CodeGen: use non-zero memset when possible for automatic variables

Summary:
Right now automatic variables are either initialized with bzero followed by a few stores, or memcpy'd from a synthesized global. We end up encountering a fair amount of code where memcpy of non-zero byte patterns would be better than memcpy from a global because it touches less memory and generates a smaller binary. The optimizer could reason about this, but it's not really worth it when clang already knows.

This code could definitely be more clever but I'm not sure it's worth it. In particular we could track a histogram of bytes seen and figure out (as we do with bzero) if a memset could be followed by a handful of stores. Similarly, we could tune the heuristics for GlobalSize, but using the same as for bzero seems conservatively OK for now.

<rdar://problem/42563091>

Reviewers: dexonsmith

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D49771

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@337887 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 66 insertions, 0 deletions

diff --git a/test/CodeGen/init.c b/test/CodeGen/init.c
index 0353ba8be1..71aba39b12 100644
--- a/test/CodeGen/init.c
+++ b/test/CodeGen/init.c
@@ -140,6 +140,72 @@ void test10(int X) {
   // CHECK: call void @bar
 }
 
+void nonzeroMemseti8() {
+  char arr[33] = { 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, };
+  // CHECK-LABEL: @nonzeroMemseti8(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 42, i32 33, i1 false)
+}
+
+void nonzeroMemseti16() {
+  unsigned short arr[17] = { 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, 0x4242, };
+  // CHECK-LABEL: @nonzeroMemseti16(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 66, i32 34, i1 false)
+}
+
+void nonzeroMemseti32() {
+  unsigned arr[9] = { 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, 0xF0F0F0F0, };
+  // CHECK-LABEL: @nonzeroMemseti32(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 -16, i32 36, i1 false)
+}
+
+void nonzeroMemseti64() {
+  unsigned long long arr[7] = { 0xAAAAAAAAAAAAAAAA, 0xAAAAAAAAAAAAAAAA, 0xAAAAAAAAAAAAAAAA, 0xAAAAAAAAAAAAAAAA, 0xAAAAAAAAAAAAAAAA,  0xAAAAAAAAAAAAAAAA,  0xAAAAAAAAAAAAAAAA,  };
+  // CHECK-LABEL: @nonzeroMemseti64(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 -86, i32 56, i1 false)
+}
+
+void nonzeroMemsetf32() {
+  float arr[9] = { 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, 0x1.cacacap+75, };
+  // CHECK-LABEL: @nonzeroMemsetf32(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 101, i32 36, i1 false)
+}
+
+void nonzeroMemsetf64() {
+  double arr[7] = { 0x1.4444444444444p+69, 0x1.4444444444444p+69, 0x1.4444444444444p+69, 0x1.4444444444444p+69, 0x1.4444444444444p+69, 0x1.4444444444444p+69, 0x1.4444444444444p+69, };
+  // CHECK-LABEL: @nonzeroMemsetf64(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 68, i32 56, i1 false)
+}
+
+void nonzeroPaddedUnionMemset() {
+  union U { char c; int i; };
+  union U arr[9] = { 0xF0, 0xF0, 0xF0, 0xF0, 0xF0, 0xF0, 0xF0, 0xF0, 0xF0, };
+  // CHECK-LABEL: @nonzeroPaddedUnionMemset(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 -16, i32 36, i1 false)
+}
+
+void nonzeroNestedMemset() {
+  union U { char c; int i; };
+  struct S { union U u; short i; };
+  struct S arr[5] = { { {0xF0}, 0xF0F0 }, { {0xF0}, 0xF0F0 }, { {0xF0}, 0xF0F0 }, { {0xF0}, 0xF0F0 }, { {0xF0}, 0xF0F0 }, };
+  // CHECK-LABEL: @nonzeroNestedMemset(
+  // CHECK-NOT: store
+  // CHECK-NOT: memcpy
+  // CHECK: call void @llvm.memset.p0i8.i32(i8* {{.*}}, i8 -16, i32 40, i1 false)
+}
 
 // PR9257
 struct test11S {