Implement sse2 and ssse3 versions for all sub_pixel_variance sizes.

Overall speedup around 5% (bus @ 1500kbps first 50 frames 4min10 ->
3min58). Specific changes to timings for each function compared to
original assembly-optimized versions (or just new version timings if
no previous assembly-optimized version was available):

sse2   4x4:    99 ->   82 cycles
sse2   4x8:           128 cycles
sse2   8x4:           121 cycles
sse2   8x8:   149 ->  129 cycles
sse2   8x16:  235 ->  245 cycles (?)
sse2  16x8:   269 ->  203 cycles
sse2  16x16:  441 ->  349 cycles
sse2  16x32:          641 cycles
sse2  32x16:          643 cycles
sse2  32x32: 1733 -> 1154 cycles
sse2  32x64:         2247 cycles
sse2  64x32:         2323 cycles
sse2  64x64: 6984 -> 4442 cycles

ssse3  4x4:           100 cycles (?)
ssse3  4x8:           103 cycles
ssse3  8x4:            71 cycles
ssse3  8x8:           147 cycles
ssse3  8x16:          158 cycles
ssse3 16x8:   188 ->  162 cycles
ssse3 16x16:  316 ->  273 cycles
ssse3 16x32:          535 cycles
ssse3 32x16:          564 cycles
ssse3 32x32:          973 cycles
ssse3 32x64:         1930 cycles
ssse3 64x32:         1922 cycles
ssse3 64x64:         3760 cycles

Change-Id: I81ff6fe51daf35a40d19785167004664d7e0c59d

1 files changed, 327 insertions, 40 deletions

diff --git a/test/variance_test.cc b/test/variance_test.cc
index dfa1a07c7..e7037d9d6 100644
--- a/test/variance_test.cc
+++ b/test/variance_test.cc
@@ -26,12 +26,55 @@ extern "C" {
 # include "vp9_rtcd.h"
 #endif
 }
+#include "test/acm_random.h"
 
 namespace {
 
 using ::std::tr1::get;
 using ::std::tr1::make_tuple;
 using ::std::tr1::tuple;
+using libvpx_test::ACMRandom;
+
+static unsigned int variance_ref(const uint8_t *ref, const uint8_t *src,
+                                 int l2w, int l2h, unsigned int *sse_ptr) {
+  int se = 0;
+  unsigned int sse = 0;
+  const int w = 1 << l2w, h = 1 << l2h;
+  for (int y = 0; y < h; y++) {
+    for (int x = 0; x < w; x++) {
+      int diff = ref[w * y + x] - src[w * y + x];
+      se += diff;
+      sse += diff * diff;
+    }
+  }
+  *sse_ptr = sse;
+  return sse - (((int64_t) se * se) >> (l2w + l2h));
+}
+
+static unsigned int subpel_variance_ref(const uint8_t *ref, const uint8_t *src,
+                                        int l2w, int l2h, int xoff, int yoff,
+                                        unsigned int *sse_ptr) {
+  int se = 0;
+  unsigned int sse = 0;
+  const int w = 1 << l2w, h = 1 << l2h;
+  for (int y = 0; y < h; y++) {
+    for (int x = 0; x < w; x++) {
+      // bilinear interpolation at a 16th pel step
+      const int a1 = ref[(w + 1) * (y + 0) + x + 0];
+      const int a2 = ref[(w + 1) * (y + 0) + x + 1];
+      const int b1 = ref[(w + 1) * (y + 1) + x + 0];
+      const int b2 = ref[(w + 1) * (y + 1) + x + 1];
+      const int a = a1 + (((a2 - a1) * xoff + 8) >> 4);
+      const int b = b1 + (((b2 - b1) * xoff + 8) >> 4);
+      const int r = a + (((b - a) * yoff + 8) >> 4);
+      int diff = r - src[w * y + x];
+      se += diff;
+      sse += diff * diff;
+    }
+  }
+  *sse_ptr = sse;
+  return sse - (((int64_t) se * se) >> (l2w + l2h));
+}
 
 template<typename VarianceFunctionType>
 class VarianceTest :
@@ -39,10 +82,13 @@ class VarianceTest :
  public:
   virtual void SetUp() {
     const tuple<int, int, VarianceFunctionType>& params = this->GetParam();
-    width_  = get<0>(params);
-    height_ = get<1>(params);
+    log2width_  = get<0>(params);
+    width_ = 1 << log2width_;
+    log2height_ = get<1>(params);
+    height_ = 1 << log2height_;
     variance_ = get<2>(params);
 
+    rnd(ACMRandom::DeterministicSeed());
     block_size_ = width_ * height_;
     src_ = new uint8_t[block_size_];
     ref_ = new uint8_t[block_size_];
@@ -58,15 +104,16 @@ class VarianceTest :
 
  protected:
   void ZeroTest();
+  void RefTest();
   void OneQuarterTest();
 
+  ACMRandom rnd;
   uint8_t* src_;
   uint8_t* ref_;
-  int width_;
-  int height_;
+  int width_, log2width_;
+  int height_, log2height_;
   int block_size_;
   VarianceFunctionType variance_;
-
 };
 
 template<typename VarianceFunctionType>
@@ -83,6 +130,22 @@ void VarianceTest<VarianceFunctionType>::ZeroTest() {
 }
 
 template<typename VarianceFunctionType>
+void VarianceTest<VarianceFunctionType>::RefTest() {
+  for (int i = 0; i < 10; ++i) {
+    for (int j = 0; j < block_size_; j++) {
+      src_[j] = rnd.Rand8();
+      ref_[j] = rnd.Rand8();
+    }
+    unsigned int sse1, sse2;
+    const unsigned int var1 = variance_(src_, width_, ref_, width_, &sse1);
+    const unsigned int var2 = variance_ref(src_, ref_, log2width_,
+                                           log2height_, &sse2);
+    EXPECT_EQ(sse1, sse2);
+    EXPECT_EQ(var1, var2);
+  }
+}
+
+template<typename VarianceFunctionType>
 void VarianceTest<VarianceFunctionType>::OneQuarterTest() {
   memset(src_, 255, block_size_);
   const int half = block_size_ / 2;
@@ -94,6 +157,66 @@ void VarianceTest<VarianceFunctionType>::OneQuarterTest() {
   EXPECT_EQ(expected, var);
 }
 
+template<typename SubpelVarianceFunctionType>
+class SubpelVarianceTest :
+    public ::testing::TestWithParam<tuple<int, int,
+                                          SubpelVarianceFunctionType> > {
+ public:
+  virtual void SetUp() {
+    const tuple<int, int, SubpelVarianceFunctionType>& params =
+        this->GetParam();
+    log2width_  = get<0>(params);
+    width_ = 1 << log2width_;
+    log2height_ = get<1>(params);
+    height_ = 1 << log2height_;
+    subpel_variance_ = get<2>(params);
+
+    rnd(ACMRandom::DeterministicSeed());
+    block_size_ = width_ * height_;
+    src_ = new uint8_t[block_size_];
+    ref_ = new uint8_t[block_size_ + width_ + height_ + 1];
+    ASSERT_TRUE(src_ != NULL);
+    ASSERT_TRUE(ref_ != NULL);
+  }
+
+  virtual void TearDown() {
+    delete[] src_;
+    delete[] ref_;
+  }
+
+ protected:
+  void RefTest();
+
+  ACMRandom rnd;
+  uint8_t* src_;
+  uint8_t* ref_;
+  int width_, log2width_;
+  int height_, log2height_;
+  int block_size_;
+  SubpelVarianceFunctionType subpel_variance_;
+};
+
+template<typename SubpelVarianceFunctionType>
+void SubpelVarianceTest<SubpelVarianceFunctionType>::RefTest() {
+  for (int x = 0; x < 16; ++x) {
+    for (int y = 0; y < 16; ++y) {
+      for (int j = 0; j < block_size_; j++) {
+        src_[j] = rnd.Rand8();
+      }
+      for (int j = 0; j < block_size_ + width_ + height_ + 1; j++) {
+        ref_[j] = rnd.Rand8();
+      }
+      unsigned int sse1, sse2;
+      const unsigned int var1 = subpel_variance_(ref_, width_ + 1, x, y,
+                                                 src_, width_, &sse1);
+      const unsigned int var2 = subpel_variance_ref(ref_, src_, log2width_,
+                                                    log2height_, x, y, &sse2);
+      EXPECT_EQ(sse1, sse2) << "at position " << x << ", " << y;
+      EXPECT_EQ(var1, var2) << "at position " << x << ", " << y;
+    }
+  }
+}
+
 // -----------------------------------------------------------------------------
 // VP8 test cases.
 
@@ -103,6 +226,7 @@ namespace vp8 {
 typedef VarianceTest<vp8_variance_fn_t> VP8VarianceTest;
 
 TEST_P(VP8VarianceTest, Zero) { ZeroTest(); }
+TEST_P(VP8VarianceTest, Ref) { RefTest(); }
 TEST_P(VP8VarianceTest, OneQuarter) { OneQuarterTest(); }
 
 const vp8_variance_fn_t variance4x4_c = vp8_variance4x4_c;
@@ -112,11 +236,11 @@ const vp8_variance_fn_t variance16x8_c = vp8_variance16x8_c;
 const vp8_variance_fn_t variance16x16_c = vp8_variance16x16_c;
 INSTANTIATE_TEST_CASE_P(
     C, VP8VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_c),
-                      make_tuple(8, 8, variance8x8_c),
-                      make_tuple(8, 16, variance8x16_c),
-                      make_tuple(16, 8, variance16x8_c),
-                      make_tuple(16, 16, variance16x16_c)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_c),
+                      make_tuple(3, 3, variance8x8_c),
+                      make_tuple(3, 4, variance8x16_c),
+                      make_tuple(4, 3, variance16x8_c),
+                      make_tuple(4, 4, variance16x16_c)));
 
 #if HAVE_MMX
 const vp8_variance_fn_t variance4x4_mmx = vp8_variance4x4_mmx;
@@ -126,11 +250,11 @@ const vp8_variance_fn_t variance16x8_mmx = vp8_variance16x8_mmx;
 const vp8_variance_fn_t variance16x16_mmx = vp8_variance16x16_mmx;
 INSTANTIATE_TEST_CASE_P(
     MMX, VP8VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_mmx),
-                      make_tuple(8, 8, variance8x8_mmx),
-                      make_tuple(8, 16, variance8x16_mmx),
-                      make_tuple(16, 8, variance16x8_mmx),
-                      make_tuple(16, 16, variance16x16_mmx)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_mmx),
+                      make_tuple(3, 3, variance8x8_mmx),
+                      make_tuple(3, 4, variance8x16_mmx),
+                      make_tuple(4, 3, variance16x8_mmx),
+                      make_tuple(4, 4, variance16x16_mmx)));
 #endif
 
 #if HAVE_SSE2
@@ -141,11 +265,11 @@ const vp8_variance_fn_t variance16x8_wmt = vp8_variance16x8_wmt;
 const vp8_variance_fn_t variance16x16_wmt = vp8_variance16x16_wmt;
 INSTANTIATE_TEST_CASE_P(
     SSE2, VP8VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_wmt),
-                      make_tuple(8, 8, variance8x8_wmt),
-                      make_tuple(8, 16, variance8x16_wmt),
-                      make_tuple(16, 8, variance16x8_wmt),
-                      make_tuple(16, 16, variance16x16_wmt)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_wmt),
+                      make_tuple(3, 3, variance8x8_wmt),
+                      make_tuple(3, 4, variance8x16_wmt),
+                      make_tuple(4, 3, variance16x8_wmt),
+                      make_tuple(4, 4, variance16x16_wmt)));
 #endif
 #endif  // CONFIG_VP8_ENCODER
 
@@ -158,22 +282,83 @@ namespace vp9 {
 
 #if CONFIG_VP9_ENCODER
 typedef VarianceTest<vp9_variance_fn_t> VP9VarianceTest;
+typedef SubpelVarianceTest<vp9_subpixvariance_fn_t> VP9SubpelVarianceTest;
 
 TEST_P(VP9VarianceTest, Zero) { ZeroTest(); }
+TEST_P(VP9VarianceTest, Ref) { RefTest(); }
+TEST_P(VP9SubpelVarianceTest, Ref) { RefTest(); }
 TEST_P(VP9VarianceTest, OneQuarter) { OneQuarterTest(); }
 
 const vp9_variance_fn_t variance4x4_c = vp9_variance4x4_c;
+const vp9_variance_fn_t variance4x8_c = vp9_variance4x8_c;
+const vp9_variance_fn_t variance8x4_c = vp9_variance8x4_c;
 const vp9_variance_fn_t variance8x8_c = vp9_variance8x8_c;
 const vp9_variance_fn_t variance8x16_c = vp9_variance8x16_c;
 const vp9_variance_fn_t variance16x8_c = vp9_variance16x8_c;
 const vp9_variance_fn_t variance16x16_c = vp9_variance16x16_c;
+const vp9_variance_fn_t variance16x32_c = vp9_variance16x32_c;
+const vp9_variance_fn_t variance32x16_c = vp9_variance32x16_c;
+const vp9_variance_fn_t variance32x32_c = vp9_variance32x32_c;
+const vp9_variance_fn_t variance32x64_c = vp9_variance32x64_c;
+const vp9_variance_fn_t variance64x32_c = vp9_variance64x32_c;
+const vp9_variance_fn_t variance64x64_c = vp9_variance64x64_c;
 INSTANTIATE_TEST_CASE_P(
     C, VP9VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_c),
-                      make_tuple(8, 8, variance8x8_c),
-                      make_tuple(8, 16, variance8x16_c),
-                      make_tuple(16, 8, variance16x8_c),
-                      make_tuple(16, 16, variance16x16_c)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_c),
+                      make_tuple(2, 3, variance4x8_c),
+                      make_tuple(3, 2, variance8x4_c),
+                      make_tuple(3, 3, variance8x8_c),
+                      make_tuple(3, 4, variance8x16_c),
+                      make_tuple(4, 3, variance16x8_c),
+                      make_tuple(4, 4, variance16x16_c),
+                      make_tuple(4, 5, variance16x32_c),
+                      make_tuple(5, 4, variance32x16_c),
+                      make_tuple(5, 5, variance32x32_c),
+                      make_tuple(5, 6, variance32x64_c),
+                      make_tuple(6, 5, variance64x32_c),
+                      make_tuple(6, 6, variance64x64_c)));
+
+const vp9_subpixvariance_fn_t subpel_variance4x4_c =
+    vp9_sub_pixel_variance4x4_c;
+const vp9_subpixvariance_fn_t subpel_variance4x8_c =
+    vp9_sub_pixel_variance4x8_c;
+const vp9_subpixvariance_fn_t subpel_variance8x4_c =
+    vp9_sub_pixel_variance8x4_c;
+const vp9_subpixvariance_fn_t subpel_variance8x8_c =
+    vp9_sub_pixel_variance8x8_c;
+const vp9_subpixvariance_fn_t subpel_variance8x16_c =
+    vp9_sub_pixel_variance8x16_c;
+const vp9_subpixvariance_fn_t subpel_variance16x8_c =
+    vp9_sub_pixel_variance16x8_c;
+const vp9_subpixvariance_fn_t subpel_variance16x16_c =
+    vp9_sub_pixel_variance16x16_c;
+const vp9_subpixvariance_fn_t subpel_variance16x32_c =
+    vp9_sub_pixel_variance16x32_c;
+const vp9_subpixvariance_fn_t subpel_variance32x16_c =
+    vp9_sub_pixel_variance32x16_c;
+const vp9_subpixvariance_fn_t subpel_variance32x32_c =
+    vp9_sub_pixel_variance32x32_c;
+const vp9_subpixvariance_fn_t subpel_variance32x64_c =
+    vp9_sub_pixel_variance32x64_c;
+const vp9_subpixvariance_fn_t subpel_variance64x32_c =
+    vp9_sub_pixel_variance64x32_c;
+const vp9_subpixvariance_fn_t subpel_variance64x64_c =
+    vp9_sub_pixel_variance64x64_c;
+INSTANTIATE_TEST_CASE_P(
+    C, VP9SubpelVarianceTest,
+    ::testing::Values(make_tuple(2, 2, subpel_variance4x4_c),
+                      make_tuple(2, 3, subpel_variance4x8_c),
+                      make_tuple(3, 2, subpel_variance8x4_c),
+                      make_tuple(3, 3, subpel_variance8x8_c),
+                      make_tuple(3, 4, subpel_variance8x16_c),
+                      make_tuple(4, 3, subpel_variance16x8_c),
+                      make_tuple(4, 4, subpel_variance16x16_c),
+                      make_tuple(4, 5, subpel_variance16x32_c),
+                      make_tuple(5, 4, subpel_variance32x16_c),
+                      make_tuple(5, 5, subpel_variance32x32_c),
+                      make_tuple(5, 6, subpel_variance32x64_c),
+                      make_tuple(6, 5, subpel_variance64x32_c),
+                      make_tuple(6, 6, subpel_variance64x64_c)));
 
 #if HAVE_MMX
 const vp9_variance_fn_t variance4x4_mmx = vp9_variance4x4_mmx;
@@ -183,26 +368,128 @@ const vp9_variance_fn_t variance16x8_mmx = vp9_variance16x8_mmx;
 const vp9_variance_fn_t variance16x16_mmx = vp9_variance16x16_mmx;
 INSTANTIATE_TEST_CASE_P(
     MMX, VP9VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_mmx),
-                      make_tuple(8, 8, variance8x8_mmx),
-                      make_tuple(8, 16, variance8x16_mmx),
-                      make_tuple(16, 8, variance16x8_mmx),
-                      make_tuple(16, 16, variance16x16_mmx)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_mmx),
+                      make_tuple(3, 3, variance8x8_mmx),
+                      make_tuple(3, 4, variance8x16_mmx),
+                      make_tuple(4, 3, variance16x8_mmx),
+                      make_tuple(4, 4, variance16x16_mmx)));
 #endif
 
 #if HAVE_SSE2
-const vp9_variance_fn_t variance4x4_wmt = vp9_variance4x4_sse2;
-const vp9_variance_fn_t variance8x8_wmt = vp9_variance8x8_sse2;
-const vp9_variance_fn_t variance8x16_wmt = vp9_variance8x16_sse2;
-const vp9_variance_fn_t variance16x8_wmt = vp9_variance16x8_sse2;
-const vp9_variance_fn_t variance16x16_wmt = vp9_variance16x16_sse2;
+const vp9_variance_fn_t variance4x4_sse2 = vp9_variance4x4_sse2;
+const vp9_variance_fn_t variance4x8_sse2 = vp9_variance4x8_sse2;
+const vp9_variance_fn_t variance8x4_sse2 = vp9_variance8x4_sse2;
+const vp9_variance_fn_t variance8x8_sse2 = vp9_variance8x8_sse2;
+const vp9_variance_fn_t variance8x16_sse2 = vp9_variance8x16_sse2;
+const vp9_variance_fn_t variance16x8_sse2 = vp9_variance16x8_sse2;
+const vp9_variance_fn_t variance16x16_sse2 = vp9_variance16x16_sse2;
+const vp9_variance_fn_t variance16x32_sse2 = vp9_variance16x32_sse2;
+const vp9_variance_fn_t variance32x16_sse2 = vp9_variance32x16_sse2;
+const vp9_variance_fn_t variance32x32_sse2 = vp9_variance32x32_sse2;
+const vp9_variance_fn_t variance32x64_sse2 = vp9_variance32x64_sse2;
+const vp9_variance_fn_t variance64x32_sse2 = vp9_variance64x32_sse2;
+const vp9_variance_fn_t variance64x64_sse2 = vp9_variance64x64_sse2;
 INSTANTIATE_TEST_CASE_P(
     SSE2, VP9VarianceTest,
-    ::testing::Values(make_tuple(4, 4, variance4x4_wmt),
-                      make_tuple(8, 8, variance8x8_wmt),
-                      make_tuple(8, 16, variance8x16_wmt),
-                      make_tuple(16, 8, variance16x8_wmt),
-                      make_tuple(16, 16, variance16x16_wmt)));
+    ::testing::Values(make_tuple(2, 2, variance4x4_sse2),
+                      make_tuple(2, 3, variance4x8_sse2),
+                      make_tuple(3, 2, variance8x4_sse2),
+                      make_tuple(3, 3, variance8x8_sse2),
+                      make_tuple(3, 4, variance8x16_sse2),
+                      make_tuple(4, 3, variance16x8_sse2),
+                      make_tuple(4, 4, variance16x16_sse2),
+                      make_tuple(4, 5, variance16x32_sse2),
+                      make_tuple(5, 4, variance32x16_sse2),
+                      make_tuple(5, 5, variance32x32_sse2),
+                      make_tuple(5, 6, variance32x64_sse2),
+                      make_tuple(6, 5, variance64x32_sse2),
+                      make_tuple(6, 6, variance64x64_sse2)));
+
+const vp9_subpixvariance_fn_t subpel_variance4x4_sse =
+    vp9_sub_pixel_variance4x4_sse;
+const vp9_subpixvariance_fn_t subpel_variance4x8_sse =
+    vp9_sub_pixel_variance4x8_sse;
+const vp9_subpixvariance_fn_t subpel_variance8x4_sse2 =
+    vp9_sub_pixel_variance8x4_sse2;
+const vp9_subpixvariance_fn_t subpel_variance8x8_sse2 =
+    vp9_sub_pixel_variance8x8_sse2;
+const vp9_subpixvariance_fn_t subpel_variance8x16_sse2 =
+    vp9_sub_pixel_variance8x16_sse2;
+const vp9_subpixvariance_fn_t subpel_variance16x8_sse2 =
+    vp9_sub_pixel_variance16x8_sse2;
+const vp9_subpixvariance_fn_t subpel_variance16x16_sse2 =
+    vp9_sub_pixel_variance16x16_sse2;
+const vp9_subpixvariance_fn_t subpel_variance16x32_sse2 =
+    vp9_sub_pixel_variance16x32_sse2;
+const vp9_subpixvariance_fn_t subpel_variance32x16_sse2 =
+    vp9_sub_pixel_variance32x16_sse2;
+const vp9_subpixvariance_fn_t subpel_variance32x32_sse2 =
+    vp9_sub_pixel_variance32x32_sse2;
+const vp9_subpixvariance_fn_t subpel_variance32x64_sse2 =
+    vp9_sub_pixel_variance32x64_sse2;
+const vp9_subpixvariance_fn_t subpel_variance64x32_sse2 =
+    vp9_sub_pixel_variance64x32_sse2;
+const vp9_subpixvariance_fn_t subpel_variance64x64_sse2 =
+    vp9_sub_pixel_variance64x64_sse2;
+INSTANTIATE_TEST_CASE_P(
+    SSE2, VP9SubpelVarianceTest,
+    ::testing::Values(make_tuple(2, 2, subpel_variance4x4_sse),
+                      make_tuple(2, 3, subpel_variance4x8_sse),
+                      make_tuple(3, 2, subpel_variance8x4_sse2),
+                      make_tuple(3, 3, subpel_variance8x8_sse2),
+                      make_tuple(3, 4, subpel_variance8x16_sse2),
+                      make_tuple(4, 3, subpel_variance16x8_sse2),
+                      make_tuple(4, 4, subpel_variance16x16_sse2),
+                      make_tuple(4, 5, subpel_variance16x32_sse2),
+                      make_tuple(5, 4, subpel_variance32x16_sse2),
+                      make_tuple(5, 5, subpel_variance32x32_sse2),
+                      make_tuple(5, 6, subpel_variance32x64_sse2),
+                      make_tuple(6, 5, subpel_variance64x32_sse2),
+                      make_tuple(6, 6, subpel_variance64x64_sse2)));
+#endif
+
+#if HAVE_SSSE3
+const vp9_subpixvariance_fn_t subpel_variance4x4_ssse3 =
+    vp9_sub_pixel_variance4x4_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance4x8_ssse3 =
+    vp9_sub_pixel_variance4x8_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance8x4_ssse3 =
+    vp9_sub_pixel_variance8x4_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance8x8_ssse3 =
+    vp9_sub_pixel_variance8x8_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance8x16_ssse3 =
+    vp9_sub_pixel_variance8x16_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance16x8_ssse3 =
+    vp9_sub_pixel_variance16x8_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance16x16_ssse3 =
+    vp9_sub_pixel_variance16x16_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance16x32_ssse3 =
+    vp9_sub_pixel_variance16x32_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance32x16_ssse3 =
+    vp9_sub_pixel_variance32x16_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance32x32_ssse3 =
+    vp9_sub_pixel_variance32x32_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance32x64_ssse3 =
+    vp9_sub_pixel_variance32x64_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance64x32_ssse3 =
+    vp9_sub_pixel_variance64x32_ssse3;
+const vp9_subpixvariance_fn_t subpel_variance64x64_ssse3 =
+    vp9_sub_pixel_variance64x64_ssse3;
+INSTANTIATE_TEST_CASE_P(
+    SSSE3, VP9SubpelVarianceTest,
+    ::testing::Values(make_tuple(2, 2, subpel_variance4x4_ssse3),
+                      make_tuple(2, 3, subpel_variance4x8_ssse3),
+                      make_tuple(3, 2, subpel_variance8x4_ssse3),
+                      make_tuple(3, 3, subpel_variance8x8_ssse3),
+                      make_tuple(3, 4, subpel_variance8x16_ssse3),
+                      make_tuple(4, 3, subpel_variance16x8_ssse3),
+                      make_tuple(4, 4, subpel_variance16x16_ssse3),
+                      make_tuple(4, 5, subpel_variance16x32_ssse3),
+                      make_tuple(5, 4, subpel_variance32x16_ssse3),
+                      make_tuple(5, 5, subpel_variance32x32_ssse3),
+                      make_tuple(5, 6, subpel_variance32x64_ssse3),
+                      make_tuple(6, 5, subpel_variance64x32_ssse3),
+                      make_tuple(6, 6, subpel_variance64x64_ssse3)));
 #endif
 #endif  // CONFIG_VP9_ENCODER