Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Thread block (CUDA programming)
open-in-new
<p>A thread block is a programming abstraction that represents a group of <a href="/facts/Thread_(computing)/hh8WHyPd">threads</a> that can be executed serially or in parallel. For better process and data mapping, threads are grouped into thread blocks. The number of threads in a thread block was formerly limited by the architecture to a total of 512 threads per block, but as of March 2010, with compute capability 2.x and higher, blocks may contain up to 1024 threads. The threads in the same thread block run on the same stream multiprocessor. Threads in the same block can communicate with each other via <a href="/facts/Shared_memory/zmpH7WuV">shared memory</a>, barrier <a href="/facts/Synchronization_(computer_science)/n7ID76uM">synchronization</a> or other synchronization primitives such as atomic operations. </p><p>Multiple blocks are combined to form a grid. All the blocks in the same grid contain the same number of threads. The number of threads in a block is limited, but grids can be used for computations that require a large number of thread blocks to operate in parallel and to use all available multiprocessors. </p><p><a href="/facts/CUDA/fvPpolot">CUDA</a> is a <a href="/facts/Parallel_computing/nQzcpzQt">parallel computing</a> platform and <a href="/facts/Programming_model/XhNua0XG">programming model</a> that higher level languages can use to exploit parallelism. In CUDA, the <a href="/facts/Compute_kernel/BxyI4vSf">kernel</a> is executed with the aid of threads. The <a href="/facts/Thread_(computing)/hh8WHyPd">thread</a> is an abstract entity that represents the execution of the kernel. A <a href="/facts/Compute_kernel/BxyI4vSf">kernel</a> is a function that compiles to run on a special device. Multi threaded applications use many such threads that are running at the same time, to organize parallel computation. Every thread has an index, which is used for calculating memory address locations and also for taking control decisions. </p>