mirror of
https://codeberg.org/ziglang/zig.git
synced 2026-04-28 19:47:08 +03:00
2085a4af56
The previous float-parsing method was lacking in a lot of areas. This commit introduces a state-of-the art implementation that is both accurate and fast to std. Code is derived from working repo https://github.com/tiehuis/zig-parsefloat. This includes more test-cases and performance numbers that are present in this commit. * Accuracy The primary testing regime has been using test-data found at https://github.com/tiehuis/parse-number-fxx-test-data. This is a fork of upstream with support for f128 test-cases added. This data has been verified against other independent implementations and represents accurate round-to-even IEEE-754 floating point semantics. * Performance Compared to the existing parseFloat implementation there is ~5-10x performance improvement using the above corpus. (f128 parsing excluded in below measurements). ** Old $ time ./test_all_fxx_data 3520298/5296694 succeeded (1776396 fail) ________________________________________________________ Executed in 28.68 secs fish external usr time 28.48 secs 0.00 micros 28.48 secs sys time 0.08 secs 694.00 micros 0.08 secs ** This Implementation $ time ./test_all_fxx_data 5296693/5296694 succeeded (1 fail) ________________________________________________________ Executed in 4.54 secs fish external usr time 4.37 secs 515.00 micros 4.37 secs sys time 0.10 secs 171.00 micros 0.10 secs Further performance numbers can be seen using the https://github.com/tiehuis/simple_fastfloat_benchmark/ repository, which compares against some other well-known string-to-float conversion functions. A breakdown can be found here: https://github.com/tiehuis/zig-parsefloat/blob/0d9f020f1a37ca88bf889703b397c1c41779f090/PERFORMANCE.md#commit-b15406a0d2e18b50a4b62fceb5a6a3bb60ca5706 In summary, we are within 20% of the C++ reference implementation and have about ~600-700MB/s throughput on a Intel I5-6500 3.5Ghz. * F128 Support Finally, f128 is now completely supported with full accuracy. This does use a slower path which is possible to improve in future. * Behavioural Changes There are a few behavioural changes to note. - `parseHexFloat` is now redundant and these are now supported directly in `parseFloat`. - We implement round-to-even in all parsing routines. This is as specified by IEEE-754. Previous code used different rounding mechanisms (standard was round-to-zero, hex-parsing looked to use round-up) so there may be subtle differences. Closes #2207. Fixes #11169.
115 lines
4.3 KiB
Zig
115 lines
4.3 KiB
Zig
const std = @import("std");
|
|
const math = std.math;
|
|
const common = @import("common.zig");
|
|
const BiasedFp = common.BiasedFp;
|
|
const Decimal = @import("decimal.zig").Decimal;
|
|
const mantissaType = common.mantissaType;
|
|
|
|
const max_shift = 60;
|
|
const num_powers = 19;
|
|
const powers = [_]u8{ 0, 3, 6, 9, 13, 16, 19, 23, 26, 29, 33, 36, 39, 43, 46, 49, 53, 56, 59 };
|
|
|
|
pub fn getShift(n: usize) usize {
|
|
return if (n < num_powers) powers[n] else max_shift;
|
|
}
|
|
|
|
/// Parse the significant digits and biased, binary exponent of a float.
|
|
///
|
|
/// This is a fallback algorithm that uses a big-integer representation
|
|
/// of the float, and therefore is considerably slower than faster
|
|
/// approximations. However, it will always determine how to round
|
|
/// the significant digits to the nearest machine float, allowing
|
|
/// use to handle near half-way cases.
|
|
///
|
|
/// Near half-way cases are halfway between two consecutive machine floats.
|
|
/// For example, the float `16777217.0` has a bitwise representation of
|
|
/// `100000000000000000000000 1`. Rounding to a single-precision float,
|
|
/// the trailing `1` is truncated. Using round-nearest, tie-even, any
|
|
/// value above `16777217.0` must be rounded up to `16777218.0`, while
|
|
/// any value before or equal to `16777217.0` must be rounded down
|
|
/// to `16777216.0`. These near-halfway conversions therefore may require
|
|
/// a large number of digits to unambiguously determine how to round.
|
|
///
|
|
/// The algorithms described here are based on "Processing Long Numbers Quickly",
|
|
/// available here: <https://arxiv.org/pdf/2101.11408.pdf#section.11>.
|
|
pub fn convertSlow(comptime T: type, s: []const u8) BiasedFp(T) {
|
|
const MantissaT = mantissaType(T);
|
|
const min_exponent = -(1 << (math.floatExponentBits(T) - 1)) + 1;
|
|
const infinite_power = (1 << math.floatExponentBits(T)) - 1;
|
|
const mantissa_explicit_bits = math.floatMantissaBits(T);
|
|
|
|
var d = Decimal(T).parse(s); // no need to recheck underscores
|
|
if (d.num_digits == 0 or d.decimal_point < Decimal(T).min_exponent) {
|
|
return BiasedFp(T).zero();
|
|
} else if (d.decimal_point >= Decimal(T).max_exponent) {
|
|
return BiasedFp(T).inf(T);
|
|
}
|
|
|
|
var exp2: i32 = 0;
|
|
// Shift right toward (1/2 .. 1]
|
|
while (d.decimal_point > 0) {
|
|
const n = @intCast(usize, d.decimal_point);
|
|
const shift = getShift(n);
|
|
d.rightShift(shift);
|
|
if (d.decimal_point < -Decimal(T).decimal_point_range) {
|
|
return BiasedFp(T).zero();
|
|
}
|
|
exp2 += @intCast(i32, shift);
|
|
}
|
|
// Shift left toward (1/2 .. 1]
|
|
while (d.decimal_point <= 0) {
|
|
const shift = blk: {
|
|
if (d.decimal_point == 0) {
|
|
break :blk switch (d.digits[0]) {
|
|
5...9 => break,
|
|
0, 1 => @as(usize, 2),
|
|
else => 1,
|
|
};
|
|
} else {
|
|
const n = @intCast(usize, -d.decimal_point);
|
|
break :blk getShift(n);
|
|
}
|
|
};
|
|
d.leftShift(shift);
|
|
if (d.decimal_point > Decimal(T).decimal_point_range) {
|
|
return BiasedFp(T).inf(T);
|
|
}
|
|
exp2 -= @intCast(i32, shift);
|
|
}
|
|
// We are now in the range [1/2 .. 1] but the binary format uses [1 .. 2]
|
|
exp2 -= 1;
|
|
while (min_exponent + 1 > exp2) {
|
|
var n = @intCast(usize, (min_exponent + 1) - exp2);
|
|
if (n > max_shift) {
|
|
n = max_shift;
|
|
}
|
|
d.rightShift(n);
|
|
exp2 += @intCast(i32, n);
|
|
}
|
|
if (exp2 - min_exponent >= infinite_power) {
|
|
return BiasedFp(T).inf(T);
|
|
}
|
|
|
|
// Shift the decimal to the hidden bit, and then round the value
|
|
// to get the high mantissa+1 bits.
|
|
d.leftShift(mantissa_explicit_bits + 1);
|
|
var mantissa = d.round();
|
|
if (mantissa >= (@as(MantissaT, 1) << (mantissa_explicit_bits + 1))) {
|
|
// Rounding up overflowed to the carry bit, need to
|
|
// shift back to the hidden bit.
|
|
d.rightShift(1);
|
|
exp2 += 1;
|
|
mantissa = d.round();
|
|
if ((exp2 - min_exponent) >= infinite_power) {
|
|
return BiasedFp(T).inf(T);
|
|
}
|
|
}
|
|
var power2 = exp2 - min_exponent;
|
|
if (mantissa < (@as(MantissaT, 1) << mantissa_explicit_bits)) {
|
|
power2 -= 1;
|
|
}
|
|
// Zero out all the bits above the explicit mantissa bits.
|
|
mantissa &= (@as(MantissaT, 1) << mantissa_explicit_bits) - 1;
|
|
return .{ .f = mantissa, .e = power2 };
|
|
}
|