CUDA Programming: A Developer's Guide to Parallel Computing with GPUsNewnes, 28 груд. 2012 р. - 600 стор. If you need to learn CUDA but don't have experience with parallel computing, CUDA Programming: A Developer's Introduction offers a detailed guide to CUDA with a grounding in parallel fundamentals. It starts by introducing CUDA and bringing you up to speed on GPU parallelism and hardware, then delving into CUDA installation. Chapters on core concepts including threads, blocks, grids, and memory focus on both parallel and CUDA-specific issues. Later, the book demonstrates CUDA in practice for optimizing applications, adjusting to new hardware, and solving common problems.
|
З цієї книги
Результати 6-10 із 87
Сторінка 6
... performance. The Cray-2 was a significant improvement on the Cray-1. It used a shared memory architecture, split into banks. These were connected to one, two, or four processors. It led the way for the creation of today's server-based ...
... performance. The Cray-2 was a significant improvement on the Cray-1. It used a shared memory architecture, split into banks. These were connected to one, two, or four processors. It led the way for the creation of today's server-based ...
Сторінка 9
... performance of a single box. Instead of paying $1600 for a high performance processor, you paid $250 and bought six medium performance processors. If your application needed huge memory capacity, the chances were that maxing out the ...
... performance of a single box. Instead of paying $1600 for a high performance processor, you paid $250 and bought six medium performance processors. If your application needed huge memory capacity, the chances were that maxing out the ...
Сторінка 13
... performance. This is not to say one is better than the other, for the traditional CPUs are aimed at serial code execution and are extremely good at it. They contain special hardware such as branch prediction units, multiple caches, etc ...
... performance. This is not to say one is better than the other, for the traditional CPUs are aimed at serial code execution and are extremely good at it. They contain special hardware such as branch prediction units, multiple caches, etc ...
Сторінка 15
... performance, not double-precision (64-bit) precision. Also be careful with the GF100 (Fermi) series, as the Tesla variant has double the number of double-precision units found in the standard desktop units, so achieves significantly ...
... performance, not double-precision (64-bit) precision. Also be careful with the GF100 (Fermi) series, as the Tesla variant has double the number of double-precision units found in the standard desktop units, so achieves significantly ...
Сторінка 18
... performance for well-written programs. ZeroMQ (0MQ) is also something that deserves a mention. This is a simple library that you link to, and we will use it later in the book for developing a multinode, multi-GPU example. ZeroMQ ...
... performance for well-written programs. ZeroMQ (0MQ) is also something that deserves a mention. This is a simple library that you link to, and we will use it later in the book for developing a multinode, multi-GPU example. ZeroMQ ...
Зміст
Chapter 8 MultiCPU and MultiGPU Solutions | 267 |
Chapter 9 Optimizing Your Application | 305 |
Chapter 10 Libraries and SDK | 441 |
Chapter 11 Designing GPUBased Systems | 503 |
Chapter 12 Common Problems Causes and Solutions | 527 |
Index | 565 |
Інші видання - Показати все
CUDA Programming: A Developer's Guide to Parallel Computing with GPUs Shane Cook Обмежений попередній перегляд - 2012 |
Загальні терміни та фрази
256 threads algorithm allocate application array atomic atomic operations blockDim.x blockIdx.x bytes calculation compiler compute 2.x const int const u32 constant memory copy CUDA CALL cuda CUDA cores dataset device device_num elements example execution Fermi Figure function GB/s GeForce GTX 470:GMEM global memory GMEM hardware host memory ID:0 GeForce GTX InfiniBand instruction issue iterations Kepler kernel L1 cache latency Linux look loop malloc Memcpy memory access memory bandwidth memory fetch merge sort node num_elem num_elements num_threads number of blocks number of threads NVIDIA OpenMP operation optimization output Parallel Nsight parameter PCI-E performance pointer prefix sum problem processor radix sort reduce registers result serial shared memory SIMD simply single SP SP SP speedup stream synchronization Tesla threadIdx.x threads per block transfer typically uint4 unsigned int usage version is faster void warp write þ¼