Those numbers suggest that you are getting some use out of the
hyperthreads, so you should keep using them.
What is the u in u;._3? And what is your CPU model?
I should have said, when you have created 3 worker threads you should
split your job into 3+1=4 tasks. The master thread pitches in
The array is periodically extended so the result of u;._3 is 512 by 512.
Using 3 threads instead of 7 and t. on 512 three by 512 pieces takes 59 sec
and J uses 10% of total cpu
I'll try slicing 512 by 3 and 512 by m pieces later.
Thanks for the comments, especially the insights into u;._3 !
On Thu
I'm surprised that the result is 512x512 when you use u;._3 on 512x512
argument. Do you pad after the operation?
1. How good the operation is for threading depends on the ratio of
processing to reading arguments/writing results. The arguments start
out in a different core's cache, and have t
Hi,
I thought I would experiment with t.
I choose an "image" processing problem on a 512 by 512 array.
Local (complex) processing occurs on 3 by 3 cells (u;._3) which results in
a 512 by 512 array. That process is iterated (^:_), here around 150 times.
So I thought this might be a good place to lo
"But what does t. do?"
Use the dictionary.
t. is an adverb.
The dictionary heading on the page says
u t. 0 0 0
This means (and it took me 2 years before I understood how to read
dictionary headings. I learned a lot of j via the "parts of speech"
dictionary access page)
The verb formed by
u
