note bulk88 <blockquote>By any body's standards, a whole 5 billionths of a second difference is hardly "huge". (Which was your assertion). And if the body of the loop did anything useful -- like call one or two of the huge macros or long twisty functions that are the reason for having the context within the sub in the first place --then those 5 nanoseconds would just disappear into the noise. </blockquote> The 5 nanoseconds can not disappear into the noise. They are not free. If they ran, they cost time. Whether it is 1 ns vs 5 ns, or 1 ms vs 5 ms, or 1 minute vs 5 minutes, the smaller choice is better. Lets see how many times Perl_get_context is called for the simplest of Perl programs. PGC=Perl_get_context. <code> C:\p517\perl\win32>perl -e "for(0..5) {print 'hello world'.\"\n\";};" hello world hello world hello world hello world hello world hello world PGC count 1096 C:\p517\perl\win32>perl -e "print 'hello world'"; hello worldPGC count 1069 C:\p517\perl\win32>perl -e "system('pause');" Press any key to continue . . . PGC count 1133 C:\p517\perl\win32> </code> <readmore> <code> /*perllib.c*/ EXTERN_C HANDLE w32_perldll_handle; EXTERN_C int PGC_Count; EXTERN_C DllExport int RunPerl(int argc, char **argv, char **env) { int exitstatus; PerlInterpreter *my_perl, *new_perl = NULL; OSVERSIONINFO osver; char szModuleName[MAX_PATH]; char *arg0 = argv[0]; char *ansi = NULL; bool use_environ = (env == environ); osver.dwOSVersionInfoSize = sizeof(osver); GetVersionEx(&osver); if (osver.dwMajorVersion > 4) { WCHAR widename[MAX_PATH]; GetModuleFileNameW(NULL, widename, sizeof(widename)/sizeof(WCHAR)); argv[0] = ansi = win32_ansipath(widename); } else { Win_GetModuleFileName(NULL, szModuleName, sizeof(szModuleName)); (void)win32_longpath(szModuleName); argv[0] = szModuleName; } #ifdef PERL_GLOBAL_STRUCT #define PERLVAR(prefix,var,type) /**/ #define PERLVARA(prefix,var,type) /**/ #define PERLVARI(prefix,var,type,init) PL_Vars.prefix##var = init; #define PERLVARIC(prefix,var,type,init) PL_Vars.prefix##var = init; #include "perlvars.h" #undef PERLVAR #undef PERLVARA #undef PERLVARI #undef PERLVARIC #endif PERL_SYS_INIT(&argc,&argv); if (!(my_perl = perl_alloc())) return (1); perl_construct(my_perl); PL_perl_destruct_level = 0; /* PERL_SYS_INIT() may update the environment, e.g. via ansify_path(). * This may reallocate the RTL environment block. Therefore we need * to make sure that `env` continues to have the same value as `environ` * if we have been called this way. If we have been called with any * other value for `env` then all environment munging by PERL_SYS_INIT() * will be lost again. */ if (use_environ) env = environ; exitstatus = perl_parse(my_perl, xs_init, argc, argv, env); if (!exitstatus) { #if defined(TOP_CLONE) && defined(USE_ITHREADS) /* XXXXXX testing */ new_perl = perl_clone(my_perl, 1); exitstatus = perl_run(new_perl); PERL_SET_THX(my_perl); #else exitstatus = perl_run(my_perl); #endif } perl_destruct(my_perl); perl_free(my_perl); #ifdef USE_ITHREADS if (new_perl) { PERL_SET_THX(new_perl); perl_destruct(new_perl); perl_free(new_perl); } #endif /* Some RTLs may want to free argv[] after main() returns. */ argv[0] = arg0; if (ansi) win32_free(ansi); PERL_SYS_TERM(); fprintf(stderr, "PGC count %u\n", PGC_Count); return (exitstatus); } </code> <code> /*win32thread.c*/ int PGC_Count = 0; void Perl_set_context(void *t) { #if defined(USE_ITHREADS) # ifdef USE_DECLSPEC_THREAD Perl_current_context = t; # else DWORD err = GetLastError(); TlsSetValue(PL_thr_key,t); SetLastError(err); # endif #endif } void * Perl_get_context(void) { #if defined(USE_ITHREADS) # ifdef USE_DECLSPEC_THREAD return Perl_current_context; # else DWORD err = GetLastError(); void *result = TlsGetValue(PL_thr_key); PGC_Count++; SetLastError(err); return result; # endif #else return NULL; #endif } </code> </readmore> Now lets try to compile an XS module. <code> C:\Documents and Settings\Owner\Desktop\cpan libs\Win32API\g>perl makefile.pl Checking if your kit is complete... Warning: the following files are missing in your kit: api-test/Release/API_test.dll api-test/Release/API_test.lib Please inform the author. Writing Makefile for Win32::API::Callback Writing MYMETA.yml and MYMETA.json Writing Makefile for Win32::API Writing MYMETA.yml and MYMETA.json PGC count 337157 C:\Documents and Settings\Owner\Desktop\cpan libs\Win32API\g>nmake install Microsoft (R) Program Maintenance Utility Version 7.10.3077 Copyright (C) Microsoft Corporation. All rights reserved. PGC count 29225 PGC count 29077 PGC count 29098 PGC count 29131 PGC count 29077 PGC count 29098 PGC count 29228 PGC count 29077 PGC count 29098 PGC count 29229 PGC count 29077 PGC count 29098 PGC count 29131 PGC count 29077 PGC count 29098 PGC count 29131 PGC count 29077 PGC count 29098 PGC count 29131 PGC count 29077 PGC count 29098 PGC count 29131 PGC count 29077 PGC count 29098 cp Type.pm blib\lib\Win32/API/Type.pm cp Callback.pm blib\lib\Win32/API/Callback.pm cp Test.pm blib\lib\Win32/API/Test.pm cp Struct.pm blib\lib\Win32/API/Struct.pm cp API.pm blib\lib\Win32/API.pm cp IATPatch.pod blib\lib\Win32/API/Callback/IATPatch.pod PGC count 135573 PGC count 29098 nmake -f Makefile all -nologo PGC count 29084 PGC count 29077 PGC count 29098 PGC count 29132 PGC count 29077 PGC count 29098 PGC count 29132 PGC count 29077 PGC count 29098 PGC count 29098 C:\perl517\bin\perl.exe C:\perl517\lib\ExtUtils\xsubpp -typemap C:\perl 517\lib\ExtUtils\typemap Callback.xs > Callback.xsc && C:\perl517\bin\perl.exe -MExtUtils::Command -e mv -- Callback.xsc Callback.c PGC count 153957 PGC count 29098 cl -c -nologo -GF -W3 -MD -Zi -DNDEBUG -O1 -G7 -DWIN32 -D_CONSOLE -DN O_STRICT -DPERL_TEXTMODE_SCRIPTS -DPERL_IMPLICIT_CONTEXT -DPERL_IMPLICIT_SYS -DU SE_PERLIO -D_USE_32BIT_TIME_T -MD -Zi -DNDEBUG -O1 -G7 -DVERSION=\"0.71\" -D XS_VERSION=\"0.71\" "-IC:\perl517\lib\CORE" Callback.c Callback.c Running Mkbootstrap for Win32::API::Callback () PGC count 1097 PGC count 11211 PGC count 29098 C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 644 Callback.bs PGC count 29077 C:\perl517\bin\perl.exe -MExtUtils::Mksymlists -e "Mksymlists('NAME'=>\ "Win32::API::Callback\", 'DLBASE' => 'Callback', 'DL_FUNCS' => { }, 'FUNCLIST' => [], 'IMPORTS' => { }, 'DL_VARS' => []);" PGC count 13035 link -out:..\blib\arch\auto\Win32\API\Callback\Callback.dll -dll -nologo -nodefaultlib -debug -opt:ref,icf -libpath:"c:\perl517\lib\CORE" -machine:x86 Callback.obj C:\perl517\lib\CORE\perl517.lib oldnames.lib kernel32.lib user32 .lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib ole aut32.lib netapi32.lib uuid.lib ws2_32.lib mpr.lib winmm.lib version.lib odbc3 2.lib odbccp32.lib comctl32.lib msvcrt.lib -def:Callback.def Creating library ..\blib\arch\auto\Win32\API\Callback\Callback.lib and object ..\blib\arch\auto\Win32\API\Callback\Callback.exp if exist ..\blib\arch\auto\Win32\API\Callback\Callback.dll.manifest mt - nologo -manifest ..\blib\arch\auto\Win32\API\Callback\Callback.dll.manifest -out putresource:..\blib\arch\auto\Win32\API\Callback\Callback.dll;2 if exist ..\blib\arch\auto\Win32\API\Callback\Callback.dll.manifest del ..\blib\arch\auto\Win32\API\Callback\Callback.dll.manifest C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 755 ..\blib\arch \auto\Win32\API\Callback\Callback.dll PGC count 29077 PGC count 35327 C:\perl517\bin\perl.exe -MExtUtils::Command -e cp -- Callback.bs ..\blib \arch\auto\Win32\API\Callback\Callback.bs PGC count 37097 C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 644 ..\blib\arch \auto\Win32\API\Callback\Callback.bs PGC count 29077 cd .. C:\perl517\bin\perl.exe C:\perl517\lib\ExtUtils\xsubpp -nolinenumbers -typemap C:\perl517\lib\ExtUtils\typemap -typemap typemap API.xs > API.xsc && C :\perl517\bin\perl.exe -MExtUtils::Command -e mv -- API.xsc API.c PGC count 156717 PGC count 29098 cl -c -nologo -GF -W3 -MD -Zi -DNDEBUG -O1 -G7 -DWIN32 -D_CONSOLE -DN O_STRICT -DPERL_TEXTMODE_SCRIPTS -DPERL_IMPLICIT_CONTEXT -DPERL_IMPLICIT_SYS -DU SE_PERLIO -D_USE_32BIT_TIME_T -MD -Zi -DNDEBUG -O1 -G7 -DVERSION=\"0.71\" -D XS_VERSION=\"0.71\" "-IC:\perl517\lib\CORE" API.c API.c c:\Documents and Settings\Owner\Desktop\cpan libs\Win32API\g\call_i686.h(44) : w arning C4101: 'pReturn' : unreferenced local variable API.c(341) : warning C4047: '=' : 'SV *' differs in levels of indirection from ' SV ** ' Running Mkbootstrap for Win32::API () PGC count 1097 PGC count 11209 PGC count 29097 C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 644 API.bs PGC count 29077 C:\perl517\bin\perl.exe -MExtUtils::Mksymlists -e "Mksymlists('NAME'=>\ "Win32::API\", 'DLBASE' => 'API', 'DL_FUNCS' => { }, 'FUNCLIST' => [], 'IMPORTS ' => { }, 'DL_VARS' => []);" PGC count 13027 link -out:blib\arch\auto\Win32\API\API.dll -dll -nologo -nodefaultlib -d ebug -opt:ref,icf -libpath:"c:\perl517\lib\CORE" -machine:x86 API.obj C:\per l517\lib\CORE\perl517.lib oldnames.lib kernel32.lib user32.lib gdi32.lib winspoo l.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib netapi32.li b uuid.lib ws2_32.lib mpr.lib winmm.lib version.lib odbc32.lib odbccp32.lib com ctl32.lib msvcrt.lib -def:API.def Creating library blib\arch\auto\Win32\API\API.lib and object blib\arch\auto\W in32\API\API.exp if exist blib\arch\auto\Win32\API\API.dll.manifest mt -nologo -manifest blib\arch\auto\Win32\API\API.dll.manifest -outputresource:blib\arch\auto\Win32\A PI\API.dll;2 if exist blib\arch\auto\Win32\API\API.dll.manifest del blib\arch\auto\Wi n32\API\API.dll.manifest C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 755 blib\arch\au to\Win32\API\API.dll PGC count 29077 PGC count 35325 C:\perl517\bin\perl.exe -MExtUtils::Command -e cp -- API.bs blib\arch\au to\Win32\API\API.bs PGC count 37097 C:\perl517\bin\perl.exe -MExtUtils::Command -e chmod -- 644 blib\arch\au to\Win32\API\API.bs PGC count 29077 Files found in blib\arch: installing files in blib\lib into architecture depende nt library tree Installing C:\perl517\site\lib\auto\Win32\API\API.dll Installing C:\perl517\site\lib\auto\Win32\API\API.exp Installing C:\perl517\site\lib\auto\Win32\API\API.lib Installing C:\perl517\site\lib\auto\Win32\API\API.pdb Installing C:\perl517\site\lib\auto\Win32\API\Callback\Callback.dll Installing C:\perl517\site\lib\auto\Win32\API\Callback\Callback.exp Installing C:\perl517\site\lib\auto\Win32\API\Callback\Callback.lib Installing C:\perl517\site\lib\auto\Win32\API\Callback\Callback.pdb PGC count 140759 PGC count 6563 Appending installation info to c:\perl517\lib/perllocal.pod PGC count 1103 PGC count 29084 PGC count 6653 C:\Documents and Settings\Owner\Desktop\cpan libs\Win32API\g> </code> Highest per process Perl_get_context count was 337157, assuming 4 ns wasted in PGC vs C stack my_perl, 1.34 ms of CPU was wasted in that process. nmake install took 11 seconds by the clock on the wall. Added all PGCs counts, comes to 2472747, * 4 ns is 9.8 ms. I am aware that 9.8ms is only %0.08 of the 11 seconds it took to run nmake install. I still say death by a 1000 cuts! Now about TLSGetValue directly. <code>C:\Documents and Settings\Owner\Desktop\cpan libs\lxs>perl -MLocal::XS -e "Local:: XS::CxtSpeed();" no cxt 47237378 cxt 13202140 no cxt no last error 22624295 C:\Documents and Settings\Owner\Desktop\cpan libs\lxs> </code> <readmore> <code> void CxtSpeed() PREINIT: LARGE_INTEGER start; LARGE_INTEGER end; int i; PPCODE: QueryPerformanceCounter(&start); for(i=0; i < 1000000000; i++){ no_cxt(); } QueryPerformanceCounter(&end); printf("no cxt %I64u\n", end.QuadPart-start.QuadPart); QueryPerformanceCounter(&start); for(i=0; i < 1000000000; i++){ cxt(aTHX); } QueryPerformanceCounter(&end); printf("cxt %I64u\n", end.QuadPart-start.QuadPart); QueryPerformanceCounter(&start); for(i=0; i < 1000000000; i++){ no_cxt_no_glr(); } QueryPerformanceCounter(&end); printf("no cxt no last error %I64u\n", end.QuadPart-start.QuadPart); </code> <code> //separate compiland #define PERL_NO_GET_CONTEXT #include <EXTERN.h> #include <perl.h> #include <XSUB.h> __declspec(dllexport) int no_cxt(){ dTHX; return ((int) my_perl) >> 1; } __declspec(dllexport) int cxt(pTHX){ return ((int) my_perl) >> 1; } __declspec(dllexport) int no_cxt_no_glr(){ void *my_perl = TlsGetValue(PL_thr_key); return ((int) my_perl) >> 1; } </code> </readmore> Remember to get PL_thr_key is 2 asm dereferences in XS DLL vs 1 inside the interp itself. My next reply will address your letter C. 995530 995689