diff --git a/libavcodec/h264qpel.c b/libavcodec/h264qpel.c
index faca1e8953..be80203c4b 100644
--- a/libavcodec/h264qpel.c
+++ b/libavcodec/h264qpel.c
@@ -20,11 +20,71 @@
  */
 
 #include "libavutil/attributes.h"
+#include "libavutil/common.h"
 #include "h264qpel.h"
 
 #define pixeltmp int16_t
 #define BIT_DEPTH 8
 #include "h264qpel_template.c"
+
+static void put_h264_qpel2_h_lowpass_8(uint8_t *dst, const uint8_t *restrict src, int dstStride, int srcStride)
+{
+    const int h = 2;
+    for (int i = 0; i < h; ++i) {
+        dst[0] = av_clip_uint8(((src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + 16) >> 5);
+        dst[1] = av_clip_uint8(((src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + 16) >> 5);
+        dst += dstStride;
+        src += srcStride;
+    }
+}
+
+static void put_h264_qpel2_v_lowpass_8(uint8_t *dst, const uint8_t *restrict src, int dstStride, int srcStride)
+{
+    const int w = 2;
+    for (int i = 0; i < w; ++i) {
+        const int srcB = src[-2*srcStride];
+        const int srcA = src[-1*srcStride];
+        const int src0 = src[0 *srcStride];
+        const int src1 = src[1 *srcStride];
+        const int src2 = src[2 *srcStride];
+        const int src3 = src[3 *srcStride];
+        const int src4 = src[4 *srcStride];
+        dst[0*dstStride] = av_clip_uint8(((src0+src1)*20 - (srcA+src2)*5 + (srcB+src3) + 16) >> 5);
+        dst[1*dstStride] = av_clip_uint8(((src1+src2)*20 - (src0+src3)*5 + (srcA+src4) + 16) >> 5);
+        dst++;
+        src++;
+    }
+}
+
+static void put_h264_qpel2_hv_lowpass_8(uint8_t *dst, pixeltmp *tmp, const uint8_t *restrict src, int dstStride, int tmpStride, int srcStride)
+{
+    const int h = 2;
+    const int w = 2;
+    src -= 2*srcStride;
+    for (int i = 0; i < h + 5; ++i) {
+        tmp[0] = (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]);
+        tmp[1] = (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]);
+        tmp += tmpStride;
+        src += srcStride;
+    }
+    tmp -= tmpStride*(h+5-2);
+    for (int i = 0; i < w; ++i) {
+        const int tmpB = tmp[-2*tmpStride];
+        const int tmpA = tmp[-1*tmpStride];
+        const int tmp0 = tmp[0 *tmpStride];
+        const int tmp1 = tmp[1 *tmpStride];
+        const int tmp2 = tmp[2 *tmpStride];
+        const int tmp3 = tmp[3 *tmpStride];
+        const int tmp4 = tmp[4 *tmpStride];
+        dst[0*dstStride] = av_clip_uint8(((tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3) + 512) >> 10);
+        dst[1*dstStride] = av_clip_uint8(((tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4) + 512) >> 10);
+        dst++;
+        tmp++;
+    }
+}
+
+H264_MC(put_, 2)
+
 #undef BIT_DEPTH
 
 #define BIT_DEPTH 9
@@ -73,7 +133,6 @@ av_cold void ff_h264qpel_init(H264QpelContext *c, int bit_depth)
     dspfunc2(put_h264_qpel, 0, 16, depth);      \
     dspfunc2(put_h264_qpel, 1,  8, depth);      \
     dspfunc2(put_h264_qpel, 2,  4, depth);      \
-    dspfunc2(put_h264_qpel, 3,  2, depth);      \
     dspfunc2(avg_h264_qpel, 0, 16, depth);      \
     dspfunc2(avg_h264_qpel, 1,  8, depth);      \
     dspfunc2(avg_h264_qpel, 2,  4, depth)
@@ -81,6 +140,7 @@ av_cold void ff_h264qpel_init(H264QpelContext *c, int bit_depth)
     switch (bit_depth) {
     default:
         SET_QPEL(8);
+        dspfunc2(put_h264_qpel, 3,  2, 8); // only used by Snow
         break;
     case 9:
         SET_QPEL(9);
diff --git a/libavcodec/h264qpel_template.c b/libavcodec/h264qpel_template.c
index b71710e6db..a55b45e824 100644
--- a/libavcodec/h264qpel_template.c
+++ b/libavcodec/h264qpel_template.c
@@ -75,81 +75,6 @@ static inline void FUNC(copy_block16)(uint8_t *dst, const uint8_t *restrict src,
 }
 
 #define H264_LOWPASS(OPNAME, OP, OP2) \
-av_unused static void FUNC(OPNAME ## h264_qpel2_h_lowpass)(uint8_t *p_dst, const uint8_t *restrict p_src, int dstStride, int srcStride)\
-{\
-    const int h=2;\
-    int i;\
-    pixel *dst = (pixel*)p_dst;\
-    const pixel *restrict src = (const pixel*)p_src;\
-    dstStride >>= sizeof(pixel)-1;\
-    srcStride >>= sizeof(pixel)-1;\
-    for(i=0; i<h; i++)\
-    {\
-        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]));\
-        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]));\
-        dst+=dstStride;\
-        src+=srcStride;\
-    }\
-}\
-\
-av_unused static void FUNC(OPNAME ## h264_qpel2_v_lowpass)(uint8_t *_dst, const uint8_t *restrict _src, int dstStride, int srcStride)\
-{\
-    const int w=2;\
-    int i;\
-    pixel *dst = (pixel*)_dst;\
-    const pixel *restrict src = (const pixel*)_src;\
-    dstStride >>= sizeof(pixel)-1;\
-    srcStride >>= sizeof(pixel)-1;\
-    for(i=0; i<w; i++)\
-    {\
-        const int srcB= src[-2*srcStride];\
-        const int srcA= src[-1*srcStride];\
-        const int src0= src[0 *srcStride];\
-        const int src1= src[1 *srcStride];\
-        const int src2= src[2 *srcStride];\
-        const int src3= src[3 *srcStride];\
-        const int src4= src[4 *srcStride];\
-        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
-        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
-        dst++;\
-        src++;\
-    }\
-}\
-\
-av_unused static void FUNC(OPNAME ## h264_qpel2_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *restrict _src, int dstStride, int tmpStride, int srcStride)\
-{\
-    const int h=2;\
-    const int w=2;\
-    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
-    int i;\
-    pixel *dst = (pixel*)_dst;\
-    const pixel *restrict src = (const pixel*)_src;\
-    dstStride >>= sizeof(pixel)-1;\
-    srcStride >>= sizeof(pixel)-1;\
-    src -= 2*srcStride;\
-    for(i=0; i<h+5; i++)\
-    {\
-        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + pad;\
-        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + pad;\
-        tmp+=tmpStride;\
-        src+=srcStride;\
-    }\
-    tmp -= tmpStride*(h+5-2);\
-    for(i=0; i<w; i++)\
-    {\
-        const int tmpB= tmp[-2*tmpStride] - pad;\
-        const int tmpA= tmp[-1*tmpStride] - pad;\
-        const int tmp0= tmp[0 *tmpStride] - pad;\
-        const int tmp1= tmp[1 *tmpStride] - pad;\
-        const int tmp2= tmp[2 *tmpStride] - pad;\
-        const int tmp3= tmp[3 *tmpStride] - pad;\
-        const int tmp4= tmp[4 *tmpStride] - pad;\
-        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
-        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
-        dst++;\
-        tmp++;\
-    }\
-}\
 static void FUNC(OPNAME ## h264_qpel4_h_lowpass)(uint8_t *_dst, const uint8_t *restrict _src, int dstStride, int srcStride)\
 {\
     const int h=4;\
@@ -540,7 +465,6 @@ static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc32)(uint8_t *dst, const uint
 
 H264_LOWPASS(put_       , op_put, op2_put)
 H264_LOWPASS(avg_       , op_avg, op2_avg)
-H264_MC(put_, 2)
 H264_MC(put_, 4)
 H264_MC(put_, 8)
 H264_MC(put_, 16)
diff --git a/tests/checkasm/h264qpel.c b/tests/checkasm/h264qpel.c
index e47d659929..7387c2510a 100644
--- a/tests/checkasm/h264qpel.c
+++ b/tests/checkasm/h264qpel.c
@@ -64,7 +64,7 @@ void checkasm_check_h264qpel(void)
 
         for (bit_depth = 8; bit_depth <= 10; bit_depth++) {
             ff_h264qpel_init(&h, bit_depth);
-            for (i = 0; i < (op ? 3 : 4); i++) {
+            for (i = 0; i < (op || bit_depth != 8 ? 3 : 4); i++) {
                 int size = 16 >> i;
                 for (j = 0; j < 16; j++)
                     if (check_func(tab[i][j], "%s_h264_qpel_%d_mc%d%d_%d", op_name, size, j & 3, j >> 2, bit_depth)) {