diff --git a/configure b/configure
index e584be7ff6..b61359c7a7 100755
--- a/configure
+++ b/configure
@@ -3347,6 +3347,7 @@ esac
 
 # determine libc flavour
 
+# uclibc defines __GLIBC__, so it needs to be checked before glibc.
 if check_cpp_condition features.h "defined __UCLIBC__"; then
     libc_type=uclibc
     add_cppflags -D_POSIX_C_SOURCE=200112 -D_XOPEN_SOURCE=600
diff --git a/libavcodec/x86/dsputil.asm b/libavcodec/x86/dsputil.asm
index 6a76655a8b..587d5ee968 100644
--- a/libavcodec/x86/dsputil.asm
+++ b/libavcodec/x86/dsputil.asm
@@ -648,46 +648,3 @@ BSWAP32_BUF
 
 INIT_XMM ssse3
 BSWAP32_BUF
-
-INIT_XMM sse2
-; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
-cglobal put_pixels16, 4,5,4
-    movsxdifnidn r2, r2d
-    lea          r4, [r2*3]
-.loop:
-    movu         m0, [r1]
-    movu         m1, [r1+r2]
-    movu         m2, [r1+r2*2]
-    movu         m3, [r1+r4]
-    lea          r1, [r1+r2*4]
-    mova       [r0], m0
-    mova    [r0+r2], m1
-    mova  [r0+r2*2], m2
-    mova    [r0+r4], m3
-    sub         r3d, 4
-    lea          r0, [r0+r2*4]
-    jnz       .loop
-    REP_RET
-
-; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
-cglobal avg_pixels16, 4,5,4
-    movsxdifnidn r2, r2d
-    lea          r4, [r2*3]
-.loop:
-    movu         m0, [r1]
-    movu         m1, [r1+r2]
-    movu         m2, [r1+r2*2]
-    movu         m3, [r1+r4]
-    lea          r1, [r1+r2*4]
-    pavgb        m0, [r0]
-    pavgb        m1, [r0+r2]
-    pavgb        m2, [r0+r2*2]
-    pavgb        m3, [r0+r4]
-    mova       [r0], m0
-    mova    [r0+r2], m1
-    mova  [r0+r2*2], m2
-    mova    [r0+r4], m3
-    sub         r3d, 4
-    lea          r0, [r0+r2*4]
-    jnz       .loop
-    REP_RET
diff --git a/libavcodec/x86/hpeldsp.asm b/libavcodec/x86/hpeldsp.asm
index 72bc111baa..0f6f9e9ad2 100644
--- a/libavcodec/x86/hpeldsp.asm
+++ b/libavcodec/x86/hpeldsp.asm
@@ -469,3 +469,46 @@ INIT_MMX mmxext
 AVG_PIXELS8_XY2
 INIT_MMX 3dnow
 AVG_PIXELS8_XY2
+
+INIT_XMM sse2
+; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+cglobal put_pixels16, 4,5,4
+    movsxdifnidn r2, r2d
+    lea          r4, [r2*3]
+.loop:
+    movu         m0, [r1]
+    movu         m1, [r1+r2]
+    movu         m2, [r1+r2*2]
+    movu         m3, [r1+r4]
+    lea          r1, [r1+r2*4]
+    mova       [r0], m0
+    mova    [r0+r2], m1
+    mova  [r0+r2*2], m2
+    mova    [r0+r4], m3
+    sub         r3d, 4
+    lea          r0, [r0+r2*4]
+    jnz       .loop
+    REP_RET
+
+; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+cglobal avg_pixels16, 4,5,4
+    movsxdifnidn r2, r2d
+    lea          r4, [r2*3]
+.loop:
+    movu         m0, [r1]
+    movu         m1, [r1+r2]
+    movu         m2, [r1+r2*2]
+    movu         m3, [r1+r4]
+    lea          r1, [r1+r2*4]
+    pavgb        m0, [r0]
+    pavgb        m1, [r0+r2]
+    pavgb        m2, [r0+r2*2]
+    pavgb        m3, [r0+r4]
+    mova       [r0], m0
+    mova    [r0+r2], m1
+    mova  [r0+r2*2], m2
+    mova    [r0+r4], m3
+    sub         r3d, 4
+    lea          r0, [r0+r2*4]
+    jnz       .loop
+    REP_RET