Skip to content

Replace MSVC lazy initialization with DllMain entry point #233

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

Draft
Copilot wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

Replace MSVC lazy initialization with DllMain entry point #233

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d5b8e64
Initial plan
Copilot Mar 14, 2026
41e4a63
Replace MSVC lazy initialization with DllMain entry point
Copilot Mar 14, 2026
64a266e
Add bounds checking for XSS_POST_RESOLVE init registry
Copilot Mar 14, 2026
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
164 changes: 33 additions & 131 deletions lib/x86simdsort.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,21 @@
#if defined(_MSC_VER)
#define XSS_ATTRIBUTE_CONSTRUCTOR
#define WIN32_LEAN_AND_MEAN
#define NOMINMAX
#include <windows.h>
#define XSS_MAX_INIT_FUNCS 512
static void (*xss_init_funcs[XSS_MAX_INIT_FUNCS])();
static int xss_init_count = 0;
#define XSS_POST_RESOLVE(resolve_func_name) \
static int CAT(xss_reg_, resolve_func_name) \
= (xss_init_funcs[xss_init_count < XSS_MAX_INIT_FUNCS \
? xss_init_count++ \
: xss_init_count] \
= &resolve_func_name, \
0);
#else
#define XSS_ATTRIBUTE_CONSTRUCTOR __attribute__((constructor))
#define XSS_POST_RESOLVE(resolve_func_name)
#endif
#include "x86simdsort.h"
#include "x86simdsort-internal.h"
Expand Down Expand Up @@ -96,76 +110,8 @@ namespace x86simdsort {
return; \
} \
} \
}

#ifdef _MSC_VER
#define DECLARE_INTERNAL_qsort(TYPE) \
static void CAT(resolve_qsort, TYPE)(void); \
static void (*internal_qsort##TYPE)(TYPE *, size_t, bool, bool) = NULL; \
template <> \
void XSS_EXPORT_SYMBOL qsort( \
TYPE *arr, size_t arrsize, bool hasnan, bool descending) \
{ \
if (internal_qsort##TYPE == NULL) { CAT(resolve_qsort, TYPE)(); } \
(*internal_qsort##TYPE)(arr, arrsize, hasnan, descending); \
}

#define DECLARE_INTERNAL_qselect(TYPE) \
static void CAT(resolve_qselect, TYPE)(void); \
static void (*internal_qselect##TYPE)(TYPE *, size_t, size_t, bool, bool) \
= NULL; \
template <> \
void XSS_EXPORT_SYMBOL qselect( \
TYPE *arr, size_t k, size_t arrsize, bool hasnan, bool descending) \
{ \
if (internal_qselect##TYPE == NULL) { CAT(resolve_qselect, TYPE)(); } \
(*internal_qselect##TYPE)(arr, k, arrsize, hasnan, descending); \
}

#define DECLARE_INTERNAL_partial_qsort(TYPE) \
static void CAT(resolve_partial_qsort, TYPE)(void); \
static void (*internal_partial_qsort##TYPE)( \
TYPE *, size_t, size_t, bool, bool) \
= NULL; \
template <> \
void XSS_EXPORT_SYMBOL partial_qsort( \
TYPE *arr, size_t k, size_t arrsize, bool hasnan, bool descending) \
{ \
if (internal_partial_qsort##TYPE == NULL) { \
CAT(resolve_partial_qsort, TYPE)(); \
} \
(*internal_partial_qsort##TYPE)(arr, k, arrsize, hasnan, descending); \
}

#define DECLARE_INTERNAL_argsort(TYPE) \
static void CAT(resolve_argsort, TYPE)(void); \
static std::vector<size_t> (*internal_argsort##TYPE)( \
const TYPE *, size_t, bool, bool) \
= NULL; \
template <> \
std::vector<size_t> XSS_EXPORT_SYMBOL argsort( \
const TYPE *arr, size_t arrsize, bool hasnan, bool descending) \
{ \
if (internal_argsort##TYPE == NULL) { CAT(resolve_argsort, TYPE)(); } \
return (*internal_argsort##TYPE)(arr, arrsize, hasnan, descending); \
}

#define DECLARE_INTERNAL_argselect(TYPE) \
static void CAT(resolve_argselect, TYPE)(void); \
static std::vector<size_t> (*internal_argselect##TYPE)( \
const TYPE *, size_t, size_t, bool) \
= NULL; \
template <> \
std::vector<size_t> XSS_EXPORT_SYMBOL argselect( \
const TYPE *arr, size_t k, size_t arrsize, bool hasnan) \
{ \
if (internal_argselect##TYPE == NULL) { \
CAT(resolve_argselect, TYPE)(); \
} \
return (*internal_argselect##TYPE)(arr, k, arrsize, hasnan); \
}

#else
} \
XSS_POST_RESOLVE(CAT(CAT(resolve_, func), TYPE))

#define DECLARE_INTERNAL_qsort(TYPE) \
static void (*internal_qsort##TYPE)(TYPE *, size_t, bool, bool) = NULL; \
Expand Down Expand Up @@ -219,8 +165,6 @@ namespace x86simdsort {
return (*internal_argselect##TYPE)(arr, k, arrsize, hasnan); \
}

#endif // _MSC_VER

/* simple constexpr function as a way around having #ifdef __FLT16_MAX__ block
* within the DISPATCH macro */
template <typename T>
Expand Down Expand Up @@ -301,65 +245,10 @@ DISPATCH_ALL(argselect,
return; \
} \
} \
}

#ifdef _MSC_VER
#define DECLARE_ALL_KEYVALUE_METHODS(TYPE1, TYPE2) \
static void CAT(CAT(resolve_keyvalue_select_, TYPE1), TYPE2)(void); \
static void CAT(CAT(resolve_keyvalue_partial_sort_, TYPE1), TYPE2)(void); \
static void CAT(CAT(resolve_keyvalue_qsort_, TYPE1), TYPE2)(void); \
static void(CAT(CAT(*internal_keyvalue_qsort_, TYPE1), TYPE2))( \
TYPE1 *, TYPE2 *, size_t, bool, bool) \
= NULL; \
static void(CAT(CAT(*internal_keyvalue_select_, TYPE1), TYPE2))( \
TYPE1 *, TYPE2 *, size_t, size_t, bool, bool) \
= NULL; \
static void(CAT(CAT(*internal_keyvalue_partial_sort_, TYPE1), TYPE2))( \
TYPE1 *, TYPE2 *, size_t, size_t, bool, bool) \
= NULL; \
template <> \
void XSS_EXPORT_SYMBOL keyvalue_qsort(TYPE1 *key, \
TYPE2 *val, \
size_t arrsize, \
bool hasnan, \
bool descending) \
{ \
if ((CAT(CAT(*internal_keyvalue_qsort_, TYPE1), TYPE2)) == NULL) { \
CAT(CAT(resolve_keyvalue_qsort_, TYPE1), TYPE2)(); \
} \
(CAT(CAT(*internal_keyvalue_qsort_, TYPE1), TYPE2))( \
key, val, arrsize, hasnan, descending); \
} \
template <> \
void XSS_EXPORT_SYMBOL keyvalue_select(TYPE1 *key, \
TYPE2 *val, \
size_t k, \
size_t arrsize, \
bool hasnan, \
bool descending) \
{ \
if ((CAT(CAT(*internal_keyvalue_select_, TYPE1), TYPE2)) == NULL) { \
CAT(CAT(resolve_keyvalue_select_, TYPE1), TYPE2)(); \
} \
(CAT(CAT(*internal_keyvalue_select_, TYPE1), TYPE2))( \
key, val, k, arrsize, hasnan, descending); \
} \
template <> \
void XSS_EXPORT_SYMBOL keyvalue_partial_sort(TYPE1 *key, \
TYPE2 *val, \
size_t k, \
size_t arrsize, \
bool hasnan, \
bool descending) \
{ \
if ((CAT(CAT(*internal_keyvalue_partial_sort_, TYPE1), TYPE2)) \
== NULL) { \
CAT(CAT(resolve_keyvalue_partial_sort_, TYPE1), TYPE2)(); \
} \
(CAT(CAT(*internal_keyvalue_partial_sort_, TYPE1), TYPE2))( \
key, val, k, arrsize, hasnan, descending); \
}
#else
XSS_POST_RESOLVE( \
CAT(CAT(CAT(CAT(resolve_, func), _), TYPE1), TYPE2))

#define DECLARE_ALL_KEYVALUE_METHODS(TYPE1, TYPE2) \
static void(CAT(CAT(*internal_keyvalue_qsort_, TYPE1), TYPE2))( \
TYPE1 *, TYPE2 *, size_t, bool, bool) \
Expand Down Expand Up @@ -402,7 +291,6 @@ DISPATCH_ALL(argselect,
(CAT(CAT(*internal_keyvalue_partial_sort_, TYPE1), TYPE2))( \
key, val, k, arrsize, hasnan, descending); \
}
#endif // _MSC_VER

#define DISPATCH_KEYVALUE_SORT(TYPE1, TYPE2, ISA) \
DECLARE_ALL_KEYVALUE_METHODS(TYPE1, TYPE2) \
Expand Down Expand Up @@ -470,3 +358,17 @@ void keyvalue_qsort_uint32_uint64(uint32_t *key, uint64_t *val, size_t size)
x86simdsort::keyvalue_qsort(key, val, size, true);
}
}

#ifdef _MSC_VER
extern "C" BOOL WINAPI DllMain(HINSTANCE hinstDLL,
DWORD fdwReason,
LPVOID lpReserved)
{
if (fdwReason == DLL_PROCESS_ATTACH) {
for (int i = 0; i < xss_init_count; i++) {
xss_init_funcs[i]();
}
}
return TRUE;
}
#endif
Loading