[compiler-rt] Add AArch64 to CMake configuration and several missing builtins

Summary:
Currently CMake doesn't build builtins for AArch64 and if one does this anyway
it's likely that at least `__multc3`, `__floatditf` and `__floatunditf` will be
missing.  There is actually more builtins to add, but these come from
different libc implementations, thus providing them makes compiler-rt for
AArch64 good enough at least for basic usage.

Builtins implementation were originally taken from FreeBSD project:

 * [[ https://reviews.freebsd.org/D2173 | __multc3 ]]
 * [[ https://reviews.freebsd.org/D2174 | __floatditf and __floatunditf ]]

Until they have been tested to find mistakes in `__float*` functions.
`__floatditf` was based on `__floatsitf`, which had the same mistakes
(fixed it in r243746).

Version of the builtins in this patch are fixed and complemented with basic
tests.  Additionally they were tested via GCC's torture (this is what revealed
these issues).

P.S. Ed (author of FreeBSD patches) asked for feedback on the list some time ago (here [[ http://lists.cs.uiuc.edu/pipermail/llvmdev/2015-March/084064.html | here ]])
and got no response, but it seems to be worth adding these builtins as is and
extracting common part later.

Reviewers: howard.hinnant, t.p.northover, jmolloy, enefaim, rengolin, zatrazz

Subscribers: asl, emaste, samsonov, aemerson, llvm-commits, rengolin

Differential Revision: http://reviews.llvm.org/D11679

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@245296 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 178 insertions, 1 deletions

diff --git a/lib/builtins/CMakeLists.txt b/lib/builtins/CMakeLists.txt
index b7a92b1d5..e6a23e85e 100644
--- a/lib/builtins/CMakeLists.txt
+++ b/lib/builtins/CMakeLists.txt
@@ -270,10 +270,29 @@ set(arm_SOURCES
   arm/unordsf2vfp.S
   ${GENERIC_SOURCES})
 
+set(aarch64_SOURCES
+  comparetf2.c
+  extenddftf2.c
+  extendsftf2.c
+  fixtfdi.c
+  fixtfsi.c
+  fixtfti.c
+  fixunstfdi.c
+  fixunstfsi.c
+  fixunstfti.c
+  floatditf.c
+  floatsitf.c
+  floatunditf.c
+  floatunsitf.c
+  multc3.c
+  trunctfdf2.c
+  trunctfsf2.c
+  ${GENERIC_SOURCES})
+
 add_custom_target(builtins)
 
 if (NOT WIN32 OR MINGW)
-  foreach (arch x86_64 i386 i686 arm)
+  foreach (arch x86_64 i386 i686 arm aarch64)
     if (CAN_TARGET_${arch})
       # Filter out generic versions of routines that are re-implemented in
       # architecture specific manner.  This prevents multiple definitions of the
diff --git a/lib/builtins/floatditf.c b/lib/builtins/floatditf.c
new file mode 100644
index 000000000..cd51dd8aa
--- /dev/null
+++ b/lib/builtins/floatditf.c
@@ -0,0 +1,50 @@
+//===-- lib/floatditf.c - integer -> quad-precision conversion ----*- C -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements di_int to quad-precision conversion for the
+// compiler-rt library in the IEEE-754 default round-to-nearest, ties-to-even
+// mode.
+//
+//===----------------------------------------------------------------------===//
+
+#define QUAD_PRECISION
+#include "fp_lib.h"
+
+#if defined(CRT_HAS_128BIT) && defined(CRT_LDBL_128BIT)
+COMPILER_RT_ABI fp_t __floatditf(di_int a) {
+
+    const int aWidth = sizeof a * CHAR_BIT;
+
+    // Handle zero as a special case to protect clz
+    if (a == 0)
+        return fromRep(0);
+
+    // All other cases begin by extracting the sign and absolute value of a
+    rep_t sign = 0;
+    du_int aAbs = (du_int)a;
+    if (a < 0) {
+        sign = signBit;
+        aAbs = ~(du_int)a + 1U;
+    }
+
+    // Exponent of (fp_t)a is the width of abs(a).
+    const int exponent = (aWidth - 1) - __builtin_clzll(aAbs);
+    rep_t result;
+
+    // Shift a into the significand field, rounding if it is a right-shift
+    const int shift = significandBits - exponent;
+    result = (rep_t)aAbs << shift ^ implicitBit;
+
+    // Insert the exponent
+    result += (rep_t)(exponent + exponentBias) << significandBits;
+    // Insert the sign bit and return
+    return fromRep(result | sign);
+}
+
+#endif
diff --git a/lib/builtins/floatunditf.c b/lib/builtins/floatunditf.c
new file mode 100644
index 000000000..8098e95e8
--- /dev/null
+++ b/lib/builtins/floatunditf.c
@@ -0,0 +1,40 @@
+//===-- lib/floatunditf.c - uint -> quad-precision conversion -----*- C -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements du_int to quad-precision conversion for the
+// compiler-rt library in the IEEE-754 default round-to-nearest, ties-to-even
+// mode.
+//
+//===----------------------------------------------------------------------===//
+
+#define QUAD_PRECISION
+#include "fp_lib.h"
+
+#if defined(CRT_HAS_128BIT) && defined(CRT_LDBL_128BIT)
+COMPILER_RT_ABI fp_t __floatunditf(du_int a) {
+
+    const int aWidth = sizeof a * CHAR_BIT;
+
+    // Handle zero as a special case to protect clz
+    if (a == 0) return fromRep(0);
+
+    // Exponent of (fp_t)a is the width of abs(a).
+    const int exponent = (aWidth - 1) - __builtin_clzll(a);
+    rep_t result;
+
+    // Shift a into the significand field and clear the implicit bit.
+    const int shift = significandBits - exponent;
+    result = (rep_t)a << shift ^ implicitBit;
+
+    // Insert the exponent
+    result += (rep_t)(exponent + exponentBias) << significandBits;
+    return fromRep(result);
+}
+
+#endif
diff --git a/lib/builtins/multc3.c b/lib/builtins/multc3.c
new file mode 100644
index 000000000..0518bc256
--- /dev/null
+++ b/lib/builtins/multc3.c
@@ -0,0 +1,68 @@
+/* ===-- multc3.c - Implement __multc3 -------------------------------------===
+ *
+ *                     The LLVM Compiler Infrastructure
+ *
+ * This file is dual licensed under the MIT and the University of Illinois Open
+ * Source Licenses. See LICENSE.TXT for details.
+ *
+ * ===----------------------------------------------------------------------===
+ *
+ * This file implements __multc3 for the compiler_rt library.
+ *
+ * ===----------------------------------------------------------------------===
+ */
+
+#include "int_lib.h"
+#include "int_math.h"
+
+/* Returns: the product of a + ib and c + id */
+
+COMPILER_RT_ABI long double _Complex
+__multc3(long double a, long double b, long double c, long double d)
+{
+    long double ac = a * c;
+    long double bd = b * d;
+    long double ad = a * d;
+    long double bc = b * c;
+    long double _Complex z;
+    __real__ z = ac - bd;
+    __imag__ z = ad + bc;
+    if (crt_isnan(__real__ z) && crt_isnan(__imag__ z)) {
+        int recalc = 0;
+        if (crt_isinf(a) || crt_isinf(b)) {
+            a = crt_copysignl(crt_isinf(a) ? 1 : 0, a);
+            b = crt_copysignl(crt_isinf(b) ? 1 : 0, b);
+            if (crt_isnan(c))
+                c = crt_copysignl(0, c);
+            if (crt_isnan(d))
+                d = crt_copysignl(0, d);
+            recalc = 1;
+        }
+        if (crt_isinf(c) || crt_isinf(d)) {
+            c = crt_copysignl(crt_isinf(c) ? 1 : 0, c);
+            d = crt_copysignl(crt_isinf(d) ? 1 : 0, d);
+            if (crt_isnan(a))
+                a = crt_copysignl(0, a);
+            if (crt_isnan(b))
+                b = crt_copysignl(0, b);
+            recalc = 1;
+        }
+        if (!recalc && (crt_isinf(ac) || crt_isinf(bd) ||
+                          crt_isinf(ad) || crt_isinf(bc))) {
+            if (crt_isnan(a))
+                a = crt_copysignl(0, a);
+            if (crt_isnan(b))
+                b = crt_copysignl(0, b);
+            if (crt_isnan(c))
+                c = crt_copysignl(0, c);
+            if (crt_isnan(d))
+                d = crt_copysignl(0, d);
+            recalc = 1;
+        }
+        if (recalc) {
+            __real__ z = CRT_INFINITY * (a * c - b * d);
+            __imag__ z = CRT_INFINITY * (a * d + b * c);
+        }
+    }
+    return z;
+}