Skip to content
Snippets Groups Projects
Commit 416ed7b1 authored by Aaron Councilman's avatar Aaron Councilman
Browse files

Parallelize both main loops in srad

parent 76a82eaf
No related branches found
No related tags found
2 merge requests!215Large benches,!214More optimizations
...@@ -40,10 +40,15 @@ let split = fork-split(loop2); ...@@ -40,10 +40,15 @@ let split = fork-split(loop2);
let loop2_body = outline(split.srad_1.fj1); let loop2_body = outline(split.srad_1.fj1);
simpl!(loop2, loop2_body); simpl!(loop2, loop2_body);
inline(srad@loop2); fork-tile[32, 0, false, false](loop3);
let split = fork-split(loop3);
let loop3_body = outline(split.srad_2.fj1);
simpl!(loop3, loop3_body);
inline(srad@loop2, srad@loop3);
delete-uncalled(*); delete-uncalled(*);
fork-split(extract, compress, loop1, loop2_body, loop3); fork-split(extract, compress, loop1, loop2_body, loop3_body);
unforkify(extract, compress, loop1, loop2_body, loop3); unforkify(extract, compress, loop1, loop2_body, loop3_body);
gcm(*); gcm(*);
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment