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 1-5 із 86
Сторінка 12
... function units. However, these shaders were operations that by their very nature took a set of 3D points that represented a polygon map. The shaders applied the same operation to many such datasets, in a hugely parallel manner, giving ...
... function units. However, these shaders were operations that by their very nature took a set of 3D points that represented a polygon map. The shaders applied the same operation to many such datasets, in a hugely parallel manner, giving ...
Сторінка 31
... function as it is within the CPU hardware. The programmer instead defines, through a kernel, what each thread will do. Thus, the kernel will read the data uniformly and the kernel code will execute transformation A, B, or C as necessary ...
... function as it is within the CPU hardware. The programmer instead defines, through a kernel, what each thread will do. Thus, the kernel will read the data uniformly and the kernel code will execute transformation A, B, or C as necessary ...
Сторінка 57
... function addKernel. This function simply takes a pointer to a destination array, c, and a couple of pointers to two input arrays, a and b. It then adds the contents of the a and b arrays together and stores the result in the destination ...
... function addKernel. This function simply takes a pointer to a destination array, c, and a couple of pointers to two input arrays, a and b. It then adds the contents of the a and b arrays together and stores the result in the destination ...
Сторінка 67
... function returns an error code, every function call must be checked and some handler written. This makes for very tiresome and highly indented programming. For example, if (cudaMalloc(.) 1⁄41⁄4 cudaSuccess) { if (cudaEventCreate(&event) ...
... function returns an error code, every function call must be checked and some handler written. This makes for very tiresome and highly indented programming. For example, if (cudaMalloc(.) 1⁄41⁄4 cudaSuccess) { if (cudaEventCreate(&event) ...
Сторінка 68
... function, which is of type cudaError_t. It then checks if this is not equal to cudaSuccess, that is, the call encountered some error. If there was an error detected, it prints to the screen the error returned plus a short description of ...
... function, which is of type cudaError_t. It then checks if this is not equal to cudaSuccess, that is, the call encountered some error. If there was an error detected, it prints to the screen the error returned plus a short description of ...
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