CBOR reader: inline get_cbor_float() and always inline get() instead

The never-inlined get_cbor_float() costs a call for every float read
from input without bulk access: reading canada.json from CBOR through a
FILE* became 5.6 % slower on Apple clang in the benchmark suite. The
helper existed only because GCC 13 stopped inlining the stream adapter's
get_character() into parse_cbor_internal. Always inlining
binary_reader::get() fixes that as well.

callgrind, all binary formats on buffer, std::istringstream and FILE*
input (canada and citm_catalog): GCC 13 0.986-1.003, GCC 16 0.994-1.006,
Clang 23 identical. Apple clang suite: FromBinaryFile/cbor/canada 0.939,
geomean of the 53 binary reader rows 0.998.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/input/binary_reader.hpp

@@ -22,6 +22,7 @@
     #include <bit>  //byteswap
 #endif
 
+#include <nlohmann/detail/bit_ops.hpp>
 #include <nlohmann/detail/exceptions.hpp>
 #include <nlohmann/detail/input/input_adapters.hpp>
 #include <nlohmann/detail/input/json_sax.hpp>
@@ -1135,16 +1136,10 @@ class binary_reader
                 return get_half_float(false);
 
             case 0xFA: // Single-Precision Float (four-byte IEEE 754)
-            {
+                return get_cbor_float<float>();
-                float number{};
-                return get_number(number) && emit_float(number);
-            }
 
             case 0xFB: // Double-Precision Float (eight-byte IEEE 754)
-            {
+                return get_cbor_float<double>();
-                double number{};
-                return get_number(number) && emit_float(number);
-            }
 
             default: // anything else (0xFF is handled inside the other types)
             {
@@ -1153,6 +1148,14 @@ class binary_reader
         }
     }
 
+    /// read a single- or double-precision float
+    template<typename NumberType>
+    bool get_cbor_float()
+    {
+        NumberType number{};
+        return get_number(number) && emit_float(number);
+    }
+
     /*!
     @brief reports a nested indefinite-length CBOR string or byte array
     @param[in] type_name  name of the rejected string type
@@ -4200,7 +4203,12 @@ class binary_reader
     `char_traits<char_type>::eof()` in that case.
 
     @return character read from the input
+
+    @note always inlined: GCC otherwise stops inlining the stream adapter's
+          get_character() into parse_cbor_internal once that function grows
+          (+0.45 % instructions for CBOR from a std::istringstream with GCC 13)
     */
+    JSON_HEDLEY_ALWAYS_INLINE
     char_int_type get()
     {
         ++chars_read;
@@ -4246,6 +4254,27 @@ class binary_reader
         return current;
     }
 
+    /// reverse the byte order of a double with a single byteswap(): GCC does
+    /// not merge the byte-wise swap of the generic version into one
+    static void byte_swap(double& number) noexcept
+    {
+        static_assert(sizeof(double) == sizeof(std::uint64_t), "double must have 64 bits");
+        std::uint64_t bits{};
+        std::memcpy(&bits, &number, sizeof(bits));
+        bits = byteswap(bits);
+        std::memcpy(&number, &bits, sizeof(bits));
+    }
+
+    /// reverse the byte order of a float with a single byteswap()
+    static void byte_swap(float& number) noexcept
+    {
+        static_assert(sizeof(float) == sizeof(std::uint32_t), "float must have 32 bits");
+        std::uint32_t bits{};
+        std::memcpy(&bits, &number, sizeof(bits));
+        bits = byteswap(bits);
+        std::memcpy(&number, &bits, sizeof(bits));
+    }
+
     template<class NumberType>
     static void byte_swap(NumberType& number)
     {

single_include/nlohmann/json.hpp

@@ -8852,6 +8852,233 @@ NLOHMANN_JSON_NAMESPACE_END
     #include <bit>  //byteswap
 #endif
 
+// #include <nlohmann/detail/bit_ops.hpp>
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+
+
+#include <cstdint> // uint64_t
+#include <cstring> // memcpy
+#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64)) && (!defined(__SIZEOF_INT128__) || (!defined(__GNUC__) && !defined(__clang__)))
+    #include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
+#endif
+
+#ifdef _MSC_VER
+    #include <cstdlib> // _byteswap_ushort, _byteswap_ulong, _byteswap_uint64
+#endif
+#if defined(_MSC_VER) && !defined(__clang__) && (defined(_M_IX86) || defined(_M_ARM))
+    #include <intrin.h> // _BitScanForward, _BitScanReverse
+#endif
+
+// #include <nlohmann/detail/macro_scope.hpp>
+// JSON_HEDLEY_ALWAYS_INLINE, NLOHMANN_JSON_NAMESPACE_BEGIN
+
+#if defined(__cpp_lib_bit_cast) || defined(__cpp_lib_bitops) || defined(__cpp_lib_byteswap)
+    #include <bit> // bit_cast, byteswap, countl_zero, countr_zero
+#endif
+
+// Portable bit-level helpers for the number and string scanners. They use
+// compiler builtins or platform-specific intrinsics where available, the
+// C++20 <bit> functions next, and plain C++ otherwise, so they work regardless
+// of byte order. (The builtins and intrinsics come first: MSVC's
+// std::countl_zero checks for LZCNT at run time unless AVX2 is enabled.)
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+
+/// number of leading zero bits of x (x != 0)
+inline int count_leading_zeros(std::uint64_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_clzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
+    _BitScanReverse64(&index, x);
+    return 63 - static_cast<int>(index);
+#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
+    if (_BitScanReverse(&index, static_cast<unsigned long>(x >> 32u))) // NOLINT(runtime/int)
+    {
+        return 31 - static_cast<int>(index);
+    }
+    _BitScanReverse(&index, static_cast<unsigned long>(x)); // NOLINT(runtime/int)
+    return 63 - static_cast<int>(index);
+#elif defined(__cpp_lib_bitops)
+    return std::countl_zero(x);
+#else
+    int n = 0;
+    for (int shift = 32; shift != 0; shift >>= 1)
+    {
+        if ((x >> (64 - shift)) == 0)
+        {
+            n += shift;
+            x <<= shift;
+        }
+    }
+    return n;
+#endif
+}
+
+/// number of trailing zero bits of x (x != 0)
+inline int count_trailing_zeros(std::uint64_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_ctzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
+    _BitScanForward64(&index, x);
+    return static_cast<int>(index);
+#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
+    if (_BitScanForward(&index, static_cast<unsigned long>(x))) // NOLINT(runtime/int)
+    {
+        return static_cast<int>(index);
+    }
+    _BitScanForward(&index, static_cast<unsigned long>(x >> 32u)); // NOLINT(runtime/int)
+    return 32 + static_cast<int>(index);
+#elif defined(__cpp_lib_bitops)
+    return std::countr_zero(x);
+#else
+    int n = 0;
+    for (int shift = 32; shift != 0; shift >>= 1)
+    {
+        if ((x << (64 - shift)) == 0)
+        {
+            n += shift;
+            x >>= shift;
+        }
+    }
+    return n;
+#endif
+}
+
+/// the object representation of @a from as a @a To (std::bit_cast in C++20)
+template<typename To, typename From>
+JSON_HEDLEY_ALWAYS_INLINE To bit_cast(const From& from) noexcept
+{
+    static_assert(sizeof(To) == sizeof(From), "bit_cast needs types of the same size");
+#if defined(__cpp_lib_bit_cast)
+    return std::bit_cast<To>(from);
+#else
+    To to {};
+    std::memcpy(&to, &from, sizeof(To));
+    return to;
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23); compilers lower
+/// it to a single bswap/rev/movbe
+inline std::uint16_t byteswap(std::uint16_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap16(x);
+#elif defined(_MSC_VER)
+    return _byteswap_ushort(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    return static_cast<std::uint16_t>((x >> 8u) | (x << 8u));
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23)
+inline std::uint32_t byteswap(std::uint32_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap32(x);
+#elif defined(_MSC_VER)
+    return _byteswap_ulong(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    return ((x & 0x000000FFu) << 24u) | ((x & 0x0000FF00u) << 8u)
+           | ((x & 0x00FF0000u) >> 8u) | ((x & 0xFF000000u) >> 24u);
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23)
+inline std::uint64_t byteswap(std::uint64_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap64(x);
+#elif defined(_MSC_VER)
+    return _byteswap_uint64(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    x = ((x & 0x00000000FFFFFFFFull) << 32u) | ((x & 0xFFFFFFFF00000000ull) >> 32u);
+    x = ((x & 0x0000FFFF0000FFFFull) << 16u) | ((x & 0xFFFF0000FFFF0000ull) >> 16u);
+    x = ((x & 0x00FF00FF00FF00FFull) << 8u) | ((x & 0xFF00FF00FF00FF00ull) >> 8u);
+    return x;
+#endif
+}
+
+/// the 128-bit product of two 64-bit numbers
+struct uint128_parts
+{
+    std::uint64_t low;
+    std::uint64_t high;
+};
+
+inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexcept
+{
+#if defined(__SIZEOF_INT128__)
+    __extension__ using uint128 = unsigned __int128;
+    const uint128 r = static_cast<uint128>(a) * b;
+    return {static_cast<std::uint64_t>(r), static_cast<std::uint64_t>(r >> 64u)};
+#elif defined(_MSC_VER) && defined(_M_X64)
+    std::uint64_t high = 0;
+    const std::uint64_t low = _umul128(a, b, &high);
+    return {low, high};
+#elif defined(_MSC_VER) && defined(_M_ARM64)
+    return {a * b, __umulh(a, b)};
+#else
+    const std::uint64_t a_lo = a & 0xFFFFFFFFu;
+    const std::uint64_t a_hi = a >> 32u;
+    const std::uint64_t b_lo = b & 0xFFFFFFFFu;
+    const std::uint64_t b_hi = b >> 32u;
+    const std::uint64_t lo_lo = a_lo * b_lo;
+    const std::uint64_t hi_lo = a_hi * b_lo;
+    const std::uint64_t lo_hi = a_lo * b_hi;
+    const std::uint64_t hi_hi = a_hi * b_hi;
+    const std::uint64_t cross = (lo_lo >> 32u) + (hi_lo & 0xFFFFFFFFu) + lo_hi;
+    return {(cross << 32u) | (lo_lo & 0xFFFFFFFFu), (hi_lo >> 32u) + (cross >> 32u) + hi_hi};
+#endif
+}
+
+/// eight bytes as a little-endian word (a single load on little-endian
+/// targets; always inlined, as GCC otherwise calls it in the number loops)
+JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
+{
+#if JSON_LITTLE_ENDIAN_TARGET
+    // the byte order already matches
+    std::uint64_t result = 0;
+    std::memcpy(&result, b, sizeof(result));
+    return result;
+#else
+    return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
+           | (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
+           | (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
+           | (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
+#endif
+}
+
+/// eight bytes as a little-endian word
+JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const char* p) noexcept
+{
+    return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+}
+
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END
+
 // #include <nlohmann/detail/exceptions.hpp>
 
 // #include <nlohmann/detail/input/input_adapters.hpp>
@@ -10316,231 +10543,6 @@ NLOHMANN_JSON_NAMESPACE_END
 #include <vector> // vector
 
 // #include <nlohmann/detail/bit_ops.hpp>
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-
-
-#include <cstdint> // uint64_t
-#include <cstring> // memcpy
-#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64)) && (!defined(__SIZEOF_INT128__) || (!defined(__GNUC__) && !defined(__clang__)))
-    #include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
-#endif
-
-#ifdef _MSC_VER
-    #include <cstdlib> // _byteswap_ushort, _byteswap_ulong, _byteswap_uint64
-#endif
-#if defined(_MSC_VER) && !defined(__clang__) && (defined(_M_IX86) || defined(_M_ARM))
-    #include <intrin.h> // _BitScanForward, _BitScanReverse
-#endif
-
-// #include <nlohmann/detail/macro_scope.hpp>
-// JSON_HEDLEY_ALWAYS_INLINE, NLOHMANN_JSON_NAMESPACE_BEGIN
-
-#if defined(__cpp_lib_bit_cast) || defined(__cpp_lib_bitops) || defined(__cpp_lib_byteswap)
-    #include <bit> // bit_cast, byteswap, countl_zero, countr_zero
-#endif
-
-// Portable bit-level helpers for the number and string scanners. They use
-// compiler builtins or platform-specific intrinsics where available, the
-// C++20 <bit> functions next, and plain C++ otherwise, so they work regardless
-// of byte order. (The builtins and intrinsics come first: MSVC's
-// std::countl_zero checks for LZCNT at run time unless AVX2 is enabled.)
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-
-/// number of leading zero bits of x (x != 0)
-inline int count_leading_zeros(std::uint64_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_clzll(x);
-#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
-    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
-    _BitScanReverse64(&index, x);
-    return 63 - static_cast<int>(index);
-#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
-    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
-    if (_BitScanReverse(&index, static_cast<unsigned long>(x >> 32u))) // NOLINT(runtime/int)
-    {
-        return 31 - static_cast<int>(index);
-    }
-    _BitScanReverse(&index, static_cast<unsigned long>(x)); // NOLINT(runtime/int)
-    return 63 - static_cast<int>(index);
-#elif defined(__cpp_lib_bitops)
-    return std::countl_zero(x);
-#else
-    int n = 0;
-    for (int shift = 32; shift != 0; shift >>= 1)
-    {
-        if ((x >> (64 - shift)) == 0)
-        {
-            n += shift;
-            x <<= shift;
-        }
-    }
-    return n;
-#endif
-}
-
-/// number of trailing zero bits of x (x != 0)
-inline int count_trailing_zeros(std::uint64_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_ctzll(x);
-#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
-    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
-    _BitScanForward64(&index, x);
-    return static_cast<int>(index);
-#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
-    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
-    if (_BitScanForward(&index, static_cast<unsigned long>(x))) // NOLINT(runtime/int)
-    {
-        return static_cast<int>(index);
-    }
-    _BitScanForward(&index, static_cast<unsigned long>(x >> 32u)); // NOLINT(runtime/int)
-    return 32 + static_cast<int>(index);
-#elif defined(__cpp_lib_bitops)
-    return std::countr_zero(x);
-#else
-    int n = 0;
-    for (int shift = 32; shift != 0; shift >>= 1)
-    {
-        if ((x << (64 - shift)) == 0)
-        {
-            n += shift;
-            x >>= shift;
-        }
-    }
-    return n;
-#endif
-}
-
-/// the object representation of @a from as a @a To (std::bit_cast in C++20)
-template<typename To, typename From>
-JSON_HEDLEY_ALWAYS_INLINE To bit_cast(const From& from) noexcept
-{
-    static_assert(sizeof(To) == sizeof(From), "bit_cast needs types of the same size");
-#if defined(__cpp_lib_bit_cast)
-    return std::bit_cast<To>(from);
-#else
-    To to {};
-    std::memcpy(&to, &from, sizeof(To));
-    return to;
-#endif
-}
-
-/// x with its bytes in reverse order (std::byteswap in C++23); compilers lower
-/// it to a single bswap/rev/movbe
-inline std::uint16_t byteswap(std::uint16_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_bswap16(x);
-#elif defined(_MSC_VER)
-    return _byteswap_ushort(x);
-#elif defined(__cpp_lib_byteswap)
-    return std::byteswap(x);
-#else
-    return static_cast<std::uint16_t>((x >> 8u) | (x << 8u));
-#endif
-}
-
-/// x with its bytes in reverse order (std::byteswap in C++23)
-inline std::uint32_t byteswap(std::uint32_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_bswap32(x);
-#elif defined(_MSC_VER)
-    return _byteswap_ulong(x);
-#elif defined(__cpp_lib_byteswap)
-    return std::byteswap(x);
-#else
-    return ((x & 0x000000FFu) << 24u) | ((x & 0x0000FF00u) << 8u)
-           | ((x & 0x00FF0000u) >> 8u) | ((x & 0xFF000000u) >> 24u);
-#endif
-}
-
-/// x with its bytes in reverse order (std::byteswap in C++23)
-inline std::uint64_t byteswap(std::uint64_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_bswap64(x);
-#elif defined(_MSC_VER)
-    return _byteswap_uint64(x);
-#elif defined(__cpp_lib_byteswap)
-    return std::byteswap(x);
-#else
-    x = ((x & 0x00000000FFFFFFFFull) << 32u) | ((x & 0xFFFFFFFF00000000ull) >> 32u);
-    x = ((x & 0x0000FFFF0000FFFFull) << 16u) | ((x & 0xFFFF0000FFFF0000ull) >> 16u);
-    x = ((x & 0x00FF00FF00FF00FFull) << 8u) | ((x & 0xFF00FF00FF00FF00ull) >> 8u);
-    return x;
-#endif
-}
-
-/// the 128-bit product of two 64-bit numbers
-struct uint128_parts
-{
-    std::uint64_t low;
-    std::uint64_t high;
-};
-
-inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexcept
-{
-#if defined(__SIZEOF_INT128__)
-    __extension__ using uint128 = unsigned __int128;
-    const uint128 r = static_cast<uint128>(a) * b;
-    return {static_cast<std::uint64_t>(r), static_cast<std::uint64_t>(r >> 64u)};
-#elif defined(_MSC_VER) && defined(_M_X64)
-    std::uint64_t high = 0;
-    const std::uint64_t low = _umul128(a, b, &high);
-    return {low, high};
-#elif defined(_MSC_VER) && defined(_M_ARM64)
-    return {a * b, __umulh(a, b)};
-#else
-    const std::uint64_t a_lo = a & 0xFFFFFFFFu;
-    const std::uint64_t a_hi = a >> 32u;
-    const std::uint64_t b_lo = b & 0xFFFFFFFFu;
-    const std::uint64_t b_hi = b >> 32u;
-    const std::uint64_t lo_lo = a_lo * b_lo;
-    const std::uint64_t hi_lo = a_hi * b_lo;
-    const std::uint64_t lo_hi = a_lo * b_hi;
-    const std::uint64_t hi_hi = a_hi * b_hi;
-    const std::uint64_t cross = (lo_lo >> 32u) + (hi_lo & 0xFFFFFFFFu) + lo_hi;
-    return {(cross << 32u) | (lo_lo & 0xFFFFFFFFu), (hi_lo >> 32u) + (cross >> 32u) + hi_hi};
-#endif
-}
-
-/// eight bytes as a little-endian word (a single load on little-endian
-/// targets; always inlined, as GCC otherwise calls it in the number loops)
-JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
-{
-#if JSON_LITTLE_ENDIAN_TARGET
-    // the byte order already matches
-    std::uint64_t result = 0;
-    std::memcpy(&result, b, sizeof(result));
-    return result;
-#else
-    return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
-           | (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
-           | (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
-           | (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
-#endif
-}
-
-/// eight bytes as a little-endian word
-JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const char* p) noexcept
-{
-    return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-}
-
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END
 
 // #include <nlohmann/detail/input/input_adapters.hpp>
 
@@ -18911,16 +18913,10 @@ class binary_reader
                 return get_half_float(false);
 
             case 0xFA: // Single-Precision Float (four-byte IEEE 754)
-            {
+                return get_cbor_float<float>();
-                float number{};
-                return get_number(number) && emit_float(number);
-            }
 
             case 0xFB: // Double-Precision Float (eight-byte IEEE 754)
-            {
+                return get_cbor_float<double>();
-                double number{};
-                return get_number(number) && emit_float(number);
-            }
 
             default: // anything else (0xFF is handled inside the other types)
             {
@@ -18929,6 +18925,14 @@ class binary_reader
         }
     }
 
+    /// read a single- or double-precision float
+    template<typename NumberType>
+    bool get_cbor_float()
+    {
+        NumberType number{};
+        return get_number(number) && emit_float(number);
+    }
+
     /*!
     @brief reports a nested indefinite-length CBOR string or byte array
     @param[in] type_name  name of the rejected string type
@@ -21976,7 +21980,12 @@ class binary_reader
     `char_traits<char_type>::eof()` in that case.
 
     @return character read from the input
+
+    @note always inlined: GCC otherwise stops inlining the stream adapter's
+          get_character() into parse_cbor_internal once that function grows
+          (+0.45 % instructions for CBOR from a std::istringstream with GCC 13)
     */
+    JSON_HEDLEY_ALWAYS_INLINE
     char_int_type get()
     {
         ++chars_read;
@@ -22022,6 +22031,27 @@ class binary_reader
         return current;
     }
 
+    /// reverse the byte order of a double with a single byteswap(): GCC does
+    /// not merge the byte-wise swap of the generic version into one
+    static void byte_swap(double& number) noexcept
+    {
+        static_assert(sizeof(double) == sizeof(std::uint64_t), "double must have 64 bits");
+        std::uint64_t bits{};
+        std::memcpy(&bits, &number, sizeof(bits));
+        bits = byteswap(bits);
+        std::memcpy(&number, &bits, sizeof(bits));
+    }
+
+    /// reverse the byte order of a float with a single byteswap()
+    static void byte_swap(float& number) noexcept
+    {
+        static_assert(sizeof(float) == sizeof(std::uint32_t), "float must have 32 bits");
+        std::uint32_t bits{};
+        std::memcpy(&bits, &number, sizeof(bits));
+        bits = byteswap(bits);
+        std::memcpy(&number, &bits, sizeof(bits));
+    }
+
     template<class NumberType>
     static void byte_swap(NumberType& number)
     {