[PATCH 0/2] LoongArch: Add optimized functions.

[Xi Ruoyao]

On Wed, 2022-09-28 at 07:22 -0700, Richard Henderson wrote:
> On 9/26/22 06:49, Xi Ruoyao via Libc-alpha wrote:
> > Hi Adhemerval and Jianbo,
> > 
> > I've customized string-fzi.h and string-maskoff.h for LoongArch (see
> > attachment).  With them on top of Adhermerval's v5 "Improve generic
> > string routines" patch and GCC & Binutils trunk, the benchmark result
> > seems comparable with the assembly version for strchr, strcmp, and
> > strchrnul.

Hi Richard,

> There is nothing in string-maskoff.h that the compiler should not be able to produce 
> itself from the generic version.  Having a brief look, the compiler simply needs to be 
> improved to unify two current AND patterns (which is an existing bug) and add the 
> additional case for bstrins.d.

Added GCC LoongArch port maintainer into Cc:.

It's actually more complicated.  Without the inline assembly in
repeat_bytes(), the compiler does not hoist the 4-instruction 64-bit
immediate load sequence out of a loop for "some reason I don't know
yet".

> Similarly, there is nothing in string-fzi.h that should not be gotten from longlong.h; 
> your only changes are to use __builtin_clz, which longlong.h exports as count_trailing_zeros.

No, it does not.  By default longlong.h uses a table driven approach for
count_{trailing,leading}_zeros.  I can add __loongarch__ (or
__loongarch_lp64) into longlong.h though.  IIUC I need to submit the
change to GCC, then Glibc merges longlong.h from GCC, right?

-- 
Xi Ruoyao <xry111@xry111.site>
School of Aerospace Science and Technology, Xidian University