Hi,
Here's something I managed to figure out. I used a feature called inline PTX to return the particular details of the thread . In this case i used it to get the warp ID, warp lane ID and the streaming multiprocessor ID. However the warp id and warp lane id is coming out as expected(ie warp lane from 0-31 and each warp getting executing) the SM ID is 0 (zero) for all the threads. When i checked the clinfo , the Max compute units: 1. So does this mean that the SM ID is zero for all the threads is zero because of that?
Also how can my nvidia quadro 410 have Max compute units as 1 when there are 192 cuda cores?
edit: apparently inline ptx doesnt work on AMD GPU's . So gathering info of the core is still unsolved on the AMD GPU's. fyi: i have another system with AMD R9 290x GPU in which I run code parallel with my NVIDIA card.