rv34: DC-only inverse transform

When decoding coefficients, detect whether the block is DC-only, and take
advantage of this knowledge to perform DC-only inverse transform.

This is achieved by:
- first, changing the 108x4 element modulo_three_table into a 108 element
  table (kind of base4), and accessing each value using mask and shifts.
- then, checking low bits for 0 (as they represent the presence of higher
  frequency coefficients)

Also provide x86 SIMD code for the DC-only inverse transform.

Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>

1 files changed, 16 insertions, 28 deletions

diff --git a/libavcodec/rv34data.h b/libavcodec/rv34data.h
index fa41a882a6..41c5b20ad7 100644
--- a/libavcodec/rv34data.h
+++ b/libavcodec/rv34data.h
@@ -50,34 +50,22 @@ static const uint8_t rv34_cbp_code[16] = {
  * A lot of four-tuples in RV40 are represented as c0*27+c1*9+c2*3+c3.
  * This table allows conversion from a value back to a vector.
  */
-static const uint8_t modulo_three_table[108][4] = {
- { 0, 0, 0, 0 }, { 0, 0, 0, 1 }, { 0, 0, 0, 2 }, { 0, 0, 1, 0 },
- { 0, 0, 1, 1 }, { 0, 0, 1, 2 }, { 0, 0, 2, 0 }, { 0, 0, 2, 1 },
- { 0, 0, 2, 2 }, { 0, 1, 0, 0 }, { 0, 1, 0, 1 }, { 0, 1, 0, 2 },
- { 0, 1, 1, 0 }, { 0, 1, 1, 1 }, { 0, 1, 1, 2 }, { 0, 1, 2, 0 },
- { 0, 1, 2, 1 }, { 0, 1, 2, 2 }, { 0, 2, 0, 0 }, { 0, 2, 0, 1 },
- { 0, 2, 0, 2 }, { 0, 2, 1, 0 }, { 0, 2, 1, 1 }, { 0, 2, 1, 2 },
- { 0, 2, 2, 0 }, { 0, 2, 2, 1 }, { 0, 2, 2, 2 }, { 1, 0, 0, 0 },
- { 1, 0, 0, 1 }, { 1, 0, 0, 2 }, { 1, 0, 1, 0 }, { 1, 0, 1, 1 },
- { 1, 0, 1, 2 }, { 1, 0, 2, 0 }, { 1, 0, 2, 1 }, { 1, 0, 2, 2 },
- { 1, 1, 0, 0 }, { 1, 1, 0, 1 }, { 1, 1, 0, 2 }, { 1, 1, 1, 0 },
- { 1, 1, 1, 1 }, { 1, 1, 1, 2 }, { 1, 1, 2, 0 }, { 1, 1, 2, 1 },
- { 1, 1, 2, 2 }, { 1, 2, 0, 0 }, { 1, 2, 0, 1 }, { 1, 2, 0, 2 },
- { 1, 2, 1, 0 }, { 1, 2, 1, 1 }, { 1, 2, 1, 2 }, { 1, 2, 2, 0 },
- { 1, 2, 2, 1 }, { 1, 2, 2, 2 }, { 2, 0, 0, 0 }, { 2, 0, 0, 1 },
- { 2, 0, 0, 2 }, { 2, 0, 1, 0 }, { 2, 0, 1, 1 }, { 2, 0, 1, 2 },
- { 2, 0, 2, 0 }, { 2, 0, 2, 1 }, { 2, 0, 2, 2 }, { 2, 1, 0, 0 },
- { 2, 1, 0, 1 }, { 2, 1, 0, 2 }, { 2, 1, 1, 0 }, { 2, 1, 1, 1 },
- { 2, 1, 1, 2 }, { 2, 1, 2, 0 }, { 2, 1, 2, 1 }, { 2, 1, 2, 2 },
- { 2, 2, 0, 0 }, { 2, 2, 0, 1 }, { 2, 2, 0, 2 }, { 2, 2, 1, 0 },
- { 2, 2, 1, 1 }, { 2, 2, 1, 2 }, { 2, 2, 2, 0 }, { 2, 2, 2, 1 },
- { 2, 2, 2, 2 }, { 3, 0, 0, 0 }, { 3, 0, 0, 1 }, { 3, 0, 0, 2 },
- { 3, 0, 1, 0 }, { 3, 0, 1, 1 }, { 3, 0, 1, 2 }, { 3, 0, 2, 0 },
- { 3, 0, 2, 1 }, { 3, 0, 2, 2 }, { 3, 1, 0, 0 }, { 3, 1, 0, 1 },
- { 3, 1, 0, 2 }, { 3, 1, 1, 0 }, { 3, 1, 1, 1 }, { 3, 1, 1, 2 },
- { 3, 1, 2, 0 }, { 3, 1, 2, 1 }, { 3, 1, 2, 2 }, { 3, 2, 0, 0 },
- { 3, 2, 0, 1 }, { 3, 2, 0, 2 }, { 3, 2, 1, 0 }, { 3, 2, 1, 1 },
- { 3, 2, 1, 2 }, { 3, 2, 2, 0 }, { 3, 2, 2, 1 }, { 3, 2, 2, 2 },
+static const uint8_t modulo_three_table[108] = {
+    0x00, 0x01, 0x02, 0x04, 0x05, 0x06, 0x08, 0x09, 0x0A,
+    0x10, 0x11, 0x12, 0x14, 0x15, 0x16, 0x18, 0x19, 0x1A,
+    0x20, 0x21, 0x22, 0x24, 0x25, 0x26, 0x28, 0x29, 0x2A,
+
+    0x40, 0x41, 0x42, 0x44, 0x45, 0x46, 0x48, 0x49, 0x4A,
+    0x50, 0x51, 0x52, 0x54, 0x55, 0x56, 0x58, 0x59, 0x5A,
+    0x60, 0x61, 0x62, 0x64, 0x65, 0x66, 0x68, 0x69, 0x6A,
+
+    0x80, 0x81, 0x82, 0x84, 0x85, 0x86, 0x88, 0x89, 0x8A,
+    0x90, 0x91, 0x92, 0x94, 0x95, 0x96, 0x98, 0x99, 0x9A,
+    0xA0, 0xA1, 0xA2, 0xA4, 0xA5, 0xA6, 0xA8, 0xA9, 0xAA,
+
+    0xC0, 0xC1, 0xC2, 0xC4, 0xC5, 0xC6, 0xC8, 0xC9, 0xCA,
+    0xD0, 0xD1, 0xD2, 0xD4, 0xD5, 0xD6, 0xD8, 0xD9, 0xDA,
+    0xE0, 0xE1, 0xE2, 0xE4, 0xE5, 0xE6, 0xE8, 0xE9, 0xEA,
 };
 
 /**