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
Сторінка 28
... elements, each of which takes one second, we can produce one output per second. However, if just one of these elements takes two seconds, the throughput of the entire pipeline is reduced to one output every two seconds. The approach to ...
... elements, each of which takes one second, we can produce one output per second. However, if just one of these elements takes two seconds, the throughput of the entire pipeline is reduced to one output every two seconds. The approach to ...
Сторінка 29
... elements by core means the cache has to coordinate and combine the writes from different cores, which is usually a bad idea. If the algorithm permits, we can exploit a certain type of data parallelism, the SIMD (single instruction ...
... elements by core means the cache has to coordinate and combine the writes from different cores, which is usually a bad idea. If the algorithm permits, we can exploit a certain type of data parallelism, the SIMD (single instruction ...
Сторінка 31
... elements in the range, it can be fetched and decoded from the program memory only once. As the range is defined and ... element has transformation A applied while another element has transformation B applied, and all others have ...
... elements in the range, it can be fetched and decoded from the program memory only once. As the range is defined and ... element has transformation A applied while another element has transformation B applied, and all others have ...
Сторінка 33
... elements (e.g., CPU cores), these are split into three queues of data, one per processing element. Each is processed independently and then written to the appropriate place in the destination queue. The fork/join pattern is typically ...
... elements (e.g., CPU cores), these are split into three queues of data, one per processing element. Each is processed independently and then written to the appropriate place in the destination queue. The fork/join pattern is typically ...
Сторінка 35
... elements present in the machine. This type of parallel decomposition has the huge advantage that it scales really well. A GPU is in many ways similar to a symmetrical multiprocessor system on a single device. Each SM is a processor in ...
... elements present in the machine. This type of parallel decomposition has the huge advantage that it scales really well. A GPU is in many ways similar to a symmetrical multiprocessor system on a single device. Each SM is a processor in ...
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