Message ID | 20221012142300.16833-1-xry111@xry111.site |
---|---|
State | New |
Headers | show |
Series | LoongArch: implement count_{leading,trailing}_zeros | expand |
Looks good to me! Thanks! 在 2022/10/12 下午10:23, Xi Ruoyao 写道: > LoongArch always support clz and ctz instructions, so we can always use > __builtin_{clz,ctz} for count_{leading,trailing}_zeros. This improves > the code of libgcc, and also benefits Glibc once we merge longlong.h > there. > > Bootstrapped and regtested on loongarch64-linux-gnu. > > include/ChangeLog: > > * longlong.h [__loongarch__] (count_leading_zeros): Define. > [__loongarch__] (count_trailing_zeros): Likewise. > [__loongarch__] (COUNT_LEADING_ZEROS_0): Likewise. > --- > include/longlong.h | 12 ++++++++++++ > 1 file changed, 12 insertions(+) > > diff --git a/include/longlong.h b/include/longlong.h > index 64a7b10f9b2..c3a6f1e7eaa 100644 > --- a/include/longlong.h > +++ b/include/longlong.h > @@ -593,6 +593,18 @@ extern UDItype __umulsidi3 (USItype, USItype); > #define UMUL_TIME 14 > #endif > > +#ifdef __loongarch__ > +# if W_TYPE_SIZE == 32 > +# define count_leading_zeros(count, x) ((count) = __builtin_clz (x)) > +# define count_trailing_zeros(count, x) ((count) = __builtin_ctz (x)) > +# define COUNT_LEADING_ZEROS_0 32 > +# elif W_TYPE_SIZE == 64 > +# define count_leading_zeros(count, x) ((count) = __builtin_clzll (x)) > +# define count_trailing_zeros(count, x) ((count) = __builtin_ctzll (x)) > +# define COUNT_LEADING_ZEROS_0 64 > +# endif > +#endif > + > #if defined (__M32R__) && W_TYPE_SIZE == 32 > #define add_ssaaaa(sh, sl, ah, al, bh, bl) \ > /* The cmp clears the condition bit. */ \
On Thu, 2022-10-13 at 16:43 +0800, Lulu Cheng wrote: > Looks good to me! > > Thanks! Pushed r13-3269. > > 在 2022/10/12 下午10:23, Xi Ruoyao 写道: > > LoongArch always support clz and ctz instructions, so we can always > > use > > __builtin_{clz,ctz} for count_{leading,trailing}_zeros. This > > improves > > the code of libgcc, and also benefits Glibc once we merge longlong.h > > there. > > > > Bootstrapped and regtested on loongarch64-linux-gnu. > > > > include/ChangeLog: > > > > * longlong.h [__loongarch__] (count_leading_zeros): Define. > > [__loongarch__] (count_trailing_zeros): Likewise. > > [__loongarch__] (COUNT_LEADING_ZEROS_0): Likewise. > > --- > > include/longlong.h | 12 ++++++++++++ > > 1 file changed, 12 insertions(+) > > > > diff --git a/include/longlong.h b/include/longlong.h > > index 64a7b10f9b2..c3a6f1e7eaa 100644 > > --- a/include/longlong.h > > +++ b/include/longlong.h > > @@ -593,6 +593,18 @@ extern UDItype __umulsidi3 (USItype, USItype); > > #define UMUL_TIME 14 > > #endif > > > > +#ifdef __loongarch__ > > +# if W_TYPE_SIZE == 32 > > +# define count_leading_zeros(count, x) ((count) = __builtin_clz > > (x)) > > +# define count_trailing_zeros(count, x) ((count) = __builtin_ctz > > (x)) > > +# define COUNT_LEADING_ZEROS_0 32 > > +# elif W_TYPE_SIZE == 64 > > +# define count_leading_zeros(count, x) ((count) = __builtin_clzll > > (x)) > > +# define count_trailing_zeros(count, x) ((count) = __builtin_ctzll > > (x)) > > +# define COUNT_LEADING_ZEROS_0 64 > > +# endif > > +#endif > > + > > #if defined (__M32R__) && W_TYPE_SIZE == 32 > > #define add_ssaaaa(sh, sl, ah, al, bh, bl) \ > > /* The cmp clears the condition bit. */ \ >
diff --git a/include/longlong.h b/include/longlong.h index 64a7b10f9b2..c3a6f1e7eaa 100644 --- a/include/longlong.h +++ b/include/longlong.h @@ -593,6 +593,18 @@ extern UDItype __umulsidi3 (USItype, USItype); #define UMUL_TIME 14 #endif +#ifdef __loongarch__ +# if W_TYPE_SIZE == 32 +# define count_leading_zeros(count, x) ((count) = __builtin_clz (x)) +# define count_trailing_zeros(count, x) ((count) = __builtin_ctz (x)) +# define COUNT_LEADING_ZEROS_0 32 +# elif W_TYPE_SIZE == 64 +# define count_leading_zeros(count, x) ((count) = __builtin_clzll (x)) +# define count_trailing_zeros(count, x) ((count) = __builtin_ctzll (x)) +# define COUNT_LEADING_ZEROS_0 64 +# endif +#endif + #if defined (__M32R__) && W_TYPE_SIZE == 32 #define add_ssaaaa(sh, sl, ah, al, bh, bl) \ /* The cmp clears the condition bit. */ \