I am trying to use the dgamma function in R to obtain values of the gamma density function across a matrix of values. Because my values are usually quite small, I am also required to do this process in log space to avoid underflow within the function.
Eg:
values = matrix(data = seq(1:9),nrow = 3,ncol = 3)
dgamma(values, shape = 10, scale = 1/10, log = T)
# [,1] [,2] [,3]
#[1,] 0.2240234 -17.29933 -42.26279
#[2,] -3.5376519 -25.29104 -51.06100
#[3,] -9.8884660 -33.65014 -60.00096
However, because I am doing this across a matrix that has quite a large dimension (usually on the order of 1000x10000), and doing this repeatedly for different valued matrices this process is a bottleneck within my code.
I am wondering if anyone has any clever tricks to speed up this process within R?
Thanks.