diff --git a/libc/src/__support/CMakeLists.txt b/libc/src/__support/CMakeLists.txt
--- a/libc/src/__support/CMakeLists.txt
+++ b/libc/src/__support/CMakeLists.txt
@@ -60,6 +60,12 @@
     arg_list.h
 )
 
+add_header_library(
+  uint128
+  HDRS
+    UInt128.h
+)
+
 # Thread support is used by other support libraries. So, we add the "threads"
 # before other directories.
 add_subdirectory(threads)
diff --git a/libc/src/__support/FPUtil/CMakeLists.txt b/libc/src/__support/FPUtil/CMakeLists.txt
--- a/libc/src/__support/FPUtil/CMakeLists.txt
+++ b/libc/src/__support/FPUtil/CMakeLists.txt
@@ -13,7 +13,6 @@
     NormalFloat.h
     PlatformDefs.h
     UInt.h
-    XFloat.h
   DEPENDS
     libc.include.math
     libc.include.errno
@@ -24,6 +23,23 @@
     libc.src.errno.errno
 )
 
+add_header_library(
+  uint
+  HDRS
+    UInt.h
+  DEPENDS
+    libc.src.__support.CPP.array
+)
+
+add_header_library(
+  xfloat
+  HDRS
+    XFloat.h
+  DEPENDS
+    .fputil #FPBits and NormalFloat
+    .uint
+)
+
 add_header_library(
   sqrt
   HDRS
diff --git a/libc/src/__support/FPUtil/UInt.h b/libc/src/__support/FPUtil/UInt.h
--- a/libc/src/__support/FPUtil/UInt.h
+++ b/libc/src/__support/FPUtil/UInt.h
@@ -9,31 +9,33 @@
 #ifndef LLVM_LIBC_UTILS_FPUTIL_UINT_H
 #define LLVM_LIBC_UTILS_FPUTIL_UINT_H
 
+#include "src/__support/CPP/Array.h"
+
 #include <stddef.h> // For size_t
 #include <stdint.h>
 
 namespace __llvm_libc {
 namespace fputil {
 
-template <size_t Bits> class UInt {
+static constexpr uint64_t Mask32 = 0xFFFFFFFF;
 
-  // This is mainly used for debugging.
-  enum Kind {
-    NotANumber,
-    Valid,
-  };
+constexpr uint64_t low(uint64_t v) { return v & Mask32; }
+constexpr uint64_t high(uint64_t v) { return (v >> 32) & Mask32; }
+
+template <size_t Bits> class UInt {
 
   static_assert(Bits > 0 && Bits % 64 == 0,
                 "Number of bits in UInt should be a multiple of 64.");
-  static constexpr uint64_t Mask32 = 0xFFFFFFFF;
   static constexpr size_t WordCount = Bits / 64;
   static constexpr uint64_t InvalidHexDigit = 20;
   uint64_t val[WordCount];
-  Kind kind;
 
-  uint64_t low(uint64_t v) { return v & Mask32; }
-
-  uint64_t high(uint64_t v) { return (v >> 32) & Mask32; }
+  constexpr void init(uint64_t x) {
+    val[0] = x;
+    for (size_t i = 1; i < WordCount; ++i) {
+      val[i] = 0;
+    }
+  }
 
   uint64_t hexval(char c) {
     uint64_t diff;
@@ -55,61 +57,64 @@
   }
 
 public:
-  UInt() { kind = Valid; }
+  constexpr UInt() {}
 
-  UInt(const UInt<Bits> &other) : kind(other.kind) {
-    if (kind == Valid) {
-      for (size_t i = 0; i < WordCount; ++i)
-        val[i] = other.val[i];
-    }
+  constexpr UInt(const UInt<Bits> &other) {
+    for (size_t i = 0; i < WordCount; ++i)
+      val[i] = other.val[i];
   }
+  /*
+    // This constructor is used for debugging.
+    explicit UInt(const char *s) {
+      size_t len = strlen(s);
+      if (len > Bits / 4 + 2 || len < 3) {
+        return;
+      }
 
-  // This constructor is used for debugging.
-  explicit UInt(const char *s) {
-    size_t len = strlen(s);
-    if (len > Bits / 4 + 2 || len < 3) {
-      kind = NotANumber;
-      return;
-    }
-
-    if (!(s[0] == '0' && s[1] == 'x')) {
-      kind = NotANumber;
-      return;
-    }
+      if (!(s[0] == '0' && s[1] == 'x')) {
+        return;
+      }
 
-    for (size_t i = 0; i < WordCount; ++i)
-      val[i] = 0;
+      for (size_t i = 0; i < WordCount; ++i)
+        val[i] = 0;
 
-    for (size_t i = len - 1, w = 0; i >= 2; --i, w += 4) {
-      uint64_t hex = hexval(s[i]);
-      if (hex == InvalidHexDigit) {
-        kind = NotANumber;
-        return;
+      for (size_t i = len - 1, w = 0; i >= 2; --i, w += 4) {
+        uint64_t hex = hexval(s[i]);
+        if (hex == InvalidHexDigit) {
+          return;
+        }
+        val[w / 64] |= (hex << (w % 64));
       }
-      val[w / 64] |= (hex << (w % 64));
     }
-
-    kind = Valid;
+  */
+  // Initialize the first word to |v| and the rest to 0.
+  constexpr UInt(uint64_t v) { init(v); }
+  /*
+    constexpr explicit UInt(const uint64_t data[WordCount]) {
+      for (size_t i = 0; i < WordCount; ++i)
+        val[i] = data[i];
+    }
+  */
+  constexpr explicit UInt(const cpp::Array<uint64_t, WordCount> &words) {
+    for (size_t i = 0; i < WordCount; ++i)
+      val[i] = words[i];
   }
 
-  explicit UInt(uint64_t v) {
-    val[0] = v;
-    for (size_t i = 1; i < WordCount; ++i)
-      val[i] = 0;
-    kind = Valid;
+  constexpr explicit operator uint64_t() const { return val[0]; }
+
+  constexpr explicit operator uint32_t() const {
+    return uint32_t(uint64_t(*this));
   }
 
-  explicit UInt(uint64_t data[WordCount]) {
+  UInt<Bits> &operator=(const UInt<Bits> &other) {
     for (size_t i = 0; i < WordCount; ++i)
-      val[i] = data[i];
-    kind = Valid;
+      val[i] = other.val[i];
+    return *this;
   }
 
-  bool is_valid() const { return kind == Valid; }
-
   // Add x to this number and store the result in this number.
   // Returns the carry value produced by the addition operation.
-  uint64_t add(const UInt<Bits> &x) {
+  constexpr uint64_t add(const UInt<Bits> &x) {
     uint64_t carry = 0;
     for (size_t i = 0; i < WordCount; ++i) {
       uint64_t res_lo = low(val[i]) + low(x.val[i]) + carry;
@@ -125,17 +130,23 @@
     return carry;
   }
 
+  constexpr UInt<Bits> operator+(const UInt<Bits> &other) const {
+    UInt<Bits> result(*this);
+    result.add(other);
+    return result;
+  }
+
   // Multiply this number with x and store the result in this number. It is
   // implemented using the long multiplication algorithm by splitting the
   // 64-bit words of this number and |x| in to 32-bit halves but peforming
   // the operations using 64-bit numbers. This ensures that we don't lose the
   // carry bits.
   // Returns the carry value produced by the multiplication operation.
-  uint64_t mul(uint64_t x) {
+  constexpr uint64_t mul(uint64_t x) {
     uint64_t x_lo = low(x);
     uint64_t x_hi = high(x);
 
-    uint64_t row1[WordCount + 1];
+    cpp::Array<uint64_t, WordCount + 1> row1;
     uint64_t carry = 0;
     for (size_t i = 0; i < WordCount; ++i) {
       uint64_t l = low(val[i]);
@@ -154,7 +165,7 @@
     }
     row1[WordCount] = carry;
 
-    uint64_t row2[WordCount + 1];
+    cpp::Array<uint64_t, WordCount + 1> row2;
     row2[0] = 0;
     carry = 0;
     for (size_t i = 0; i < WordCount; ++i) {
@@ -183,13 +194,25 @@
     return r1[WordCount];
   }
 
-  void shift_left(size_t s) {
+  constexpr UInt<Bits> operator*(const UInt<Bits> &other) const {
+    UInt<Bits> result(0);
+    result.mul(other[0]);
+    for (size_t i = 0; i < WordCount; ++i) {
+      UInt<Bits> row_result(*this);
+      row_result.mul(other[i]);
+      row_result.shift_left(64 * i);
+      result = result + row_result;
+    }
+    return result;
+  }
+
+  constexpr void shift_left(size_t s) {
     const size_t drop = s / 64;  // Number of words to drop
     const size_t shift = s % 64; // Bits to shift in the remaining words.
     const uint64_t mask = ((uint64_t(1) << shift) - 1) << (64 - shift);
 
     for (size_t i = WordCount; drop > 0 && i > 0; --i) {
-      if (i - drop > 0)
+      if (i > drop)
         val[i - 1] = val[i - drop - 1];
       else
         val[i - 1] = 0;
@@ -202,7 +225,13 @@
     }
   }
 
-  void shift_right(size_t s) {
+  constexpr UInt<Bits> operator<<(size_t s) const {
+    UInt<Bits> result(*this);
+    result.shift_left(s);
+    return result;
+  }
+
+  constexpr void shift_right(size_t s) {
     const size_t drop = s / 64;  // Number of words to drop
     const size_t shift = s % 64; // Bit shift in the remaining words.
     const uint64_t mask = (uint64_t(1) << shift) - 1;
@@ -221,8 +250,53 @@
     }
   }
 
+  constexpr UInt<Bits> operator>>(size_t s) const {
+    UInt<Bits> result(*this);
+    result.shift_right(s);
+    return result;
+  }
+
+  constexpr UInt<Bits> operator&(const UInt<Bits> &other) const {
+    UInt<Bits> result;
+    for (size_t i = 0; i < WordCount; ++i)
+      result.val[i] = val[i] & other.val[i];
+    return result;
+  }
+
+  constexpr UInt<Bits> operator|(const UInt<Bits> &other) const {
+    UInt<Bits> result;
+    for (size_t i = 0; i < WordCount; ++i)
+      result.val[i] = val[i] | other.val[i];
+    return result;
+  }
+
+  constexpr UInt<Bits> operator^(const UInt<Bits> &other) const {
+    UInt<Bits> result;
+    for (size_t i = 0; i < WordCount; ++i)
+      result.val[i] = val[i] ^ other.val[i];
+    return result;
+  }
+
+  constexpr bool operator==(const UInt<Bits> &other) const {
+    for (size_t i = 0; i < WordCount; ++i) {
+      if (val[i] != other.val[i])
+        return false;
+    }
+    return true;
+  }
+
+  constexpr bool operator!=(const UInt<Bits> &other) const {
+    for (size_t i = 0; i < WordCount; ++i) {
+      if (val[i] != other.val[i])
+        return true;
+    }
+    return false;
+  }
+
+  // Return the i-th 64-bit word of the number.
   const uint64_t &operator[](size_t i) const { return val[i]; }
 
+  // Return the i-th 64-bit word of the number.
   uint64_t &operator[](size_t i) { return val[i]; }
 
   uint64_t *data() { return val; }
@@ -230,7 +304,47 @@
   const uint64_t *data() const { return val; }
 };
 
+template <>
+constexpr UInt<128> UInt<128>::operator*(const UInt<128> &other) const {
+  // temp low covers bits 0-63, middle covers 32-95, high covers 64-127, and
+  // high overflow covers 96-159.
+  uint64_t temp_low = low(val[0]) * low(other[0]);
+  uint64_t temp_middle_1 = low(val[0]) * high(other[0]);
+  uint64_t temp_middle_2 = high(val[0]) * low(other[0]);
+
+  // temp_middle is split out so that overflows can be handled, but since
+  // but since the result will be truncated to 128 bits any overflow from here
+  // on doesn't matter.
+  uint64_t temp_high = low(val[0]) * low(other[1]) +
+                       high(val[0]) * high(other[0]) +
+                       low(val[1]) * low(other[0]);
+
+  uint64_t temp_high_overflow =
+      low(val[0]) * high(other[1]) + high(val[0]) * low(other[1]) +
+      low(val[1]) * high(other[0]) + high(val[1]) * low(other[0]);
+
+  // temp_low_middle has just the high 32 bits of low, as well as any
+  // overflow.
+  uint64_t temp_low_middle =
+      high(temp_low) + low(temp_middle_1) + low(temp_middle_2);
+
+  uint64_t new_low = low(temp_low) + (low(temp_low_middle) << 32);
+  uint64_t new_high = high(temp_low_middle) + high(temp_middle_1) +
+                      high(temp_middle_2) + temp_high +
+                      (low(temp_high_overflow) << 32);
+  UInt<128> result(0);
+  result[0] = new_low;
+  result[1] = new_high;
+  return result;
+}
+
 } // namespace fputil
 } // namespace __llvm_libc
 
+/* TODO: determine the best way to support uint128 using this class.
+#if !defined(__SIZEOF_INT128__)
+using __uint128_t = __llvm_libc::internal::UInt<128>;
+#endif // uint128 is not defined, define it with this class.
+*/
+
 #endif // LLVM_LIBC_UTILS_FPUTIL_UINT_H
diff --git a/libc/src/math/generic/CMakeLists.txt b/libc/src/math/generic/CMakeLists.txt
--- a/libc/src/math/generic/CMakeLists.txt
+++ b/libc/src/math/generic/CMakeLists.txt
@@ -1091,7 +1091,9 @@
   HDRS
     dp_trig.h
   DEPENDS
-    libc.src.__support.FPUtil.fputil
+    libc.src.__support.FPUtil.fputil #FPBits and ManipulationFunction
+    libc.src.__support.FPUtil.xfloat
+    libc.src.__support.FPUtil.uint
   COMPILE_OPTIONS
    -O3
 )
diff --git a/libc/test/src/__support/CMakeLists.txt b/libc/test/src/__support/CMakeLists.txt
--- a/libc/test/src/__support/CMakeLists.txt
+++ b/libc/test/src/__support/CMakeLists.txt
@@ -40,6 +40,16 @@
     libc.src.__support.arg_list
 )
 
+add_libc_unittest(
+  uint128_test
+  SUITE
+    libc_support_unittests
+  SRCS
+    uint128_test.cpp
+  DEPENDS
+    libc.src.__support.FPUtil.uint
+)
+
 add_executable(
   libc_str_to_float_comparison_test
   str_to_float_comparison_test.cpp
diff --git a/libc/test/src/__support/uint128_test.cpp b/libc/test/src/__support/uint128_test.cpp
new file mode 100644
--- /dev/null
+++ b/libc/test/src/__support/uint128_test.cpp
@@ -0,0 +1,176 @@
+//===-- Unittests for the 128 bit integer class ---------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/__support/FPUtil/UInt.h"
+
+#include "utils/UnitTest/Test.h"
+
+// while I could use "ASSERT_TRUE(a == b)", this will tell me what the values
+// actually are.
+#define EXPECT_128_EQ(LHS, RHS)                                                \
+  {                                                                            \
+    EXPECT_EQ((LHS)[0], (RHS)[0]);                                             \
+    EXPECT_EQ((LHS)[1], (RHS)[1]);                                             \
+  }
+#define ASSERT_128_EQ(LHS, RHS)                                                \
+  {                                                                            \
+    ASSERT_EQ((LHS)[0], (RHS)[0]);                                             \
+    ASSERT_EQ((LHS)[1], (RHS)[1]);                                             \
+  }
+
+using UInt128 = __llvm_libc::fputil::UInt<128>;
+
+TEST(LlvmLibcUInt128ClassTest, BasicInit) {
+  UInt128 empty;
+  UInt128 half_val(12345);
+  UInt128 full_val({12345, 67890});
+  ASSERT_TRUE(half_val != full_val);
+}
+
+TEST(LlvmLibcUInt128ClassTest, AdditionTests) {
+  UInt128 val1(12345);
+  UInt128 val2(54321);
+  UInt128 result1(66666);
+  EXPECT_128_EQ(val1 + val2, result1);
+  EXPECT_128_EQ((val1 + val2), (val2 + val1)); // addition is reciprocal
+
+  // Test overflow
+  UInt128 val3({0xf000000000000001, 0});
+  UInt128 val4({0x100000000000000f, 0});
+  UInt128 result2({0x10, 0x1});
+  EXPECT_128_EQ(val3 + val4, result2);
+  EXPECT_128_EQ(val3 + val4, val4 + val3);
+}
+
+TEST(LlvmLibcUInt128ClassTest, MultiplicationTests) {
+  UInt128 val1({5, 0});
+  UInt128 val2({10, 0});
+  UInt128 result1({50, 0});
+  EXPECT_128_EQ((val1 * val2), result1);
+  EXPECT_128_EQ((val1 * val2), (val2 * val1)); // multiplication is reciprocal
+
+  // Check that the multiplication works accross the whole number
+  UInt128 val3({0xf, 0});
+  UInt128 val4({0x1111111111111111, 0x1111111111111111});
+  UInt128 result2({0xffffffffffffffff, 0xffffffffffffffff});
+  EXPECT_128_EQ((val3 * val4), result2);
+  EXPECT_128_EQ((val3 * val4), (val4 * val3));
+
+  // Check that multiplication doesn't reorder the bits.
+  UInt128 val5({2, 0});
+  UInt128 val6({0x1357024675316420, 0x0123456776543210});
+  UInt128 result3({0x26ae048cea62c840, 0x02468aceeca86420});
+
+  EXPECT_128_EQ((val5 * val6), result3);
+  EXPECT_128_EQ((val5 * val6), (val6 * val5));
+
+  // Make sure that multiplication handles overflow correctly.
+  UInt128 val7(2);
+  UInt128 val8({0x8000800080008000, 0x8000800080008000});
+  UInt128 result4({0x0001000100010000, 0x0001000100010001});
+  EXPECT_128_EQ((val7 * val8), result4);
+  EXPECT_128_EQ((val7 * val8), (val8 * val7));
+
+  // val9 is the 128 bit mantissa of 1e60 as a float, val10 is the mantissa for
+  // 1e-60. They almost cancel on the high bits, but the result we're looking
+  // for is just the low bits. The full result would be
+  // 0x7fffffffffffffffffffffffffffffff3a4f32d17f40d08f917cf11d1e039c50
+  UInt128 val9({0x01D762422C946590, 0x9F4F2726179A2245});
+  UInt128 val10({0x3792F412CB06794D, 0xCDB02555653131B6});
+  UInt128 result5({0x917cf11d1e039c50, 0x3a4f32d17f40d08f});
+  EXPECT_128_EQ((val9 * val10), result5);
+  EXPECT_128_EQ((val9 * val10), (val10 * val9));
+}
+
+TEST(LlvmLibcUInt128ClassTest, ShiftLeftTests) {
+  UInt128 val1(0x0123456789abcdef);
+  UInt128 result1(0x123456789abcdef0);
+  EXPECT_128_EQ((val1 << 4), result1);
+
+  UInt128 val2({0x13579bdf02468ace, 0x123456789abcdef0});
+  UInt128 result2({0x02468ace00000000, 0x9abcdef013579bdf});
+  EXPECT_128_EQ((val2 << 32), result2);
+
+  UInt128 result3({0, 0x13579bdf02468ace});
+  EXPECT_128_EQ((val2 << 64), result3);
+
+  UInt128 result4({0, 0x02468ace00000000});
+  EXPECT_128_EQ((val2 << 96), result4);
+
+  UInt128 result5({0, 0x2468ace000000000});
+  EXPECT_128_EQ((val2 << 100), result5);
+
+  UInt128 result6({0, 0});
+  EXPECT_128_EQ((val2 << 128), result6);
+  EXPECT_128_EQ((val2 << 256), result6);
+}
+
+TEST(LlvmLibcUInt128ClassTest, ShiftRightTests) {
+  UInt128 val1(0x0123456789abcdef);
+  UInt128 result1(0x00123456789abcde);
+  EXPECT_128_EQ((val1 >> 4), result1);
+
+  UInt128 val2({0x13579bdf02468ace, 0x123456789abcdef0});
+  UInt128 result2({0x9abcdef013579bdf, 0x0000000012345678});
+  EXPECT_128_EQ((val2 >> 32), result2);
+
+  UInt128 result3({0x123456789abcdef0, 0});
+  EXPECT_128_EQ((val2 >> 64), result3);
+
+  UInt128 result4({0x0000000012345678, 0});
+  EXPECT_128_EQ((val2 >> 96), result4);
+
+  UInt128 result5({0x0000000001234567, 0});
+  EXPECT_128_EQ((val2 >> 100), result5);
+
+  UInt128 result6({0, 0});
+  EXPECT_128_EQ((val2 >> 128), result6);
+  EXPECT_128_EQ((val2 >> 256), result6);
+}
+
+TEST(LlvmLibcUInt128ClassTest, AndTests) {
+  UInt128 base({0xffff00000000ffff, 0xffffffff00000000});
+  UInt128 val128({0xf0f0f0f00f0f0f0f, 0xff00ff0000ff00ff});
+  uint64_t val64 = 0xf0f0f0f00f0f0f0f;
+  int val32 = 0x0f0f0f0f;
+  UInt128 result128({0xf0f0000000000f0f, 0xff00ff0000000000});
+  UInt128 result64(0xf0f0000000000f0f);
+  UInt128 result32(0x00000f0f);
+  EXPECT_128_EQ((base & val128), result128);
+  EXPECT_128_EQ((base & val64), result64);
+  EXPECT_128_EQ((base & val32), result32);
+}
+
+TEST(LlvmLibcUInt128ClassTest, OrTests) {
+  UInt128 base({0xffff00000000ffff, 0xffffffff00000000});
+  UInt128 val128({0xf0f0f0f00f0f0f0f, 0xff00ff0000ff00ff});
+  uint64_t val64 = 0xf0f0f0f00f0f0f0f;
+  int val32 = 0x0f0f0f0f;
+  UInt128 result128({0xfffff0f00f0fffff, 0xffffffff00ff00ff});
+  UInt128 result64({0xfffff0f00f0fffff, 0xffffffff00000000});
+  UInt128 result32({0xffff00000f0fffff, 0xffffffff00000000});
+  EXPECT_128_EQ((base | val128), result128);
+  EXPECT_128_EQ((base | val64), result64);
+  EXPECT_128_EQ((base | val32), result32);
+}
+
+TEST(LlvmLibcUInt128ClassTest, EqualsTests) {
+  UInt128 a1({0xffffffff00000000, 0xffff00000000ffff});
+  UInt128 a2({0xffffffff00000000, 0xffff00000000ffff});
+  UInt128 b({0xff00ff0000ff00ff, 0xf0f0f0f00f0f0f0f});
+  UInt128 a_reversed({0xffff00000000ffff, 0xffffffff00000000});
+  UInt128 a_upper(0xffff00000000ffff);
+  UInt128 a_lower(0xffffffff00000000);
+  ASSERT_TRUE(a1 == a1);
+  ASSERT_TRUE(a1 == a2);
+  ASSERT_FALSE(a1 == b);
+  ASSERT_FALSE(a1 == a_reversed);
+  ASSERT_FALSE(a1 == a_lower);
+  ASSERT_FALSE(a1 == a_upper);
+  ASSERT_TRUE(a_lower != a_upper);
+}