Enzo Rucci

An energy-aware performance analysis of SWIMM: Smith-Waterman implementation on Intel's Multicore and Manycore architectures

Alignment is essential in many areas such as biological, chemical and criminal forensics. The well‐known Smith–Waterman (SW) algorithm is able to retrieve the optimal local alignment with quadratic time and space complexity. There are several implementations that take advantage of computing parallelization, such as manycores, FPGAs or GPUs, in order to reduce the alignment effort. In this research, we adapt, develop and tune the SW algorithm named SWIMM on a heterogeneous platform based on Intels Xeon and Xeon Phi coprocessor. SWIMM is a free tool available in a public git repository https://github.com/enzorucci/SWIMM. We efficiently exploit data and thread‐level parallelism, reaching up to 380 GCUPS on heterogeneous architecture, 350 GCUPS for the isolated Xeon and 50 GCUPS on Xeon Phi. Despite the heterogeneous implementation obtaining the best performance, it is also the most energy‐demanding. In fact, we also present a trade‐off analysis between performance and power consumption. The greenest configuration is based on an isolated multicore system that exploits AVX2 instruction set architecture reaching 1.5 GCUPS/Watts. Copyright

Smith-Waterman Algorithm on Heterogeneous Systems: A Case Study

The well-known Smith-Waterman (SW) algorithm is a high-sensitivity method for local alignments. However, SW is expensive in terms of both execution time and memory usage, which makes it impractical in many applications. Some heuristics are possible but at the expense of losing sensitivity. Fortunately, previous research have shown that new computing platforms such as GPUs and FPGAs are able to accelerate SW and achieve impressive speedups. In this paper we have explored SW acceleration on a heterogeneous platform equipped with an Intel Xeon Phi coprocessor. Our evaluation, using the well-known Swiss-Prot database as a benchmark, has shown that a hybrid CPU-Phi heterogeneous system is able to achieve competitive performance (62.6 GCUPS), even with moderate low-level optimisations.

OSWALD: OpenCL Smith–Waterman on Altera’s FPGA for Large Protein Databases

The well-known Smith–Waterman algorithm is a high-sensitivity method for local sequence alignment. Unfortunately, the Smith–Waterman algorithm has quadratic time complexity, which makes it computationally demanding for large protein databases. In this paper, we present OSWALD, a portable, fully functional and general implementation to accelerate Smith–Waterman database searches in heterogeneous platforms based on Altera’s FPGA. OSWALD exploits OpenMP multithreading and SIMD computing through SSE and AVX2 extensions on the host while taking advantage of pipeline and vectorial parallelism by way of OpenCL on the FPGAs. Performance evaluations on two different heterogeneous architectures with real amino acid datasets show that OSWALD is competitive in comparison with other top-performing Smith–Waterman implementations, attaining up to 442 GCUPS peak with the best GCUPS/watts ratio.The well-known Smith–Waterman algorithm is a high-sensitivity method for local sequence alignment. Unfortunately, the Smith–Waterman algorithm has quadratic time complexity, which makes it computat...

State-of-the-Art in Smith–Waterman Protein Database Search on HPC Platforms

Searching biological sequence database is a common and repeated task in bioinformatics and molecular biology. The Smith–Waterman algorithm is the most accurate method for this kind of search. Unfortunately, this algorithm is computationally demanding and the situation gets worse due to the exponential growth of biological data in the last years. For that reason, the scientific community has made great efforts to accelerate Smith–Waterman biological database searches in a wide variety of hardware platforms. We give a survey of the state-of-the-art in Smith–Waterman protein database search, focusing on four hardware architectures: central processing units, graphics processing units, field programmable gate arrays and Xeon Phi coprocessors. After briefly describing each hardware platform, we analyse temporal evolution, contributions, limitations and experimental work and the results of each implementation. Additionally, as energy efficiency is becoming more important every day, we also survey performance/power consumption works. Finally, we give our view on the future of Smith–Waterman protein searches considering next generations of hardware architectures and its upcoming technologies.

First Experiences Accelerating Smith-Waterman on Intel's Knights Landing Processor.

The well-known Smith-Waterman (SW) algorithm is the most commonly used method for local sequence alignments. However, SW is very computationally demanding for large protein databases. There are several implementations that take advantage of parallel capacities on many-cores, FPGAs or GPUs, in order to increase the alignment throughtput. In this paper, we have explored SW acceleration on Intel KNL processor. The novelty of this architecture requires the revision of previous programming and optimization techniques on many-core architectures. To the best of authors knowledge, this is the first KNL architecture assessment for SW algorithm. Our evaluation, using the renowned Environmental NR database as benchmark, has shown that multi-threading and SIMD exploitation showed competitive performance (351 GCUPS) in comparison with other implementations.

Accelerating Smith-Waterman Alignment of Long DNA Sequences with OpenCL on FPGA.

With the greater importance of parallel architectures such as GPUs or Xeon Phi accelerators, the scientific community has developed efficient solutions in the bioinformatics field. In this context, FPGAs begin to stand out as high performance devices with moderate power consumption. This paper presents and evaluates a parallel strategy of the well-known Smith-Waterman algorithm using OpenCL on Intel/Altera’s FPGA for long DNA sequences. We efficiently exploit data and pipeline parallelism on a Intel/Altera Stratix V FPGA reaching upto 114 GCUPS in less than 25 watt power requirements.

Relation between cost of drug treatment and body mass index in people with type 2 diabetes in Latin America

Aims Despite the frequent association of obesity with type 2 diabetes (T2D), the effect of the former on the cost of drug treatment of the latest has not been specifically addressed. We studied the association of overweight/obesity on the cost of drug treatment of hyperglycemia, hypertension and dyslipidemia in a population with T2D. Methods This observational study utilized data from the QUALIDIAB database on 3,099 T2D patients seen in Diabetes Centers in Argentina, Chile, Colombia, Peru, and Venezuela. Data were grouped according to body mass index (BMI) as Normal (18.5≤BMI<25), Overweight (25≤BMI<30), and Obese (BMI≥30). Thereafter, we assessed clinical and metabolic data and cost of drug treatment in each category. Statistical analyses included group comparisons for continuous variables (parametric or non-parametric tests), Chi-square tests for differences between proportions, and multivariable regression analysis to assess the association between BMI and monthly cost of drug treatment. Results Although all groups showed comparable degree of glycometabolic control (FBG, HbA1c), we found significant differences in other metabolic control indicators. Total cost of drug treatment of hyperglycemia and associated cardiovascular risk factors (CVRF) increased significantly (p<0.001) with increment of BMI. Hyperglycemia treatment cost showed a significant increase concordant with BMI whereas hypertension and dyslipidemia did not. Despite different values and percentages of increase, this growing cost profile was reproduced in every participating country. BMI significantly and independently affected hyperglycemia treatment cost. Conclusions Our study shows for the first time that BMI significantly increases total expenditure on drugs for T2D and its associated CVRF treatment in Latin America.

SWIMM 2.0: Enhanced Smith–Waterman on Intel’s Multicore and Manycore Architectures Based on AVX-512 Vector Extensions

The well-known Smith–Waterman (SW) algorithm is the most commonly used method for local sequence alignments, but its acceptance is limited by the computational requirements for large protein databases. Although the acceleration of SW has already been studied on many parallel platforms, there are hardly any studies which take advantage of the latest Intel architectures based on AVX-512 vector extensions. This SIMD set is currently supported by Intel’s Knights Landing (KNL) accelerator and Intel’s Skylake (SKL) general purpose processors. In this paper, we present an SW version that is optimized for both architectures: the renowned SWIMM 2.0. The novelty of this vector instruction set requires the revision of previous programming and optimization techniques. SWIMM 2.0 is based on a massive multi-threading and SIMD exploitation. It is competitive in terms of performance compared with other state-of-the-art implementations, reaching 511 GCUPS on a single KNL node and 734 GCUPS on a server equipped with a dual SKL processor. Moreover, these successful performance rates make SWIMM 2.0 the most efficient energy footprint implementation in this study achieving 2.94 GCUPS/Watts on the SKL processor.

Self-administered structured food record for measuring individual energy and nutrient intake in large cohorts: Design and validation

INTRODUCTION Several instruments developed to assess dietary intake of groups or populations have strengths and weaknesses that affect their specific application. No self-administered, closed-ended dietary survey was previously used in Argentina to assess current food and nutrient intake on a daily basis. OBJECTIVE To design and validate a self-administered, structured food record (NutriQuid, NQ) representative of the adult Argentine populations food consumption pattern to measure individual energy and nutrient intake. MATERIALS AND METHODS Records were loaded onto a database using software that checks a regional nutrition information system (SARA program), automatically quantifying energy and nutrient intake. NQ validation included two phases: (1) NQ construct validity comparing records kept simultaneously by healthy volunteers (45-75 years) and a nutritionist who provided meals (reference), and (2) verification of whether NQ reflected target population consumption (calories and nutrients), week consumption differences, respondent acceptability, and ease of data entry/analysis. Data analysis included descriptive statistics, repeated measures ANOVA, intraclass correlation coefficient, nonparametric regression, and cross-classification into quintiles. RESULTS The first validation (study group vs. reference) showed an underestimation (10%) of carbohydrate, fat, and energy intake. Second validation: 109 volunteers (91% response) completed the NQ for seven consecutive days. Record completion took about 9min/day, and data entry 3-6min. Mean calorie intake was 2240±119kcal/day (42% carbohydrates, 17% protein, and 41% fat). Intake significantly increased in the weekend. CONCLUSION NQ is a simple and efficient tool to assess dietary intake in large samples.

Blocked All-Pairs Shortest Paths Algorithm on Intel Xeon Phi KNL Processor: A Case Study

Manycores are consolidating in HPC community as a way of improving performance while keeping power efficiency. Knights Landing is the recently released second generation of Intel Xeon Phi architecture. While optimizing applications on CPUs, GPUs and first Xeon Phi’s has been largely studied in the last years, the new features in Knights Landing processors require the revision of programming and optimization techniques for these devices. In this work, we selected the Floyd-Warshall algorithm as a representative case study of graph and memory-bound applications. Starting from the default serial version, we show how data, thread and compiler level optimizations help the parallel implementation to reach 338 GFLOPS.