CUDA Programming: A Developer's Guide to Parallel Computing with GPUs
Newnes, 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.
Результати 1-5 із 86
With SIMD instructions on such a processor, we eliminate all redundant instruction memory fetches, and generate one sixteenth of the memory read and write cycles compared with fetching and writing 1 byte at a time.
To program the Cell, you write a program to execute on the PowerPC core processor. It then invokes a program, using an entirely different binary, on each of the stream processing elements (SPEs). Each SPE is actually a core in itself.
This means instead of one trip to global memory of an unknown latency, we now have twodone to write the old data and one to ... of the programmer-controlled on-chip memory is that the programmeris in control of when the writes happen.
The latter approach is often better where the CPU cores need to write data back to memory. Interleaving the data elements by core means the cache has to coordinate and combine the writes from different cores, which is usually a bad idea ...
The worst case in a cachecoherent system is where each core writes adjacent memory locations as each write forces a global update to every core's cache. A non cache-coherent system by comparison does not automatically update the other ...
Відгуки відвідувачів - Написати рецензію
Chapter 8 MultiCPU and MultiGPU Solutions
Chapter 9 Optimizing Your Application
Chapter 10 Libraries and SDK
Chapter 11 Designing GPUBased Systems
Chapter 12 Common Problems Causes and Solutions