summaryrefslogtreecommitdiff
path: root/lib/Target/ARM/README.txt
diff options
context:
space:
mode:
authorEvan Cheng <evan.cheng@apple.com>2009-09-28 09:14:39 +0000
committerEvan Cheng <evan.cheng@apple.com>2009-09-28 09:14:39 +0000
commit5adb66a646e2ec32265263739f5b01c3f50c176a (patch)
tree38b5fb6a9d2665466cd3b88031122d9c95de6110 /lib/Target/ARM/README.txt
parent705428ae4a7fa6d97a95f7811fa2e36630a43c9c (diff)
downloadllvm-5adb66a646e2ec32265263739f5b01c3f50c176a.tar.gz
llvm-5adb66a646e2ec32265263739f5b01c3f50c176a.tar.bz2
llvm-5adb66a646e2ec32265263739f5b01c3f50c176a.tar.xz
Make ARM and Thumb2 32-bit immediate materialization into a single 32-bit pseudo
instruction. This makes it re-materializable. Thumb2 will split it back out into two instructions so IT pass will generate the right mask. Also, this expose opportunies to optimize the movw to a 16-bit move. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82982 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/ARM/README.txt')
-rw-r--r--lib/Target/ARM/README.txt8
1 files changed, 8 insertions, 0 deletions
diff --git a/lib/Target/ARM/README.txt b/lib/Target/ARM/README.txt
index 08435c57eb..8fb1da3008 100644
--- a/lib/Target/ARM/README.txt
+++ b/lib/Target/ARM/README.txt
@@ -592,3 +592,11 @@ conditional move:
it saves an instruction and a register.
//===---------------------------------------------------------------------===//
+
+add/sub/and/or + i32 imm can be simplified by folding part of the immediate
+into the operation.
+
+//===---------------------------------------------------------------------===//
+
+It might be profitable to cse MOVi16 if there are lots of 32-bit immediates
+with the same bottom half.