Skip to main content
. Author manuscript; available in PMC: 2014 May 1.
Published in final edited form as: J Parallel Distrib Comput. 2013 Jan 16;73(5):10.1016/j.jpdc.2013.01.001. doi: 10.1016/j.jpdc.2013.01.001

Figure 5.

Figure 5

The execution time and the computational speedup between the two versions of the Toeplitz reconstruction strategy on one Tesla M2070 GPU. In step 1, a reduction in execution time of 17.5 hours (63098.20 s to 55.64 s, about 1134x speedup) was obtained for the image size of 256x256x32 with 1574656 input samples per coil. Note that Step 3 takes the same amount of time across the two versions as they use the same conjugate gradient solver.