LoongArch: Set default alignment for functions and labels with -mtune
Checks
Commit Message
The LA464 micro-architecture is sensitive to alignment of code. The
Loongson team has benchmarked various combinations of function, the
results [1] show that 16-byte label alignment together with 32-byte
function alignment gives best results in terms of SPEC score.
Add a mtune-based table-driven mechanism to set the default of
-falign-{functions,labels}. As LA464 is the first (and the only for
now) uarch supported by GCC, the same setting is also used for
the "generic" -mtune=loongarch64. In the future we may set different
settings for LA{2,3,6}64 once we add the support for them.
Bootstrapped and regtested on loongarch64-linux-gnu. Ok for trunk?
gcc/ChangeLog:
* config/loongarch/loongarch-tune.h (loongarch_align): New
struct.
* config/loongarch/loongarch-def.h (loongarch_cpu_align): New
array.
* config/loongarch/loongarch-def.c (loongarch_cpu_align): Define
the array.
* config/loongarch/loongarch.cc
(loongarch_option_override_internal): Set the value of
-falign-functions= if -falign-functions is enabled but no value
is given. Likewise for -falign-labels=.
---
gcc/config/loongarch/loongarch-def.c | 12 ++++++++++++
gcc/config/loongarch/loongarch-def.h | 1 +
gcc/config/loongarch/loongarch-tune.h | 8 ++++++++
gcc/config/loongarch/loongarch.cc | 6 ++++++
4 files changed, 27 insertions(+)
Comments
LGTM! Thanks!
在 2023/6/14 上午8:43, Xi Ruoyao 写道:
> The LA464 micro-architecture is sensitive to alignment of code. The
> Loongson team has benchmarked various combinations of function, the
> results [1] show that 16-byte label alignment together with 32-byte
> function alignment gives best results in terms of SPEC score.
>
> Add a mtune-based table-driven mechanism to set the default of
> -falign-{functions,labels}. As LA464 is the first (and the only for
> now) uarch supported by GCC, the same setting is also used for
> the "generic" -mtune=loongarch64. In the future we may set different
> settings for LA{2,3,6}64 once we add the support for them.
>
> Bootstrapped and regtested on loongarch64-linux-gnu. Ok for trunk?
>
> gcc/ChangeLog:
>
> * config/loongarch/loongarch-tune.h (loongarch_align): New
> struct.
> * config/loongarch/loongarch-def.h (loongarch_cpu_align): New
> array.
> * config/loongarch/loongarch-def.c (loongarch_cpu_align): Define
> the array.
> * config/loongarch/loongarch.cc
> (loongarch_option_override_internal): Set the value of
> -falign-functions= if -falign-functions is enabled but no value
> is given. Likewise for -falign-labels=.
> ---
> gcc/config/loongarch/loongarch-def.c | 12 ++++++++++++
> gcc/config/loongarch/loongarch-def.h | 1 +
> gcc/config/loongarch/loongarch-tune.h | 8 ++++++++
> gcc/config/loongarch/loongarch.cc | 6 ++++++
> 4 files changed, 27 insertions(+)
>
> diff --git a/gcc/config/loongarch/loongarch-def.c b/gcc/config/loongarch/loongarch-def.c
> index fc4ebbefede..6729c857f7c 100644
> --- a/gcc/config/loongarch/loongarch-def.c
> +++ b/gcc/config/loongarch/loongarch-def.c
> @@ -72,6 +72,18 @@ loongarch_cpu_cache[N_TUNE_TYPES] = {
> },
> };
>
> +struct loongarch_align
> +loongarch_cpu_align[N_TUNE_TYPES] = {
> + [CPU_LOONGARCH64] = {
> + .function = "32",
> + .label = "16",
> + },
> + [CPU_LA464] = {
> + .function = "32",
> + .label = "16",
> + },
> +};
> +
> /* The following properties cannot be looked up directly using "cpucfg".
> So it is necessary to provide a default value for "unknown native"
> tune targets (i.e. -mtune=native while PRID does not correspond to
> diff --git a/gcc/config/loongarch/loongarch-def.h b/gcc/config/loongarch/loongarch-def.h
> index 778b1409956..fb8bb88eb52 100644
> --- a/gcc/config/loongarch/loongarch-def.h
> +++ b/gcc/config/loongarch/loongarch-def.h
> @@ -144,6 +144,7 @@ extern int loongarch_cpu_issue_rate[];
> extern int loongarch_cpu_multipass_dfa_lookahead[];
>
> extern struct loongarch_cache loongarch_cpu_cache[];
> +extern struct loongarch_align loongarch_cpu_align[];
> extern struct loongarch_rtx_cost_data loongarch_cpu_rtx_cost_data[];
>
> #ifdef __cplusplus
> diff --git a/gcc/config/loongarch/loongarch-tune.h b/gcc/config/loongarch/loongarch-tune.h
> index ba31c4f08c3..5c03262daff 100644
> --- a/gcc/config/loongarch/loongarch-tune.h
> +++ b/gcc/config/loongarch/loongarch-tune.h
> @@ -48,4 +48,12 @@ struct loongarch_cache {
> int simultaneous_prefetches; /* number of parallel prefetch */
> };
>
> +/* Alignment for functions and labels for best performance. For new uarchs
> + the value should be measured via benchmarking. See the documentation for
> + -falign-functions and -falign-labels in invoke.texi for the format. */
> +struct loongarch_align {
> + const char *function; /* default value for -falign-functions */
> + const char *label; /* default value for -falign-labels */
> +};
> +
> #endif /* LOONGARCH_TUNE_H */
> diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
> index eb73d11b869..5b8b93eb24b 100644
> --- a/gcc/config/loongarch/loongarch.cc
> +++ b/gcc/config/loongarch/loongarch.cc
> @@ -6249,6 +6249,12 @@ loongarch_option_override_internal (struct gcc_options *opts)
> && !opts->x_optimize_size)
> opts->x_flag_prefetch_loop_arrays = 1;
>
> + if (opts->x_flag_align_functions && !opts->x_str_align_functions)
> + opts->x_str_align_functions = loongarch_cpu_align[LARCH_ACTUAL_TUNE].function;
> +
> + if (opts->x_flag_align_labels && !opts->x_str_align_labels)
> + opts->x_str_align_labels = loongarch_cpu_align[LARCH_ACTUAL_TUNE].label;
> +
> if (TARGET_DIRECT_EXTERN_ACCESS && flag_shlib)
> error ("%qs cannot be used for compiling a shared library",
> "-mdirect-extern-access");
Pushed r14-1839.
On Thu, 2023-06-15 at 09:12 +0800, Lulu Cheng wrote:
> LGTM! Thanks!
>
> 在 2023/6/14 上午8:43, Xi Ruoyao 写道:
> > The LA464 micro-architecture is sensitive to alignment of code. The
> > Loongson team has benchmarked various combinations of function, the
> > results [1] show that 16-byte label alignment together with 32-byte
> > function alignment gives best results in terms of SPEC score.
> >
> > Add a mtune-based table-driven mechanism to set the default of
> > -falign-{functions,labels}. As LA464 is the first (and the only for
> > now) uarch supported by GCC, the same setting is also used for
> > the "generic" -mtune=loongarch64. In the future we may set
> > different
> > settings for LA{2,3,6}64 once we add the support for them.
> >
> > Bootstrapped and regtested on loongarch64-linux-gnu. Ok for trunk?
> >
> > gcc/ChangeLog:
> >
> > * config/loongarch/loongarch-tune.h (loongarch_align): New
> > struct.
> > * config/loongarch/loongarch-def.h (loongarch_cpu_align):
> > New
> > array.
> > * config/loongarch/loongarch-def.c (loongarch_cpu_align):
> > Define
> > the array.
> > * config/loongarch/loongarch.cc
> > (loongarch_option_override_internal): Set the value of
> > -falign-functions= if -falign-functions is enabled but no
> > value
> > is given. Likewise for -falign-labels=.
> > ---
> > gcc/config/loongarch/loongarch-def.c | 12 ++++++++++++
> > gcc/config/loongarch/loongarch-def.h | 1 +
> > gcc/config/loongarch/loongarch-tune.h | 8 ++++++++
> > gcc/config/loongarch/loongarch.cc | 6 ++++++
> > 4 files changed, 27 insertions(+)
> >
> > diff --git a/gcc/config/loongarch/loongarch-def.c
> > b/gcc/config/loongarch/loongarch-def.c
> > index fc4ebbefede..6729c857f7c 100644
> > --- a/gcc/config/loongarch/loongarch-def.c
> > +++ b/gcc/config/loongarch/loongarch-def.c
> > @@ -72,6 +72,18 @@ loongarch_cpu_cache[N_TUNE_TYPES] = {
> > },
> > };
> >
> > +struct loongarch_align
> > +loongarch_cpu_align[N_TUNE_TYPES] = {
> > + [CPU_LOONGARCH64] = {
> > + .function = "32",
> > + .label = "16",
> > + },
> > + [CPU_LA464] = {
> > + .function = "32",
> > + .label = "16",
> > + },
> > +};
> > +
> > /* The following properties cannot be looked up directly using
> > "cpucfg".
> > So it is necessary to provide a default value for "unknown
> > native"
> > tune targets (i.e. -mtune=native while PRID does not correspond
> > to
> > diff --git a/gcc/config/loongarch/loongarch-def.h
> > b/gcc/config/loongarch/loongarch-def.h
> > index 778b1409956..fb8bb88eb52 100644
> > --- a/gcc/config/loongarch/loongarch-def.h
> > +++ b/gcc/config/loongarch/loongarch-def.h
> > @@ -144,6 +144,7 @@ extern int loongarch_cpu_issue_rate[];
> > extern int loongarch_cpu_multipass_dfa_lookahead[];
> >
> > extern struct loongarch_cache loongarch_cpu_cache[];
> > +extern struct loongarch_align loongarch_cpu_align[];
> > extern struct loongarch_rtx_cost_data
> > loongarch_cpu_rtx_cost_data[];
> >
> > #ifdef __cplusplus
> > diff --git a/gcc/config/loongarch/loongarch-tune.h
> > b/gcc/config/loongarch/loongarch-tune.h
> > index ba31c4f08c3..5c03262daff 100644
> > --- a/gcc/config/loongarch/loongarch-tune.h
> > +++ b/gcc/config/loongarch/loongarch-tune.h
> > @@ -48,4 +48,12 @@ struct loongarch_cache {
> > int simultaneous_prefetches; /* number of parallel prefetch */
> > };
> >
> > +/* Alignment for functions and labels for best performance. For
> > new uarchs
> > + the value should be measured via benchmarking. See the
> > documentation for
> > + -falign-functions and -falign-labels in invoke.texi for the
> > format. */
> > +struct loongarch_align {
> > + const char *function; /* default value for -falign-
> > functions */
> > + const char *label; /* default value for -falign-labels */
> > +};
> > +
> > #endif /* LOONGARCH_TUNE_H */
> > diff --git a/gcc/config/loongarch/loongarch.cc
> > b/gcc/config/loongarch/loongarch.cc
> > index eb73d11b869..5b8b93eb24b 100644
> > --- a/gcc/config/loongarch/loongarch.cc
> > +++ b/gcc/config/loongarch/loongarch.cc
> > @@ -6249,6 +6249,12 @@ loongarch_option_override_internal (struct
> > gcc_options *opts)
> > && !opts->x_optimize_size)
> > opts->x_flag_prefetch_loop_arrays = 1;
> >
> > + if (opts->x_flag_align_functions && !opts->x_str_align_functions)
> > + opts->x_str_align_functions =
> > loongarch_cpu_align[LARCH_ACTUAL_TUNE].function;
> > +
> > + if (opts->x_flag_align_labels && !opts->x_str_align_labels)
> > + opts->x_str_align_labels =
> > loongarch_cpu_align[LARCH_ACTUAL_TUNE].label;
> > +
> > if (TARGET_DIRECT_EXTERN_ACCESS && flag_shlib)
> > error ("%qs cannot be used for compiling a shared library",
> > "-mdirect-extern-access");
>
@@ -72,6 +72,18 @@ loongarch_cpu_cache[N_TUNE_TYPES] = {
},
};
+struct loongarch_align
+loongarch_cpu_align[N_TUNE_TYPES] = {
+ [CPU_LOONGARCH64] = {
+ .function = "32",
+ .label = "16",
+ },
+ [CPU_LA464] = {
+ .function = "32",
+ .label = "16",
+ },
+};
+
/* The following properties cannot be looked up directly using "cpucfg".
So it is necessary to provide a default value for "unknown native"
tune targets (i.e. -mtune=native while PRID does not correspond to
@@ -144,6 +144,7 @@ extern int loongarch_cpu_issue_rate[];
extern int loongarch_cpu_multipass_dfa_lookahead[];
extern struct loongarch_cache loongarch_cpu_cache[];
+extern struct loongarch_align loongarch_cpu_align[];
extern struct loongarch_rtx_cost_data loongarch_cpu_rtx_cost_data[];
#ifdef __cplusplus
@@ -48,4 +48,12 @@ struct loongarch_cache {
int simultaneous_prefetches; /* number of parallel prefetch */
};
+/* Alignment for functions and labels for best performance. For new uarchs
+ the value should be measured via benchmarking. See the documentation for
+ -falign-functions and -falign-labels in invoke.texi for the format. */
+struct loongarch_align {
+ const char *function; /* default value for -falign-functions */
+ const char *label; /* default value for -falign-labels */
+};
+
#endif /* LOONGARCH_TUNE_H */
@@ -6249,6 +6249,12 @@ loongarch_option_override_internal (struct gcc_options *opts)
&& !opts->x_optimize_size)
opts->x_flag_prefetch_loop_arrays = 1;
+ if (opts->x_flag_align_functions && !opts->x_str_align_functions)
+ opts->x_str_align_functions = loongarch_cpu_align[LARCH_ACTUAL_TUNE].function;
+
+ if (opts->x_flag_align_labels && !opts->x_str_align_labels)
+ opts->x_str_align_labels = loongarch_cpu_align[LARCH_ACTUAL_TUNE].label;
+
if (TARGET_DIRECT_EXTERN_ACCESS && flag_shlib)
error ("%qs cannot be used for compiling a shared library",
"-mdirect-extern-access");