ライフサイエンスコーパス: GPU

1 GPU parallelism improves speed and makes iteration a tra

2 e gas conditions with CO2 permeance of 1,020 GPU and CO2/N2 selectivity as high as 680, demonstrating

3 3.5x10(-7) mol m(-2) s(-1) Pa(-1) (ca. 1000 GPU).

4 We demonstrate the new software using 1024 GPUs in parallel on one of the world's fastest supercomp

5 from 4 to 10 (resp. With 2 CPU threads and 2 GPUs, H-BLAST can be faster than 16-threaded NCBI-BLASTX

6 howing a 23.5 CO(2)/N(2) selectivity at 2350 GPU of CO(2).

7 electivity of 663 with H(2) permeance of 240 GPU was achieved for promising green energy resource-H(2

8 aged membranes had a CO(2) permeance of 2504 GPU and ideal selectivity values of 37.2 and 23.8 for CO

9 lectivity of 58.8 and CO(2) permeance of 310 GPU at 35 degrees C.

10 ncreased propylene permeance (reaching 186.5 GPU) while maintaining an appealing propylene/propane se

11 -score-GPU is 68 times faster on an ATI 5870 GPU, on average, than the original CPU single-threaded i

12 smission rate for (LDH/FAS)(25)-PDMS of 7748 GPU together with CO(2) selectivity factors (SF) for SF(

13 atasets respectively on a single GPU node (8 GPUs) of the Cori Supercomputer.

14 speed of 7 frames per second using A100-80GB GPU.

15 n of Scrooge, KSW2, Edlib, Darwin-GPU, and a GPU implementation of GenASM, respectively.

16 Arioc, a GPU-accelerated short-read aligner, can compute WGS (who

17 a user-friendly interface between cupSODA, a GPU-powered kinetic simulator, and PySB, a Python-based

18 For numerical implementation, we developed a GPU-accelerated version of differential evolution to nav

19 onvenient, the second module may be run in a GPU-free environment.

20 n achieve performance that exceeds that of a GPU-based coprocessor.

21 ate how the cost of divergent branching on a GPU can be amortized across algorithms like HCP in order

22 racy within a single day of computation on a GPU cluster.

23 es (approximately 13 slices) per second on a GPU with 12 GB RAM compared with 6-8 minutes per slice f

24 Running on a GPU, the training time is sped up 21x and 30x (over CPU)

25 te a human/mouse alignment in under 6 h on a GPU-containing node without pre-partitioning, maintainin

26 nd oxRNA molecular dynamics simulations on a GPU-enabled high performance computing server.

27 In this work, we present a GPU-accelerated cosine similarity implementation for Tan

28 Here we propose a GPU-accelerated biclustering algorithm, based on searchi

29 y in a matter of minutes without requiring a GPU.

30 E will be effectively inaccessible without a GPU, and some assume CUDA.

31 hout requiring any technical knowledge about GPUs, C++ or GeNN.

32 Finally, we developed a freely accessible, GPU and CPU-powered dashboard that combines interactive

33 allelization strategy and leverages advanced GPU features.

34 'Anton' machine and large ensembles of AMBER GPU simulations.

35 an automated workflow tool to perform AMBER GPU MD simulations.

36 and user-friendly environment and the AMBER GPU code for a robust and high-performance simulation en

37 dings by using a fully force-field-based and GPU-accelerated approach, which allows the simulations t

38 s and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds +/- 40.5 and 204.

39 By leveraging parallel computing and GPU acceleration, our package achieves significant impro

40 umba for just-in-time compilation on CPU and GPU achieves hundred-fold speed improvements.

41 act of using hardware with different CPU and GPU features on the power consumption and latency for th

42 ory efficiency, easy access to multi-CPU and GPU hardware, and to distributed and cloud-based paralle

43 In our experiments with a four core CPU and GPU, SWIFTLINK achieves a 8.5x speed-up over the single-

44 00x on average), respectively, with FPGA and GPU acceleration.

45 00x on average), respectively, with FPGA and GPU acceleration.

46 raphy, deep learning, physical modeling, and GPU-accelerated robust optimization, with automatic anal

47 nd limitations of recent parallelization and GPU-based efforts are highlighted.

48 s free, open-source, platformindependent and GPU-vendor independent.

49 ke advantage of both multiple processors and GPU-acceleration to perform the numerically-demanding co

50 It benefits from using multiple threads and GPU calculations.

51 for better efficiency among various CPUs and GPUs combinations.

52 rted hardware types (including both CPUs and GPUs) and perform well on all of them.

53 y the observation that, compared to CPUs and GPUs, cutting-edge FPGAs demonstrate-in certain cases-su

54 heterogeneous computer that couples CPUs and GPUs, to accelerate BLASTX and BLASTP-basic tools of NCB

55 coprocessor architectures such as FPGAs and GPUs.

56 average 1.81 x speedup over the state-of-art GPU acceleration with only 7.2% of the energy, and a spe

57 By employing state-of-the-art GPU simulations and nano-particle resolved colloidal exp

58 esigned to run on any commercially available GPU and on any operating system.

59 ware executes concurrently on each available GPU device.

60 with the number of chains, and the available GPU memory limits the size of protein complexes which ca

61 We present a C-based, GPU-accelerated implementation of nested sampling that i

62 nstrate dramatic speed differentials between GPU assisted performance and CPU executions as the compu

63 differences in hardware architecture between GPUs and CPUs complicate the porting of existing code.

64 terface to handle the communications between GPUs.

65 uential NCBI-BLAST, the speedups achieved by GPU-BLAST range mostly between 3 and 4.

66 rty seconds when using an NVIDIA Tesla C2050 GPU.

67 Combining GPU and HCP, resulted in a speedup of at most 1,860-fold

68 sing a standard VR headset with a compatible GPU.

69 k, called GiCOPS, for efficient and complete GPU-acceleration of the modern database peptide search a

70 A detailed energy breakdown confirmed GPU usage as the dominant source of power consumption, u

71 SCENA is equipped with CPU + GPU (Central Processing Units + Graphics Processing Unit

72 federate both computational resources (CPU, GPU, FPGA, etc.) and datastores to support popular bioin

73 paper, we design and implement a new-age CPU-GPU HPC framework, called GiCOPS, for efficient and comp

74 We implement co-parallelization of CPU-GPU processing, which leads to a significant reduction o

75 Finally, the CPU-GPU methods and optimizations proposed in our work for c

76 mplementation utilizing multicore hybrid CPU/GPU computing resources, which can process terabytes of

77 ination and sample jitter in addition to CPU/GPU accelerated reconstruction for large datasets.

78 SneakySnake efficient to implement on CPUs, GPUs and FPGAs.

79 SneakySnake efficient to implement on CPUs, GPUs, and FPGAs.

80 of biochemical network models on NVIDIA CUDA GPUs.

81 CPU version of Scrooge, KSW2, Edlib, Darwin-GPU, and a GPU implementation of GenASM, respectively.

82 ics processing unit (GPU), we have developed GPU-BLAST, an accelerated version of the popular NCBI-BL

83 ource, hybrid multithreaded and distributed, GPU accelerated simulator of universal quantum circuits.

84 based architectures, a need for an efficient GPU accelerated strategy has emerged.

85 up in computation time on a cluster of eight GPUs compared to running the method on a single GPU.

86 st alternative method by 2.4-fold with eight GPUs.

87 mework (CUDAMPF) implemented on CUDA-enabled GPUs presented here, offers a finer-grained parallelism

88 the Smith-Waterman algorithm on CUDA-enabled GPUs.

89 anks to a PyTorch-based backend that enables GPU acceleration, pyaging is capable of rapid inference,

90 Cytokit offers (i) an end-to-end, GPU-accelerated image processing pipeline; (ii) efficien

91 Existing GPU based strategies have either been optimized for a sp

92 see text] improvement over several existing GPU-based database search algorithms for sufficiently la

93 is either comparable or better than existing GPU strategies.

94 se of sub-optimal algorithms in the existing GPU-accelerated methods resulting in significantly ineff

95 sive, thereby demanding the use of expensive GPUs.

96 sion of the code able to efficiently exploit GPU-accelerated systems for both the genetic relationshi

97 structures and memory allocation to exploit GPU parallel processing capabilities.

98 no method is currently available to exploit GPU technology for the reverse engineering of mechanisti

99 Extended GPU-based computational studies of a ternary complex con

100 g model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoi

101 Thanks to faster GPU-based algorithms, atomistic and coarse-grained simul

102 d in microarray gene expression analysis for GPU-equipped computers.

103 parallelized CCS algorithm using CUDA C for GPU computing.

104 ADEPT, a new sequence alignment strategy for GPU architectures that is domain independent, supporting

105 The implementation of MDR for GPUs (MDRGPU) includes core features of the widely used

106 n short-read alignments per second in a four-GPU system; it can align the reads from a human WGS sequ

107 tion approaches going all the way up to full GPU-accelerated ray tracing, they do not provide size-sp

108 o systems so that users can make use of GeNN GPU acceleration when developing their models in Brian,

109 In this paper, we present the GeNN (GPU-enhanced Neuronal Networks) framework, which aims to

110 training reports and a single desktop-grade GPU.

111 neural nets are implemented on power-hungry GPUs, beyond the reach of low-power edge-devices.

112 Our theoretical model is implemented in GPU (Graphics Processing Unit) accelerated software whic

113 HIP includes GPU-accelerated support for most common image processing

114 Massively Parallel Architectures, Including GPU Nodes (CAMPAIGN), a central resource for data cluste

115 was not sufficient to overcome the increased GPU cost.

116 out using the Amber software on inexpensive GPUs, providing approximately 1 mus/day per GPU, and >2.

117 curacy while achieving outstanding intranode GPU scalability.

118 very well with increasing CPU cores, and its GPU version, implemented in OpenCL, can have up to 158x

119 CPU strategies as well as the fastest known GPU methods for each domain.

120 fically, we characterize the effect of known GPU optimization techniques like use of shared memory.

121 showed localization of fluorescently labeled GPUs (~7% of total injected dose per gram tissue) in the

122 rabricks used here, these workflows are less GPU optimized and require benchmarking on the platform o

123 ing >10 times faster and requiring much less GPU memory than them.

124 Further, leveraging GPU instances has significantly improved the run-time of

125 Mendel-GPU, our OpenCL software, runs on Linux platforms and is

126 sentation learning workflow with minibatched GPU-accelerated clustering algorithms allows us to scale

127 MMseqs2-GPU is available under an open-source license at .

128 a stochastic simulation algorithm on modern GPUs, we simulated the dynamics of over one million neur

129 roviding close-to-peak performance on modern GPUs.

130 When two or more GPUs are available, Arioc's speed increases proportionat

131 Blocked multi-GPU parallel inference has been integrated into the main

132 (BLASTP, SWIPE, SWIMM2.0), can exploit multi-GPU nodes with linear scaling, and features an impressiv

133 per, we provide an optimized intranode multi-GPU implementation that can efficiently solve large-scal

134 source packages to run in a single or multi-GPU environment.

135 We have adapted Arioc to recent multi-GPU hardware architectures that support high-bandwidth p

136 provide 40 or more CPU threads and multiple GPU (general-purpose graphics processing unit) devices.

137 s driver enables it to scale across multiple GPUs and allows easy integration into software pipelines

138 ions compute tasks optimally across multiple GPUs.

139 peer-to-peer memory accesses among multiple GPUs.

140 al works have considered leveraging multiple GPUs to accelerate the ptychographic reconstruction.

141 Monte Carlo simulations running on multiple GPUs; we find a rounded transition and localization phys

142 can run in parallel in a single or multiple GPUs and each kernel simulates and scores the error of a

143 (GSH)-responsive polyurethane nanoparticles (GPUs) using a GSH-cleavable disulfide bond containing po

144 New GPU code further increases the speed of RMSD and TM-scor

145 the better performance provided by an Nvidia GPU.

146 ithub.com/aresio/cupSODA (requires an Nvidia GPU; developer.nvidia.com/cuda-gpus).

147 PDB file for pocket detection to our NVIDIA GPU-equipped servers through a WebGL graphical interface

148 d subsequently can be run on suitable NVIDIA GPU accelerators.

149 s, and OpenCL kernels support AMD and Nvidia GPUs.

150 tforms and is portable across AMD and nVidia GPUs.

151 stem consisting of x86 processors and NVIDIA GPUs.

152 nd tools, written in 'C for CUDA' for Nvidia GPUs.

153 to harness the computational power of NVIDIA GPUs (Graphics Processing Units) to greatly reduce proce

154 e execution of network simulations on NVIDIA GPUs, through a flexible and extensible interface, which

155 ementations negate the apparent advantage of GPU implementations.

156 comparisons inflate the actual advantages of GPU technology.

157 t of structures, WE organizes an ensemble of GPU-accelerated MD trajectory segments via intermittent

158 No knowledge of GPU computing is required from the user.

159 The use of GPU does not deteriorate the accuracy of our results.

160 raries will lead to a widespread adoption of GPUs in computational genomics.

161 Embracing the multicore functionality of GPUs represents a major avenue of local accelerated comp

162 riant callers scaled well with the number of GPUs across platforms, whereas somatic variant callers e

163 hibited more variation between the number of GPUs and computing platforms.

164 rs exhibited more variation in the number of GPUs with the fastest runtimes, suggesting that, at leas

165 CUDASW++4.0 changes the standing of GPUs in protein sequence database search with Smith-Wate

166 as well as the state-of-art acceleration on GPU and FPGA platforms.

167 borative review, and that can be deployed on GPU servers or cloud platforms.

168 offers improved computational efficiency on GPU-enabled systems over popular RNN architectures.

169 products to be most efficiently executed on GPU.

170 an open-source software package that runs on GPU and TPU accelerators through the JAX machine learnin

171 dynamics simulations in implicit solvent on GPU processors were used to generate ensembles of trajec

172 ng capabilities to facilitate computation on GPUs with limited memory.

173 and 7x faster than PointNovo and DeepNovo on GPUs, respectively, thus being more suitable for the ana

174 xtension algorithm for better performance on GPUs, and offers a performance tuning mechanism for bett

175 orithms optimized for parallel processing on GPUs and CPUs.

176 Memory requirements on GPUs have been reduced to fit widely available hardware,

177 en an impetus to accelerate MC simulation on GPUs whereas thread divergence remains a major issue for

178 Here we benchmark one GPU-accelerated software suite called NVIDIA Parabricks

179 Here, we develop KegAlign, an optimized GPU-enabled pairwise aligner.

180 With these enhancements, the optimized GPU implementation was on average an estimated 12,144 ti

181 MorphOT, which allows the use of both CPU or GPU resources.

182 GPUs, providing approximately 1 mus/day per GPU, and >2.5 ms data presented here.

183 nts, the author developed a high-performance GPU-based framework for the material point method, prior

184 tients undergoing esophagectomy with planned GPU reconstruction.

185 On cloud platforms, GPU-accelerated germline callers resulted in cost saving

186 remains a challenge, as only highly powerful GPUs, such as the A40 and A100, can (partially) compete

187 itude performance improvements over previous GPU-based approaches (CUDASW++3.0, ADEPT, SW#DB).

188 simulations, run using graphical processors (GPUs), were used to investigate the effect of conformati

189 sing software that uses graphics processors (GPUs) to address the most computationally intensive step

190 veloped a tool, called PtyGer (Ptychographic GPU(multiple)-based reconstruction), implementing our hy

191 ual Xeon 5520 and 3X speedup versus BEAGLE's GPU implementation on a Tesla T10 GPU for very large dat

192 TM-score-GPU is 68 times faster on an ATI 5870 GPU, on average, t

193 TM-score-GPU was applied to six sets of models from Nutritious Ri

194 ore for Graphical Processing Units (TM-score-GPU), using a new and novel hybrid Kabsch/quaternion met

195 nhanced snapshot compressive imaging (SeSCI)(GPU) showed the best performance of the CS algorithms st

196 Since GPUs are not always available on the same computing envi

197 search process can be performed on a single GPU in a massively parallel fashion.

198 large-scale ptychography datasets, a single GPU is typically insufficient for analysis and reconstru

199 DNA based datasets respectively on a single GPU node (8 GPUs) of the Cori Supercomputer.

200 ent simulations with performance on a single GPU that rivals the speed achieved by hundreds of CPUs.

201 ands of simultaneous simulations on a single GPU, HDRL-FP enables rapid convergence to the optimal re

202 a 10 mm path in under 15 minutes on a single GPU, which is 5-8 orders of magnitude faster than compet

203 ses of extensive genomic regions on a single GPU.

204 s compared to running the method on a single GPU.

205 xploiting hierarchical parallelism on single GPU and takes full advantage of limited resources based

206 ightweight architecture to train on standard GPUs.

207 benchmark dataset of 71 protein structures, GPU-I-TASSER achieves on average a 10x speedup with comp

208 reparation using any computer and a suitable GPU.

209 RABiTPy supports GPU and CPU processing as well as cloud computing.

210 s BEAGLE's GPU implementation on a Tesla T10 GPU for very large data sizes.

211 thermore, H-BLAST is 1.5-4 times faster than GPU-BLAST.

212 In this study, we demonstrate that GPU-accelerated high-speed FLIM can effectively separate

213 Our study demonstrates that GPUs can be used to greatly accelerate genomic workflows

214 The GPU implementation substantially decreases computational

215 The GPU version of Scrooge achieves a 4.0x, 80.4x, 6.8x, 12.

216 The GPU-based parallel implementation of the Gillespie stoch

217 uses the NVIDIA CUDA interface to access the GPU.

218 parallel Graphics Processing Unit, i.e. the GPU computing technology.

219 ve, single-threaded CPU implementations, the GPU yields a large improvement in the execution time.

220 t enables high-performance simulation in the GPU-resident NAMD3 molecular dynamics engine.

221 a model using the thread parallelism of the GPU.

222 by 25-fold solely by parallelization on the GPU.

223 g of biomolecules into a grid/lattice on the GPU.

224 urn, better facilitates its mapping onto the GPU.

225 obs-MPI using eight nodes is faster than the GPU-accelerated QuickProbs running on a Tesla K20.

226 -TASSER by extending its capabilities to the GPU architecture.

227 Using the GPU to store and render the image sequence data enables

228 es interactively on the system CPU while the GPU handles 3-D visualization tasks.

229 e more expensive than CPU runs because their GPU acceleration was not sufficient to overcome the incr

230 This GPU implementation allows for large-scale analysis of ep

231 fying Arioc's implementation to exploit this GPU memory architecture we obtained a further 1.8x-2.9x

232 We also improve its speed through GPU parallelism.

233 petitive processes and facilitates access to GPU clusters, whose high-performance processing power ma

234 mitation by using graphical processing unit (GPU) base-calling.

235 recent advances in graphics processing unit (GPU) computing have added a promising new option.

236 Graphics processing unit (GPU) computing is an affordable alternative for accelera

237 oit the power of a graphics-processing unit (GPU) from a browser without any third-party plugin.

238 A Graphics Processing Unit (GPU) implementation and downsampling strategies enable t

239 aster than current graphics processing unit (GPU) implementations.

240 s pipeline with a graphical processing unit (GPU) in 1-12 h (depending on frame size).

241 data analysis in a graphics processing unit (GPU) infrastructure.

242 ver and distributed Graphic Processing Unit (GPU) parallel computations.

243 cessor cores and a graphics processing unit (GPU) simultaneously.

244 ork, relative to a graphics processing unit (GPU) that uses a comparable 12-nanometer technology proc

245 IA Volta 100 (V100) Graphic Processing Unit (GPU) to 46.71 seconds for our largest dataset of 11.3 mi

246 that can use the graphical processing unit (GPU) to reduce runtime.

247 rallel manner on a graphics processing unit (GPU) using CUDA platform.

248 a general-purpose graphics processing unit (GPU), we have developed GPU-BLAST, an accelerated versio

249 a modern consumer graphics processing unit (GPU), we report a 92x increase in the speed of an exhaus

250 rn traditional and graphics processing unit (GPU)-accelerated machines, from workstations to supercom

251 Here the graphics processing unit (GPU)-accelerated MMseqs2 delivers 6x faster single-prote

252 With graphics processing unit (GPU)-based CUDA C/C++ implementation, this new attenuati

253 ifts, and extended graphics processing unit (GPU)-based quantum mechanics/molecular mechanics (QM/MM)

254 its mapping onto a graphics processing unit (GPU).

255 rallel computing on graphic processing unit (GPU).

256 on an NVIDIA V100 graphics processing unit (GPU).

257 implemented in a graphical processing unit (GPU).

258 eature that allows graphics-processing-unit (GPU)-based processing for interactive data analysis, suc

259 Graphical Processing Units (GPU) computing is now ubiquitous in the current-generati

260 ms accelerated on Graphics Processing Units (GPU), scaled magnetic versions of p-bit IMs could lead t

261 take advantage of graphics processing units (GPUs) and result in many fold higher speedups over previ

262 Graphics processing units (GPUs) are capable of efficiently running highly parallel

263 on ATI and nVidia graphics processing units (GPUs) for maximal speed.

264 GPU that exploits graphics processing units (GPUs) for parallel stochastic simulations of biological/

265 infrastructures, Graphics Processing Units (GPUs) offer opportunities to accelerate genomic workflow

266 Graphics processing units (GPUs) provide an inexpensive and computationally powerfu

267 Although graphics processing units (GPUs) provide high performance for such large-scale ptyc

268 port for multiple graphics processing units (GPUs) support, which makes it possible to run efficientl

269 By using graphics processing units (GPUs) the time needed to build these models is decreased

270 , we use multiple graphics processing units (GPUs) to compute the real frequency spectrum of the boso

271 s in parallel, on graphics processing units (GPUs) using NVidia Compute Unified Device Architecture (

272 uding inexpensive graphics processing units (GPUs), it has remained infeasible to simulate the foldin

273 tionary models on graphics processing units (GPUs), making use of the large number of processing core

274 r computing using graphics processing units (GPUs), such as PyTorch and TensorFlow.

275 Graphics processing units (GPUs), the hardware responsible for rendering computer g

276 intensive use of graphics processing units (GPUs), we have been able to run the latter model for mor

277 performance grade graphics processing units (GPUs).

278 so one or several graphics processing units (GPUs).

279 with 4 cores of graphical processing units (GPUs; GK210, Nvidia Tesla K80, USA).

280 ty after esophagectomy with gastric pull-up (GPU).

281 MEDUSA uses GPU (graphics processing unit) accelerated hardware and

282 Our proposed strategy uses GPU specific optimizations that do not rely on the natur

283 to parallelize evolutionary algorithms using GPU computing for the inference of mechanistic GRNs that

284 ctive data mining of spectral features using GPU-based manipulation of the spectral distribution.

285 past aortic stenosis (AS) are studied using GPU-accelerated patient-specific computational fluid dyn

286 Using GPUs and multiple cores, ASTRAL-MP is able to analyze da

287 Using GPUs to run MDR on a genome-wide dataset allows for stat

288 able to perform chromosome simulations using GPUs via OpenMM Python API, called Open-MiChroM.

289 on for batch effect removal, and can utilize GPU when available.

290 By utilizing GPUs, we achieve around a 30-fold speedup in protein and

291 Capturing metadata (e.g. package versions, GPU model) currently requires repetitious code and is di

292 ython, Matlab and Java as well as CPU versus GPU implementations.

293 temporal and computational (e.g. CPU versus GPU) scales, and then to visualize and interpret integra

294 d ensemble (WE) strategy in combination with GPU computing.

295 esults show that the GP model, combined with GPU-enabled PPLs, effectively retrieves true emission sc

296 It requires a windows computer with GPU that supports OpenCL 1.2 and OpenGL 4.0.

297 get genes leveraging parallel computing with GPU devices, (iii) all-in-one analytics with novel featu

298 Using DOCTORS, parallel computing with GPU enables the cone-beam CT dose estimation nearly in r

299 f our former DASC algorithm implemented with GPU.

300 and is accompanied by a Python version with GPU acceleration.