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 83
Сторінка 44
... Global Memory MMU (448/512Bit)-120GB/S-256K to 4GB Optional+64Bits Memory across SP0 SP1 SP2 SP3 SP4 SP5 SP6 SP7 Crossbar 0 1 23 45 67 8 9 AB C D EF Shared Memory (16x 1K) SM1 ... Global Memory L2 Cache Texture Cache Constant Cache L1 Cache.
... Global Memory MMU (448/512Bit)-120GB/S-256K to 4GB Optional+64Bits Memory across SP0 SP1 SP2 SP3 SP4 SP5 SP6 SP7 Crossbar 0 1 23 45 67 8 9 AB C D EF Shared Memory (16x 1K) SM1 ... Global Memory L2 Cache Texture Cache Constant Cache L1 Cache.
Сторінка 45
... memory is used for read-only data and is cached on all hardware revisions. Like texture memory, constant memory is simply a view into the main global memory. Global memory is supplied via GDDR (Graphic Double Data Rate) on the graphics ...
... memory is used for read-only data and is cached on all hardware revisions. Like texture memory, constant memory is simply a view into the main global memory. Global memory is supplied via GDDR (Graphic Double Data Rate) on the graphics ...
Сторінка 50
... memory pattern at compile time. However, to exploit the cache, the application either needs to have a sequential ... global atomic operations. Compared to having to go out to the global memory on the GPU, using the shared cache is an ...
... memory pattern at compile time. However, to exploit the cache, the application either needs to have a sequential ... global atomic operations. Compared to having to go out to the global memory on the GPU, using the shared cache is an ...
Сторінка 100
... memory bandwidth culprit. For this you need to look at the alternative approach given by the data decomposition ... global memory, so this approach is an order of magnitude slower. Even if you can use the L2 cache on the Fermi/Kepler ...
... memory bandwidth culprit. For this you need to look at the alternative approach given by the data decomposition ... global memory, so this approach is an order of magnitude slower. Even if you can use the L2 cache on the Fermi/Kepler ...
Сторінка 101
A Developer's Guide to Parallel Computing with GPUs Shane Cook. decrease the number of global memory reads or writes, but you do coalesce all the writes to memory. The kernel for this approach is as follows: __shared__ unsigned int ...
A Developer's Guide to Parallel Computing with GPUs Shane Cook. decrease the number of global memory reads or writes, but you do coalesce all the writes to memory. The kernel for this approach is as follows: __shared__ unsigned int ...
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