PPT-CS 179: GPU Programming

Lecture 12 Homework 4 BreadthFirst Search Given source vertex S Find min edges to reach every vertex from S Assume source is vertex 0 0 1 1 2 2 3 Sequential pseudocode let Q be a queue. Lecture 2: more basics. Recap. Can use GPU to solve highly parallelizable problems. Straightforward extension to C++. Separate CUDA code into .cu and .. cuh. files and compile with . nvcc. to create object files (.o files). Sathish. . Vadhiyar. Parallel Programming. GPU. Graphical Processing Unit. A single GPU consists of large number of cores – hundreds of cores.. Whereas a single CPU can consist of 2, 4, 8 or 12 cores. Host-Device Data Transfer. 1. Moving data is slow. So far we’ve only considered performance when the data is already on the GPU. This neglects the slowest part of GPU programming: getting data on and off of GPU. Host-Device Data Transfer. 1. Moving data is slow. So far we’ve only considered performance when the data is already on the GPU. This neglects the slowest part of GPU programming: getting data on and off of GPU. Lecture 5: GPU Compute . Architecture. 1. Last time.... GPU Memory System. Different kinds of memory pools, caches, . etc. Different optimization techniques. 2. Warp Schedulers. Warp schedulers find a warp that is ready to execute its next instruction and available execution cores and then start execution. Add GPUs: Accelerate Science Applications. © NVIDIA 2013. Small Changes, Big Speed-up. Application Code. . GPU. C. PU. Use GPU to Parallelize. Compute-Intensive Functions. Rest of Sequential. CPU Code. Topics. Non-numerical algorithms. Parallel breadth-first search (BFS). Texture memory. GPUs – good for many numerical calculations…. What about “non-numerical” problems?. Graph Algorithms. Graph Algorithms. Topics. Non-numerical algorithms. Parallel breadth-first search (BFS). Texture memory. GPUs – good for many numerical calculations…. What about “non-numerical” problems?. Graph Algorithms. Graph Algorithms. Lecture 7. Last Week. Memory optimizations using different GPU caches. Atomic operations. Synchronization with __. syncthreads. (). Week 3. Advanced GPU-accelerable algorithms. “Reductions” to parallelize problems that don’t seem intuitively parallelizable. Patrick Cozzi. University of Pennsylvania. CIS 565 - Fall 2014. Lectures. Monday. 6-9pm. Moore 212. Fall. and . Spring. 2012 lectures were recorded. Attendance is required for guest lectures. Image from . Patrick Cozzi. University of Pennsylvania. CIS 565 - Fall 2013. Lectures. Monday and Wednesday. 6-7:30pm. Towne . 307. Fall. and . Spring. 2012 lectures were recorded. Attendance is required for guest lectures. The Desired Brand Effect Stand Out in a Saturated Market with a Timeless Brand The Desired Brand Effect Stand Out in a Saturated Market with a Timeless Brand Recap. Some algorithms are “less obviously parallelizable”:. Reduction. Sorts. FFT (and certain recursive algorithms). Parallel FFT structure (radix-2). Bit-reversed access. http://staff.ustc.edu.cn/~csli/graduate/algorithms/book6/chap32.htm.