[Bug target/82533] inefficient code generation for copy loop on falkor
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82533 Andrew Pinski changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED Resolution|--- |WONTFIX --- Comment #3 from Andrew Pinski --- Falkor is no longer a product so closing as won't fix.
[Bug target/82533] inefficient code generation for copy loop on falkor
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82533 --- Comment #2 from Jim Wilson --- Created attachment 42349 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=42349=edit proposed fix
[Bug target/82533] inefficient code generation for copy loop on falkor
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82533 --- Comment #1 from Jim Wilson --- A reviewer suggested using register_offset in the address cost structure to fix this. That doesn't prevent all reg+reg addressing modes from being generated, though this might be fixable with some work. However, a bigger problem, is that it disables reg+reg addressing modes for both loads and stores, and disabling reg+reg loads reduces performance on Falkor. It is only the reg+reg quad-word store that needs to be disabled for best performance. To make this happen, we need to modify the md file.