept. - University of Torino - Italy Massimo Torquati Computer

More information

Parallel Processing SIMD, Vector and GPU s cont.

Parallel Processing SIMD, Vector and GPU s cont. Parallel Processing SIMD, Vector and GPU s cont. EECS4201 Fall 2016 York University 1 Multithreading First, we start with multithreading Multithreading is used in GPU s 2 1 Thread Level Parallelism ILP

More information

FASTA. Besides that, FASTA package provides SSEARCH, an implementation of the optimal Smith- Waterman algorithm.

FASTA. Besides that, FASTA package provides SSEARCH, an implementation of the optimal Smith- Waterman algorithm. FASTA INTRODUCTION Definition (by David J. Lipman and William R. Pearson in 1985) - Compares a sequence of protein to another sequence or database of a protein, or a sequence of DNA to another sequence

More information

EITF20: Computer Architecture Part2.2.1: Pipeline-1

EITF20: Computer Architecture Part2.2.1: Pipeline-1 EITF20: Computer Architecture Part2.2.1: Pipeline-1 Liang Liu liang.liu@eit.lth.se 1 Outline Reiteration Pipelining Harzards Structural hazards Data hazards Control hazards Implementation issues Multi-cycle

More information

15-780: Graduate Artificial Intelligence. Computational biology: Sequence alignment and profile HMMs

15-780: Graduate Artificial Intelligence. Computational biology: Sequence alignment and profile HMMs 5-78: Graduate rtificial Intelligence omputational biology: Sequence alignment and profile HMMs entral dogma DN GGGG transcription mrn UGGUUUGUG translation Protein PEPIDE 2 omparison of Different Organisms

More information

Near Memory Key/Value Lookup Acceleration MemSys 2017

Near Memory Key/Value Lookup Acceleration MemSys 2017 Near Key/Value Lookup Acceleration MemSys 2017 October 3, 2017 Scott Lloyd, Maya Gokhale Center for Applied Scientific Computing This work was performed under the auspices of the U.S. Department of Energy

More information