Enhance the init generation logic to emit a memset followed by a few stores when

a global is larger than 32 bytes and has fewer than 6 non-zero values in the
initializer.  Previously we'd turn something like this:

char test8(int X) {
  char str[10000] = "abc";

into a 10K global variable which we then memcpy'd from.  Now we generate:

  %str = alloca [10000 x i8], align 16
  %tmp = getelementptr inbounds [10000 x i8]* %str, i64 0, i64 0
  call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 10000, i32 16, i1 false)
  store i8 97, i8* %tmp, align 16
  %0 = getelementptr [10000 x i8]* %str, i64 0, i64 1
  store i8 98, i8* %0, align 1
  %1 = getelementptr [10000 x i8]* %str, i64 0, i64 2
  store i8 99, i8* %1, align 2

Which is much smaller in space and also likely faster.

This is part of PR279

llvm-svn: 120645

1 files changed, 12 insertions, 0 deletions

diff --git a/clang/test/CodeGen/init.c b/clang/test/CodeGen/init.c
index dc9f82a6c1a..2dee0432efc 100644
--- a/clang/test/CodeGen/init.c
+++ b/clang/test/CodeGen/init.c
@@ -58,3 +58,15 @@ struct a7 {
 };
 
 struct a7 test7 = { .b = 0, .v = "bar" };
+
+
+// PR279 comment #3
+char test8(int X) {
+  char str[100000] = "abc"; // tail should be memset.
+  return str[X];
+// CHECK: @test8(
+// CHECK: call void @llvm.memset
+// CHECK: store i8 97
+// CHECK: store i8 98
+// CHECK: store i8 99
+}