CS6023 GPU Programming

Schedule

Month	Dates	Topic	Comments
July	27, 29, 30, 31	Introduction, Computation	Hello World, One, Two, Three Grid, Blocks, Threads Kernel Launch: 1D, 1D-General, 2D
August	3, 5, 6, 7	Computation	CPU-GPU Communication (cudaMalloc, cudaMemcpy) Global variables Matrix mult.: CPU, Outer parallel, Outer+Inner parallel
	10, 12, 13, 14	Computation	Thread Divergence Divergence due to switch Problem Set 1
	17, 19, 20, 21	Memory	Memory Coalescing AoS versus SoA Barrier
	24, 27, 28	Memory	Linked List Copying Shared Memory Shared Memory with Barrier String Permutation Dynamic Shared Memory Dynamic Shared Memory with Multiple Arrays CUDA GDB Error Handling Dangling Pointer
	31	Memory	Texture Memory (via CUDA SDK) Constant Memory Bank Conflicts Problem Set 2 NvProf Original Code Loop Fusion Kernel Fusion Converting Loop to Blocks
September	2, 3, 4	Synchronization	Convolution Worklist Insertion Task Donation
	7, 9, 10, 11	Synchronization	Reduction: i + N/2, N - i, i + 1 Prefix Sum / Scan
	16, 17, 18	Synchronization	MidSem on 16 from 5 PM to 6:30 PM No Global Barrier Global Barrier using Atomics Hierarchical Global Barrier
	21, 23, 24, 25	Synchronization	Linked List Insertion CPU-GPU Shared Pinned Memory Persistent Kernel Problem Set 3
	28, 30	Synchronization	Array increment: Sequential, Parallel Thrust basics Thrust Reduction Thrust Prefix Sum Thrust-like device vector implementation
October	1, 2	Functions	Basic Stream Program with Asynchronous memcpy with cudaHostAlloc Cooperative Kernels
	5, 7, 8, 9	Functions	Dynamic Parallelism Conditional Child Kernels using Global Device Memory with Non-Blocking Streams
	12, 14, 15, 16	Functions	MultiGPU: Number of Devices Cross-Device Synchronization
	19, 21, 22, 23	Topics	PTX: CUDA Code, Assembly Code Basic Warp Voting Converting Mask to Count (popc) Use of ffs Conditional Participation in ballot
	26, 28, 29, 30	Topics	Loop Unrolling, Unrolled Assembly Heterogeneous Computation
November	2, 4, 5, 6	Topics	with Shared Variable Task Distribution OpenMP Reduction with HostAlloc'ed Memory Dynamic Scheduling OpenCL: Driver, Kernel
	19		EndSem from 10:00 -- 12:00

GPU Programming Crossword Puzzle (click and type)

Courtesy: crosswordlabs.com