McCool Michael Reinders James Robison Arch - Structured Parallel Programming: Patterns for Efficient Computation

1.1 Add two vectors in C, with implied serial ordering

1.2 Overlapping (aliased) arguments in C

1.3 Add two vectors using Cilk Plus array notation

1.4 An ordered sum creates a dependence in C

1.5 A parallel sum, expressed as a reduction operation in Cilk Plus

1.6 Function calls with step-by-step ordering specified in C

1.7 Function calls with no required ordering in Cilk Plus

1.8 Serial vector addition coded as a loop in C

1.9 Parallel vector addition using Cilk Plus

1.10 Parallel vector addition using ArBB

1.11 Scalar function for addition in C

1.12 Vectorized function for addition in Cilk Plus

1.13 Serial Fibonacci computation in C

1.14

1.15 Vector computation in ArBB

1.16 Elemental function computation in ArBB

3.1 Serial sequence in pseudocode

3.2 Serial sequence, second example, in pseudocode

3.3 Serial selection in pseudocode

3.4 Iteration using a while loop in pseudocode

3.5 Iteration using a for loop in pseudocode

3.6 Demonstration of while/for equivalence in pseudocode

3.7 A difficult example in C

3.8 Another difficult example in C

3.9 Serial implementation of reduction

3.10 Serial implementation of scan

3.11 Superscalar sequence in pseudocode

4.1 Serial implementation of SAXPY in C

4.2 Tiled implementation of SAXPY in TBB

4.3 SAXPY in Cilk Plus using cilk_for

4.4 SAXPY in Cilk Plus using cilk_for and array notation for explicit vectorization

4.5 SAXPY in OpenMP

4.6 SAXPY in ArBB, using a vector expression

4.7 SAXPY in ArBB, using binding code for vector expression implementation

4.8 SAXPY in ArBB, using an elemental function

4.9 SAXPY in ArBB, call operation

4.10 SAXPY in OpenCL kernel language

4.11 Serial implementation of Mandelbrot in C

4.12 Tiled implementation of Mandelbrot in TBB

4.13 Mandelbrot using cilk_for in Cilk Plus

4.14 Mandelbrot in Cilk Plus using cilk_for and array notation for explicit vectorization

4.15 Mandelbrot in OpenMP

4.16 Mandelbrot elemental function for ArBB map operation

4.17 Mandelbrot call code for ArBB implementation

4.18 Mandelbrot binding code for ArBB implementation

4.19 Mandelbrot kernel code for OpenCL implementation

5.1 Serial reduction in C++ for 0 or more elements

5.2 Serial reduction in C++ for 1 or more elements

5.3 Serial implementation of dot product in C++

5.4 Vectorized dot product implemented using SSE intrinsics

5.5 Dot product implemented in TBB

5.6 with double-precision operations

5.7 Dot product implemented in Cilk Plus array notation

5.8 Dot product implementation in Cilk Plus using explicit tiling

5.9 with double-precision operations for multiplication and accumulation

5.10 Dot product implemented in OpenMP

5.11 Dot product implemented in ArBB

5.12 Dot product implementation in ArBB, wrapper code

5.13 High-precision dot product implemented in ArBB

5.14 Serial implementation of inclusive scan in C++

5.15 Serial implementation of exclusive scan in C++

5.16 Three-phase tiled implementation of a scan in OpenMP

5.17 Serial integrated table preparation in C++

5.18 Generic test function for integration

5.19 Concrete instantiation of test function for integration

5.20 Serial implementation of integrated table lookup in C++

5.21 Integrated table preparation in Cilk Plus

5.22 Integrated table preparation in TBB

5.23 Integrated table preparation in ArBB

5.24 Integrated table lookup in ArBB

6.1 Serial implementation of gather in pseudocode

6.2 Serial implementation of scatter in pseudocode

6.3 Array of structures (AoS) data organization

6.4 Structure of arrays (SoA) data organization

7.1 Serial implementation of stencil

7.2 Serial 2D recurrence

8.1 Recursive implementation of the map pattern in Cilk Plus

8.2 that changes tail call into a goto

8.3 Cleaned-up semi-recursive map in Cilk Plus

8.4 Three loop forms illustrating steal-continuation versus steal-child

8.5 Flat algorithm for polynomial multiplication using Cilk Plus array notation

8.6 Karatsuba multiplication in Cilk Plus

8.7 Type for scratch space

8.8 Pseudocode for recursive matrix multiplication

8.9 Code shared by Quicksort implementations

8.10 Fully recursive parallel Quicksort using Cilk Plus

8.11 Semi-recursive parallel Quicksort using Cilk Plus

8.12 Semi-iterative parallel Quicksort using TBB

8.13 Quicksort in TBB that achieves Cilk Plus space guarantee