[vlc-devel] [PATCH 1/3] packetizer: startcode_helper: prefer intrinsics

[Francois Cartegnie]

There's no universal cross compiler way to store
a vector constant have dependency listed in the next
assembly block. With pure assembly, there's risk
of clobbering constant if the compiler auto vector
the TRY_MATCH sections.
---
 modules/packetizer/startcode_helper.h | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/modules/packetizer/startcode_helper.h b/modules/packetizer/startcode_helper.h
index 2b61e5cf98..fd7b8249d2 100644
--- a/modules/packetizer/startcode_helper.h
+++ b/modules/packetizer/startcode_helper.h
@@ -22,7 +22,7 @@
 
 #include <vlc_cpu.h>
 
-#if !defined(CAN_COMPILE_SSE2) && defined(HAVE_SSE2_INTRINSICS)
+#if defined(HAVE_SSE2_INTRINSICS)
    #include <emmintrin.h>
 #endif
 
@@ -63,30 +63,26 @@ static inline const uint8_t * startcode_FindAnnexB_SSE2( const uint8_t *p, const
     alignedend = end - ((intptr_t) end & 15);
     if( alignedend > p )
     {
-#ifdef CAN_COMPILE_SSE2
-        asm volatile(
-            "pxor   %%xmm1, %%xmm1\n"
-            ::: "xmm1"
-        );
-#else
-        __m128i zeros = _mm_set1_epi8( 0x00 );
+#ifdef HAVE_SSE2_INTRINSICS
+    __m128i zeros = _mm_set1_epi8( 0x00 );
 #endif
         for( ; p < alignedend; p += 16)
         {
             uint32_t match;
-#ifdef CAN_COMPILE_SSE2
+#ifdef HAVE_SSE2_INTRINSICS
+            __m128i v = _mm_load_si128((__m128i*)p);
+            __m128i res = _mm_cmpeq_epi8( zeros, v );
+            match = _mm_movemask_epi8( res ); /* mask will be in reversed match order */
+#else
             asm volatile(
+                "pxor      %%xmm1,   %%xmm1\n"
                 "movdqa   0(%[v]),   %%xmm0\n"
                 "pcmpeqb   %%xmm1,   %%xmm0\n"
                 "pmovmskb  %%xmm0,   %[match]\n"
                 : [match]"=r"(match)
                 : [v]"r"(p)
-                : "xmm0"
+                : "xmm0", "xmm1"
             );
-#else
-            __m128i v = _mm_load_si128((__m128i*)p);
-            __m128i res = _mm_cmpeq_epi8( zeros, v );
-            match = _mm_movemask_epi8( res ); /* mask will be in reversed match order */
 #endif
             if( match & 0x000F )
                 TRY_MATCH(p, 0);
-- 
2.25.4