[vlc-devel] commit: SSE3 detection (runtime) (Jean-Baptiste Kempf )

[git version control]

vlc | branch: master | Jean-Baptiste Kempf <jb at videolan.org> | Tue Sep 22 19:34:00 2009 +0200| [ceb2efd46999603aa75a59201b4e869d9c36e458] | committer: Jean-Baptiste Kempf 

SSE3 detection (runtime)

Isn't fork() supposed to be slow on Windows?

> http://git.videolan.org/gitweb.cgi/vlc.git/?a=commit;h=ceb2efd46999603aa75a59201b4e869d9c36e458
---

 src/libvlc-module.c |    8 ++++++++
 src/libvlc.c        |    3 +++
 src/misc/cpu.c      |   18 ++++++++++++++++++
 3 files changed, 29 insertions(+), 0 deletions(-)

diff --git a/src/libvlc-module.c b/src/libvlc-module.c
index d92e614..18cefcd 100644
--- a/src/libvlc-module.c
+++ b/src/libvlc-module.c
@@ -1009,6 +1009,12 @@ static const char *const ppsz_clock_descriptions[] =
     "If your processor supports the SSE2 instructions set, VLC can take " \
     "advantage of them.")
 
+#define SSE3_TEXT N_("Enable CPU SSE3 support")
+#define SSE3_LONGTEXT N_( \
+    "If your processor supports the SSE3 instructions set, VLC can take " \
+    "advantage of them.")
+
+
 #define ALTIVEC_TEXT N_("Enable CPU AltiVec support")
 #define ALTIVEC_LONGTEXT N_( \
     "If your processor supports the AltiVec instructions set, VLC can take " \
@@ -1927,6 +1933,8 @@ vlc_module_begin ()
         change_need_restart ()
     add_bool( "sse2", 1, NULL, SSE2_TEXT, SSE2_LONGTEXT, true )
         change_need_restart ()
+    add_bool( "sse3", 1, NULL, SSE3_TEXT, SSE3_LONGTEXT, true )
+        change_need_restart ()
 #endif
 #if defined( __powerpc__ ) || defined( __ppc__ ) || defined( __ppc64__ )
     add_bool( "altivec", 1, NULL, ALTIVEC_TEXT, ALTIVEC_LONGTEXT, true )
diff --git a/src/libvlc.c b/src/libvlc.c
index 97755fd..a1784b1 100644
--- a/src/libvlc.c
+++ b/src/libvlc.c
@@ -761,12 +761,15 @@ int libvlc_InternalInit( libvlc_int_t *p_libvlc, int i_argc,
         cpu_flags &= ~CPU_CAPABILITY_SSE;
     if( !config_GetInt( p_libvlc, "sse2" ) )
         cpu_flags &= ~CPU_CAPABILITY_SSE2;
+    if( !config_GetInt( p_libvlc, "sse3" ) )
+        cpu_flags &= ~CPU_CAPABILITY_SSE3;
 
     PRINT_CAPABILITY( CPU_CAPABILITY_MMX, "MMX" );
     PRINT_CAPABILITY( CPU_CAPABILITY_3DNOW, "3DNow!" );
     PRINT_CAPABILITY( CPU_CAPABILITY_MMXEXT, "MMXEXT" );
     PRINT_CAPABILITY( CPU_CAPABILITY_SSE, "SSE" );
     PRINT_CAPABILITY( CPU_CAPABILITY_SSE2, "SSE2" );
+    PRINT_CAPABILITY( CPU_CAPABILITY_SSE3, "SSE3" );
 
 #elif defined( __powerpc__ ) || defined( __ppc__ ) || defined( __ppc64__ )
     if( !config_GetInt( p_libvlc, "altivec" ) )
diff --git a/src/misc/cpu.c b/src/misc/cpu.c
index 615484c..9ca2ab8 100644
--- a/src/misc/cpu.c
+++ b/src/misc/cpu.c
@@ -201,6 +201,24 @@ uint32_t CPUCapabilities( void )
     }
 # endif
 
+# if defined (__SSE3__)
+    i_capabilities |= CPU_CAPABILITY_SSE3;
+# elif defined (CAN_COMPILE_SSE3)
+    if( i_ecx & 0x00000001 )
+    {
+        /* We test if OS supports the SSE3 instructions */
+        pid_t pid = fork();
+        if( pid == 0 )
+        {
+            /* Test a SSE3 instruction */
+            __asm__ __volatile__ ( "movsldup %%xmm1, %%xmm0\n" : : );
+            exit(0);
+        }
+        if( check_OS_capability( "SSE3", pid ) )
+            i_capabilities |= CPU_CAPABILITY_SSE3;
+    }
+# endif
+
     /* test for additional capabilities */
     cpuid( 0x80000000 );