HIGH PERFORMANCE COMPUTING OKULICKA-DŁUŻEWSKA F. Księgarnia

High Performance Computing

1 Introduction to HPC
2 MPI
2.1 Program compilation and running
2.2 Using MPI library
2.2.1 MPI headers
2.2.2 MPI functions
2.2.3 Types of MPI Calls
2.2.4 MPI programs
2.3 Communication
2.3.1 Messsages in MPI
2.4 Non-blocking communication
2.4.1 Non-blocking modes
2.4.2 Completion
2.4.3 Multiple completion
2.4.4 PROBE
2.4.5 CANCELL
2.5 Persistent communication
2.5.1 Send-receive
2.5.2 MPI_Request_free
2.6 Collective communication
2.6.1 Barrier synchronization
2.6.2 Broadcast
2.6.3 Scatter
2.6.4 Gather
2.6.5 MPLReduce
2.7 Timers
2.8 Datatypes in MPI
2.8.1 Derived data in MPI
2.9 Virtual topologies
2.9.1 Cartesian topologies
2.9.2 Graph topologies
3 Parallel linear algebra
3.1 Gaussian Elimination
3.1.1 Computational cost
3.1.2 Parallel Gaussian Elimination
3.1.3 Partia! pivoting
3.2 Backward substitution
4 Standard Libraries
4.1 BLAS
4.2 Gauss using BLAS
4.3 ATLAS
4.4 LAPACK
4.5 ScaLAPACK
4.6 BLACS
4.7 PBLAS
4.8 Gauss with PBLAS
4.9 Data layouts
4.10 PETSc
5 Parallel LU
5.1 LU by BLAS
5.2 LU on the two-dimensional grid
5.2.1 Seąuential LU
5.2.2 Parallel LU algorithm
5.3 LU in LAPACK
5.3.1 LAPACK Metodology
5.4 Sparse LU
5.5 Loops order in LU decomposition
6 Parallel Matrix Multiplication
6.1 Cannon‘s Algorithm on 2D grid
6.1.1 ID Cannon‘s Algorithm
6.2 Strassen‘s Algorithm
6.3 DNS Algorithm {Dekel, Nassimi, Sahni)
6.4 Finał remarks
7 Parallel graph algorithms
7.1 Basic definitions
7.2 Finding a minimum spanning tree
7.2.1 Prim‘s Algorithm
7.3 Dijkstra algorithm for finding the shortest path
7.4 The all pairs shortest path problem
7.4.1 Parallel Dijkstra‘s algorithm
7.4.2 Cannon‘s algorithm
7.4.3 Floyd‘s algorithm
7.5 List representation
8 Parallel błock algorithms
8.1 Błock Gaussian elimination
8.2 Błock backward substitution
8.3 LAPACK Metodology
8.4 ScaLAPACK
8.5 Błock LU
8.5.1 LU on 2D grid
8.6 Cyclic reduction
8.7 Błock iteratWe methods
8.7.1 Błock Jacobi iteration
8.7.2 Błock Gauss-Seidel iteration
9 Basic Iterative Methods
9.1 Stationary iterative methods
9.2 Krylov methods
9.2.1 CG algorithm
10 Preconditioners
10.1 Matrices of iterations and preconditionirij
10.2 LU preconditioner
10.3 ILU Preconditioner
10.3.1 ILUT Preconditioner
10.4 SPAI
10.5 Polynomial Preconditioners
11 Preconditioned CG
11.1 Non-standard inner product
11.2 Split preconditioner
12 Computer Performance
12.1 The CPU speed
12.2 Speedup
12.2.1 AmdahTs theorem
12.2.2 Scaled speedup
12.2.3 Super linear speedup
12.3 Efficiency
12.3.1 Numerical efficiency
12.4 Communication
12.5 Benchmarks
13 Introduction to PETSc
13.1 PETSc and MPI
13.2 Program structure
13.2.1 Naming conventions
13.3 Basic data types
13.3.1 PETSc and C data structures
13.4 Calling PETSc routines
13.5 Basic routines
13.6 Memory allocation
13.7 Vectors
13.7.1 Vector declaration
13.7.2 Vector creation
13.7.3 Destruction
13.7.4 Setting values
13.7.5 Assembly phase
13.7.6 Accessing va!ues
13.7.7 Operations on vectors
13.7.8 Yector printing
13.8 Matrices
13.8.1 Declaration
13.8.2 Matrix creation
13.8.3 Destruction
13.8.4 Setting value
13.8.5 Assembly phase
13.8.6 Operations on Matrices
13.8.7 Printing
13.9 Solving linear system - generał scheme
13.10 Krylov methods
13.11 Direct methodsin PETSc
13.12 Preconditioners
13.13 Monitors
13.13.1 Convergence
13.14 Solving linear system
13.14.1 Direct methods
13.15 Explicit preconditioned operator

182 pages, Paperback

Po otrzymaniu zamówienia poinformujemy,
czy wybrany tytuł polskojęzyczny lub anglojęzyczny jest aktualnie na półce księgarni.