diff --git a/libavcodec/x86/huffyuvdsp.asm b/libavcodec/x86/huffyuvdsp.asm
index 0d8cae354a..623183354d 100644
--- a/libavcodec/x86/huffyuvdsp.asm
+++ b/libavcodec/x86/huffyuvdsp.asm
@@ -24,61 +24,7 @@
 
 SECTION .text
 
-
-%macro INT16_LOOP 2 ; %1 = a/u (aligned/unaligned), %2 = add/sub
-    movd    m4, maskd
-    SPLATW  m4, m4
-    add     wd, wd
-    test    wq, 2*mmsize - 1
-    jz %%.tomainloop
-    push  tmpq
-%%.wordloop:
-    sub     wq, 2
-%ifidn %2, add
-    mov   tmpw, [srcq+wq]
-    add   tmpw, [dstq+wq]
-%else
-    mov   tmpw, [src1q+wq]
-    sub   tmpw, [src2q+wq]
-%endif
-    and   tmpw, maskw
-    mov     [dstq+wq], tmpw
-    test    wq, 2*mmsize - 1
-    jnz %%.wordloop
-    pop   tmpq
-%%.tomainloop:
-%ifidn %2, add
-    add     srcq, wq
-%else
-    add     src1q, wq
-    add     src2q, wq
-%endif
-    add     dstq, wq
-    neg     wq
-    jz      %%.end
-%%.loop:
-%ifidn %2, add
-    mov%1   m0, [srcq+wq]
-    mov%1   m1, [dstq+wq]
-    mov%1   m2, [srcq+wq+mmsize]
-    mov%1   m3, [dstq+wq+mmsize]
-%else
-    mov%1   m0, [src1q+wq]
-    mov%1   m1, [src2q+wq]
-    mov%1   m2, [src1q+wq+mmsize]
-    mov%1   m3, [src2q+wq+mmsize]
-%endif
-    p%2w    m0, m1
-    p%2w    m2, m3
-    pand    m0, m4
-    pand    m2, m4
-    mov%1   [dstq+wq]       , m0
-    mov%1   [dstq+wq+mmsize], m2
-    add     wq, 2*mmsize
-    jl %%.loop
-%%.end:
-    RET
-%endmacro
+%include "libavcodec/x86/huffyuvdsp_template.asm"
 
 %if ARCH_X86_32
 INIT_MMX mmx
diff --git a/libavcodec/x86/huffyuvdsp_init.c b/libavcodec/x86/huffyuvdsp_init.c
index 26cf6214d8..a522074565 100644
--- a/libavcodec/x86/huffyuvdsp_init.c
+++ b/libavcodec/x86/huffyuvdsp_init.c
@@ -28,6 +28,7 @@
 
 void ff_add_int16_mmx(uint16_t *dst, const uint16_t *src, unsigned mask, int w);
 void ff_add_int16_sse2(uint16_t *dst, const uint16_t *src, unsigned mask, int w);
+
 void ff_add_hfyu_left_pred_bgr32_mmx(uint8_t *dst, const uint8_t *src,
                                      intptr_t w, uint8_t *left);
 void ff_add_hfyu_left_pred_bgr32_sse2(uint8_t *dst, const uint8_t *src,
diff --git a/libavcodec/x86/huffyuvdsp_template.asm b/libavcodec/x86/huffyuvdsp_template.asm
new file mode 100644
index 0000000000..7e14542671
--- /dev/null
+++ b/libavcodec/x86/huffyuvdsp_template.asm
@@ -0,0 +1,76 @@
+;******************************************************************************
+;* SIMD-optimized HuffYUV functions
+;* Copyright (c) 2008 Loren Merritt
+;* Copyright (c) 2014 Christophe Gisquet
+;*
+;* This file is part of FFmpeg.
+;*
+;* FFmpeg is free software; you can redistribute it and/or
+;* modify it under the terms of the GNU Lesser General Public
+;* License as published by the Free Software Foundation; either
+;* version 2.1 of the License, or (at your option) any later version.
+;*
+;* FFmpeg is distributed in the hope that it will be useful,
+;* but WITHOUT ANY WARRANTY; without even the implied warranty of
+;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+;* Lesser General Public License for more details.
+;*
+;* You should have received a copy of the GNU Lesser General Public
+;* License along with FFmpeg; if not, write to the Free Software
+;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+;******************************************************************************
+
+%macro INT16_LOOP 2 ; %1 = a/u (aligned/unaligned), %2 = add/sub
+    movd    m4, maskd
+    SPLATW  m4, m4
+    add     wd, wd
+    test    wq, 2*mmsize - 1
+    jz %%.tomainloop
+    push  tmpq
+%%.wordloop:
+    sub     wq, 2
+%ifidn %2, add
+    mov   tmpw, [srcq+wq]
+    add   tmpw, [dstq+wq]
+%else
+    mov   tmpw, [src1q+wq]
+    sub   tmpw, [src2q+wq]
+%endif
+    and   tmpw, maskw
+    mov     [dstq+wq], tmpw
+    test    wq, 2*mmsize - 1
+    jnz %%.wordloop
+    pop   tmpq
+%%.tomainloop:
+%ifidn %2, add
+    add     srcq, wq
+%else
+    add     src1q, wq
+    add     src2q, wq
+%endif
+    add     dstq, wq
+    neg     wq
+    jz      %%.end
+%%.loop:
+%ifidn %2, add
+    mov%1   m0, [srcq+wq]
+    mov%1   m1, [dstq+wq]
+    mov%1   m2, [srcq+wq+mmsize]
+    mov%1   m3, [dstq+wq+mmsize]
+%else
+    mov%1   m0, [src1q+wq]
+    mov%1   m1, [src2q+wq]
+    mov%1   m2, [src1q+wq+mmsize]
+    mov%1   m3, [src2q+wq+mmsize]
+%endif
+    p%2w    m0, m1
+    p%2w    m2, m3
+    pand    m0, m4
+    pand    m2, m4
+    mov%1   [dstq+wq]       , m0
+    mov%1   [dstq+wq+mmsize], m2
+    add     wq, 2*mmsize
+    jl %%.loop
+%%.end:
+    RET
+%endmacro
diff --git a/libavcodec/x86/huffyuvencdsp.asm b/libavcodec/x86/huffyuvencdsp.asm
index eeef81ab8e..6a7f1a0f49 100644
--- a/libavcodec/x86/huffyuvencdsp.asm
+++ b/libavcodec/x86/huffyuvencdsp.asm
@@ -27,62 +27,10 @@
 
 SECTION .text
 
+%include "libavcodec/x86/huffyuvdsp_template.asm"
+
 ; void ff_diff_int16(uint8_t *dst, const uint8_t *src1, const uint8_t *src2,
 ;                    unsigned mask, int w);
-%macro INT16_LOOP 2 ; %1 = a/u (aligned/unaligned), %2 = add/sub
-    movd    m4, maskd
-    SPLATW  m4, m4
-    add     wd, wd
-    test    wq, 2*mmsize - 1
-    jz %%.tomainloop
-    push  tmpq
-%%.wordloop:
-    sub     wq, 2
-%ifidn %2, add
-    mov   tmpw, [srcq+wq]
-    add   tmpw, [dstq+wq]
-%else
-    mov   tmpw, [src1q+wq]
-    sub   tmpw, [src2q+wq]
-%endif
-    and   tmpw, maskw
-    mov     [dstq+wq], tmpw
-    test    wq, 2*mmsize - 1
-    jnz %%.wordloop
-    pop   tmpq
-%%.tomainloop:
-%ifidn %2, add
-    add     srcq, wq
-%else
-    add     src1q, wq
-    add     src2q, wq
-%endif
-    add     dstq, wq
-    neg     wq
-    jz      %%.end
-%%.loop:
-%ifidn %2, add
-    mov%1   m0, [srcq+wq]
-    mov%1   m1, [dstq+wq]
-    mov%1   m2, [srcq+wq+mmsize]
-    mov%1   m3, [dstq+wq+mmsize]
-%else
-    mov%1   m0, [src1q+wq]
-    mov%1   m1, [src2q+wq]
-    mov%1   m2, [src1q+wq+mmsize]
-    mov%1   m3, [src2q+wq+mmsize]
-%endif
-    p%2w    m0, m1
-    p%2w    m2, m3
-    pand    m0, m4
-    pand    m2, m4
-    mov%1   [dstq+wq]       , m0
-    mov%1   [dstq+wq+mmsize], m2
-    add     wq, 2*mmsize
-    jl %%.loop
-%%.end:
-    RET
-%endmacro
 
 %if ARCH_X86_32
 INIT_MMX mmx