[Bug target/96789] x264: sub4x4_dct() improves when vectorization is disabled

[linkw at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96789

--- Comment #27 from Kewen Lin <linkw at gcc dot gnu.org> ---
(In reply to Hongtao.liu from comment #22)
> >One of my workmates found that if we disable vectorization for SPEC2017 >525.x264_r function sub4x4_dct in source file x264_src/common/dct.c with ?>explicit function attribute __attribute__((optimize("no-tree-vectorize"))), it >can speed up by 4%.
> 
> For CLX, if we disable slp vectorization in sub4x4_dct by 
> __attribute__((optimize("no-tree-slp-vectorize"))), it can also speed up by
> 4%.
> 
> > Thanks Richi! Should we take care of this case? or neglect this kind of
> > extension as "no instruction"? I was intent to handle it in target specific
> > code, but it isn't recorded into cost vector while it seems too heavy to do
> > the bb_info slp_instances revisits in finish_cost.
> 
> For i386 backend unsigned char --> unsigned short is no "no instruction",

Thanks for the information, it means it's target specific.

> but in this case
> ---
> 1033  _134 = MEM[(pixel *)pix1_295 + 2B];                                   
> 
> 1034  _135 = (short unsigned int) _134;
> ---
> 
> It could be combined and optimized to 
> ---
> movzbl  19(%rcx), %r8d
> ---
> 
> So, if "unsigned char" variable is loaded from memory, then the convertion
> would also be "no instruction", i'm not sure if backend cost model could
> handle such situation.

Probably you can try to tweak it in ix86_add_stmt_cost? when the statement is
UB to UH conversion statement, further check if the def of the input UB is MEM.