[X86] Add -malign-double support

The -malign-double flag causes i64 and f64 types to have alignment 8
instead of 4. On x86-64, the behavior of -malign-double is enabled by default.

Rebases and cleans phosek's work here: http://reviews.llvm.org/D12860

Patch by Sean Klein

Reviewers: rnk

Subscribers: rnk, jfb, dschuff, phosek

Differential Revision: http://reviews.llvm.org/D19734

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@268473 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 123 insertions, 0 deletions

diff --git a/include/clang/Basic/LangOptions.def b/include/clang/Basic/LangOptions.def
index 9426960876..1468df5e3f 100644
--- a/include/clang/Basic/LangOptions.def
+++ b/include/clang/Basic/LangOptions.def
@@ -156,6 +156,7 @@ VALUE_LANGOPT(PackStruct  , 32, 0,
               "default struct packing maximum alignment")
 VALUE_LANGOPT(MaxTypeAlign  , 32, 0,
               "default maximum alignment for types")
+VALUE_LANGOPT(AlignDouble            , 1, 0, "Controls if doubles should be aligned to 8 bytes (x86 only)")
 COMPATIBLE_VALUE_LANGOPT(PICLevel    , 2, 0, "__PIC__ level")
 COMPATIBLE_VALUE_LANGOPT(PIELevel    , 2, 0, "__PIE__ level")
 COMPATIBLE_LANGOPT(GNUInline         , 1, 0, "GNU inline semantics")
diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index aaa4ce92f7..2ec5d47084 100644
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -1320,6 +1320,8 @@ def mfix_and_continue : Flag<["-"], "mfix-and-continue">, Group<clang_ignored_m_
 def mieee_fp : Flag<["-"], "mieee-fp">, Group<clang_ignored_m_Group>;
 def minline_all_stringops : Flag<["-"], "minline-all-stringops">, Group<clang_ignored_m_Group>;
 def mno_inline_all_stringops : Flag<["-"], "mno-inline-all-stringops">, Group<clang_ignored_m_Group>;
+def malign_double : Flag<["-"], "malign-double">, Group<m_Group>, Flags<[CC1Option]>,
+  HelpText<"Align doubles to two words in structs (x86 only)">;
 def mfloat_abi_EQ : Joined<["-"], "mfloat-abi=">, Group<m_Group>;
 def mfpmath_EQ : Joined<["-"], "mfpmath=">, Group<m_Group>;
 def mfpu_EQ : Joined<["-"], "mfpu=">, Group<m_Group>;
diff --git a/lib/Basic/TargetInfo.cpp b/lib/Basic/TargetInfo.cpp
index 40d6001e53..f6973f3942 100644
--- a/lib/Basic/TargetInfo.cpp
+++ b/lib/Basic/TargetInfo.cpp
@@ -275,6 +275,10 @@ void TargetInfo::adjust(const LangOptions &Opts) {
     UseBitFieldTypeAlignment = false;
   if (Opts.ShortWChar)
     WCharType = UnsignedShort;
+  if (Opts.AlignDouble) {
+    DoubleAlign = LongLongAlign = 64;
+    LongDoubleAlign = 64;
+  }
 
   if (Opts.OpenCL) {
     // OpenCL C requires specific widths for types, irrespective of
diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp
index 02a570076b..69a4366213 100644
--- a/lib/Frontend/CompilerInvocation.cpp
+++ b/lib/Frontend/CompilerInvocation.cpp
@@ -1758,6 +1758,7 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
   Opts.EmitAllDecls = Args.hasArg(OPT_femit_all_decls);
   Opts.PackStruct = getLastArgIntValue(Args, OPT_fpack_struct_EQ, 0, Diags);
   Opts.MaxTypeAlign = getLastArgIntValue(Args, OPT_fmax_type_align_EQ, 0, Diags);
+  Opts.AlignDouble = Args.hasArg(OPT_malign_double);
   Opts.PICLevel = getLastArgIntValue(Args, OPT_pic_level, 0, Diags);
   Opts.PIELevel = getLastArgIntValue(Args, OPT_pie_level, 0, Diags);
   Opts.Static = Args.hasArg(OPT_static_define);
diff --git a/test/CodeGen/malign-double.cpp b/test/CodeGen/malign-double.cpp
new file mode 100644
index 0000000000..0cda4dc368
--- /dev/null
+++ b/test/CodeGen/malign-double.cpp
@@ -0,0 +1,115 @@
+// RUN: %clang_cc1 -malign-double -triple i386-unknown-linux -emit-llvm %s -o - \
+// RUN:   | FileCheck --check-prefix=CHECK-ON --check-prefix=CHECK %s
+
+// RUN: %clang_cc1 -triple i386-unknown-linux -emit-llvm %s -o - \
+// RUN:   | FileCheck --check-prefix=CHECK-OFF --check-prefix=CHECK %s
+
+/* Structs S1, S2, S3, S4, and union U5 are taken from Intel, "IA-64
+   Software Conventions and Runtime Architecture Guide", version of
+   August 1999, Section 4.2, Figures 4-1 through 4-5.
+   A Union containing a double was also thrown in for good measure. */
+
+struct S1 {
+  char c;
+};
+
+unsigned S1_align = __alignof(struct S1);
+unsigned S1_size = sizeof(struct S1);
+// CHECK: @S1_align = global i32 1, align 4
+// CHECK: @S1_size = global i32 1, align 4
+
+unsigned S1_c_offset = (unsigned) &((struct S1*) 0)->c;
+// CHECK: @S1_c_offset = global i32 0, align 4
+
+struct S2{
+  char c;
+  char d;
+  short s;
+  int n;
+};
+
+unsigned S2_align = __alignof(struct S2);
+unsigned S2_size = sizeof(struct S2);
+// CHECK: @S2_align = global i32 4, align 4
+// CHECK: @S2_size = global i32 8, align 4
+
+unsigned S2_c_offset = (unsigned) &((struct S2*) 0)->c;
+unsigned S2_d_offset = (unsigned) &((struct S2*) 0)->d;
+unsigned S2_s_offset = (unsigned) &((struct S2*) 0)->s;
+unsigned S2_n_offset = (unsigned) &((struct S2*) 0)->n;
+// CHECK: @S2_c_offset = global i32 0, align 4
+// CHECK: @S2_d_offset = global i32 1, align 4
+// CHECK: @S2_s_offset = global i32 2, align 4
+// CHECK: @S2_n_offset = global i32 4, align 4
+
+struct S3 {
+  char c;
+  short s;
+};
+
+unsigned S3_align = __alignof(struct S3);
+unsigned S3_size = sizeof(struct S3);
+// CHECK: @S3_align = global i32 2, align 4
+// CHECK: @S3_size = global i32 4, align 4
+
+unsigned S3_c_offset = (unsigned) &((struct S3*) 0)->c;
+unsigned S3_s_offset = (unsigned) &((struct S3*) 0)->s;
+// CHECK: @S3_c_offset = global i32 0, align 4
+// CHECK: @S3_s_offset = global i32 2, align 4
+
+struct S4 {
+  char c;
+  double d;
+  short s;
+};
+
+unsigned S4_align = __alignof(struct S4);
+unsigned S4_size = sizeof(struct S4);
+// CHECK-ON: @S4_align = global i32 8, align 4
+// CHECK-ON: @S4_size = global i32 24, align 4
+// CHECK-OFF: @S4_align = global i32 4, align 4
+// CHECK-OFF: @S4_size = global i32 16, align 4
+
+unsigned S4_c_offset = (unsigned) &((struct S4*) 0)->c;
+unsigned S4_d_offset = (unsigned) &((struct S4*) 0)->d;
+unsigned S4_s_offset = (unsigned) &((struct S4*) 0)->s;
+// CHECK: @S4_c_offset = global i32 0, align 4
+// CHECK-ON: @S4_d_offset = global i32 8, align 4
+// CHECK-ON: @S4_s_offset = global i32 16, align 4
+// CHECK-OFF: @S4_d_offset = global i32 4, align 4
+// CHECK-OFF: @S4_s_offset = global i32 12, align 4
+
+union S5 {
+  char c;
+  short s;
+  int j;
+};
+
+unsigned S5_align = __alignof(union S5);
+unsigned S5_size = sizeof(union S5);
+// CHECK: @S5_align = global i32 4, align 4
+// CHECK: @S5_size = global i32 4, align 4
+
+unsigned S5_c_offset = (unsigned) &((union S5*) 0)->c;
+unsigned S5_s_offset = (unsigned) &((union S5*) 0)->s;
+unsigned S5_j_offset = (unsigned) &((union S5*) 0)->j;
+// CHECK: @S5_c_offset = global i32 0, align 4
+// CHECK: @S5_s_offset = global i32 0, align 4
+// CHECK: @S5_j_offset = global i32 0, align 4
+
+union S6 {
+  char c;
+  double d;
+};
+
+unsigned S6_align = __alignof(union S6);
+unsigned S6_size = sizeof(union S6);
+// CHECK-ON: @S6_align = global i32 8, align 4
+// CHECK-ON: @S6_size = global i32 8, align 4
+// CHECK-OFF: @S6_align = global i32 4, align 4
+// CHECK-OFF: @S6_size = global i32 8, align 4
+
+unsigned S6_c_offset = (unsigned) &((union S6*) 0)->c;
+unsigned S6_d_offset = (unsigned) &((union S6*) 0)->d;
+// CHECK: @S6_c_offset = global i32 0, align 4
+// CHECK: @S6_d_offset = global i32 0, align 4