[PATCH] merge consecutive 16-byte loads into one 32-byte load (PR22329)
spatel at rotateright.com
Fri Jan 30 12:00:01 PST 2015
Hi delena, hfinkel, mkuper, RKSimon,
This patch detects consecutive loads using the existing EltsFromConsecutiveLoads() logic. This fixes:
This patch effectively reverts the tablegen additions of D6492 / http://reviews.llvm.org/rL224344...which in hindsight were a horrible hack. :)
The test cases that were added with that patch are simply modified to load from varying offsets of a base pointer. These loads did not match the existing tablegen patterns.
A happy side effect of doing this optimization earlier is that we can now fold the load into a math op where possible; this is shown in some of the updated checks in the test file.
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 10594 bytes
Desc: not available
More information about the llvm-commits