[FFmpeg-devel] [PATCH] libavutil: add x86 optimized av_popcount

[James Almer]

Signed-off-by: James Almer <jamrial at gmail.com>
---
I decided to go the configure route since other features (cmov, clz) also do
it , but if prefered this could instead be done with a new intmath.h header 
in the x86/ folder containing something like

#if defined(__GNUC__) && defined(__POPCNT__)
    #define av_popcount   __builtin_popcount
#if ARCH_X86_64
    #define av_popcount64 __builtin_popcountll
#endif
#endif

For a cleaner compile time check.

 configure           | 12 ++++++++++--
 libavutil/intmath.h | 13 +++++++++++++
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/configure b/configure
index d037da1..3f1c394 100755
--- a/configure
+++ b/configure
@@ -1610,6 +1610,7 @@ ARCH_FEATURES="
     fast_64bit
     fast_clz
     fast_cmov
+    fast_popcnt
     local_aligned_8
     local_aligned_16
     local_aligned_32
@@ -3908,13 +3909,20 @@ elif enabled x86; then
             cpuflags="-march=$cpu"
             disable i686
         ;;
-        # targets that do support nopl and conditional mov (cmov)
+        # targets that do support nopl and conditional mov (cmov) but not popcnt
         i686|pentiumpro|pentium[23]|pentium-m|athlon|athlon-tbird|athlon-4|athlon-[mx]p|athlon64*|k8*|opteron*|athlon-fx\
-        |core*|atom|bonnell|nehalem|westmere|silvermont|sandybridge|ivybridge|haswell|broadwell|amdfam10|barcelona|b[dt]ver*)
+        |core2*|atom|bonnell)
             cpuflags="-march=$cpu"
             enable i686
             enable fast_cmov
         ;;
+        # targets that do support nopl, conditional mov (cmov) and popcnt
+        core-*|corei*|nehalem|westmere|silvermont|sandybridge|ivybridge|haswell|broadwell|amdfam10|barcelona|b[dt]ver*)
+            cpuflags="-march=$cpu"
+            enable i686
+            enable fast_cmov
+            enable fast_popcnt
+        ;;
         # targets that do support conditional mov but on which it's slow
         pentium4|pentium4m|prescott|nocona)
             cpuflags="-march=$cpu"
diff --git a/libavutil/intmath.h b/libavutil/intmath.h
index fa549c8..e95eced 100644
--- a/libavutil/intmath.h
+++ b/libavutil/intmath.h
@@ -53,6 +53,19 @@
 #endif
 #endif /* AV_GCC_VERSION_AT_LEAST(3,4) */
 
+#if HAVE_FAST_POPCNT
+#if AV_GCC_VERSION_AT_LEAST(4,5)
+#ifndef av_popcount
+    #define av_popcount   __builtin_popcount
+#endif /* av_popcount */
+#if HAVE_FAST_64BIT
+#ifndef av_popcount64
+    #define av_popcount64 __builtin_popcountll
+#endif /* av_popcount64 */
+#endif /* HAVE_FAST_64BIT */
+#endif /* AV_GCC_VERSION_AT_LEAST(4,5) */
+#endif /* HAVE_FAST_POPCNT */
+
 extern const uint8_t ff_log2_tab[256];
 
 #ifndef ff_log2
-- 
2.3.0