Skip to content

[stubs] Implement unsigned/signed div/mod ti3 for Win64 #13295

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

[stubs] Implement unsigned/signed div/mod ti3 for Win64 #13295

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9e6ac4b
Impl udivti3, divti3, umodti3, and modti3 on Win64
troughton Dec 6, 2017
b362218
Fix mistake in __divti3 implementation...
troughton Dec 6, 2017
5f416ef
CHAR_BIT is defined in limits.h
troughton Dec 6, 2017
62af2c5
Add checks for __mode__ support within each if block
troughton Dec 6, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
308 changes: 302 additions & 6 deletions stdlib/public/stubs/Stubs.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -323,6 +323,18 @@ swift::swift_stdlib_readLine_stdin(unsigned char **LinePtr) {
#endif
}

#if __has_attribute(__mode__)
#define SWIFT_MODE_DI __attribute__((__mode__(DI)))
#define SWIFT_MODE_TI __attribute__((__mode__(TI)))
#else
#define SWIFT_MODE_DI
#define SWIFT_MODE_TI
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please make this a hard error. Without this, the types are completely the wrong size and you do not get any type of warning/error that things went wrong.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The problem with a hard error is that I moved this out of the #if blocks, since the definitions are used by multiple disjoint if blocks. If we hard error, then that applies to every platform, even ones that will never need to use the types.

The alternatives would be to either warn or to duplicate these definitions and move them back into each #if block. The problem that then arises is that the definitions become conditional on what #if blocks we'd already encountered, unless we #defined and #undefd the types within each block.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've addressed this by adding a 3-line check for __mode__ support within each #if block.

#endif

typedef int ti_int SWIFT_MODE_TI;
typedef unsigned tu_int SWIFT_MODE_TI;
typedef int di_int SWIFT_MODE_DI;
typedef unsigned du_int SWIFT_MODE_DI;

// Although this builtin is provided by clang rt builtins,
// it isn't provided by libgcc, which is the default
Expand All @@ -336,7 +348,10 @@ swift::swift_stdlib_readLine_stdin(unsigned char **LinePtr) {
(defined(__linux__) && defined(__s390x__)) || \
(defined(__ANDROID__) && defined(__arm64__))

typedef int ti_int __attribute__((__mode__(TI)));
#if !(__has_attribute(__mode__))
#error "The __mode__ attribute is required."
#endif

SWIFT_RUNTIME_STDLIB_INTERFACE
ti_int
__muloti4(ti_int a, ti_int b, int* overflow)
Expand Down Expand Up @@ -389,13 +404,11 @@ __muloti4(ti_int a, ti_int b, int* overflow)
// some other lower-level architecture issue that I'm
// missing. Perhaps relevant bug report:
// FIXME: https://llvm.org/bugs/show_bug.cgi?id=14469
#if __has_attribute(__mode__)
#define SWIFT_MODE_DI __attribute__((__mode__(DI)))
#else
#define SWIFT_MODE_DI

#if !(__has_attribute(__mode__))
#error "The __mode__ attribute is required."
#endif

typedef int di_int SWIFT_MODE_DI;
SWIFT_RUNTIME_STDLIB_INTERFACE
di_int
__mulodi4(di_int a, di_int b, int* overflow)
Expand Down Expand Up @@ -435,6 +448,289 @@ __mulodi4(di_int a, di_int b, int* overflow)
}
return result;
}

#if defined(_WIN64)

#if !(__has_attribute(__mode__))
#error "The __mode__ attribute is required."
#endif

typedef union
{
tu_int all;
struct
{
du_int low;
du_int high;
}s;
} utwords;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This technically is a GNU extension (union fields may only be access through initialized fields) and breaks aliasing. At that point, you should assume that the __mode__ extension is available


SWIFT_RUNTIME_STDLIB_INTERFACE
tu_int
__udivmodti4(tu_int a, tu_int b, tu_int* rem)
{
const unsigned n_udword_bits = sizeof(du_int) * CHAR_BIT;
const unsigned n_utword_bits = sizeof(tu_int) * CHAR_BIT;
utwords n;
n.all = a;
utwords d;
d.all = b;
utwords q;
utwords r;
unsigned sr;
/* special cases, X is unknown, K != 0 */
if (n.s.high == 0)
{
if (d.s.high == 0)
{
/* 0 X
* ---
* 0 X
*/
if (rem)
*rem = n.s.low % d.s.low;
return n.s.low / d.s.low;
}
/* 0 X
* ---
* K X
*/
if (rem)
*rem = n.s.low;
return 0;
}
/* n.s.high != 0 */
if (d.s.low == 0)
{
if (d.s.high == 0)
{
/* K X
* ---
* 0 0
*/
if (rem)
*rem = n.s.high % d.s.low;
return n.s.high / d.s.low;
}
/* d.s.high != 0 */
if (n.s.low == 0)
{
/* K 0
* ---
* K 0
*/
if (rem)
{
r.s.high = n.s.high % d.s.high;
r.s.low = 0;
*rem = r.all;
}
return n.s.high / d.s.high;
}
/* K K
* ---
* K 0
*/
if ((d.s.high & (d.s.high - 1)) == 0) /* if d is a power of 2 */
{
if (rem)
{
r.s.low = n.s.low;
r.s.high = n.s.high & (d.s.high - 1);
*rem = r.all;
}
return n.s.high >> __builtin_ctzll(d.s.high);
}
/* K K
* ---
* K 0
*/
sr = __builtin_clzll(d.s.high) - __builtin_clzll(n.s.high);
/* 0 <= sr <= n_udword_bits - 2 or sr large */
if (sr > n_udword_bits - 2)
{
if (rem)
*rem = n.all;
return 0;
}
++sr;
/* 1 <= sr <= n_udword_bits - 1 */
/* q.all = n.all << (n_utword_bits - sr); */
q.s.low = 0;
q.s.high = n.s.low << (n_udword_bits - sr);
/* r.all = n.all >> sr; */
r.s.high = n.s.high >> sr;
r.s.low = (n.s.high << (n_udword_bits - sr)) | (n.s.low >> sr);
}
else /* d.s.low != 0 */
{
if (d.s.high == 0)
{
/* K X
* ---
* 0 K
*/
if ((d.s.low & (d.s.low - 1)) == 0) /* if d is a power of 2 */
{
if (rem)
*rem = n.s.low & (d.s.low - 1);
if (d.s.low == 1)
return n.all;
sr = __builtin_ctzll(d.s.low);
q.s.high = n.s.high >> sr;
q.s.low = (n.s.high << (n_udword_bits - sr)) | (n.s.low >> sr);
return q.all;
}
/* K X
* ---
* 0 K
*/
sr = 1 + n_udword_bits + __builtin_clzll(d.s.low)
- __builtin_clzll(n.s.high);
/* 2 <= sr <= n_utword_bits - 1
* q.all = n.all << (n_utword_bits - sr);
* r.all = n.all >> sr;
*/
if (sr == n_udword_bits)
{
q.s.low = 0;
q.s.high = n.s.low;
r.s.high = 0;
r.s.low = n.s.high;
}
else if (sr < n_udword_bits) // 2 <= sr <= n_udword_bits - 1
{
q.s.low = 0;
q.s.high = n.s.low << (n_udword_bits - sr);
r.s.high = n.s.high >> sr;
r.s.low = (n.s.high << (n_udword_bits - sr)) | (n.s.low >> sr);
}
else // n_udword_bits + 1 <= sr <= n_utword_bits - 1
{
q.s.low = n.s.low << (n_utword_bits - sr);
q.s.high = (n.s.high << (n_utword_bits - sr)) |
(n.s.low >> (sr - n_udword_bits));
r.s.high = 0;
r.s.low = n.s.high >> (sr - n_udword_bits);
}
}
else
{
/* K X
* ---
* K K
*/
sr = __builtin_clzll(d.s.high) - __builtin_clzll(n.s.high);
/*0 <= sr <= n_udword_bits - 1 or sr large */
if (sr > n_udword_bits - 1)
{
if (rem)
*rem = n.all;
return 0;
}
++sr;
/* 1 <= sr <= n_udword_bits
* q.all = n.all << (n_utword_bits - sr);
* r.all = n.all >> sr;
*/
q.s.low = 0;
if (sr == n_udword_bits)
{
q.s.high = n.s.low;
r.s.high = 0;
r.s.low = n.s.high;
}
else
{
r.s.high = n.s.high >> sr;
r.s.low = (n.s.high << (n_udword_bits - sr)) | (n.s.low >> sr);
q.s.high = n.s.low << (n_udword_bits - sr);
}
}
}
/* Not a special case
* q and r are initialized with:
* q.all = n.all << (n_utword_bits - sr);
* r.all = n.all >> sr;
* 1 <= sr <= n_utword_bits - 1
*/
unsigned int carry = 0;
for (; sr > 0; --sr)
{
/* r:q = ((r:q) << 1) | carry */
r.s.high = (r.s.high << 1) | (r.s.low >> (n_udword_bits - 1));
r.s.low = (r.s.low << 1) | (q.s.high >> (n_udword_bits - 1));
q.s.high = (q.s.high << 1) | (q.s.low >> (n_udword_bits - 1));
q.s.low = (q.s.low << 1) | carry;
/* carry = 0;
* if (r.all >= d.all)
* {
* r.all -= d.all;
* carry = 1;
* }
*/
const ti_int s = (ti_int)(d.all - r.all - 1) >> (n_utword_bits - 1);
carry = s & 1;
r.all -= d.all & s;
}
q.all = (q.all << 1) | carry;
if (rem)
*rem = r.all;
return q.all;
}

/* Returns: a % b */

SWIFT_RUNTIME_STDLIB_INTERFACE
tu_int
__umodti3(tu_int a, tu_int b)
{
tu_int r;
__udivmodti4(a, b, &r);
return r;
}

/* Returns: a / b */

SWIFT_RUNTIME_STDLIB_INTERFACE
tu_int
__udivti3(tu_int a, tu_int b)
{
return __udivmodti4(a, b, 0);
}

/*Returns: a % b */

SWIFT_RUNTIME_STDLIB_INTERFACE
ti_int
__modti3(ti_int a, ti_int b)
{
const int bits_in_tword_m1 = (int)(sizeof(ti_int) * CHAR_BIT) - 1;
ti_int s = b >> bits_in_tword_m1; /* s = b < 0 ? -1 : 0 */
b = (b ^ s) - s; /* negate if s == -1 */
s = a >> bits_in_tword_m1; /* s = a < 0 ? -1 : 0 */
a = (a ^ s) - s; /* negate if s == -1 */
tu_int r;
__udivmodti4(a, b, &r);
return ((ti_int)r ^ s) - s; /* negate if s == -1 */
}

/* Returns: a / b */

SWIFT_RUNTIME_STDLIB_INTERFACE
ti_int
__divti3(ti_int a, ti_int b)
{
const int bits_in_tword_m1 = (int)(sizeof(ti_int) * CHAR_BIT) - 1;
ti_int s_a = a >> bits_in_tword_m1; /* s_a = a < 0 ? -1 : 0 */
ti_int s_b = b >> bits_in_tword_m1; /* s_b = b < 0 ? -1 : 0 */
a = (a ^ s_a) - s_a; /* negate if s_a == -1 */
b = (b ^ s_b) - s_b; /* negate if s_b == -1 */
s_a ^= s_b; /* sign of quotient */
return (__udivmodti4(a, b, (tu_int*)0) ^ s_a) - s_a; /* negate if s_a == -1 */
}

#endif // defined(_WIN64)
#endif

#if defined(__CYGWIN__) || defined(_WIN32)
Expand Down