In this paper, a parallel implementation of a previously constrained
hyperspectral coded aperture (CHYCA) algorithm
for compressive sensing on graphics processing units (GPUs)
is proposed. CHYCA method combines the ideas of spectral
unmixing and compressive sensing exploiting the high
spatial correlation that can be observed in the data and the
generally low number of endmembers needed in order to
explain the data. The performance of CHYCA relies which
does not depend on the tuning of a regularization parameter,
which is a time consuming task offering good performance
compared with a previously hyperspectral coded aperture
(HYCA) method. The proposed implementation exploits the
GPU architecture at low level, thus taking full advantage of
the computational power of GPUs using shared memory and
coalesced accesses to memory. Experimental results using
simulated data reveals speedups up to 56 times, with regards
to serial implementation.