• Janne Grunau's avatar
    aarch64: Faster intra_predict_4x4_h · b16268ac
    Janne Grunau authored
    Use multiplication with 0x01010101 for splats.
    
    On a cortex-a53:
                         gcc 4.9.2   llvm 3.6   neon (before)   neon (after)
    intra_predict_4x4_h: 162         147        160/155         139/135
    b16268ac
Name
Last commit
Last update
..
asm-offsets.c Loading commit data...
asm-offsets.h Loading commit data...
asm.S Loading commit data...
bitstream-a.S Loading commit data...
cabac-a.S Loading commit data...
dct-a.S Loading commit data...
dct.h Loading commit data...
deblock-a.S Loading commit data...
mc-a.S Loading commit data...
mc-c.c Loading commit data...
mc.h Loading commit data...
pixel-a.S Loading commit data...
pixel.h Loading commit data...
predict-a.S Loading commit data...
predict-c.c Loading commit data...
predict.h Loading commit data...
quant-a.S Loading commit data...
quant.h Loading commit data...