- 博客(4)
- 收藏
- 关注
原创 CUDA programming(4) --resources
Threads Thread is a sequential set of instructions executed alongside other threads in a processor. Multithreading is the ability for a processor to execute a few processes simultaneously. Resources global memory is shared across all threads shared memory
2022-02-09 11:29:54
61
原创 Fundamentals of GPU programming (3)
CUDA program structure use CUDA API to query for compatible devices cudaError_t cudaGetDeviceProperties(cudaDevProp* prop, int dev) Example: int device=1; cudaDeviceProp props; cudaGetDeviceProperties(&props, device) allocate memory on the CUDA dev
2022-02-06 01:48:01
655
原创 Fundamentals of GPU programming (2)
Parallelism and GPU Architecture CPU is optimized to process a single sequence of instructions. It is extremely fast but there are some walls, such as memory, power, and instruction level parallelism. Two speedup ways. Given a process that requires time TT
2022-02-06 01:38:29
153
原创 Fundamentals of GPU Programming(1)
Recorded by Ruijiao, from ECE6397 by Dr. David Mayerich, UH Goals Understand fundamentals of GPU hardware. Understand fundamentals of parallel programming. Practical experince in implemeting algorithms on highly-parrallel heterogeneous systems. Processors
2022-02-06 01:35:46
155
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人