What parameters to choose - threads, blocks, warps

Accelerated Computing CUDA CUDA Programming and Performance
1

What parameters to choose (threads, blocks, warps) in order to achieve as many parallel calculations as possible at once?

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "NVIDIA GeForce GTX 960M"
  CUDA Driver Version / Runtime Version          11.8 / 11.8
  CUDA Capability Major/Minor version number:    5.0
  Total amount of global memory:                 4096 MBytes (4294836224 bytes)
  (005) Multiprocessors, (128) CUDA Cores/MP:    640 CUDA Cores
  GPU Max Clock rate:                            1176 MHz (1.18 GHz)
  Memory Clock rate:                             2505 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 2097152 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total shared memory per multiprocessor:        65536 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 4 copy engine(s)
  Run time limit on kernels:                     No
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
  Device supports Unified Addressing (UVA):      Yes
  Device supports Managed Memory:                Yes
  Device supports Compute Preemption:            No
  Supports Cooperative Kernel Launch:            No
  Supports MultiDevice Co-op Kernel Launch:      No
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.8, CUDA Runtime Version = 11.8, NumDevs = 1
Result = PASS
2

That depends on the calculations. The maximum number of threads that can run simultaneously is given by multiprocessors * max threads per multiprocessor

3

So in my case:

Multiprocessors: 005
Maximum number of threads per multiprocessor: 2048

is the maximum number of of threads that can run simultaneously 5 x 2048 = 10 240?

How to define it if I need to run one main function on the GPU, generating random numbers, which will pass these numbers to as many GPU threads as possible for further parallel processing?

4

For general understanding of launch sizing, this training series may be useful, particularly units 1-3. (And there are numerous forums questions on the web about this topic.) For the second question on generating random numbers, this question may be useful.