S
SAD image, stereo matching
483
Scalability
atlas construction
789
CCL
580
CT image reconstruction
676
fast circuit optimization
375
MO computations
8
speed-limit-sign recognition
498 , 508 , 512–513
SVM
293
Scale Invariant Feature Transform (SIFT), speed-limit-sign recognition
505 , 508–510
Scaling
black hole simulations
107–108
CT image reconstruction
674
dynamical quadrature grids
37 , 40–41
electronic structure
65 , 67 , 71–72
fast circuit optimization
375
genome matching
182–183
Graph Cuts for computer vision
445 , 447
MO computations
18
molecular electrostatics
50
object detection
520 , 524 , 532–533 , 542
pattern matching acceleration
194–195
SPIRiT MRI
734
VSM
458
Scaling coefficient, LB models
396–397
Scan algorithms
integral image calculation
526–530
pattern matching acceleration
188–191 , 196–198
Scatter-gather iterations, Multi-GPU Cascade SVM
305
Scattering angle, photon transport
247 , 254–255
Scattering direction
LB methods
384–385
photon transport
254–256
Scheduling kernel, macro-gate event-driven simulation
352
Schrödinger equation
electronic structure
59
MO computations
8
Scientific simulation, GPU computing status
2
Scratch memory model, atlas construction
786–787
Scripting, ABM transition function behavior
317–319
Secondary structure, RNA folding problem
199–200
Seed buffer, photon transport
256
Segmentation
atlas construction
771–772
brain connectivity reconstruction
793–797 , 802 , 809 , 811–812
CCL
569 , 574
DBT
651
Graph Cuts for computer vision
439 , 447–448
macro-gates
349–350 , 356–358
medical imaging
737
radiographic image simulation
815–816
real-time stereo
475 , 487
Segmentation algorithm, gate-level simulation
347–350 , 355–360 , 363
Semiautomatic axon segmentation, brain connectivity reconstruction
793–795
Sensitivity list, macro-gate event-driven simulation
352
Separability property, integral image calculation
527
Sequence database scanning, with SW algorithm
long sequences
168–169
overview
155–157
registers and loop unrolling
163–168
shared memory implementation
160–162
simple CUDA implementation
157–160
Sequential minimal optimization (SMO)
future work
310
map step
298
reduce step
299–302
testing phase
302–303
Serial input/output operations, image/video processing
558–560
SGEMM
character recognition
289
SVM
303
Shared map, ASR
604 , 608–610 , 615
Shooting function, photon transport
258
Short-range cutoff, electrostatics calculations
50–55 , 57–58
SHUTTLE dataset, SVM evaluation
308
Sierpinski triangle, IFS
264
Signal-to-noise ratio (SNR)
black hole simulations
103
CT reconstruction
704–706
MRI reconstruction
720 , 723–724 , 726
SPIRiT MRI
723–724 , 726
Signal processing
GPU computing status
599–600
LDPC
619
real-time stereo
473–474
speed-limit-sign recognition
514
SPIRiT MRI
723
Similarity evaluation, chemical informatics
algorithmic transformation and memory optimization
27–30
core methods
22
data-parallel objective function
23–25
LINGO overview
21–22
overview
19–21
parallelization and arithmetic optimization
22–27
performance comparison
30 , 32
3D shape molecule overlay
21
SIML, chemical informatics
19 , 22 , 28–33
Simulation kernel, gate-level simulation
352 , 354
Simulation phase, gate-level simulation
event-driven
352
oblivious simulation
352–354
overview
351–355
test benches
354–355
Simultaneous algebraic reconstruction techniques (SART)
iterative CT reconstruction algorithms
700–702
and OS-SIRT
695
Simultaneous iterative reconstruction techniques (SIRT), CT reconstruction
694 , 700–702
Single instruction multiple data (SIMD)
CT image reconstruction
676
DBT GPU acceleration
650
fast circuit optimization
366–367
GPU-based parallelization
368
ITK-based medical imaging
738
and OS-SIRT
696
path tracing for random walks
401 , 403
speech models
614
stereo matching
489
Single-instruction multiple-thread (SIMT)
DBT GPU acceleration
650
gate-level simulation
345–346
genome-matching acceleration
174
Single-photon emission computed tomography (SPECT), tomographic image reconstruction
685
Single-precision (SP)
ASR
613
black hole simulations
105–107
CT image reconstruction
663
dynamical quadrature grids
39
electronic structure
67 , 69 , 71
FFT
629 , 640
MD methods
69
MRI reconstruction
720
n -body simulations
131
object detection
539–540
radiographic image simulation
828
SPIRiT MRI
724 , 728 , 733
Single resolution adaptive window, stereo matching
487–491
Sizing heuristics, macro-gates
355
Skin strain
CUDA kernel code
422
and facial pose
418–419
Skip-ahead algorithm, Mersenne Twister MT19937
240–242
Slack allocation (SA), fast circuit optimization evaluation
374
SMILES string, and LINGO
21–22 , 28
Smith-Waterman (SW) algorithm
pattern matching
algorithms, implementations, evaluations
187–192
antidiagonal approach
188–189
basic problem
185–186
core method
186–187
data packing
192
future work
196
hash tables
192
overlapping search
191–192
overview
193–196
reduced dependency
187–188
row/column parallel approach
188–191
protein identification
long sequences
168–169
overview
156–157
registers and loop unrolling
163–168
shared memory implementation
160–162
simple CUDA implementation
157–160
sequence database scanning
155–156
Sobol quasi-random generator
formulation
235
implementation
236
overview
231–232 , 235
parallelization
235–236
performance evaluation
242–245
Soft-thresholding, SPIRiT MRI
727 , 729
Solution construction phase, AntMinerGPU
329–330
Solution-evaluation kernel, AntMinerGPU
335–337
Source reading, de-mosaicing
588–589
Sparse-matrix vector multiplication (SpMV), MRI reconstruction
717
Sparse warps, random walks in path tracing
404
Sparsity, SPIRiT MRI
724
Speech feature extactor, speech recognition application
602
Speech model
performance analysis
613–615
speech recognition application
602
Speed-limit-sign recognition
compute power adjustments
511–512
fast-radial symmetry
505–506
feature-based pipeline
499–501
FFT correlation with nonlinear filters
507
future work
513–514
implementation
505–507
methods
499–505
overview
497–498
pipeline scalability
512–513
recognition results
508
results
507–513
SIFT-based pipeline
505
template-based pipeline
500–505
Spin-orbit (SO) interactions, black hole simulations
109
Spring forces, and LB methods
395
Stage-parallel processing, object detection
536–537 , 540
State-based agent simulation, ABM with CUDA
314–315
Static pathway, VSM
452–453 , 455–457 , 459 , 466–467
Statistical modeling
GPU computing status
229
speed-limit-sign recognition
512
Stellar spectral synthesis
basic problem
95
flux calculation/aggregation
95–96
GRASSY platform
division of labor
97–98
interpolation decomposition
97
overview
97
performance model
100
precision issues
98–99
pseudo-code
98–99
testing
100
texture packing
97
steps
94–95
Stereo matching
algorithms, implementations, evaluations
475–485
basic problem
473–474
core method
475
cross-checking
484–485
foreground vs . full image
490–493
Middlebury evaluation
486–487
multiresolution background modeling
475–478
multiresolution vs . single resolution
487–490
multiresolution stereo matching
478–479
performance evaluation
486–493
single CUDA kernel
479–485
Stream compaction, object detections
533–535
Streaming-multiprocessors (SMs)
CT image reconstruction
672–673 , 675
DBT GPU acceleration
650–652
speed-limit-sign recognition
512–513
tomographic image reconstruction
684
Stream processors (SP)
gate-level simulation
345
LDPC performance
626
Strong classifiers, object detection
521–522
Structure of Array (SoA) format
ABM communication
318
XML-driven CUDA code generation
316–317
Stump-based classifier, definition
521–522
Successive overview relaxation (SOR) method, atlas construction
778–780
Sum-product algorithm (SPA), LDPC
620–621 , 626
Sum of squared differences (SSD), B-splines
754
Supercomputing clusters
black hole simulations
107–109
pattern matching acceleration
185–196
Support vector machine (SVM)
algorithms, implementations, evaluations
296–306
basic problem
293
binary SVM
294–295
block/grid sizes
303–304
core method
294–295
future work
310
GPU performance
308–310
instance port
306
multiclass SVM
295
Multi-GPU cascade SVM
304–305 , 307 , 310
performance evaluation
306–310
SMO map step
298
SMO reduce step
299–302
testing phase
302–303
SwissProt database
pattern matching
186
and SW algorithm
157 , 168
Synthesizable test benches, gate-level simulation
354–355
System-level compilation, gate-level simulation
combinatorial logic extraction
348
definition
347
levelization
348
macro-gate segmentation
349–350
synthesis
348
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
3.133.126.199