Scott LaVarnway 3bf02ad74a vpx: hadamard: use ptrdiff_t instead of int for stride ...

Eliminates the following instruction for the x86 (64 bit)
intrinsic code:

movslq %esi,%rax

Change-Id: I8f5ebd40726f998708a668b0f52ea7a0576befae

2017-10-26 11:41:48 -07:00

..

bitdepth_conversion_vsx.h

Add Hadamard for Power8

2017-03-15 23:46:18 -03:00

hadamard_vsx.c

vpx: hadamard: use ptrdiff_t instead of int for stride

2017-10-26 11:41:48 -07:00

intrapred_vsx.c

ppc: h predictor 8x8

2017-04-19 19:57:51 -07:00

inv_txfm_vsx.c

ppc: Add vpx_idct32x32_1024_add_vsx

2017-09-30 19:31:20 +00:00

sad_vsx.c

ppc: Add vpx_sadnxmx4d_vsx for n,m = {8, 16, 32 ,64}

2017-05-24 13:27:09 +00:00

transpose_vsx.h

Add Hadamard for Power8

2017-03-15 23:46:18 -03:00

types_vsx.h

ppc: d45 predictor 8x8

2017-04-19 19:57:51 -07:00

variance_vsx.c

ppc: Add get_mb_ss_vsx

2017-05-12 17:23:00 +02:00

vpx_convolve_vsx.c

Remove get_filter_base() and get_filter_offset() in convolve

2017-09-05 15:22:36 -07:00