I readed the programming guide and parts of the bestpractiseguide but I still have some questions about the memory management of cuda:
What is the maximum size of texture memory? It’s only limited by the size of totalglobalmem (DRAM), isn’t it?
The texture cache size is 8 kb per multiprocessor?
The existence of texture cache data is not bound to the lifetime of a block, but to the execution time of a kernel?
I hope you can help me.
Thanks in advance!