libvpx: Pull from upstream

source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c

Index: source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c
diff --git a/source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c b/source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c
index 4e80b255e88fb318e31f25b504d380d46fb6afe7..4672aa6b8cf2300d123ebbae22a1daf8b2112490 100644
--- a/source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c
+++ b/source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c
@@ -11,6 +11,83 @@
 #include <emmintrin.h>
 #include "vpx_ports/mem.h"
 
+void vp9_minmax_8x8_sse2(const uint8_t *s, int p, const uint8_t *d, int dp,
+                         int *min, int *max) {
+  __m128i u0, s0, d0, diff, maxabsdiff, minabsdiff, negdiff, absdiff0, absdiff;
+  u0  = _mm_setzero_si128();
+  // Row 0
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff0 = _mm_max_epi16(diff, negdiff);
+  // Row 1
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(absdiff0, absdiff);
+  minabsdiff = _mm_min_epi16(absdiff0, absdiff);
+  // Row 2
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 2 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 2 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+  // Row 3
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 3 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 3 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+  // Row 4
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 4 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 4 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+  // Row 5
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 5 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 5 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+  // Row 6
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 6 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 6 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+  // Row 7
+  s0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(s + 7 * p)), u0);
+  d0 = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i *)(d + 7 * dp)), u0);
+  diff = _mm_subs_epi16(s0, d0);
+  negdiff = _mm_subs_epi16(u0, diff);
+  absdiff = _mm_max_epi16(diff, negdiff);
+  maxabsdiff = _mm_max_epi16(maxabsdiff, absdiff);
+  minabsdiff = _mm_min_epi16(minabsdiff, absdiff);
+
+  maxabsdiff = _mm_max_epi16(maxabsdiff, _mm_srli_si128(maxabsdiff, 8));
+  maxabsdiff = _mm_max_epi16(maxabsdiff, _mm_srli_epi64(maxabsdiff, 32));
+  maxabsdiff = _mm_max_epi16(maxabsdiff, _mm_srli_epi64(maxabsdiff, 16));
+  *max = _mm_extract_epi16(maxabsdiff, 0);
+
+  minabsdiff = _mm_min_epi16(minabsdiff, _mm_srli_si128(minabsdiff, 8));
+  minabsdiff = _mm_min_epi16(minabsdiff, _mm_srli_epi64(minabsdiff, 32));
+  minabsdiff = _mm_min_epi16(minabsdiff, _mm_srli_epi64(minabsdiff, 16));
+  *min = _mm_extract_epi16(minabsdiff, 0);
+}
 
 unsigned int vp9_avg_8x8_sse2(const uint8_t *s, int p) {
   __m128i s0, s1, u0;
@@ -57,6 +134,179 @@ unsigned int vp9_avg_4x4_sse2(const uint8_t *s, int p) {
   return (avg + 8) >> 4;
 }
 
+static void hadamard_col8_sse2(__m128i *in, int iter) {
+  __m128i a0 = in[0];
+  __m128i a1 = in[1];
+  __m128i a2 = in[2];
+  __m128i a3 = in[3];
+  __m128i a4 = in[4];
+  __m128i a5 = in[5];
+  __m128i a6 = in[6];
+  __m128i a7 = in[7];
+
+  __m128i b0 = _mm_add_epi16(a0, a1);
+  __m128i b1 = _mm_sub_epi16(a0, a1);
+  __m128i b2 = _mm_add_epi16(a2, a3);
+  __m128i b3 = _mm_sub_epi16(a2, a3);
+  __m128i b4 = _mm_add_epi16(a4, a5);
+  __m128i b5 = _mm_sub_epi16(a4, a5);
+  __m128i b6 = _mm_add_epi16(a6, a7);
+  __m128i b7 = _mm_sub_epi16(a6, a7);
+
+  a0 = _mm_add_epi16(b0, b2);
+  a1 = _mm_add_epi16(b1, b3);
+  a2 = _mm_sub_epi16(b0, b2);
+  a3 = _mm_sub_epi16(b1, b3);
+  a4 = _mm_add_epi16(b4, b6);
+  a5 = _mm_add_epi16(b5, b7);
+  a6 = _mm_sub_epi16(b4, b6);
+  a7 = _mm_sub_epi16(b5, b7);
+
+  if (iter == 0) {
+    b0 = _mm_add_epi16(a0, a4);
+    b7 = _mm_add_epi16(a1, a5);
+    b3 = _mm_add_epi16(a2, a6);
+    b4 = _mm_add_epi16(a3, a7);
+    b2 = _mm_sub_epi16(a0, a4);
+    b6 = _mm_sub_epi16(a1, a5);
+    b1 = _mm_sub_epi16(a2, a6);
+    b5 = _mm_sub_epi16(a3, a7);
+
+    a0 = _mm_unpacklo_epi16(b0, b1);
+    a1 = _mm_unpacklo_epi16(b2, b3);
+    a2 = _mm_unpackhi_epi16(b0, b1);
+    a3 = _mm_unpackhi_epi16(b2, b3);
+    a4 = _mm_unpacklo_epi16(b4, b5);
+    a5 = _mm_unpacklo_epi16(b6, b7);
+    a6 = _mm_unpackhi_epi16(b4, b5);
+    a7 = _mm_unpackhi_epi16(b6, b7);
+
+    b0 = _mm_unpacklo_epi32(a0, a1);
+    b1 = _mm_unpacklo_epi32(a4, a5);
+    b2 = _mm_unpackhi_epi32(a0, a1);
+    b3 = _mm_unpackhi_epi32(a4, a5);
+    b4 = _mm_unpacklo_epi32(a2, a3);
+    b5 = _mm_unpacklo_epi32(a6, a7);
+    b6 = _mm_unpackhi_epi32(a2, a3);
+    b7 = _mm_unpackhi_epi32(a6, a7);
+
+    in[0] = _mm_unpacklo_epi64(b0, b1);
+    in[1] = _mm_unpackhi_epi64(b0, b1);
+    in[2] = _mm_unpacklo_epi64(b2, b3);
+    in[3] = _mm_unpackhi_epi64(b2, b3);
+    in[4] = _mm_unpacklo_epi64(b4, b5);
+    in[5] = _mm_unpackhi_epi64(b4, b5);
+    in[6] = _mm_unpacklo_epi64(b6, b7);
+    in[7] = _mm_unpackhi_epi64(b6, b7);
+  } else {
+    in[0] = _mm_add_epi16(a0, a4);
+    in[7] = _mm_add_epi16(a1, a5);
+    in[3] = _mm_add_epi16(a2, a6);
+    in[4] = _mm_add_epi16(a3, a7);
+    in[2] = _mm_sub_epi16(a0, a4);
+    in[6] = _mm_sub_epi16(a1, a5);
+    in[1] = _mm_sub_epi16(a2, a6);
+    in[5] = _mm_sub_epi16(a3, a7);
+  }
+}
+
+void vp9_hadamard_8x8_sse2(int16_t const *src_diff, int src_stride,
+                           int16_t *coeff) {
+  __m128i src[8];
+  src[0] = _mm_load_si128((const __m128i *)src_diff);
+  src[1] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[2] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[3] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[4] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[5] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[6] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+  src[7] = _mm_load_si128((const __m128i *)(src_diff += src_stride));
+
+  hadamard_col8_sse2(src, 0);
+  hadamard_col8_sse2(src, 1);
+
+  _mm_store_si128((__m128i *)coeff, src[0]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[1]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[2]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[3]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[4]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[5]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[6]);
+  coeff += 8;
+  _mm_store_si128((__m128i *)coeff, src[7]);
+}
+
+void vp9_hadamard_16x16_sse2(int16_t const *src_diff, int src_stride,
+                             int16_t *coeff) {
+  int idx;
+  for (idx = 0; idx < 4; ++idx) {
+    int16_t const *src_ptr = src_diff + (idx >> 1) * 8 * src_stride
+                                + (idx & 0x01) * 8;
+    vp9_hadamard_8x8_sse2(src_ptr, src_stride, coeff + idx * 64);
+  }
+
+  for (idx = 0; idx < 64; idx += 8) {
+    __m128i coeff0 = _mm_load_si128((const __m128i *)coeff);
+    __m128i coeff1 = _mm_load_si128((const __m128i *)(coeff + 64));
+    __m128i coeff2 = _mm_load_si128((const __m128i *)(coeff + 128));
+    __m128i coeff3 = _mm_load_si128((const __m128i *)(coeff + 192));
+
+    __m128i b0 = _mm_add_epi16(coeff0, coeff1);
+    __m128i b1 = _mm_sub_epi16(coeff0, coeff1);
+    __m128i b2 = _mm_add_epi16(coeff2, coeff3);
+    __m128i b3 = _mm_sub_epi16(coeff2, coeff3);
+
+    coeff0 = _mm_add_epi16(b0, b2);
+    coeff1 = _mm_add_epi16(b1, b3);
+    coeff0 = _mm_srai_epi16(coeff0, 1);
+    coeff1 = _mm_srai_epi16(coeff1, 1);
+    _mm_store_si128((__m128i *)coeff, coeff0);
+    _mm_store_si128((__m128i *)(coeff + 64), coeff1);
+
+    coeff2 = _mm_sub_epi16(b0, b2);
+    coeff3 = _mm_sub_epi16(b1, b3);
+    coeff2 = _mm_srai_epi16(coeff2, 1);
+    coeff3 = _mm_srai_epi16(coeff3, 1);
+    _mm_store_si128((__m128i *)(coeff + 128), coeff2);
+    _mm_store_si128((__m128i *)(coeff + 192), coeff3);
+
+    coeff += 8;
+  }
+}
+
+int16_t vp9_satd_sse2(const int16_t *coeff, int length) {
+  int i;
+  __m128i sum = _mm_load_si128((const __m128i *)coeff);
+  __m128i sign = _mm_srai_epi16(sum, 15);
+  __m128i val = _mm_xor_si128(sum, sign);
+  sum = _mm_sub_epi16(val, sign);
+  coeff += 8;
+
+  for (i = 8; i < length; i += 8) {
+    __m128i src_line = _mm_load_si128((const __m128i *)coeff);
+    sign = _mm_srai_epi16(src_line, 15);
+    val = _mm_xor_si128(src_line, sign);
+    val = _mm_sub_epi16(val, sign);
+    sum = _mm_add_epi16(sum, val);
+    coeff += 8;
+  }
+
+  val = _mm_srli_si128(sum, 8);
+  sum = _mm_add_epi16(sum, val);
+  val = _mm_srli_epi64(sum, 32);
+  sum = _mm_add_epi16(sum, val);
+  val = _mm_srli_epi32(sum, 16);
+  sum = _mm_add_epi16(sum, val);
+
+  return _mm_extract_epi16(sum, 0);
+}
+
 void vp9_int_pro_row_sse2(int16_t *hbuf, uint8_t const*ref,
                           const int ref_stride, const int height) {
   int idx;