=== parameters ===
seed=0
test=3
method=1
nbr_taxa=128
taxa_length=131072
max_iterations=500
nbr_trees=50
tree_implementation=2
tree_topology=1
taxa_initialization=1
threads_per_block=1024
gpu_selected=-1
data size=8 bits

=== static sequences ===
taxa_length_aligned=131072
cpu memory alignment=32
full_size=33423360 (=131072 * 255 * 1)


==== CUDA init ====
CUDA Device Query... there are 1 CUDA devices.
GPU 0: GeForce GTX 660, compute capability 3.0
select default GPU
gpu_name=GeForce GTX 660

=== cuda parsimony init ===
gpu taxa_length_aligned=131072
gpu full_size=33423360
threads per block=1024
blocks per grid=128
========================================
=== test for iterative method on GPU ===
========================================
cpu elapsed=34.4618
gpu elapsed=34.4621
iterations=500
total=25000
