Random note about bswap.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108396 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/README.txt b/lib/Target/ARM/README.txt
index 83c4f67bd7904188d84f582ca1c968e6226c50c2..0cb8ff01181d7db9bbc7538a4235a67ffe794ab6 100644 (file)
--- a/lib/Target/ARM/README.txt
+++ b/lib/Target/ARM/README.txt
@@ -631,3 +631,29 @@ The following is much shorter:
 
 
 //===---------------------------------------------------------------------===//
+
+The code generated for bswap on armv4/5 (CPUs without rev) is less than ideal:
+
+int a(int x) { return __builtin_bswap32(x); }
+
+a:
+       mov     r1, #255, 24
+       mov     r2, #255, 16
+       and     r1, r1, r0, lsr #8
+       and     r2, r2, r0, lsl #8
+       orr     r1, r1, r0, lsr #24
+       orr     r0, r2, r0, lsl #24
+       orr     r0, r0, r1
+       bx      lr
+
+Something like the following would be better (fewer instructions/registers):
+       eor     r1, r0, r0, ror #16
+       bic     r1, r1, #0xff0000
+       mov     r1, r1, lsr #8
+       eor     r0, r1, r0, ror #8
+       bx      lr
+
+A custom Thumb version would also be a slight improvement over the generic
+version.
+
+//===---------------------------------------------------------------------===//