Hi,
I see a comparison of TI C66 DSP and GPU slide, which said:
• The DSP has 8 functional units that can run 8 instructions per cycle
• In term of “CUDA cores” each DSP has 16 “cores”
• In C6678 the HYPER LINK enables to connect DSPs in pairs so you can get 32 cores @1.2GHZ
Could you explain the line 2 and line 3 where 16 and 32 are from?
Thanks,