Implement the first half of PR3290: if there is a store of an

integer to a (transitive) bitcast the alloca and if that integer
has the full size of the alloca, then it clobbers the whole thing.
Handle this by extracting pieces out of the stored integer and 
filing them away in the SROA'd elements.

This triggers fairly frequently because the CFE uses integers to
pass small structs by value and the inliner exposes these.  For 
example, in kimwitu++, I see a bunch of these with i64 stores to
"%struct.std::pair<std::_Rb_tree_const_iterator<kc::impl_abstract_phylum*>,bool>"

In 176.gcc I see a few i32 stores to "%struct..0anon".

In the testcase, this is a difference between compiling test1 to:

_test1:
	subl	$12, %esp
	movl	20(%esp), %eax
	movl	%eax, 4(%esp)
	movl	16(%esp), %eax
	movl	%eax, (%esp)
	movl	(%esp), %eax
	addl	4(%esp), %eax
	addl	$12, %esp
	ret

vs:

_test1:
	movl	8(%esp), %eax
	addl	4(%esp), %eax
	ret

The second half of this will be to handle loads of the same form.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61853 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 31 insertions, 0 deletions

diff --git a/test/Transforms/ScalarRepl/copy-aggregate.ll b/test/Transforms/ScalarRepl/copy-aggregate.ll
new file mode 100644
index 0000000000..c3685d0930
--- /dev/null
+++ b/test/Transforms/ScalarRepl/copy-aggregate.ll
@@ -0,0 +1,31 @@
+; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis | not grep alloca
+; PR3290
+
+;; Store of integer to whole alloca struct.
+define i32 @test1(i64 %V) nounwind {
+	%X = alloca {{i32, i32}}
+	%Y = bitcast {{i32,i32}}* %X to i64*
+	store i64 %V, i64* %Y
+
+	%A = getelementptr {{i32,i32}}* %X, i32 0, i32 0, i32 0
+	%B = getelementptr {{i32,i32}}* %X, i32 0, i32 0, i32 1
+	%a = load i32* %A
+	%b = load i32* %B
+	%c = add i32 %a, %b
+	ret i32 %c
+}
+
+;; Store of integer to whole struct/array alloca.
+define float @test2(i128 %V) nounwind {
+	%X = alloca {[4 x float]}
+	%Y = bitcast {[4 x float]}* %X to i128*
+	store i128 %V, i128* %Y
+
+	%A = getelementptr {[4 x float]}* %X, i32 0, i32 0, i32 0
+	%B = getelementptr {[4 x float]}* %X, i32 0, i32 0, i32 3
+	%a = load float* %A
+	%b = load float* %B
+	%c = add float %a, %b
+	ret float %c
+}
+