This has been implemented. Tweak it into another note
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26944 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/PowerPC/README.txt b/lib/Target/PowerPC/README.txt
index c90343e..c9fba7f 100644
--- a/lib/Target/PowerPC/README.txt
+++ b/lib/Target/PowerPC/README.txt
@@ -552,34 +552,20 @@
float foo(float X) { return (int)(X); }
-Currently produces
+Currently produces:
_foo:
- lis r2, ha16(LCPI1_0)
- lis r3, 17200
fctiwz f0, f1
stfd f0, -8(r1)
- lwz r4, -4(r1)
- xoris r4, r4, 32768
- stw r4, -12(r1)
- stw r3, -16(r1)
- lfs f0, lo16(LCPI1_0)(r2)
- lfd f1, -16(r1)
- fsub f0, f1, f0
+ lwz r2, -4(r1)
+ extsw r2, r2
+ std r2, -16(r1)
+ lfd f0, -16(r1)
+ fcfid f0, f0
frsp f1, f0
blr
-When we have ppc64 working properly, it could produce the nicer code:
+We could use a target dag combine to turn the lwz/extsw into an lwa when the
+lwz has a single use. Since LWA is cracked anyway, this would be a codesize
+win only.
-_foo:
- fctiwz f0, f1
- stfd f0, -8(r1)
- lwz r4, -4(r1)
- extsh r4, r4
- std r4, -16(r1)
- lfd f1, -16(r1)
- fcfid f0, f0
- frsp f0, f0
- blr
-
-Note: this would speed up SingleSource/Misc/pi by about 30%