Open main menu

CDOT Wiki β

Changes

BetaT

280 bytes removed, 18:20, 12 April 2017
CPU VS GPU Loop Comparisons Only
== CPU VS GPU Loop Comparisons Only==
Executing the program again with a problem size of 2000 2000 or 4,000,000 we yield the following results. Keep in mind this is only for the kernel launch or the for-loops executing, not the program as a whole.
Keep in mind these times are only for the kernel launches and not the program as a whole.
Device with compute capability 3.0 found (index 0) Name: Quadro K2000 Compute Capability: 3.0 Total Global Memory: 2147483648 Max Threads per block: 1024 maxGridSize: 002EF650 maxThreadsDim: 002EF644 Clock Rate in khz: 954000PARALLIZED GPU CODE
Fist for loop - took - 0 millisecs
Press any key to continue . . .
As compared to the ORIGINAL CPU version of the original programCODE
Initialize arrays loop - took - 17 milliseconds
212
edits