Course Syllabus | 1. CPU Architecture vs. GPU Architecture
CPU Architecture BasicsMulticore and multiprocessor basics
GPU Architecture basics
How is the GPU connected to the host?
Why is parallel programming for GPUs different than for multicore?
What is a GPU thread and how does it execute?
How can I identify my GPU?
Part II. CUDA C and Fortran
1. Low-level GPU Programming and CUDA
How does data get to the GPU? How does a program run on the GPU?
What kinds of parallelism is appropriate for a GPU?
The CUDA programming model
Host code to control GPU, allocate memory, launch kernels
Kernel code to execute on GPU
Scalar routine executed on one thread
Launched in parallel on a grid of thread blocks
2. The Host Program
Declaring and allocating device memory data
Moving data to and from the device
Launching kernels
SHORT LAB
3. Writing Kernels
What is allowed in a kernel vs. what is not allowed
Grids, Blocks, Threads, Warps
4. Building and Running CUDA Programs
Compiler options
Running your program
The CUDA Runtime API
CUDA Fortran vs. CUDA C
LAB
5. Performance Tuning, Tips and Tricks
Measuring performance, using cudaprof
Optimizing your kernels
Optimize communication between host and GPU
Optimize device memory accesses, shared memory usage
Optimize the kernel code
loop unrolling
thread block unrolling
grid unrolling
pipelining
Debugging
PERFORMANCE LAB
Part III. PGI Accelerator Model
1. High-level GPU Programming using the PGI Accelerator Model
What role does a high-level model play?
Basic concepts and directive syntax
Accelerator compute and data regions
Appropriate algorithms for a GPU
2. Building and Running Accelerator Programs
Command line options
Enabling compiler feedback
SHORT LAB
3. Accelerator Directive Details
Compute regions
Clauses on the compute region directive
What can appear in a compute region
Obstacles to successful acceleration
Loop directive
Clauses on the loop directive
Loop schedules
Data regions
Clauses on the data region directive
LAB
4. Interpreting compiler feedback
Using pgprof source browser
Hindrances to parallelism
Data movement feedback
Reading kernel schedules
LAB
5. Performance Tuning, Tips and Tricks
Appropriate algorithm
Optimizing data movement between host and GPU
Data regions, mirrored / reflected data, CUDA data
Optimizing kernel performance
Tuning the kernel schedule
unroll clauses
Choosing accelerator device
PGI Unified Binary
Performance profiling information
GPU initialization time on Linux
PERFORMANCE LAB
Part IV. Wrapup, Questions
1. Accelerators in HPC
Past, present, future role of accelerators in HPC
Past, present, future of programming models for accelerators
Day 3, Molecular Dynamics Codes on GUGPUs - CSCS: Sadaf Alam, Jeff Poznanovic, and Tim Robinson
Pre-requisites: familiarity with running parallel MD on clusters
- Introduction of GPGPU technologies for scientific computing
- Overview of parallel classical molecular dynamics software
- Evolution of GPU acceleration for classical molecular dynamics software
- Walkthrough using GPU accelerated NAMD / pmemd (Rosa vs. Eiger)
- Demo with Case studies
- Tips and tricks for optimal usage of GPU accelerated simulations
- Advanced topics and future outlook
- LAB session |