X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=include%2Fllvm%2FSupport%2FMathExtras.h;h=b7b3c02dcfe76be2cf9572cb4308f4aed4dc9905;hp=9c5f32cd5ff2fc27534a702bd00842cdf66bd9a6;hb=156d5ee497ef9b6b08bad403f66c52bb15887db9;hpb=34247a0f356edf45ae3ad9ce04e1f90a77c6dba7 diff --git a/include/llvm/Support/MathExtras.h b/include/llvm/Support/MathExtras.h index 9c5f32cd5ff..b7b3c02dcfe 100644 --- a/include/llvm/Support/MathExtras.h +++ b/include/llvm/Support/MathExtras.h @@ -14,9 +14,229 @@ #ifndef LLVM_SUPPORT_MATHEXTRAS_H #define LLVM_SUPPORT_MATHEXTRAS_H -#include "llvm/System/DataTypes.h" +#include "llvm/Support/Compiler.h" +#include "llvm/Support/SwapByteOrder.h" +#include +#include +#include + +#ifdef _MSC_VER +#include +#endif + +#ifdef __ANDROID_NDK__ +#include +#endif namespace llvm { +/// \brief The behavior an operation has on an input of 0. +enum ZeroBehavior { + /// \brief The returned value is undefined. + ZB_Undefined, + /// \brief The returned value is numeric_limits::max() + ZB_Max, + /// \brief The returned value is numeric_limits::digits + ZB_Width +}; + +namespace detail { +template struct TrailingZerosCounter { + static std::size_t count(T Val, ZeroBehavior) { + if (!Val) + return std::numeric_limits::digits; + if (Val & 0x1) + return 0; + + // Bisection method. + std::size_t ZeroBits = 0; + T Shift = std::numeric_limits::digits >> 1; + T Mask = std::numeric_limits::max() >> Shift; + while (Shift) { + if ((Val & Mask) == 0) { + Val >>= Shift; + ZeroBits |= Shift; + } + Shift >>= 1; + Mask >>= Shift; + } + return ZeroBits; + } +}; + +#if __GNUC__ >= 4 || _MSC_VER +template struct TrailingZerosCounter { + static std::size_t count(T Val, ZeroBehavior ZB) { + if (ZB != ZB_Undefined && Val == 0) + return 32; + +#if __has_builtin(__builtin_ctz) || LLVM_GNUC_PREREQ(4, 0, 0) + return __builtin_ctz(Val); +#elif _MSC_VER + unsigned long Index; + _BitScanForward(&Index, Val); + return Index; +#endif + } +}; + +#if !defined(_MSC_VER) || defined(_M_X64) +template struct TrailingZerosCounter { + static std::size_t count(T Val, ZeroBehavior ZB) { + if (ZB != ZB_Undefined && Val == 0) + return 64; + +#if __has_builtin(__builtin_ctzll) || LLVM_GNUC_PREREQ(4, 0, 0) + return __builtin_ctzll(Val); +#elif _MSC_VER + unsigned long Index; + _BitScanForward64(&Index, Val); + return Index; +#endif + } +}; +#endif +#endif +} // namespace detail + +/// \brief Count number of 0's from the least significant bit to the most +/// stopping at the first 1. +/// +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of 0. Only ZB_Width and ZB_Undefined are +/// valid arguments. +template +std::size_t countTrailingZeros(T Val, ZeroBehavior ZB = ZB_Width) { + static_assert(std::numeric_limits::is_integer && + !std::numeric_limits::is_signed, + "Only unsigned integral types are allowed."); + return detail::TrailingZerosCounter::count(Val, ZB); +} + +namespace detail { +template struct LeadingZerosCounter { + static std::size_t count(T Val, ZeroBehavior) { + if (!Val) + return std::numeric_limits::digits; + + // Bisection method. + std::size_t ZeroBits = 0; + for (T Shift = std::numeric_limits::digits >> 1; Shift; Shift >>= 1) { + T Tmp = Val >> Shift; + if (Tmp) + Val = Tmp; + else + ZeroBits |= Shift; + } + return ZeroBits; + } +}; + +#if __GNUC__ >= 4 || _MSC_VER +template struct LeadingZerosCounter { + static std::size_t count(T Val, ZeroBehavior ZB) { + if (ZB != ZB_Undefined && Val == 0) + return 32; + +#if __has_builtin(__builtin_clz) || LLVM_GNUC_PREREQ(4, 0, 0) + return __builtin_clz(Val); +#elif _MSC_VER + unsigned long Index; + _BitScanReverse(&Index, Val); + return Index ^ 31; +#endif + } +}; + +#if !defined(_MSC_VER) || defined(_M_X64) +template struct LeadingZerosCounter { + static std::size_t count(T Val, ZeroBehavior ZB) { + if (ZB != ZB_Undefined && Val == 0) + return 64; + +#if __has_builtin(__builtin_clzll) || LLVM_GNUC_PREREQ(4, 0, 0) + return __builtin_clzll(Val); +#elif _MSC_VER + unsigned long Index; + _BitScanReverse64(&Index, Val); + return Index ^ 63; +#endif + } +}; +#endif +#endif +} // namespace detail + +/// \brief Count number of 0's from the most significant bit to the least +/// stopping at the first 1. +/// +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of 0. Only ZB_Width and ZB_Undefined are +/// valid arguments. +template +std::size_t countLeadingZeros(T Val, ZeroBehavior ZB = ZB_Width) { + static_assert(std::numeric_limits::is_integer && + !std::numeric_limits::is_signed, + "Only unsigned integral types are allowed."); + return detail::LeadingZerosCounter::count(Val, ZB); +} + +/// \brief Get the index of the first set bit starting from the least +/// significant bit. +/// +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of 0. Only ZB_Max and ZB_Undefined are +/// valid arguments. +template T findFirstSet(T Val, ZeroBehavior ZB = ZB_Max) { + if (ZB == ZB_Max && Val == 0) + return std::numeric_limits::max(); + + return countTrailingZeros(Val, ZB_Undefined); +} + +/// \brief Get the index of the last set bit starting from the least +/// significant bit. +/// +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of 0. Only ZB_Max and ZB_Undefined are +/// valid arguments. +template T findLastSet(T Val, ZeroBehavior ZB = ZB_Max) { + if (ZB == ZB_Max && Val == 0) + return std::numeric_limits::max(); + + // Use ^ instead of - because both gcc and llvm can remove the associated ^ + // in the __builtin_clz intrinsic on x86. + return countLeadingZeros(Val, ZB_Undefined) ^ + (std::numeric_limits::digits - 1); +} + +/// \brief Macro compressed bit reversal table for 256 bits. +/// +/// http://graphics.stanford.edu/~seander/bithacks.html#BitReverseTable +static const unsigned char BitReverseTable256[256] = { +#define R2(n) n, n + 2 * 64, n + 1 * 64, n + 3 * 64 +#define R4(n) R2(n), R2(n + 2 * 16), R2(n + 1 * 16), R2(n + 3 * 16) +#define R6(n) R4(n), R4(n + 2 * 4), R4(n + 1 * 4), R4(n + 3 * 4) + R6(0), R6(2), R6(1), R6(3) +#undef R2 +#undef R4 +#undef R6 +}; + +/// \brief Reverse the bits in \p Val. +template +T reverseBits(T Val) { + unsigned char in[sizeof(Val)]; + unsigned char out[sizeof(Val)]; + std::memcpy(in, &Val, sizeof(Val)); + for (unsigned i = 0; i < sizeof(Val); ++i) + out[(sizeof(Val) - i) - 1] = BitReverseTable256[in[i]]; + std::memcpy(&Val, out, sizeof(Val)); + return Val; +} // NOTE: The following support functions use the _32/_64 extensions instead of // type overloading so that signed and unsigned integers can be used without @@ -32,6 +252,12 @@ inline uint32_t Lo_32(uint64_t Value) { return static_cast(Value); } +/// Make_64 - This functions makes a 64-bit integer from a high / low pair of +/// 32-bit integers. +inline uint64_t Make_64(uint32_t High, uint32_t Low) { + return ((uint64_t)High << 32) | (uint64_t)Low; +} + /// isInt - Checks if an integer fits into the given bit width. template inline bool isInt(int64_t x) { @@ -51,10 +277,17 @@ inline bool isInt<32>(int64_t x) { return static_cast(x) == x; } +/// isShiftedInt - Checks if a signed integer is an N bit number shifted +/// left by S. +template +inline bool isShiftedInt(int64_t x) { + return isInt(x) && (x % (1< inline bool isUInt(uint64_t x) { - return N >= 64 || x < (UINT64_C(1)<= 64 || x < (UINT64_C(1)<<(N)); } // Template specializations to get better code for common cases. template<> @@ -70,31 +303,50 @@ inline bool isUInt<32>(uint64_t x) { return static_cast(x) == x; } -/// isMask_32 - This function returns true if the argument is a sequence of ones -/// starting at the least significant bit with the remainder zero (32 bit -/// version). Ex. isMask_32(0x0000FFFFU) == true. +/// isShiftedUInt - Checks if a unsigned integer is an N bit number shifted +/// left by S. +template +inline bool isShiftedUInt(uint64_t x) { + return isUInt(x) && (x % (1<= 64 || x < (UINT64_C(1)<<(N)); +} + +/// isIntN - Checks if an signed integer fits into the given (dynamic) +/// bit width. +inline bool isIntN(unsigned N, int64_t x) { + return N >= 64 || (-(INT64_C(1)<<(N-1)) <= x && x < (INT64_C(1)<<(N-1))); +} + +/// isMask_32 - This function returns true if the argument is a non-empty +/// sequence of ones starting at the least significant bit with the remainder +/// zero (32 bit version). Ex. isMask_32(0x0000FFFFU) == true. inline bool isMask_32(uint32_t Value) { return Value && ((Value + 1) & Value) == 0; } -/// isMask_64 - This function returns true if the argument is a sequence of ones -/// starting at the least significant bit with the remainder zero (64 bit -/// version). +/// isMask_64 - This function returns true if the argument is a non-empty +/// sequence of ones starting at the least significant bit with the remainder +/// zero (64 bit version). inline bool isMask_64(uint64_t Value) { return Value && ((Value + 1) & Value) == 0; } /// isShiftedMask_32 - This function returns true if the argument contains a -/// sequence of ones with the remainder zero (32 bit version.) +/// non-empty sequence of ones with the remainder zero (32 bit version.) /// Ex. isShiftedMask_32(0x0000FF00U) == true. inline bool isShiftedMask_32(uint32_t Value) { - return isMask_32((Value - 1) | Value); + return Value && isMask_32((Value - 1) | Value); } /// isShiftedMask_64 - This function returns true if the argument contains a -/// sequence of ones with the remainder zero (64 bit version.) +/// non-empty sequence of ones with the remainder zero (64 bit version.) inline bool isShiftedMask_64(uint64_t Value) { - return isMask_64((Value - 1) | Value); + return Value && isMask_64((Value - 1) | Value); } /// isPowerOf2_32 - This function returns true if the argument is a power of @@ -112,210 +364,101 @@ inline bool isPowerOf2_64(uint64_t Value) { /// ByteSwap_16 - This function returns a byte-swapped representation of the /// 16-bit argument, Value. inline uint16_t ByteSwap_16(uint16_t Value) { -#if defined(_MSC_VER) && !defined(_DEBUG) - // The DLL version of the runtime lacks these functions (bug!?), but in a - // release build they're replaced with BSWAP instructions anyway. - return _byteswap_ushort(Value); -#else - uint16_t Hi = Value << 8; - uint16_t Lo = Value >> 8; - return Hi | Lo; -#endif + return sys::SwapByteOrder_16(Value); } /// ByteSwap_32 - This function returns a byte-swapped representation of the /// 32-bit argument, Value. inline uint32_t ByteSwap_32(uint32_t Value) { -#if (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) && !defined(__ICC) - return __builtin_bswap32(Value); -#elif defined(_MSC_VER) && !defined(_DEBUG) - return _byteswap_ulong(Value); -#else - uint32_t Byte0 = Value & 0x000000FF; - uint32_t Byte1 = Value & 0x0000FF00; - uint32_t Byte2 = Value & 0x00FF0000; - uint32_t Byte3 = Value & 0xFF000000; - return (Byte0 << 24) | (Byte1 << 8) | (Byte2 >> 8) | (Byte3 >> 24); -#endif + return sys::SwapByteOrder_32(Value); } /// ByteSwap_64 - This function returns a byte-swapped representation of the /// 64-bit argument, Value. inline uint64_t ByteSwap_64(uint64_t Value) { -#if (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) && !defined(__ICC) - return __builtin_bswap64(Value); -#elif defined(_MSC_VER) && !defined(_DEBUG) - return _byteswap_uint64(Value); -#else - uint64_t Hi = ByteSwap_32(uint32_t(Value)); - uint32_t Lo = ByteSwap_32(uint32_t(Value >> 32)); - return (Hi << 32) | Lo; -#endif + return sys::SwapByteOrder_64(Value); } -/// CountLeadingZeros_32 - this function performs the platform optimal form of -/// counting the number of zeros from the most significant bit to the first one -/// bit. Ex. CountLeadingZeros_32(0x00F000FF) == 8. -/// Returns 32 if the word is zero. -inline unsigned CountLeadingZeros_32(uint32_t Value) { - unsigned Count; // result +/// \brief Count the number of ones from the most significant bit to the first +/// zero bit. +/// +/// Ex. CountLeadingOnes(0xFF0FFF00) == 8. +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of all ones. Only ZB_Width and +/// ZB_Undefined are valid arguments. +template +std::size_t countLeadingOnes(T Value, ZeroBehavior ZB = ZB_Width) { + static_assert(std::numeric_limits::is_integer && + !std::numeric_limits::is_signed, + "Only unsigned integral types are allowed."); + return countLeadingZeros(~Value, ZB); +} + +/// \brief Count the number of ones from the least significant bit to the first +/// zero bit. +/// +/// Ex. countTrailingOnes(0x00FF00FF) == 8. +/// Only unsigned integral types are allowed. +/// +/// \param ZB the behavior on an input of all ones. Only ZB_Width and +/// ZB_Undefined are valid arguments. +template +std::size_t countTrailingOnes(T Value, ZeroBehavior ZB = ZB_Width) { + static_assert(std::numeric_limits::is_integer && + !std::numeric_limits::is_signed, + "Only unsigned integral types are allowed."); + return countTrailingZeros(~Value, ZB); +} + +namespace detail { +template struct PopulationCounter { + static unsigned count(T Value) { + // Generic version, forward to 32 bits. + static_assert(SizeOfT <= 4, "Not implemented!"); #if __GNUC__ >= 4 - // PowerPC is defined for __builtin_clz(0) -#if !defined(__ppc__) && !defined(__ppc64__) - if (!Value) return 32; -#endif - Count = __builtin_clz(Value); + return __builtin_popcount(Value); #else - if (!Value) return 32; - Count = 0; - // bisection method for count leading zeros - for (unsigned Shift = 32 >> 1; Shift; Shift >>= 1) { - uint32_t Tmp = Value >> Shift; - if (Tmp) { - Value = Tmp; - } else { - Count |= Shift; - } - } + uint32_t v = Value; + v = v - ((v >> 1) & 0x55555555); + v = (v & 0x33333333) + ((v >> 2) & 0x33333333); + return ((v + (v >> 4) & 0xF0F0F0F) * 0x1010101) >> 24; #endif - return Count; -} - -/// CountLeadingOnes_32 - this function performs the operation of -/// counting the number of ones from the most significant bit to the first zero -/// bit. Ex. CountLeadingOnes_32(0xFF0FFF00) == 8. -/// Returns 32 if the word is all ones. -inline unsigned CountLeadingOnes_32(uint32_t Value) { - return CountLeadingZeros_32(~Value); -} - -/// CountLeadingZeros_64 - This function performs the platform optimal form -/// of counting the number of zeros from the most significant bit to the first -/// one bit (64 bit edition.) -/// Returns 64 if the word is zero. -inline unsigned CountLeadingZeros_64(uint64_t Value) { - unsigned Count; // result -#if __GNUC__ >= 4 - // PowerPC is defined for __builtin_clzll(0) -#if !defined(__ppc__) && !defined(__ppc64__) - if (!Value) return 64; -#endif - Count = __builtin_clzll(Value); -#else - if (sizeof(long) == sizeof(int64_t)) { - if (!Value) return 64; - Count = 0; - // bisection method for count leading zeros - for (unsigned Shift = 64 >> 1; Shift; Shift >>= 1) { - uint64_t Tmp = Value >> Shift; - if (Tmp) { - Value = Tmp; - } else { - Count |= Shift; - } - } - } else { - // get hi portion - uint32_t Hi = Hi_32(Value); - - // if some bits in hi portion - if (Hi) { - // leading zeros in hi portion plus all bits in lo portion - Count = CountLeadingZeros_32(Hi); - } else { - // get lo portion - uint32_t Lo = Lo_32(Value); - // same as 32 bit value - Count = CountLeadingZeros_32(Lo)+32; - } } -#endif - return Count; -} +}; -/// CountLeadingOnes_64 - This function performs the operation -/// of counting the number of ones from the most significant bit to the first -/// zero bit (64 bit edition.) -/// Returns 64 if the word is all ones. -inline unsigned CountLeadingOnes_64(uint64_t Value) { - return CountLeadingZeros_64(~Value); -} - -/// CountTrailingZeros_32 - this function performs the platform optimal form of -/// counting the number of zeros from the least significant bit to the first one -/// bit. Ex. CountTrailingZeros_32(0xFF00FF00) == 8. -/// Returns 32 if the word is zero. -inline unsigned CountTrailingZeros_32(uint32_t Value) { +template struct PopulationCounter { + static unsigned count(T Value) { #if __GNUC__ >= 4 - return Value ? __builtin_ctz(Value) : 32; + return __builtin_popcountll(Value); #else - static const unsigned Mod37BitPosition[] = { - 32, 0, 1, 26, 2, 23, 27, 0, 3, 16, 24, 30, 28, 11, 0, 13, - 4, 7, 17, 0, 25, 22, 31, 15, 29, 10, 12, 6, 0, 21, 14, 9, - 5, 20, 8, 19, 18 - }; - return Mod37BitPosition[(-Value & Value) % 37]; + uint64_t v = Value; + v = v - ((v >> 1) & 0x5555555555555555ULL); + v = (v & 0x3333333333333333ULL) + ((v >> 2) & 0x3333333333333333ULL); + v = (v + (v >> 4)) & 0x0F0F0F0F0F0F0F0FULL; + return unsigned((uint64_t)(v * 0x0101010101010101ULL) >> 56); #endif -} - -/// CountTrailingOnes_32 - this function performs the operation of -/// counting the number of ones from the least significant bit to the first zero -/// bit. Ex. CountTrailingOnes_32(0x00FF00FF) == 8. -/// Returns 32 if the word is all ones. -inline unsigned CountTrailingOnes_32(uint32_t Value) { - return CountTrailingZeros_32(~Value); -} - -/// CountTrailingZeros_64 - This function performs the platform optimal form -/// of counting the number of zeros from the least significant bit to the first -/// one bit (64 bit edition.) -/// Returns 64 if the word is zero. -inline unsigned CountTrailingZeros_64(uint64_t Value) { -#if __GNUC__ >= 4 - return Value ? __builtin_ctzll(Value) : 64; -#else - static const unsigned Mod67Position[] = { - 64, 0, 1, 39, 2, 15, 40, 23, 3, 12, 16, 59, 41, 19, 24, 54, - 4, 64, 13, 10, 17, 62, 60, 28, 42, 30, 20, 51, 25, 44, 55, - 47, 5, 32, 65, 38, 14, 22, 11, 58, 18, 53, 63, 9, 61, 27, - 29, 50, 43, 46, 31, 37, 21, 57, 52, 8, 26, 49, 45, 36, 56, - 7, 48, 35, 6, 34, 33, 0 - }; - return Mod67Position[(-Value & Value) % 67]; -#endif -} - -/// CountTrailingOnes_64 - This function performs the operation -/// of counting the number of ones from the least significant bit to the first -/// zero bit (64 bit edition.) -/// Returns 64 if the word is all ones. -inline unsigned CountTrailingOnes_64(uint64_t Value) { - return CountTrailingZeros_64(~Value); -} + } +}; +} // namespace detail -/// CountPopulation_32 - this function counts the number of set bits in a value. -/// Ex. CountPopulation(0xF000F000) = 8 +/// \brief Count the number of set bits in a value. +/// Ex. countPopulation(0xF000F000) = 8 /// Returns 0 if the word is zero. -inline unsigned CountPopulation_32(uint32_t Value) { -#if __GNUC__ >= 4 - return __builtin_popcount(Value); +template +inline unsigned countPopulation(T Value) { + static_assert(std::numeric_limits::is_integer && + !std::numeric_limits::is_signed, + "Only unsigned integral types are allowed."); + return detail::PopulationCounter::count(Value); +} + +/// Log2 - This function returns the log base 2 of the specified value +inline double Log2(double Value) { +#if defined(__ANDROID_API__) && __ANDROID_API__ < 18 + return __builtin_log(Value) / __builtin_log(2.0); #else - uint32_t v = Value - ((Value >> 1) & 0x55555555); - v = (v & 0x33333333) + ((v >> 2) & 0x33333333); - return ((v + (v >> 4) & 0xF0F0F0F) * 0x1010101) >> 24; -#endif -} - -/// CountPopulation_64 - this function counts the number of set bits in a value, -/// (64 bit edition.) -inline unsigned CountPopulation_64(uint64_t Value) { -#if __GNUC__ >= 4 - return __builtin_popcountll(Value); -#else - uint64_t v = Value - ((Value >> 1) & 0x5555555555555555ULL); - v = (v & 0x3333333333333333ULL) + ((v >> 2) & 0x3333333333333333ULL); - v = (v + (v >> 4)) & 0x0F0F0F0F0F0F0F0FULL; - return unsigned((uint64_t)(v * 0x0101010101010101ULL) >> 56); + return log2(Value); #endif } @@ -323,26 +466,26 @@ inline unsigned CountPopulation_64(uint64_t Value) { /// -1 if the value is zero. (32 bit edition.) /// Ex. Log2_32(32) == 5, Log2_32(1) == 0, Log2_32(0) == -1, Log2_32(6) == 2 inline unsigned Log2_32(uint32_t Value) { - return 31 - CountLeadingZeros_32(Value); + return 31 - countLeadingZeros(Value); } /// Log2_64 - This function returns the floor log base 2 of the specified value, /// -1 if the value is zero. (64 bit edition.) inline unsigned Log2_64(uint64_t Value) { - return 63 - CountLeadingZeros_64(Value); + return 63 - countLeadingZeros(Value); } /// Log2_32_Ceil - This function returns the ceil log base 2 of the specified /// value, 32 if the value is zero. (32 bit edition). /// Ex. Log2_32_Ceil(32) == 5, Log2_32_Ceil(1) == 0, Log2_32_Ceil(6) == 3 inline unsigned Log2_32_Ceil(uint32_t Value) { - return 32-CountLeadingZeros_32(Value-1); + return 32 - countLeadingZeros(Value - 1); } /// Log2_64_Ceil - This function returns the ceil log base 2 of the specified /// value, 64 if the value is zero. (64 bit edition.) inline unsigned Log2_64_Ceil(uint64_t Value) { - return 64-CountLeadingZeros_64(Value-1); + return 64 - countLeadingZeros(Value - 1); } /// GreatestCommonDivisor64 - Return the greatest common divisor of the two @@ -404,24 +547,39 @@ inline uint32_t FloatToBits(float Float) { return T.I; } -/// Platform-independent wrappers for the C99 isnan() function. -int IsNAN(float f); -int IsNAN(double d); - -/// Platform-independent wrappers for the C99 isinf() function. -int IsInf(float f); -int IsInf(double d); - /// MinAlign - A and B are either alignments or offsets. Return the minimum /// alignment that may be assumed after adding the two together. -static inline uint64_t MinAlign(uint64_t A, uint64_t B) { +inline uint64_t MinAlign(uint64_t A, uint64_t B) { // The largest power of 2 that divides both A and B. - return (A | B) & -(A | B); + // + // Replace "-Value" by "1+~Value" in the following commented code to avoid + // MSVC warning C4146 + // return (A | B) & -(A | B); + return (A | B) & (1 + ~(A | B)); +} + +/// \brief Aligns \c Addr to \c Alignment bytes, rounding up. +/// +/// Alignment should be a power of two. This method rounds up, so +/// alignAddr(7, 4) == 8 and alignAddr(8, 4) == 8. +inline uintptr_t alignAddr(const void *Addr, size_t Alignment) { + assert(Alignment && isPowerOf2_64((uint64_t)Alignment) && + "Alignment is not a power of two!"); + + assert((uintptr_t)Addr + Alignment - 1 >= (uintptr_t)Addr); + + return (((uintptr_t)Addr + Alignment - 1) & ~(uintptr_t)(Alignment - 1)); +} + +/// \brief Returns the necessary adjustment for aligning \c Ptr to \c Alignment +/// bytes, rounding up. +inline size_t alignmentAdjustment(const void *Ptr, size_t Alignment) { + return alignAddr(Ptr, Alignment) - (uintptr_t)Ptr; } /// NextPowerOf2 - Returns the next power of two (in 64-bits) /// that is strictly greater than A. Returns zero on overflow. -static inline uint64_t NextPowerOf2(uint64_t A) { +inline uint64_t NextPowerOf2(uint64_t A) { A |= (A >> 1); A |= (A >> 2); A |= (A >> 4); @@ -431,32 +589,97 @@ static inline uint64_t NextPowerOf2(uint64_t A) { return A + 1; } -/// RoundUpToAlignment - Returns the next integer (mod 2**64) that is -/// greater than or equal to \arg Value and is a multiple of \arg -/// Align. Align must be non-zero. -/// -/// Examples: -/// RoundUpToAlignment(5, 8) = 8 -/// RoundUpToAlignment(17, 8) = 24 -/// RoundUpToAlignment(~0LL, 8) = 0 -inline uint64_t RoundUpToAlignment(uint64_t Value, uint64_t Align) { - return ((Value + Align - 1) / Align) * Align; +/// Returns the power of two which is less than or equal to the given value. +/// Essentially, it is a floor operation across the domain of powers of two. +inline uint64_t PowerOf2Floor(uint64_t A) { + if (!A) return 0; + return 1ull << (63 - countLeadingZeros(A, ZB_Undefined)); } -/// OffsetToAlignment - Return the offset to the next integer (mod 2**64) that -/// is greater than or equal to \arg Value and is a multiple of \arg -/// Align. Align must be non-zero. +/// Returns the next integer (mod 2**64) that is greater than or equal to +/// \p Value and is a multiple of \p Align. \p Align must be non-zero. +/// +/// If non-zero \p Skew is specified, the return value will be a minimal +/// integer that is greater than or equal to \p Value and equal to +/// \p Align * N + \p Skew for some integer N. If \p Skew is larger than +/// \p Align, its value is adjusted to '\p Skew mod \p Align'. +/// +/// Examples: +/// \code +/// RoundUpToAlignment(5, 8) = 8 +/// RoundUpToAlignment(17, 8) = 24 +/// RoundUpToAlignment(~0LL, 8) = 0 +/// RoundUpToAlignment(321, 255) = 510 +/// +/// RoundUpToAlignment(5, 8, 7) = 7 +/// RoundUpToAlignment(17, 8, 1) = 17 +/// RoundUpToAlignment(~0LL, 8, 3) = 3 +/// RoundUpToAlignment(321, 255, 42) = 552 +/// \endcode +inline uint64_t RoundUpToAlignment(uint64_t Value, uint64_t Align, + uint64_t Skew = 0) { + Skew %= Align; + return (Value + Align - 1 - Skew) / Align * Align + Skew; +} + +/// Returns the offset to the next integer (mod 2**64) that is greater than +/// or equal to \p Value and is a multiple of \p Align. \p Align must be +/// non-zero. inline uint64_t OffsetToAlignment(uint64_t Value, uint64_t Align) { return RoundUpToAlignment(Value, Align) - Value; } -/// abs64 - absolute value of a 64-bit int. Not all environments support -/// "abs" on whatever their name for the 64-bit int type is. The absolute -/// value of the largest negative number is undefined, as with "abs". -inline int64_t abs64(int64_t x) { - return (x < 0) ? -x : x; +/// SignExtend32 - Sign extend B-bit number x to 32-bit int. +/// Usage int32_t r = SignExtend32<5>(x); +template inline int32_t SignExtend32(uint32_t x) { + return int32_t(x << (32 - B)) >> (32 - B); +} + +/// \brief Sign extend number in the bottom B bits of X to a 32-bit int. +/// Requires 0 < B <= 32. +inline int32_t SignExtend32(uint32_t X, unsigned B) { + return int32_t(X << (32 - B)) >> (32 - B); +} + +/// SignExtend64 - Sign extend B-bit number x to 64-bit int. +/// Usage int64_t r = SignExtend64<5>(x); +template inline int64_t SignExtend64(uint64_t x) { + return int64_t(x << (64 - B)) >> (64 - B); +} + +/// \brief Sign extend number in the bottom B bits of X to a 64-bit int. +/// Requires 0 < B <= 64. +inline int64_t SignExtend64(uint64_t X, unsigned B) { + return int64_t(X << (64 - B)) >> (64 - B); +} + +/// \brief Add two unsigned integers, X and Y, of type T. +/// Clamp the result to the maximum representable value of T on overflow. +template +typename std::enable_if::value, T>::type +SaturatingAdd(T X, T Y) { + // Hacker's Delight, p. 29 + T Z = X + Y; + if (Z < X || Z < Y) + return std::numeric_limits::max(); + else + return Z; +} + +/// \brief Multiply two unsigned integers, X and Y, of type T. +/// Clamp the result to the maximum representable value of T on overflow. +template +typename std::enable_if::value, T>::type +SaturatingMultiply(T X, T Y) { + // Hacker's Delight, p. 30 + T Z = X * Y; + if (Y != 0 && Z / Y != X) + return std::numeric_limits::max(); + else + return Z; } +extern const float huge_valf; } // End llvm namespace #endif