Add SSE2 versions of av1_fht8x16 and av1_fht16x8

Encoder speedup ~2% with ext-tx + rect-tx

Change-Id: Id56ddf102a887de31d181bde6d8ef8c4f03da945
This commit is contained in:
Geza Lore
2016-09-02 16:05:53 +01:00
committed by Debargha Mukherjee
parent e51ee021dc
commit 1a800f6539
8 changed files with 647 additions and 172 deletions

View File

@@ -137,7 +137,7 @@ class TransformTestBase {
// The minimum quant value is 4.
for (int j = 0; j < num_coeffs_; ++j) {
EXPECT_EQ(output_block[j], output_ref_block[j])
ASSERT_EQ(output_block[j], output_ref_block[j])
<< "Error: not bit-exact result at index: " << j
<< " at test block: " << i;
}