Change uses of getTypeSize to getABITypeSize, getTypeStoreSize

or getTypeSizeInBits as appropriate in ScalarReplAggregates.
The right change to make was not always obvious, so it would
be good to have an sroa guru review this.  While there I noticed
some bugs, and fixed them: (1) arrays of x86 long double have
holes due to alignment padding, but this wasn't being spotted
by HasStructPadding (renamed to HasPadding).  The same goes
for arrays of oddly sized ints.  Vectors also suffer from this,
in fact the problem for vectors is much worse because basic
vector assumptions seem to be broken by vectors of type with
alignment padding.   I didn't try to fix any of these vector
problems.  (2) The code for extracting smaller integers from
larger ones (in the "int union" case) was wrong on big-endian
machines for integers with size not a multiple of 8, like i1.
Probably this is impossible to hit via llvm-gcc, but I fixed
it anyway while there and added a testcase.  I also got rid of
some trailing whitespace and changed a function name which
had an obvious typo in it.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@43672 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 30 insertions, 0 deletions

diff --git a/test/Transforms/ScalarRepl/2007-11-03-bigendian_apint.ll b/test/Transforms/ScalarRepl/2007-11-03-bigendian_apint.ll
new file mode 100644
index 0000000..d2d2b24
--- /dev/null
+++ b/test/Transforms/ScalarRepl/2007-11-03-bigendian_apint.ll
@@ -0,0 +1,30 @@
+; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis | not grep shr
+
+%struct.S = type { i16 }
+
+define i1 @f(i16 signext  %b) zeroext  {
+entry:
+	%b_addr = alloca i16		; <i16*> [#uses=2]
+	%retval = alloca i32		; <i32*> [#uses=2]
+	%s = alloca %struct.S		; <%struct.S*> [#uses=2]
+	%tmp = alloca i32		; <i32*> [#uses=2]
+	%"alloca point" = bitcast i32 0 to i32		; <i32> [#uses=0]
+	store i16 %b, i16* %b_addr
+	%tmp1 = getelementptr %struct.S* %s, i32 0, i32 0		; <i16*> [#uses=1]
+	%tmp2 = load i16* %b_addr, align 2		; <i16> [#uses=1]
+	store i16 %tmp2, i16* %tmp1, align 2
+	%tmp3 = getelementptr %struct.S* %s, i32 0, i32 0		; <i16*> [#uses=1]
+	%tmp34 = bitcast i16* %tmp3 to [2 x i1]*		; <[2 x i1]*> [#uses=1]
+	%tmp5 = getelementptr [2 x i1]* %tmp34, i32 0, i32 1		; <i1*> [#uses=1]
+	%tmp6 = load i1* %tmp5, align 1		; <i1> [#uses=1]
+	%tmp67 = zext i1 %tmp6 to i32		; <i32> [#uses=1]
+	store i32 %tmp67, i32* %tmp, align 4
+	%tmp8 = load i32* %tmp, align 4		; <i32> [#uses=1]
+	store i32 %tmp8, i32* %retval, align 4
+	br label %return
+
+return:		; preds = %entry
+	%retval9 = load i32* %retval		; <i32> [#uses=1]
+	%retval910 = trunc i32 %retval9 to i1		; <i1> [#uses=1]
+	ret i1 %retval910
+}