106 lines
4.0 KiB
Diff
106 lines
4.0 KiB
Diff
The original patch had
|
|
#define TARGET_CPU_NBITS 8
|
|
but I've changed it to
|
|
#define TARGET_CPU_NBITS 7
|
|
|
|
commit 5522dec054cb940fe83661b96249aa12c54c1d77
|
|
Author: Andre Vieira <andre.simoesdiasvieira@arm.com>
|
|
Date: Fri Apr 8 15:12:23 2022 +0100
|
|
|
|
aarch64: PR target/105157 Increase number of cores TARGET_CPU_DEFAULT can encode
|
|
|
|
This addresses the compile-time increase seen in the PR target/105157. This was
|
|
being caused by selecting the wrong core tuning, as when we added the latest
|
|
AArch64 the TARGET_CPU_generic tuning was pushed beyond the 0x3f mask we used
|
|
to encode both target cpu and attributes into TARGET_CPU_DEFAULT.
|
|
|
|
gcc/ChangeLog:
|
|
|
|
PR target/105157
|
|
* config.gcc: Shift ext_mask by TARGET_CPU_NBITS.
|
|
* config/aarch64/aarch64.h (TARGET_CPU_NBITS): New macro.
|
|
(TARGET_CPU_MASK): Likewise.
|
|
(TARGET_CPU_DEFAULT): Use TARGET_CPU_NBITS.
|
|
* config/aarch64/aarch64.cc (aarch64_get_tune_cpu): Use TARGET_CPU_MASK.
|
|
(aarch64_get_arch): Likewise.
|
|
(aarch64_override_options): Use TARGET_CPU_NBITS.
|
|
|
|
--- a/gcc/config.gcc
|
|
+++ b/gcc/config.gcc
|
|
@@ -4261,7 +4261,7 @@ case "${target}" in
|
|
ext_val=`echo $ext_val | sed -e 's/[a-z0-9]\+//'`
|
|
done
|
|
|
|
- ext_mask="(("$ext_mask") << 6)"
|
|
+ ext_mask="(("$ext_mask") << TARGET_CPU_NBITS)"
|
|
if [ x"$base_id" != x ]; then
|
|
target_cpu_cname="TARGET_CPU_$base_id | $ext_mask"
|
|
fi
|
|
--- a/gcc/config/aarch64/aarch64.c
|
|
+++ b/gcc/config/aarch64/aarch64.c
|
|
@@ -18053,6 +18053,9 @@ aarch64_validate_mtune (const char *str, const struct processor **res)
|
|
return false;
|
|
}
|
|
|
|
+static_assert (TARGET_CPU_generic < TARGET_CPU_MASK,
|
|
+ "TARGET_CPU_NBITS is big enough");
|
|
+
|
|
/* Return the CPU corresponding to the enum CPU.
|
|
If it doesn't specify a cpu, return the default. */
|
|
|
|
@@ -18062,12 +18065,12 @@ aarch64_get_tune_cpu (enum aarch64_processor cpu)
|
|
if (cpu != aarch64_none)
|
|
return &all_cores[cpu];
|
|
|
|
- /* The & 0x3f is to extract the bottom 6 bits that encode the
|
|
- default cpu as selected by the --with-cpu GCC configure option
|
|
+ /* The & TARGET_CPU_MASK is to extract the bottom TARGET_CPU_NBITS bits that
|
|
+ encode the default cpu as selected by the --with-cpu GCC configure option
|
|
in config.gcc.
|
|
???: The whole TARGET_CPU_DEFAULT and AARCH64_CPU_DEFAULT_FLAGS
|
|
flags mechanism should be reworked to make it more sane. */
|
|
- return &all_cores[TARGET_CPU_DEFAULT & 0x3f];
|
|
+ return &all_cores[TARGET_CPU_DEFAULT & TARGET_CPU_MASK];
|
|
}
|
|
|
|
/* Return the architecture corresponding to the enum ARCH.
|
|
@@ -18079,7 +18082,8 @@ aarch64_get_arch (enum aarch64_arch arch)
|
|
if (arch != aarch64_no_arch)
|
|
return &all_architectures[arch];
|
|
|
|
- const struct processor *cpu = &all_cores[TARGET_CPU_DEFAULT & 0x3f];
|
|
+ const struct processor *cpu
|
|
+ = &all_cores[TARGET_CPU_DEFAULT & TARGET_CPU_MASK];
|
|
|
|
return &all_architectures[cpu->arch];
|
|
}
|
|
@@ -18166,7 +18170,7 @@ aarch64_override_options (void)
|
|
{
|
|
/* Get default configure-time CPU. */
|
|
selected_cpu = aarch64_get_tune_cpu (aarch64_none);
|
|
- aarch64_isa_flags = TARGET_CPU_DEFAULT >> 6;
|
|
+ aarch64_isa_flags = TARGET_CPU_DEFAULT >> TARGET_CPU_NBITS;
|
|
}
|
|
|
|
if (selected_tune)
|
|
--- a/gcc/config/aarch64/aarch64.h
|
|
+++ b/gcc/config/aarch64/aarch64.h
|
|
@@ -813,10 +813,16 @@ enum target_cpus
|
|
TARGET_CPU_generic
|
|
};
|
|
|
|
+/* Define how many bits are used to represent the CPU in TARGET_CPU_DEFAULT.
|
|
+ This needs to be big enough to fit the value of TARGET_CPU_generic.
|
|
+ All bits after this are used to represent the AARCH64_CPU_DEFAULT_FLAGS. */
|
|
+#define TARGET_CPU_NBITS 7
|
|
+#define TARGET_CPU_MASK ((1 << TARGET_CPU_NBITS) - 1)
|
|
+
|
|
/* If there is no CPU defined at configure, use generic as default. */
|
|
#ifndef TARGET_CPU_DEFAULT
|
|
#define TARGET_CPU_DEFAULT \
|
|
- (TARGET_CPU_generic | (AARCH64_CPU_DEFAULT_FLAGS << 6))
|
|
+ (TARGET_CPU_generic | (AARCH64_CPU_DEFAULT_FLAGS << TARGET_CPU_NBITS))
|
|
#endif
|
|
|
|
/* If inserting NOP before a mult-accumulate insn remember to adjust the
|