Issue #4258: Use 30-bit digits for Python longs, on 64-bit platforms.

Backport of r70459.

4 files changed, 106 insertions, 18 deletions

diff --git a/Include/longintrepr.h b/Include/longintrepr.h
index d713293..d6d7ecd 100644
--- a/Include/longintrepr.h
+++ b/Include/longintrepr.h
@@ -7,26 +7,61 @@ extern "C" {
 
 /* This is published for the benefit of "friend" marshal.c only. */
 
-/* Parameters of the long integer representation.
-   These shouldn't have to be changed as C should guarantee that a short
-   contains at least 16 bits, but it's made changeable anyway.
-   Note: 'digit' should be able to hold 2*MASK+1, and 'twodigits'
-   should be able to hold the intermediate results in 'mul'
-   (at most (BASE-1)*(2*BASE+1) == MASK*(2*MASK+3)).
-   Also, x_sub assumes that 'digit' is an unsigned type, and overflow
-   is handled by taking the result mod 2**N for some N > SHIFT.
-   And, at some places it is assumed that MASK fits in an int, as well.
-   long_pow() requires that SHIFT be divisible by 5. */
+/* Parameters of the long 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:
+
+   - long_pow() requires that PyLong_SHIFT be divisible by 5
+
+   - 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 long <-> 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
+
+  The values 15 and 30 should fit all of the above requirements, on any
+  platform.
+*/
+
+#if HAVE_STDINT_H
+#include <stdint.h>
+#endif
+
+#if PYLONG_BITS_IN_DIGIT == 30
+#if !(defined HAVE_UINT64_T && defined HAVE_UINT32_T &&          \
+      defined HAVE_INT64_T && defined HAVE_INT32_T)
+#error "30-bit long digits requested, but the necessary types are not available on this platform"
+#endif
+typedef PY_UINT32_T digit;
+typedef PY_INT32_T sdigit; /* signed variant of digit */
+typedef PY_UINT64_T twodigits;
+typedef PY_INT64_T stwodigits; /* signed variant of twodigits */
+#define PyLong_SHIFT	30
+#elif PYLONG_BITS_IN_DIGIT == 15
 typedef unsigned short digit;
-typedef short sdigit;                   /* signed variant of digit */
-#define BASE_TWODIGITS_TYPE long
-typedef unsigned BASE_TWODIGITS_TYPE twodigits;
-typedef BASE_TWODIGITS_TYPE stwodigits; /* signed variant of twodigits */
-
-#define PyLong_SHIFT    15
-#define PyLong_BASE     ((digit)1 << PyLong_SHIFT)
-#define PyLong_MASK     ((digit)(PyLong_BASE - 1))
+typedef short sdigit; /* signed variant of digit */
+typedef unsigned long twodigits;
+typedef long stwodigits; /* signed variant of twodigits */
+#define PyLong_SHIFT	15
+#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))
 
 /* b/w compatibility with Python 2.5 */
 #define SHIFT	PyLong_SHIFT
diff --git a/Include/longobject.h b/Include/longobject.h
index fa511a7..ea9e387 100644
--- a/Include/longobject.h
+++ b/Include/longobject.h
@@ -24,6 +24,7 @@ PyAPI_FUNC(long) PyLong_AsLong(PyObject *);
 PyAPI_FUNC(unsigned long) PyLong_AsUnsignedLong(PyObject *);
 PyAPI_FUNC(unsigned long) PyLong_AsUnsignedLongMask(PyObject *);
 PyAPI_FUNC(Py_ssize_t) PyLong_AsSsize_t(PyObject *);
+PyAPI_FUNC(PyObject *) PyLong_GetInfo(void);
 
 /* For use by intobject.c only */
 #define _PyLong_AsSsize_t PyLong_AsSsize_t
diff --git a/Include/pyport.h b/Include/pyport.h
index 54411f2..53352f1 100644
--- a/Include/pyport.h
+++ b/Include/pyport.h
@@ -80,6 +80,57 @@ Used in:  PY_LONG_LONG
 #endif
 #endif /* HAVE_LONG_LONG */
 
+/* a build with 30-bit digits for Python long integers needs an exact-width
+ * 32-bit unsigned integer type to store those digits.  (We could just use
+ * type 'unsigned long', but that would be wasteful on a system where longs
+ * are 64-bits.)  On Unix systems, the autoconf macro AC_TYPE_UINT32_T defines
+ * uint32_t to be such a type unless stdint.h or inttypes.h defines uint32_t.
+ * However, it doesn't set HAVE_UINT32_T, so we do that here.
+ */
+#if (defined UINT32_MAX || defined uint32_t)
+#ifndef PY_UINT32_T
+#define HAVE_UINT32_T 1
+#define PY_UINT32_T uint32_t
+#endif
+#endif
+
+/* Macros for a 64-bit unsigned integer type; used for type 'twodigits' in the
+ * long integer implementation, when 30-bit digits are enabled.
+ */
+#if (defined UINT64_MAX || defined uint64_t)
+#ifndef PY_UINT64_T
+#define HAVE_UINT64_T 1
+#define PY_UINT64_T uint64_t
+#endif
+#endif
+
+/* Signed variants of the above */
+#if (defined INT32_MAX || defined int32_t)
+#ifndef PY_INT32_T
+#define HAVE_INT32_T 1
+#define PY_INT32_T int32_t
+#endif
+#endif
+#if (defined INT64_MAX || defined int64_t)
+#ifndef PY_INT64_T
+#define HAVE_INT64_T 1
+#define PY_INT64_T int64_t
+#endif
+#endif
+
+/* If PYLONG_BITS_IN_DIGIT is not defined then we'll use 30-bit digits if all
+   the necessary integer types are available, and we're on a 64-bit platform
+   (as determined by SIZEOF_VOID_P); otherwise we use 15-bit digits. */
+
+#ifndef PYLONG_BITS_IN_DIGIT
+#if (defined HAVE_UINT64_T && defined HAVE_INT64_T && \
+     defined HAVE_UINT32_T && defined HAVE_INT32_T && SIZEOF_VOID_P >= 8)
+#define PYLONG_BITS_IN_DIGIT 30
+#else
+#define PYLONG_BITS_IN_DIGIT 15
+#endif
+#endif
+
 /* uintptr_t is the C9X name for an unsigned integral type such that a
  * legitimate void* can be cast to uintptr_t and then back to void* again
  * without loss of information.  Similarly for intptr_t, wrt a signed
diff --git a/Include/pythonrun.h b/Include/pythonrun.h
index b2b3afd..4ce0536 100644
--- a/Include/pythonrun.h
+++ b/Include/pythonrun.h
@@ -123,6 +123,7 @@ PyAPI_FUNC(void) _PyExc_Init(void);
 PyAPI_FUNC(void) _PyImportHooks_Init(void);
 PyAPI_FUNC(int) _PyFrame_Init(void);
 PyAPI_FUNC(int) _PyInt_Init(void);
+PyAPI_FUNC(int) _PyLong_Init(void);
 PyAPI_FUNC(void) _PyFloat_Init(void);
 PyAPI_FUNC(int) PyByteArray_Init(void);