2

Recently, I am reading the book 'Programming Massively Parallel processors'. One of the reading exercise in chapter 3 ask me to detect which assignment for SM is possible. The problem looks like below

Indicate which of the following assignments per multiprocessor is possible:

  1. 8 blocks with 128 threads each on a device with compute capability 1.0.
  2. 8 blocks with 128 threads each on a device with compute capability 1.2.
  3. 8 blocks with 128 threads each on a device with compute capability 3.0.
  4. 16 blocks with 64 threads each on a device with compute capability 1.0.
  5. 16 blocks with 64 threads each on a device with compute capability 1.2.
  6. 16 blocks with 64 threads each on a device with compute capability 3.0.

From the most recent CUDA programming guild, I only find the specification for compute capability 3.0 whose allows up to 16 blocks and 2048 threads per SM and up 1024 threads per block. Unfortunately, I did not find any information related to compute capability 1.0.

Can anyone tell me where to find the block specification for compute capability 1.0? Thank you very much

Wenbo Hou
  • 23
  • 3
  • 1
    NVIDIA maintains an [archive](https://developer.nvidia.com/cuda-toolkit-archive) of old CUDA versions going back some ten years. You could also perform a quick Google search for older versions of the CUDA Programming Guide, such as [this copy](http://www.umiacs.umd.edu/~ramani/cmsc828e_gpusci/CUDA21.pdf) of the guide for CUDA 2.1. – njuffa Dec 14 '18 at 08:45

1 Answers1

2

See the page of CUDA in Wikipedia, there is a valid specification to all devices. it will be in Compute capability (version) section.

But here is a photo about it:

enter image description here

koviroli
  • 1,422
  • 1
  • 15
  • 27