Partial IDCT 16x16 avx2
- Function level improvement:
functions sse2 avx2 percentage
idct16x16_256 365 226 38%
idct16x16_38 n/a 136 n/a
idct16x16_10 171 110 35%
idct16x16_1 34 26 23%
- Integrated in AV1 for default scan order.
Change-Id: Ieb1a8e730bea9c371ebc0e5f4a748640d8f5e921
diff --git a/aom_dsp/aom_dsp.cmake b/aom_dsp/aom_dsp.cmake
index f00348c..75ee564 100644
--- a/aom_dsp/aom_dsp.cmake
+++ b/aom_dsp/aom_dsp.cmake
@@ -62,8 +62,10 @@
set(AOM_DSP_COMMON_INTRIN_AVX2
"${AOM_ROOT}/aom_dsp/x86/aom_subpixel_8t_intrin_avx2.c"
- "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_avx2.c"
- "${AOM_ROOT}/aom_dsp/x86/loopfilter_avx2.c")
+ "${AOM_ROOT}/aom_dsp/x86/loopfilter_avx2.c"
+ "${AOM_ROOT}/aom_dsp/x86/inv_txfm_avx2.c"
+ "${AOM_ROOT}/aom_dsp/x86/inv_txfm_common_avx2.h"
+ "${AOM_ROOT}/aom_dsp/x86/txfm_common_avx2.h")
set(AOM_DSP_COMMON_ASM_NEON
"${AOM_ROOT}/aom_dsp/arm/aom_convolve8_avg_neon_asm.asm"
@@ -282,6 +284,9 @@
set(AOM_DSP_ENCODER_ASM_SSE4_1 "${AOM_ROOT}/aom_dsp/x86/sad_sse4.asm")
set(AOM_DSP_ENCODER_INTRIN_AVX2
+ "${AOM_ROOT}/aom_dsp/x86/fwd_dct32x32_impl_avx2.h"
+ "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_avx2.c"
+ "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_avx2.h"
"${AOM_ROOT}/aom_dsp/x86/sad4d_avx2.c"
"${AOM_ROOT}/aom_dsp/x86/sad_avx2.c"
"${AOM_ROOT}/aom_dsp/x86/sad_impl_avx2.c"