9,121
edits
Difference between revisions of "NVGate DSP computation SPU"
Jump to navigation
Jump to search
NVGate DSP computation SPU (view source)
Revision as of 14:56, 15 February 2022
, 14:56, 15 February 2022no edit summary
| Line 2: | Line 2: | ||
SPU computation for normal DSP : OR34 V1 - Or35V1 - OR36V1 OR36V22 (normal DSP) - OR38V1 - OR38V2 (Normal DSP). | SPU computation for normal DSP : OR34 V1 - Or35V1 - OR36V1 OR36V22 (normal DSP) - OR38V1 - OR38V2 (Normal DSP). | ||
Because of the linearity of the computation, we simplify by | Because of the linearity of the computation, we simplify by saying: 1DSP = 12 SPU. This allow a simplification for SPU computation. So we can deduce: | ||
==FFT== | ==FFT== | ||