[PATCH 5/5] [AARCH64] Add variant support to -m*=native and add thunderxt88pass1.
Andrew Pinski
apinski@cavium.com
Tue Nov 17 22:11:00 GMT 2015
Since ThunderX T88 pass 1 (variant 0) is a ARMv8 part while pass 2 (variant 1)
is an ARMv8.1 part, I needed to add detecting of the variant also for this
difference. Also I simplify a little bit and combined the single core and
arch detecting cases so it would be easier to add variant.
OK? Bootstrapped and tested on aarch64-linux-gnu with no regressions.
Tested -mcpu=native on both T88 pass 1 and T88 pass 2 to make sure it is
deecting the two seperately.
Thanks,
Andrew Pinski
* config/aarch64/aarch64-cores.def: Add -1 as the variant to all of the cores.
(thunderxt88pass1): New core.
* config/aarch64/driver-aarch64.c (struct aarch64_core_data): Add variant field.
(ALL_VARIANTS): New define.
(AARCH64_CORE): Support VARIANT operand.
(cpu_data): Likewise.
(host_detect_local_cpu): Parse variant field of /proc/cpuinfo. Combine the arch
and single core case and support variant searching.
* common/config/aarch64/aarch64-common.c (AARCH64_CORE): Add VARIANT operand.
* config/aarch64/aarch64-opts.h (AARCH64_CORE): Likewise.
* config/aarch64/aarch64.c (AARCH64_CORE): Likewise.
* config/aarch64/aarch64.h (AARCH64_CORE): Likewise.
* config/aarch64/aarch64-tune.md: Regernate.
---
gcc/common/config/aarch64/aarch64-common.c | 2 +-
gcc/config/aarch64/aarch64-cores.def | 27 ++++++-----
gcc/config/aarch64/aarch64-opts.h | 2 +-
gcc/config/aarch64/aarch64-tune.md | 2 +-
gcc/config/aarch64/aarch64.c | 2 +-
gcc/config/aarch64/aarch64.h | 2 +-
gcc/config/aarch64/driver-aarch64.c | 78 ++++++++++++++++--------------
7 files changed, 64 insertions(+), 51 deletions(-)
diff --git a/gcc/common/config/aarch64/aarch64-common.c b/gcc/common/config/aarch64/aarch64-common.c
index e312bbc..f6fd7e7 100644
--- a/gcc/common/config/aarch64/aarch64-common.c
+++ b/gcc/common/config/aarch64/aarch64-common.c
@@ -141,7 +141,7 @@ struct arch_to_arch_name
the default set of architectural feature flags they support. */
static const struct processor_name_to_arch all_cores[] =
{
-#define AARCH64_CORE(NAME, X, IDENT, ARCH_IDENT, FLAGS, COSTS, IMP, PART) \
+#define AARCH64_CORE(NAME, X, IDENT, ARCH_IDENT, FLAGS, COSTS, IMP, PART, VARIANT) \
{NAME, AARCH64_ARCH_##ARCH_IDENT, FLAGS},
#include "config/aarch64/aarch64-cores.def"
{"generic", AARCH64_ARCH_8A, AARCH64_FL_FOR_ARCH8},
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index 05ee525..52a9906 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -21,7 +21,7 @@
Before using #include to read this file, define a macro:
- AARCH64_CORE(CORE_NAME, CORE_IDENT, SCHEDULER_IDENT, ARCH_IDENT, FLAGS, COSTS, IMP, PART)
+ AARCH64_CORE(CORE_NAME, CORE_IDENT, SCHEDULER_IDENT, ARCH_IDENT, FLAGS, COSTS, IMP, PART, VARIANT)
The CORE_NAME is the name of the core, represented as a string constant.
The CORE_IDENT is the name of the core, represented as an identifier.
@@ -37,31 +37,36 @@
PART is the part number of the CPU. On a GNU/Linux system it can be found
in /proc/cpuinfo. For big.LITTLE systems this should use the macro AARCH64_BIG_LITTLE
where the big part number comes as the first arugment to the macro and little is the
- second. */
+ second.
+ VARIANT is the variant of the CPU. In a GNU/Linux system it can found
+ in /proc/cpuinfo. If this is -1, this means it can match any variant. */
/* V8 Architecture Processors. */
/* ARM cores. */
-AARCH64_CORE("cortex-a53", cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa53, 0x41, 0xd03)
-AARCH64_CORE("cortex-a57", cortexa57, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, 0x41, 0xd07)
-AARCH64_CORE("cortex-a72", cortexa72, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, 0x41, 0xd08)
+AARCH64_CORE("cortex-a53", cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa53, 0x41, 0xd03, -1)
+AARCH64_CORE("cortex-a57", cortexa57, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, 0x41, 0xd07, -1)
+AARCH64_CORE("cortex-a72", cortexa72, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, 0x41, 0xd08, -1)
/* Samsung cores */
-AARCH64_CORE("exynos-m1", exynosm1, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa72, 0x53, 0x001)
+AARCH64_CORE("exynos-m1", exynosm1, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa72, 0x53, 0x001, -1)
/* Qualcomm cores */
-AARCH64_CORE("qdf24xx", qdf24xx, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa57, 0x51, 0x800)
+AARCH64_CORE("qdf24xx", qdf24xx, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa57, 0x51, 0x800, -1)
/* Cavium cores */
-AARCH64_CORE("thunderx", thunderx, thunderx, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a1)
+/* ThunderX T88 pass 1 is 8.0-a arch. */
+AARCH64_CORE("thunderxt88pass1", thunderxt88pass1, thunderx, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a1, 0)
+/* ThunderX T88 pass 2 and on is 8.1-a arch. */
+AARCH64_CORE("thunderx", thunderx, thunderx, 8_1A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO | AARCH64_FL_LSE, thunderx, 0x43, 0x0a1, -1)
/* APM cores */
-AARCH64_CORE("xgene1", xgene1, xgene1, 8A, AARCH64_FL_FOR_ARCH8, xgene1, 0x50, 0x000)
+AARCH64_CORE("xgene1", xgene1, xgene1, 8A, AARCH64_FL_FOR_ARCH8, xgene1, 0x50, 0x000, -1)
/* V8 big.LITTLE implementations. */
-AARCH64_CORE("cortex-a57.cortex-a53", cortexa57cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, 0x41, AARCH64_BIG_LITTLE(0xd07, 0xd03))
-AARCH64_CORE("cortex-a72.cortex-a53", cortexa72cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, 0x41, AARCH64_BIG_LITTLE(0xd08, 0xd03))
+AARCH64_CORE("cortex-a57.cortex-a53", cortexa57cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, 0x41, AARCH64_BIG_LITTLE(0xd07, 0xd03), -1)
+AARCH64_CORE("cortex-a72.cortex-a53", cortexa72cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, 0x41, AARCH64_BIG_LITTLE(0xd08, 0xd03), -1)
#undef AARCH64_CORE
diff --git a/gcc/config/aarch64/aarch64-opts.h b/gcc/config/aarch64/aarch64-opts.h
index 5534867..c66cd72 100644
--- a/gcc/config/aarch64/aarch64-opts.h
+++ b/gcc/config/aarch64/aarch64-opts.h
@@ -25,7 +25,7 @@
/* The various cores that implement AArch64. */
enum aarch64_processor
{
-#define AARCH64_CORE(NAME, INTERNAL_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART) \
+#define AARCH64_CORE(NAME, INTERNAL_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
INTERNAL_IDENT,
#include "aarch64-cores.def"
/* Used to indicate that no processor has been specified. */
diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index c65a124..28b573e 100644
--- a/gcc/config/aarch64/aarch64-tune.md
+++ b/gcc/config/aarch64/aarch64-tune.md
@@ -1,5 +1,5 @@
;; -*- buffer-read-only: t -*-
;; Generated automatically by gentune.sh from aarch64-cores.def
(define_attr "tune"
- "cortexa53,cortexa57,cortexa72,exynosm1,qdf24xx,thunderx,xgene1,cortexa57cortexa53,cortexa72cortexa53"
+ "cortexa53,cortexa57,cortexa72,exynosm1,qdf24xx,thunderxt88pass1,thunderx,xgene1,cortexa57cortexa53,cortexa72cortexa53"
(const (symbol_ref "((enum attr_tune) aarch64_tune)")))
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index a5971a1..d244846 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -526,7 +526,7 @@ static const struct processor all_architectures[] =
/* Processor cores implementing AArch64. */
static const struct processor all_cores[] =
{
-#define AARCH64_CORE(NAME, IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART) \
+#define AARCH64_CORE(NAME, IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
{NAME, IDENT, SCHED, AARCH64_ARCH_##ARCH, \
all_architectures[AARCH64_ARCH_##ARCH].architecture_version, \
FLAGS, &COSTS##_tunings},
diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index c6582a4..6f06369 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -464,7 +464,7 @@ enum reg_class
enum target_cpus
{
-#define AARCH64_CORE(NAME, INTERNAL_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART) \
+#define AARCH64_CORE(NAME, INTERNAL_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
TARGET_CPU_##INTERNAL_IDENT,
#include "aarch64-cores.def"
TARGET_CPU_generic
diff --git a/gcc/config/aarch64/driver-aarch64.c b/gcc/config/aarch64/driver-aarch64.c
index ea1e856..b11d914 100644
--- a/gcc/config/aarch64/driver-aarch64.c
+++ b/gcc/config/aarch64/driver-aarch64.c
@@ -40,20 +40,22 @@ struct aarch64_core_data
const char *arch;
unsigned char implementer_id; /* Exactly 8 bits */
unsigned int part_no; /* 12 bits + 12 bits */
+ unsigned variant;
};
#define AARCH64_BIG_LITTLE(BIG, LITTLE) \
(((BIG)&0xFFFu) << 12 | ((LITTLE) & 0xFFFu))
#define INVALID_IMP ((unsigned char) -1)
#define INVALID_CORE ((unsigned)-1)
+#define ALL_VARIANTS ((unsigned)-1)
-#define AARCH64_CORE(CORE_NAME, CORE_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART) \
- { CORE_NAME, #ARCH, IMP, PART },
+#define AARCH64_CORE(CORE_NAME, CORE_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
+ { CORE_NAME, #ARCH, IMP, PART, VARIANT },
static struct aarch64_core_data cpu_data [] =
{
#include "aarch64-cores.def"
- { NULL, NULL, INVALID_IMP, INVALID_CORE }
+ { NULL, NULL, INVALID_IMP, INVALID_CORE, ALL_VARIANTS }
};
@@ -149,7 +151,6 @@ contains_core_p (unsigned *arr, unsigned core)
const char *
host_detect_local_cpu (int argc, const char **argv)
{
- const char *arch_id = NULL;
const char *res = NULL;
static const int num_exts = ARRAY_SIZE (ext_to_feat_string);
char buf[128];
@@ -158,10 +159,11 @@ host_detect_local_cpu (int argc, const char **argv)
bool tune = false;
bool cpu = false;
unsigned int i = 0;
- int core_idx = -1;
unsigned char imp = INVALID_IMP;
unsigned int cores[2] = { INVALID_CORE, INVALID_CORE };
unsigned int n_cores = 0;
+ unsigned int variants[2] = { ALL_VARIANTS, ALL_VARIANTS };
+ unsigned int n_variants = 0;
bool processed_exts = false;
const char *ext_string = "";
@@ -203,6 +205,19 @@ host_detect_local_cpu (int argc, const char **argv)
goto not_found;
}
+ if (strstr (buf, "variant") != NULL)
+ {
+ unsigned cvariant = parse_field (buf);
+ if (!contains_core_p (variants, cvariant))
+ {
+ if (n_variants == 2)
+ goto not_found;
+
+ variants[n_variants++] = cvariant;
+ }
+ continue;
+ }
+
if (strstr (buf, "part") != NULL)
{
unsigned ccore = parse_field (buf);
@@ -245,32 +260,41 @@ host_detect_local_cpu (int argc, const char **argv)
f = NULL;
/* Weird cpuinfo format that we don't know how to handle. */
- if (n_cores == 0 || n_cores > 2 || imp == INVALID_IMP)
+ if (n_cores == 0 || n_cores > 2
+ || (n_cores == 1 && n_variants != 1)
+ || imp == INVALID_IMP)
goto not_found;
- if (arch)
+
+ /* Simple case, one core type or just looking for the arch. */
+ if (n_cores == 1 || arch)
{
/* Search for one of the cores in the list. */
for (i = 0; cpu_data[i].name != NULL; i++)
if (cpu_data[i].implementer_id == imp
- && contains_core_p (cores, cpu_data[i].part_no))
- {
- arch_id = cpu_data[i].arch;
- break;
- }
- if (!arch_id)
+ && cores[0] == cpu_data[i].part_no
+ && (cpu_data[i].variant == ALL_VARIANTS
+ || variants[0] == cpu_data[i].variant))
+ break;
+ if (cpu_data[i].name == NULL)
goto not_found;
- const char* arch_name = get_arch_name_from_id (arch_id);
+ if (arch)
+ {
+ const char* arch_name = get_arch_name_from_id (cpu_data[i].arch);
- /* We got some arch indentifier that's not in aarch64-arches.def? */
- if (!arch_name)
- goto not_found;
+ /* We got some arch indentifier that's not in aarch64-arches.def? */
+ if (!arch_name)
+ goto not_found;
- res = concat ("-march=", arch_name, NULL);
+ res = concat ("-march=", arch_name, NULL);
+ }
+ else
+ res = concat ("-m", cpu ? "cpu" : "tune", "=",
+ cpu_data[i].name, NULL);
}
/* We have big.LITTLE. */
- else if (n_cores == 2)
+ else
{
for (i = 0; cpu_data[i].name != NULL; i++)
{
@@ -284,22 +308,6 @@ host_detect_local_cpu (int argc, const char **argv)
if (!res)
goto not_found;
}
- /* The simple, non-big.LITTLE case. */
- else
- {
- for (i = 0; cpu_data[i].name != NULL; i++)
- if (cores[0] == cpu_data[i].part_no
- && cpu_data[i].implementer_id == imp)
- {
- core_idx = i;
- break;
- }
- if (core_idx == -1)
- goto not_found;
-
- res = concat ("-m", cpu ? "cpu" : "tune", "=",
- cpu_data[core_idx].name, NULL);
- }
if (tune)
return res;
--
1.9.1
More information about the Gcc-patches
mailing list