[x265] [PATCH] IDCT: C code optimization as per new interface
praveen at multicorewareinc.com
praveen at multicorewareinc.com
Tue Oct 28 13:11:21 CET 2014
# HG changeset patch
# User Praveen Tiwari
# Date 1414492528 -19800
# Node ID b94b25c88de7cd7df4e2f3c223e2e229488b7d54
# Parent be9f280c503f7128b8e7f6aff5e983c76f3796c0
IDCT: C code optimization as per new interface
diff -r be9f280c503f -r b94b25c88de7 source/common/dct.cpp
--- a/source/common/dct.cpp Tue Oct 28 15:41:06 2014 +0530
+++ b/source/common/dct.cpp Tue Oct 28 16:05:28 2014 +0530
@@ -530,18 +530,7 @@
ALIGN_VAR_32(int16_t, coef[4 * 4]);
ALIGN_VAR_32(int16_t, block[4 * 4]);
-#define N (4)
- for (int i = 0; i < N; i++)
- {
- for (int j = 0; j < N; j++)
- {
- block[i * N + j] = (int16_t)src[i * N + j];
- }
- }
-
-#undef N
-
- partialButterflyInverse4(block, coef, shift_1st, 4); // Forward DST BY FAST ALGORITHM, block input, coef output
+ partialButterflyInverse4(src, coef, shift_1st, 4); // Forward DST BY FAST ALGORITHM, block input, coef output
partialButterflyInverse4(coef, block, shift_2nd, 4); // Forward DST BY FAST ALGORITHM, coef input, coeff output
for (int i = 0; i < 4; i++)
@@ -558,18 +547,7 @@
ALIGN_VAR_32(int16_t, coef[8 * 8]);
ALIGN_VAR_32(int16_t, block[8 * 8]);
-#define N (8)
- for (int i = 0; i < N; i++)
- {
- for (int j = 0; j < N; j++)
- {
- block[i * N + j] = (int16_t)src[i * N + j];
- }
- }
-
-#undef N
-
- partialButterflyInverse8(block, coef, shift_1st, 8);
+ partialButterflyInverse8(src, coef, shift_1st, 8);
partialButterflyInverse8(coef, block, shift_2nd, 8);
for (int i = 0; i < 8; i++)
{
@@ -585,18 +563,7 @@
ALIGN_VAR_32(int16_t, coef[16 * 16]);
ALIGN_VAR_32(int16_t, block[16 * 16]);
-#define N (16)
- for (int i = 0; i < N; i++)
- {
- for (int j = 0; j < N; j++)
- {
- block[i * N + j] = (int16_t)src[i * N + j];
- }
- }
-
-#undef N
-
- partialButterflyInverse16(block, coef, shift_1st, 16);
+ partialButterflyInverse16(src, coef, shift_1st, 16);
partialButterflyInverse16(coef, block, shift_2nd, 16);
for (int i = 0; i < 16; i++)
{
@@ -612,18 +579,7 @@
ALIGN_VAR_32(int16_t, coef[32 * 32]);
ALIGN_VAR_32(int16_t, block[32 * 32]);
-#define N (32)
- for (int i = 0; i < N; i++)
- {
- for (int j = 0; j < N; j++)
- {
- block[i * N + j] = (int16_t)src[i * N + j];
- }
- }
-
-#undef N
-
- partialButterflyInverse32(block, coef, shift_1st, 32);
+ partialButterflyInverse32(src, coef, shift_1st, 32);
partialButterflyInverse32(coef, block, shift_2nd, 32);
for (int i = 0; i < 32; i++)
More information about the x265-devel
mailing list