Search

Arm usage has substantially grown in the High-Performance Computing (HPC) community. Japanese supercomputer Fugaku, powered by Arm-based A64FX processors, held the top position on the Top500 list between June 2020 and June 2022, currently sitting in the fourth position. The recently released 7th generation of Amazon EC2 instances for compute-intensive workloads (C7 g) is also powered by Arm Graviton3 processors. Projects like European Mont-Blanc and U.S. DOE/NNSA Astra are further examples of Arm irruption in HPC. In parallel, over the last decade, the rapid improvement of genomic sequencing technologies and the exponential growth of sequencing data has placed a significant bottleneck on the computational side. While most genomics applications have been thoroughly tested and optimized for x86 systems, just a few are prepared to perform efficiently on Arm machines. Moreover, these applications do not exploit the newly introduced Scalable Vector Extensions (SVE). This paper presents GenArchBench, the first genome analysis benchmark suite targeting Arm architectures. We have selected computationally demanding kernels from the most widely used tools in genome data analysis and ported them to Arm-based A64FX and Graviton3 processors. Overall, the GenArch benchmark suite comprises 13 multi-core kernels from critical stages of widely-used genome analysis pipelines, including base-calling, read mapping, variant calling, and genome assembly. Our benchmark suite includes different input data sets per kernel (small and large), each with a corresponding regression test to verify the correctness of each execution automatically. Moreover, the porting features the usage of the novel Arm SVE instructions, algorithmic and code optimizations, and the exploitation of Arm-optimized libraries. We present the optimizations implemented in each kernel and a detailed performance evaluation and comparison of their performance on four different HPC machines (i.e., A64FX, Graviton3, Intel Xeon, This work has been partially supported by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033 (contracts PID2019-107255GB-C21, PID2019-105660RB-C21, PID2022136454NB-C22, and TED2021-132634A-I00), by the Generalitat de Catalunya, Spain (contract 2021-SGR-763), by the Gobierno de Aragón (T58_23R research group), by the European Union NextGenerationEU/ PRTR, and by Lenovo BSC Contract-Framework Contract (2020)., Peer Reviewed, Postprint (published version)

The ever-increasing yields in genome sequence data production pose a computational challenge to current genome sequence analysis tools, jeopardizing the future of personalized medicine. Leveraging hardware accelerators (GPUs, FPGAs, and ASICs) to accelerate computationally-intensive algorithms like sequence alignment has become paramount. Recently, the wavefront alignment algorithm was introduced, significantly reducing the execution time to perform sequence alignment. This paper presents the first-ever ASIC accelerator of the WFA integrated into a RISC-V system-on-chip. Our designed chip greatly accelerates sequence alignment, delivering up to 1076 × better performance over the CPU implementation of the WFA running on the RISC-V core of the chip., This work has been partially supported by the European HiPEAC Network of Excellence, by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033 (contracts PID2019-107255GB-C21, PID 2020-113614RB-C21 and TED2021-132634A-I00), by the Generalitat de Catalunya (contract 2021-SGR-00763 and 2021-SGR-00574), by the European Union within the framework of the ERDF of Catalonia 2014-2020 under the DRAC project [001-P-001723], by the European NextGenerationEU/PRTR, by the Lenovo-BSC Contract-Framework (2022), and by the IBM/BSC Deep Learning Center initiative. M. Moreto has been partially supported by the Spanish Ministry of Economy, Industry and Competitiveness under Ramon y Cajal fellowship No. RYC-2016-21104., Peer Reviewed, Postprint (author's final draft)

In the last years, advances in genome sequencing technologies have enabled the proliferation of genomic applications that guide personalized medicine. These applications have an enormous computational cost due to the large amount of genomic data they process. The first step in many of these applications consists in aligning DNA reads against a reference genome. Very recently, the wavefront alignment (WFA) algorithm has been introduced, significantly reducing the execution time of the read alignment process. This paper presents the first FPGA-based hardware/software co-designed accelerator of such relevant algorithm. Compared to the reference WFA CPU-only implementation, the proposed accelerator achieves performance speedups of up to 13.5 while consuming up to 14.6 less energy when aligning short reads. When aligning long reads, the proposed accelerator achieves speedups of up to 9.9 while consuming up to 10.9 less energy., This work has been partially supported by the European HiPEAC Network of Excellence, by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033 (contracts PID2019-107255GB-C21 and TED2021-132634A-I00), by the Generalitat de Catalunya (contract 2021-SGR-00763), by the European Union within the framework of the ERDF of Catalonia 2014-2020 under the DRAC project [001-P-001723], by the European NextGenerationEU/PRTR, by the Lenovo-BSC Contract-Framework (2022), and by the IBM/BSC Deep Learning Center initiative. M. Moreto has been partially supported by the Spanish Ministry of Economy, Industry and Competitiveness under Ramon y Cajal fellowship No. RYC-2016-21104., Peer Reviewed, Postprint (author's final draft)

Recent advances in sequencing technologies have made sequencing analysis a fundamental tool for genomics and healthcare research. Before any biological insights can be drawn, sequence data has to be analyzed using complex and computational-intensive sequence analysis tools. In particular, sequence alignment is a fundamental building block present in numerous sequence analysis tools. However, DP-based sequence alignment implementations fail to scale with longer sequence lengths due to the quadratic memory requirements and quickly become memory-bounded. As a result, numerous research efforts have focused on developing efficient and scalable sequence alignment algorithms and hardware accelerators. Unfortunately, current state-of-the-art sequence alignment algorithms, namely the WFA and BiWFA algorithms, are still limited by memory constraints and struggle to scale efficiently on modern many-core architectures. Processing-In-Memory (PIM) is an emergent architectural paradigm that seeks to accelerate memory-bound applications by moving computation closer to the data to mitigate data-movement penalties. This work aims to develop a PIM-enabled implementation of the BiWFA algorithm optimized for the UPMEM architecture. Advances in genomics and sequencing technologies demand faster and more scalable analysis methods that can process longer sequences with higher accuracy. However, classical pairwise alignment methods, based on dynamic programming (DP), impose impractical computational requirements to align long and noisy sequences like those produced by PacBio, and Nanopore technologies. The recently proposed Wavefront Alignment (WFA) algorithm paves the way for more efficient alignment tools, improving time and memory complexity over previous methods. Notwithstanding the advantages of the WFA algorithm, modern high performance computing (HPC) platforms rely on accelerator-based architectures that exploit parallel computing resources to improve over classical computing CPUs.

The RISC-V ISA has gained significant momentum in High-Performance Computing (HPC) research and market due to its open-source nature, fostering collaborative research and innovation. The ever-growing RISC-V-based hardware/software ecosystem has made it an attractive option for HPC application development and production. Within the field of biomedical research, genome data analysis has emerged as a crucial step towards personalized medicine, demanding substantial computational resources and more efficient tools.This paper presents a benchmark suite of genome analysis kernels ported to RISC-V and their evaluation on modern RISC-V systems. Our work evaluates the RISC-V toolchain’s maturity and the software/hardware ecosystem’s readiness for its adoption for genome data analysis. This study aims to provide valuable guidance for researchers and practitioners interested in adopting RISC-V for genome analysis, and provides feedback to the RISC-V community on the challenges that need to be addressed for RISC-V to become an efficient HPC platform., This work has been partially supported by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033 (contracts PID2019-107255GB-C21, PID2019-105660RB-C21, and TED2021-132634A-I00), by the Generalitat de Catalunya (contract 2021-SGR-763), by the Gobierno de Aragon (T58_23R research group), by the European Union NextGenerationEU/PRTR, and by Lenovo-BSC Contract-Framework Contract (2020)., Peer Reviewed, Postprint (author's final draft)

Sequence alignment remains a fundamental problem in computer science with practical applications ranging from pattern matching to computational biology. The ever-increasing volumes of genomic data produced by modern DNA sequencers motivate improved software and hardware sequence alignment accelerators that scale with longer sequence lengths and high error rates without losing accuracy. Furthermore, the wide variety of use cases requiring sequence alignment demands flexible and efficient solutions that can match or even outperform expensive application-specific accelerators. To address these challenges, we propose GMX, a set of ISA extensions that enable efficient sequence alignment computations based on dynamic programming (DP). GMX extensions provide the basic building-block operations to perform fast tile-wise computations of the DP matrix, reducing the memory footprint and allowing easy integration into widely-used algorithms and tools. Furthermore, we provide an efficient hardware implementation that integrates GMX extensions in a RISC-V-based edge system-on-chip (SoC). Compared to widely-used software implementations, our hardware-software co-design leveraging GMX extensions obtains speed-ups from 25–265 ×, scaling to megabyte-long sequences. Compared to domain-specific accelerators (DSA), we demonstrate that GMX-accelerated implementations demand significantly less memory bandwidth, requiring less area per processing element (PE). As a result, a single GMX-enabled core achieves a throughput per area between 0.35-0.52 × that of state-of-the-art DSAs while being more flexible and reusing the core’s resources. Post-place-and-route results for a GMX-enhanced SoC in 22nm technology shows that GMX extensions only account for 1.7% of the overall area while consuming just 8.47mW. We conclude that GMX extensions represent versatile and scalable ISA additions to improve the performance of genome analysis tools and other use cases that require fast and efficient sequence, This work has been partially supported by the European HiPEAC Network of Excellence, by the Spanish Ministry of Science and Innovation [PID2019-107255GB-C21, TED2021-132634A-I00, and PID2020-113614RB-C21], by the Generalitat de Catalunya [2021- SGR-00763], by the European Union within the framework of the ERDF of Catalonia 2014-2020 under the DRAC project [001-P-001723] and by the European NextGenerationEU/PRTR, by Lenovo-BSC Contract-Framework Contract (2022), by National Science Foundation (NSF) within the PPoSS Award #2118709, and by the eProcessor project which received funding from the European HighPerformance Computing Joint Undertaking (JU) under grant agreement No 956702. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and the respective national research organisations from Spain (PCI2021-121991/ MCIN/AEI/10.13039/501100011033), Sweden, Greece, Italy, France, and Germany. The eProcessor project is also co-funded by the UE NextGenerationEU/PRTR. M. Doblas has been supported through an FPU fellowship [FPU20/04076]; Q. Aguado-Puig has been supported by PRE2021-101059 (founded by MCIN/AEI/10.13039/50110 0011033 and FSE+)., Peer Reviewed, Postprint (author's final draft)

Arm usage has substantially grown in the High-Performance Computing (HPC) community. Japanese supercomputer Fugaku, powered by Arm-based A64FX processors, held the top position on the Top500 list between June 2020 and June 2022, currently sitting in the second position. The recently released 7th generation of Amazon EC2 instances for compute-intensive workloads (C7g) is also powered by Arm Graviton3 processors. Projects like European Mont-Blanc and U.S. DOE/NNSA Astra are further examples of Arm irruption in HPC. In parallel, over the last decade, the rapid improvement of genomic sequencing technologies and the exponential growth of sequencing data has placed a significant bottleneck on the computational side. While the majority of genomics applications have been thoroughly tested and optimized for x86 systems, just a few are prepared to perform efficiently on Arm machines, let alone exploit the advantages of the newly introduced Scalable Vector Extensions (SVE). This thesis presents GenArchBench, the first genome analysis benchmark suite targeting Arm architectures. We have selected a set of computationally demanding kernels from the most widely used tools in genome data analysis and ported them to Arm-based A64FX and Graviton3 processors. The porting features the usage of the novel Arm SVE instructions, algorithmic and code optimizations, and the exploitation of Arm-optimized libraries. All in all, the GenArch benchmark suite comprises 13 multi-core kernels from critical stages of widely-used genome analysis pipelines, including base-calling, read mapping, variant calling, and genome assembly. Moreover, our benchmark suite includes different input data sets per kernel (small and large), each with a corresponding regression test to verify the correctness of each execution automatically. In this work, we present the optimizations implemented in each kernel and a detailed performance evaluation and comparison of their performance on four different architectures (i.e.

In molecular dynamics simulations we can often increase the time step by imposing constraints on bond lengths and bond angles. This allows us to extend the length of the time interval and therefore the range of physical phenomena that we can afford to simulate. We examine the existing algorithms and software for solving nonlinear constraint equations in parallel and we explain why it is necessary to advance the state-of-the-art. We present ILVES-PC, a new algorithm for imposing bond constraints on proteins accurately and efficiently. It solves the same system of differential algebraic equations as the celebrated SHAKE algorithm, but ILVES-PC solves the nonlinear constraint equations using Newton's method rather than the nonlinear Gauss-Seidel method. Moreover, ILVES-PC solves the necessary linear systems using a specialized linear solver that exploits the structure of the protein. ILVES-PC can rapidly solve constraint equations as accurately as the hardware will allow. The run-time of ILVES-PC is proportional to the number of constraints. We have integrated ILVES-PC into GROMACS and simulated proteins of different sizes. Compared with SHAKE, we have achieved speedups of up to 4.9× in single-threaded executions and up to 76× in shared-memory multi-threaded executions. Moreover, ILVES-PC is more accurate than P-LINCS algorithm. Our work is a proof-of-concept of the utility of software designed specifically for the simulation of polymers., This work has been partially supported by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033 (contracts PID2019-107255GB-C21, PID2019-105660RB-C21, and PID2019-107293GB-I00), by the Generalitat de Catalunya (contract 2017-SGR-1328), by the Gobierno de Aragón (E45_20R T58_20R research groups), and by Lenovo-BSC Contract-Framework Contract (2020). Santiago Marco was supported by the Agencia Estatal de Investigación (Spain) under Juan de la Cierva fellowship grant IJC2020-045916-I. Miquel Moretó was partially supported by the Agencia Estatal de Investigación (Spain) under Ramón y Cajal fellowship number RYC-2016-21104. Carl Christian Kjelgaard Mikkelsen is supported by eSSENCE, a collaborative e-Science programme funded by the Swedish Research Council within the framework of the strategic research areas designated by the Swedish Government., Peer Reviewed, Postprint (published version)

Here the Human Pangenome Reference Consortium presents a first draft of the human pangenome reference. The pangenome contains 47 phased, diploid assemblies from a cohort of genetically diverse individuals 1. These assemblies cover more than 99% of the expected sequence in each genome and are more than 99% accurate at the structural and base pair levels. Based on alignments of the assemblies, we generate a draft pangenome that captures known variants and haplotypes and reveals new alleles at structurally complex loci. We also add 119 million base pairs of euchromatic polymorphic sequences and 1,115 gene duplications relative to the existing reference GRCh38. Roughly 90 million of the additional base pairs are derived from structural variation. Using our draft pangenome to analyse short-read data reduced small variant discovery errors by 34% and increased the number of structural variants detected per haplotype by 104% compared with GRCh38-based workflows, which enabled the typing of the vast majority of structural variant alleles per sample.

Motivation: Advances in genomics and sequencing technologies demand faster and more scalable analysis methods that can process longer sequences with higher accuracy. However, classical pairwise alignment methods, based on dynamic programming (DP), impose impractical computational requirements to align long and noisy sequences like those produced by PacBio, and Nanopore technologies. The recently proposed WFA algorithm paves the way for more efficient alignment tools, improving time and memory complexity over previous methods. However, high-performance computing (HPC) platforms require efficient parallel algorithms and tools to exploit the computing resources available on modern accelerator-based architectures. Results: This paper presents WFA-GPU, a GPU (Graphics Processing Unit)-accelerated tool to compute exact gap-affine alignments based on the WFA algorithm. We present the algorithmic adaptations and performance optimizations that allow exploiting the massively parallel capabilities of modern GPU devices to accelerate the alignment computations. In particular, we propose a CPU-GPU co-design capable of performing inter-sequence and intra-sequence parallel sequence alignment, combining a succinct WFA-data representation with an efficient GPU implementation. As a result, we demonstrate that our implementation outperforms the original multi-threaded WFA implementation by up to 4.3 × and up to 18.2 × when using heuristic methods on long and noisy sequences. Compared to other state-of-the-art tools and libraries, the WFA-GPU is up to 29 × faster than other GPU implementations and up to four orders of magnitude faster than other CPU implementations. Furthermore, WFA-GPU is the only GPU solution capable of correctly aligning long reads using a commodity GPU., This research was supported by the European Union Regional Development Fund within the framework of the ERDF Operational Program of Catalonia 2014-2020 with a grant of 50% of total cost eligible under theDRAC project [001-P-001723] and Lenovo-BSC Contract-Framework Contract (2020). This work has also been granted by the Spanish Ministerio de Ciencia e Innovacion MCIN AEI/10.13039/501100011033 under contracts [PID2020-113614RB-C21] and [TIN2015-65316-P],NextGenerationEU/PRTR (projectTED2021132634A-I00), and by the Generalitat de Catalunya GenCat-DIUiE (GRR) (contracts [2021-SGR-00574], [2017-SGR-1328], [2017-SGR313], and [2017-SGR-1414]). M.M. was partially supported by the Spanish Ministry of Economy, Industry and Competitiveness under Ramon y Cajal fellowship number [RYC-2016-21104]. S.M. was supported by Juan de la Cierva fellowship grant [IJC2020-045916-I] funded by MCIN/AEI/10.13039/501100011033 and by European Union NextGenerationEU/PRTR. Q.A.was supported by the Spanish Ministerio de Ciencia e Innovacion under grant [PRE2021-101059]., Peer Reviewed, Postprint (published version)

Single-nucleotide variants (SNVs) in segmental duplications (SDs) have not been systematically assessed because of the limitations of mapping short-read sequencing data1,2. Here we constructed 1:1 unambiguous alignments spanning high-identity SDs across 102 human haplotypes and compared the pattern of SNVs between unique and duplicated regions3,4. We find that human SNVs are elevated 60% in SDs compared to unique regions and estimate that at least 23% of this increase is due to interlocus gene conversion (IGC) with up to 4.3 megabase pairs of SD sequence converted on average per human haplotype. We develop a genome-wide map of IGC donors and acceptors, including 498 acceptor and 454 donor hotspots affecting the exons of about 800 protein-coding genes. These include 171 genes that have ‘relocated’ on average 1.61 megabase pairs in a subset of human haplotypes. Using a coalescent framework, we show that SD regions are slightly evolutionarily older when compared to unique sequences, probably owing to IGC. SNVs in SDs, however, show a distinct mutational spectrum: a 27.1% increase in transversions that convert cytosine to guanine or the reverse across all triplet contexts and a 7.6% reduction in the frequency of CpG-associated mutations when compared to unique DNA. We reason that these distinct mutational properties help to maintain an overall higher GC content of SD DNA compared to that of unique DNA, probably driven by GC-biased conversion between paralogous sequences5,6., We thank T. Brown for help in editing this manuscript, P. Green for valuable suggestions, and R. Seroussi and his staff for their generous donation of time and resources. This work was supported in part by grants from the US National Institutes of Health (NIH 5R01HG002385, 5U01HG010971 and 1U01HG010973 to E.E.E.; K99HG011041 to P.H.; and F31AI150163 to W.S.D.). W.S.D. was supported in part by a Fellowship in Understanding Dynamic and Multi-scale Systems from the James S. McDonnell Foundation. E.E.E. is an investigator of the Howard Hughes Medical Institute (HHMI). This article is subject to HHMI’s Open Access to Publications policy. HHMI laboratory heads have previously granted a nonexclusive CC BY 4.0 licence to the public and a sublicensable licence to HHMI in their research articles. Pursuant to those licences, the author-accepted manuscript of this article can be made freely available under a CC BY 4.0 licence immediately on publication., Peer Reviewed, "Article signat per 19 autors/es: Mitchell R. Vollger, Philip C. Dishuck, William T. Harvey, William S. DeWitt, Xavi Guitart, Michael E. Goldberg, Allison N. Rozanski, Julian Lucas, Mobin Asri, Human Pangenome Reference Consortium, Katherine M. Munson, Alexandra P. Lewis, Kendra Hoekzema, Glennis A. Logsdon, David Porubsky, Benedict Paten, Kelley Harris, PingHsun Hsieh & Evan E. Eichler", Postprint (published version)

Nowadays, the efficient analysis and exploitation of genomic information is paramount to future advancements in the healthcare sector, such as better diagnosis techniques and the development of improved disease treatments. In the past decades, the exponential increase in the biological data production has fostered the development of more efficient genomic pipelines. For that, modern genome analysis requires better and more scalable algorithms, and improved high-performance implementations that can exploit current hardware accelerators. For most genome analysis pipelines, sequence mapping is one of the most computationally intensive and time-consuming processing stages. The ultimate goal of this work is to propose techniques to accelerate read mapping, leveraging novel algorithms and hardware vector extensions. In this thesis, we present a thorough performance characterization of the most widely-used genome-mapping tools and propose acceleration techniques that can effectively improve the performance of these tools. To that end, first, we identify the most time-consuming kernels, their performance bottlenecks, and the underlying causes of inefficiency. Afterwards, we design and implement an accelerated version of one of the most time-consuming steps: pairwise sequence alignment. For that, we propose to replace the classical dynamic-programming algorithm, used within these tools, with the recently proposed wavefront alignment algorithm (WFA). Moreover, we design and implement the first fully-vectorized version of the WFA, leveraging Intel's AVX2 and AVX-512 instructions, to further accelerate sequence-to-sequence alignment. As a result, we demonstrate that our vectorized WFA implementation outperforms the original scalar WFA implementation between 1.1x-2.4x. In turn, this renders speedups from 2.4x up to 826.7x compared to the most widely-used alignment algorithm, KSW2 (used within Minimap2 and Bwa-Mem2). We conclude that these tools can be significantly accelerated b

The RISC-V open Instruction Set Architecture (ISA) has proven to be a solid alternative to licensed ISAs. In the past 5 years, a plethora of industrial and academic cores and accelerators have been developed implementing this open ISA. In this paper, we present Sargantana, a 64-bit processor based on RISC-V that implements the RV64G ISA, a subset of the vector instructions extension (RVV 0.7.1), and custom application-specific instructions. Sargantana features a highly optimized 7-stage pipeline implementing out-of-order write-back, register renaming, and a non-blocking memory pipeline. Moreover, Sar-gantana features a Single Instruction Multiple Data (SIMD) unit that accelerates domain-specific applications. Sargantana achieves a 1.26 GHz frequency in the typical corner, and up to 1.69 GHz in the fast corner using 22nm FD-SOI commercial technology. As a result, Sargantana delivers a 1.77× higher Instructions Per Cycle (IPC) than our previous 5-stage in-order DVINO core, reaching 2.44 CoreMark/MHz. Our core design delivers comparable or even higher performance than other state-of-the-art academic cores performance under Autobench EEMBC benchmark suite. This way, Sargantana lays the foundations for future RISC-V based core designs able to meet industrial-class performance requirements for scientific, real-time, and high-performance computing applications., This work has been partially supported by the Spanish Ministry of Economy and Competitiveness (contract PID2019- 107255GB-C21), by the Generalitat de Catalunya (contract 2017-SGR-1328), by the European Union within the framework of the ERDF of Catalonia 2014-2020 under the DRAC project [001-P-001723], and by Lenovo-BSC Contract-Framework (2020). The Spanish Ministry of Economy, Industry and Competitiveness has partially supported M. Doblas and V. Soria-Pardos through a FPU fellowship no. FPU20-04076 and FPU20-02132 respectively. G. Lopez-Paradis has been supported by the Generalitat de Catalunya through a FI fellowship 2021FI-B00994. S. Marco-Sola was supported by Juan de la Cierva fellowship grant IJC2020-045916-I funded by MCIN/AEI/10.13039/501100011033 and by “European Union NextGenerationEU/PRTR”, and M. Moretó through a Ramon y Cajal fellowship no. RYC-2016-21104., Peer Reviewed, Postprint (author's final draft)

Advances in genomics and sequencing technologies demand faster and more scalable analysis methods that can process longer sequences with higher accuracy. However, classical pairwise alignment methods, based on dynamic programming (DP), impose impractical computational requirements to align long and noisy sequences like those produced by PacBio, and Nanopore technologies. The recently proposed Wavefront Alignment (WFA) algorithm paves the way for more efficient alignment tools, improving time and memory complexity over previous methods. Notwithstanding the advantages of the WFA algorithm, modern high performance computing (HPC) platforms rely on accelerator-based architectures that exploit parallel computing resources to improve over classical computing CPUs. Hence, a GPU-enabled implementation of the WFA could exploit the hardware resources of modern GPUs and further accelerate sequence alignment in current genome analysis pipelines. This thesis presents two GPU-accelerated implementations based on the WFA for fast pairwise DNA sequence alignment: eWFA-GPU and WFA-GPU. Our first proposal, eWFA-GPU, computes the exact edit-distance alignment between two short sequences (up to a few thousand bases), taking full advantage of the massive parallel capabilities of modern GPUs. We propose a succinct representation of the alignment data that successfully reduces the overall amount of memory required, allowing the exploitation of the fast on-chip memory of a GPU. Our results show that eWFA-GPU outperforms by 3-9X the edit-distance WFA implementation running on a 20 core machine. Compared to other state-of-the-art tools computing the edit-distance, eWFA-GPU is up to 265X faster than CPU tools and up to 56 times faster than other GPU-enabled implementations. Our second contribution, the WFA-GPU tool, extends the work of eWFA-GPU to compute the exact gap-affine distance (i.e., a more general alignment problem) between arbitrary long sequences. In this work, we propose a CPU-GPU

Sequence alignment remains a fundamental problem with practical applications ranging from pattern recognition to computational biology. Traditional algorithms based on dynamic programming are hard to parallelize, require significant amounts of memory, and fail to scale for large inputs. This work presents eWFA-GPU, a GPU (graphics processing unit)-accelerated tool to compute the exact edit-distance sequence alignment based on the wavefront alignment algorithm (WFA). This approach exploits the similarities between the input sequences to accelerate the alignment process while requiring less memory than other algorithms. Our implementation takes full advantage of the massive parallel capabilities of modern GPUs to accelerate the alignment process. In addition, we propose a succinct representation of the alignment data that successfully reduces the overall amount of memory required, allowing the exploitation of the fast shared memory of a GPU. Our results show that our GPU implementation outperforms by 3- 9× the baseline edit-distance WFA implementation running on a 20 core machine. As a result, eWFA-GPU is up to 265 times faster than state-of-the-art CPU implementation, and up to 56 times faster than state-of-the-art GPU implementations., This work was supported in part by the European Unions’s Horizon 2020 Framework Program through the DeepHealth Project under Grant 825111; in part by the European Union Regional Development Fund within the Framework of the European Regional Development Fund (ERDF) Operational Program of Catalonia 2014–2020 with a Grant of 50% of Total Cost Eligible through the Designing RISC-V-based Accelerators for next-generation Computers Project under Grant 001-P-001723; in part by the Ministerio de Ciencia e Innovacion (MCIN) Agencia Estatal de Investigación (AEI)/10.13039/501100011033 under Contract PID2020-113614RB-C21 and Contract TIN2015-65316-P; and in part by the Generalitat de Catalunya (GenCat)-Departament de Recerca i Universitats (DIUiE) (GRR) under Contract 2017-SGR-313, Contract 2017-SGR-1328, and Contract 2017-SGR-1414. The work of Miquel Moreto was supported in part by the Spanish Ministry of Economy, Industry and Competitiveness under Ramon y Cajal Fellowship under Grant RYC-2016-21104., Peer Reviewed, Postprint (published version)

Millions of species are currently being sequenced, and their genomes are being compared. Many of them have more complex genomes than model systems and raise novel challenges for genome alignment. Widely used local alignment strategies often produce limited or incongruous results when applied to genomes with dispersed repeats, long indels, and highly diverse sequences. Moreover, alignment using many-to-many or reciprocal best hit approaches conflicts with well-studied patterns between species with different rounds of whole-genome duplication. Here, we introduce Anchored Wavefront alignment (AnchorWave), which performs whole-genome duplication–informed collinear anchor identification between genomes and performs base pair–resolved global alignment for collinear blocks using a two-piece affine gap cost strategy. This strategy enables AnchorWave to precisely identify multikilobase indels generated by transposable element (TE) presence/absence variants (PAVs). When aligning two maize genomes, AnchorWave successfully recalled 87% of previously reported TE PAVs. By contrast, other genome alignment tools showed low power for TE PAV recall. AnchorWave precisely aligns up to three times more of the genome as position matches or indels than the closest competitive approach when comparing diverse genomes. Moreover, AnchorWave recalls transcription factor–binding sites at a rate of 1.05- to 74.85-fold higher than other tools with significantly lower false-positive alignments. AnchorWave complements available genome alignment tools by showing obvious improvement when applied to genomes with dispersed repeats, active TEs, high sequence diversity, and whole-genome duplication variation., This project is supported by the United States Department of Agriculture Agricultural Research Service, NSF No. 1822330, NSF No. 1854828, the European Union's Horizon 2020 Framework Programme under the DeepHealth project [825111], the European Union Regional Development Fund within the framework of The European Regional Development Fund Operational Program of Catalonia 2014 to 2020 with a grant of 50% of total cost eligible under the DRAC project [001-P-001723], and National Natural Science Foundation of China No. 31900486. M.C.S. was supported by NSF Postdoctoral Research Fellowship in Biology No. 1907343. M.M. was partially supported by the Spanish Ministry of Economy, Industry, and Competitiveness under Ramón y Cajal (RYC) fellowship number RYC-2016-21104., Peer Reviewed, Postprint (published version)

Pre-alignment filters are useful for reducing the computational requirements of genomic sequence mappers. Most of them are based on estimating or computing the edit distance between sequences and their candidate locations in a reference genome using a subset of the dynamic programming table used to compute Levenshtein distance. Some of their FPGA implementations of use classic HDL toolchains, thus limiting their portability. Currently, most FPGA accelerators offered by heterogeneous cloud providers support C/C++ HLS. In this work, we implement and optimize several state-of-the-art pre-alignment filters using C/C++ based-HLS to expand their portability to a wide range of systems supporting the OpenCL runtime. Moreover, we perform a complete analysis of the performance and accuracy of the filters and analyze the implications of the results. The maximum throughput obtained by an exact filter is 95.1 MPairs/s including memory transfers using 100 bp sequences, which is the highest ever reported for a comparable system and more than two times faster than previous HDL-based results. The best energy efficiency obtained from the accelerator (not considering host CPU) is 2.1 MPairs/J, more than one order of magnitude higher than other accelerator-based comparable approaches from the state of the art., 10.13039/501100008530-European Union Regional Development Fund (ERDF) within the framework of the ERDF Operational Program of Catalonia 2014-2020 with a grant of 50% of the total cost eligible under the Designing RISC-V based Accelerators for next generation computers project (DRAC) (Grant Number: [001-P-001723]) 10.13039/501100002809-Catalan Government (Grant Number: 2017-SGR-313 and 2017-SGR-1624) 10.13039/501100004837-Spanish Ministry of Science, Innovation and Universities (Grant Number: PID2020-113614RB-C21 and RTI2018-095209-B-C22), Peer Reviewed, Postprint (published version)

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud Computing or heterogeneous High-Performance Computing (HPC). The DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. The toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111, DeepHealth Project. Lluc Alvarez has been supported by the Spanish Ministry of Economy, Industry and Competitiveness under the Juan de la Cierva Formacion fellowship No. FJCI-2016-30984. Miquel Moreto has been supported by the Spanish Ministry of Economy, Industry and Competitiveness under the Ramon y Cajal fellowship No. RYC-2016-21104., Peer Reviewed, Postprint (author's final draft)

An FPGA accelerator for the computation of the semi-global Levenshtein distance between a pattern and a reference text is presented. The accelerator provides an important benefit to reduce the execution time of read-mappers used in short-read genomic sequencing. Previous attempts to solve the same problem in FPGA use the Myers algorithm following a column approach to compute the dynamic programming table. We use an approach based on diagonals that allows for some resource savings while maintaining a very high throughput of 1 alignment per clock cycle. The design is implemented in OpenCL and tested on two FPGA accelerators. The maximum performance obtained is 91.5 MPairs/s for 100 × 120 sequences and 47 MPairs/s for 300 × 360 sequences, the highest ever reported for this problem., This research was supported by the EU Regional Development Fund under the DRAC project [001-P-001723], by the MINECO-Spain (contract TIN2017-84553-C2-1-R), by the MICIU-Spain (contract RTI2018-095209-B-C22) and by the Catalan government (contracts 2017-SGR-1624, 2017-SGR313, 2017-SGR-1328). M.M. was partially supported by the MINECO under RYC-2016-21104. We thank Intel for granting us access to the DevCloud system and let us join the HARP research program. The presented HARP-2 results were obtained on resources hosted at the Paderborn Center for Parallel Computing (PC2) in the Intel Hardware Accelerator Research Program (HARP2)., Peer Reviewed, Postprint (author's final draft)

In the last years, advances in next-generation sequencing technologies have enabled the proliferation of genomic applications that guide personalized medicine. These applications have an enormous computational cost due to the large amount of genomic data they process. The first step in many of these applications consists in aligning reads against a reference genome. Very recently, the wavefront alignment algorithm has been introduced, significantly reducing the execution time of the read alignment process. This paper presents the first FPGA- based hardware/software co-designed accelerator of such relevant algorithm. Compared to the reference WFA CPU-only implementation, the proposed FPGA accelerator achieves performance speedups of up to 13.5× while consuming up to 14.6× less energy.ed medicine. These applications have an enormous computational cost due to the large amount of genomic data they process. The first step in many of these applications consists in aligning reads against a reference genome. Very recently, the wavefront alignment algorithm has been introduced, significantly reducing the execution time of the read alignment process. This paper presents the first FPGA- based hardware/software co-designed accelerator of such relevant algorithm. Compared to the reference WFA CPU-only imple- mentation, the proposed FPGA accelerator achieves performance speedups of up to 13.5× while consuming up to 14.6× less energy., This work has been supported by the European HiPEAC Network of Excellence, by the Spanish Ministry of Science and Innovation (contract PID2019-107255GB-C21/AEI/10.13039/501100011033), by the Generalitat de Catalunya (contracts 2017-SGR-1414 and 2017-SGR-1328), by the IBM/BSC Deep Learning Center initiative, and by the DRAC project, which is co-financed by the European Union Regional Development Fund within the framework of the ERDF Operational Program of Catalonia 2014-2020 with a grant of 50% of total eligible cost. Ll. Alvarez has been partially supported by the Spanish Ministry of Economy, Industry and Competitiveness under the Juan de la Cierva Formacion fellowship No. FJCI-2016-30984. M. Moreto has been partially supported by the Spanish Ministry of Economy, Industry and Competitiveness under Ramon y Cajal fellowship No. RYC-2016-21104., Peer Reviewed, Postprint (author's final draft)