mirror of
https://github.com/python/cpython.git
synced 2026-05-20 01:10:57 +00:00
863729e9c6
* bpo-46218: Change long_pow() to sliding window algorithm The primary motivation is to eliminate long_pow's reliance on that the number of bits in a long "digit" is a multiple of 5. Now it no longer cares how many bits are in a digit. But the sliding window approach also allows cutting the precomputed table of small powers in half, which reduces initialization overhead enough that the approach pays off for smaller exponents too. Depending on exponent bit patterns, a sliding window may also be able to save some bigint multiplies (sometimes when at least 5 consecutive exponent bits are 0, regardless of their starting bit position modulo 5). Note: boosting the window width to 6 didn't work well overall. It give marginal speed improvements for huge exponents, but the increased overhead (the small-power table needs twice as many entries) made it a loss for smaller exponents. Co-authored-by: Oleg Iarygin <dralife@yandex.ru>
93 lines
3.6 KiB
C
93 lines
3.6 KiB
C
#ifndef Py_LIMITED_API
|
|
#ifndef Py_LONGINTREPR_H
|
|
#define Py_LONGINTREPR_H
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
|
|
/* This is published for the benefit of "friends" marshal.c and _decimal.c. */
|
|
|
|
/* Parameters of the integer representation. There are two different
|
|
sets of parameters: one set for 30-bit digits, stored in an unsigned 32-bit
|
|
integer type, and one set for 15-bit digits with each digit stored in an
|
|
unsigned short. The value of PYLONG_BITS_IN_DIGIT, defined either at
|
|
configure time or in pyport.h, is used to decide which digit size to use.
|
|
|
|
Type 'digit' should be able to hold 2*PyLong_BASE-1, and type 'twodigits'
|
|
should be an unsigned integer type able to hold all integers up to
|
|
PyLong_BASE*PyLong_BASE-1. x_sub assumes that 'digit' is an unsigned type,
|
|
and that overflow is handled by taking the result modulo 2**N for some N >
|
|
PyLong_SHIFT. The majority of the code doesn't care about the precise
|
|
value of PyLong_SHIFT, but there are some notable exceptions:
|
|
|
|
- PyLong_{As,From}ByteArray require that PyLong_SHIFT be at least 8
|
|
|
|
- long_hash() requires that PyLong_SHIFT is *strictly* less than the number
|
|
of bits in an unsigned long, as do the PyLong <-> long (or unsigned long)
|
|
conversion functions
|
|
|
|
- the Python int <-> size_t/Py_ssize_t conversion functions expect that
|
|
PyLong_SHIFT is strictly less than the number of bits in a size_t
|
|
|
|
- the marshal code currently expects that PyLong_SHIFT is a multiple of 15
|
|
|
|
- NSMALLNEGINTS and NSMALLPOSINTS should be small enough to fit in a single
|
|
digit; with the current values this forces PyLong_SHIFT >= 9
|
|
|
|
The values 15 and 30 should fit all of the above requirements, on any
|
|
platform.
|
|
*/
|
|
|
|
#if PYLONG_BITS_IN_DIGIT == 30
|
|
typedef uint32_t digit;
|
|
typedef int32_t sdigit; /* signed variant of digit */
|
|
typedef uint64_t twodigits;
|
|
typedef int64_t stwodigits; /* signed variant of twodigits */
|
|
#define PyLong_SHIFT 30
|
|
#define _PyLong_DECIMAL_SHIFT 9 /* max(e such that 10**e fits in a digit) */
|
|
#define _PyLong_DECIMAL_BASE ((digit)1000000000) /* 10 ** DECIMAL_SHIFT */
|
|
#elif PYLONG_BITS_IN_DIGIT == 15
|
|
typedef unsigned short digit;
|
|
typedef short sdigit; /* signed variant of digit */
|
|
typedef unsigned long twodigits;
|
|
typedef long stwodigits; /* signed variant of twodigits */
|
|
#define PyLong_SHIFT 15
|
|
#define _PyLong_DECIMAL_SHIFT 4 /* max(e such that 10**e fits in a digit) */
|
|
#define _PyLong_DECIMAL_BASE ((digit)10000) /* 10 ** DECIMAL_SHIFT */
|
|
#else
|
|
#error "PYLONG_BITS_IN_DIGIT should be 15 or 30"
|
|
#endif
|
|
#define PyLong_BASE ((digit)1 << PyLong_SHIFT)
|
|
#define PyLong_MASK ((digit)(PyLong_BASE - 1))
|
|
|
|
/* Long integer representation.
|
|
The absolute value of a number is equal to
|
|
SUM(for i=0 through abs(ob_size)-1) ob_digit[i] * 2**(SHIFT*i)
|
|
Negative numbers are represented with ob_size < 0;
|
|
zero is represented by ob_size == 0.
|
|
In a normalized number, ob_digit[abs(ob_size)-1] (the most significant
|
|
digit) is never zero. Also, in all cases, for all valid i,
|
|
0 <= ob_digit[i] <= MASK.
|
|
The allocation function takes care of allocating extra memory
|
|
so that ob_digit[0] ... ob_digit[abs(ob_size)-1] are actually available.
|
|
|
|
CAUTION: Generic code manipulating subtypes of PyVarObject has to
|
|
aware that ints abuse ob_size's sign bit.
|
|
*/
|
|
|
|
struct _longobject {
|
|
PyObject_VAR_HEAD
|
|
digit ob_digit[1];
|
|
};
|
|
|
|
PyAPI_FUNC(PyLongObject *) _PyLong_New(Py_ssize_t);
|
|
|
|
/* Return a copy of src. */
|
|
PyAPI_FUNC(PyObject *) _PyLong_Copy(PyLongObject *src);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
#endif /* !Py_LONGINTREPR_H */
|
|
#endif /* Py_LIMITED_API */
|