@@ -108,4 +108,20 @@ enum aarch64_key_type {
AARCH64_KEY_B
};
+/* Load pair policy type. */
+enum aarch64_ldp_policy {
+ LDP_POLICY_DEFAULT,
+ LDP_POLICY_ALWAYS,
+ LDP_POLICY_NEVER,
+ LDP_POLICY_ALIGNED
+};
+
+/* Store pair policy type. */
+enum aarch64_stp_policy {
+ STP_POLICY_DEFAULT,
+ STP_POLICY_ALWAYS,
+ STP_POLICY_NEVER,
+ STP_POLICY_ALIGNED
+};
+
#endif
@@ -568,6 +568,30 @@ struct tune_params
/* Place prefetch struct pointer at the end to enable type checking
errors when tune_params misses elements (e.g., from erroneous merges). */
const struct cpu_prefetch_tune *prefetch;
+/* An enum specifying how to handle load pairs using a fine-grained policy:
+ - LDP_POLICY_ALIGNED: Emit ldp if the source pointer is aligned
+ to at least double the alignment of the type.
+ - LDP_POLICY_ALWAYS: Emit ldp regardless of alignment.
+ - LDP_POLICY_NEVER: Do not emit ldp. */
+
+ enum aarch64_ldp_policy_model
+ {
+ LDP_POLICY_ALIGNED,
+ LDP_POLICY_ALWAYS,
+ LDP_POLICY_NEVER
+ } ldp_policy_model;
+/* An enum specifying how to handle store pairs using a fine-grained policy:
+ - STP_POLICY_ALIGNED: Emit stp if the source pointer is aligned
+ to at least double the alignment of the type.
+ - STP_POLICY_ALWAYS: Emit stp regardless of alignment.
+ - STP_POLICY_NEVER: Do not emit stp. */
+
+ enum aarch64_stp_policy_model
+ {
+ STP_POLICY_ALIGNED,
+ STP_POLICY_ALWAYS,
+ STP_POLICY_NEVER
+ } stp_policy_model;
};
/* Classifies an address.
@@ -1015,6 +1039,7 @@ bool extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset);
bool aarch64_mergeable_load_pair_p (machine_mode, rtx, rtx);
bool aarch64_operands_ok_for_ldpstp (rtx *, bool, machine_mode);
bool aarch64_operands_adjust_ok_for_ldpstp (rtx *, bool, machine_mode);
+bool aarch64_mem_ok_with_ldpstp_policy_model (rtx, bool, machine_mode);
void aarch64_swap_ldrstr_operands (rtx *, bool);
extern void aarch64_asm_output_pool_epilogue (FILE *, const char *,
@@ -30,11 +30,6 @@
AARCH64_EXTRA_TUNING_OPTION ("rename_fma_regs", RENAME_FMA_REGS)
-/* Don't create non-8 byte aligned load/store pair. That is if the
-two load/stores are not at least 8 byte aligned don't create load/store
-pairs. */
-AARCH64_EXTRA_TUNING_OPTION ("slow_unaligned_ldpw", SLOW_UNALIGNED_LDPW)
-
/* Some of the optional shift to some arthematic instructions are
considered cheap. Logical shift left <=4 with or without a
zero extend are considered cheap. Sign extend; non logical shift left
@@ -44,9 +39,6 @@ AARCH64_EXTRA_TUNING_OPTION ("cheap_shift_extend", CHEAP_SHIFT_EXTEND)
/* Disallow load/store pair instructions on Q-registers. */
AARCH64_EXTRA_TUNING_OPTION ("no_ldp_stp_qregs", NO_LDP_STP_QREGS)
-/* Disallow load-pair instructions to be formed in combine/peephole. */
-AARCH64_EXTRA_TUNING_OPTION ("no_ldp_combine", NO_LDP_COMBINE)
-
AARCH64_EXTRA_TUNING_OPTION ("rename_load_regs", RENAME_LOAD_REGS)
AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
@@ -1357,7 +1357,9 @@ static const struct tune_params generic_tunings =
Neoverse V1. It does not have a noticeable effect on A64FX and should
have at most a very minor effect on SVE2 cores. */
(AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params cortexa35_tunings =
@@ -1391,7 +1393,9 @@ static const struct tune_params cortexa35_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params cortexa53_tunings =
@@ -1425,7 +1429,9 @@ static const struct tune_params cortexa53_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params cortexa57_tunings =
@@ -1459,7 +1465,9 @@ static const struct tune_params cortexa57_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_RENAME_FMA_REGS), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params cortexa72_tunings =
@@ -1493,7 +1501,9 @@ static const struct tune_params cortexa72_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params cortexa73_tunings =
@@ -1527,7 +1537,9 @@ static const struct tune_params cortexa73_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
@@ -1562,7 +1574,9 @@ static const struct tune_params exynosm1_tunings =
48, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &exynosm1_prefetch_tune
+ &exynosm1_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params thunderxt88_tunings =
@@ -1594,8 +1608,10 @@ static const struct tune_params thunderxt88_tunings =
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_SLOW_UNALIGNED_LDPW), /* tune_flags. */
- &thunderxt88_prefetch_tune
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ &thunderxt88_prefetch_tune,
+ tune_params::LDP_POLICY_ALIGNED, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALIGNED /* stp_policy_model. */
};
static const struct tune_params thunderx_tunings =
@@ -1627,9 +1643,10 @@ static const struct tune_params thunderx_tunings =
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_SLOW_UNALIGNED_LDPW
- | AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND), /* tune_flags. */
- &thunderx_prefetch_tune
+ (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND), /* tune_flags. */
+ &thunderx_prefetch_tune,
+ tune_params::LDP_POLICY_ALIGNED, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALIGNED /* stp_policy_model. */
};
static const struct tune_params tsv110_tunings =
@@ -1663,7 +1680,9 @@ static const struct tune_params tsv110_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &tsv110_prefetch_tune
+ &tsv110_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params xgene1_tunings =
@@ -1696,7 +1715,9 @@ static const struct tune_params xgene1_tunings =
17, /* max_case_values. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NO_LDP_STP_QREGS), /* tune_flags. */
- &xgene1_prefetch_tune
+ &xgene1_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params emag_tunings =
@@ -1729,7 +1750,9 @@ static const struct tune_params emag_tunings =
17, /* max_case_values. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NO_LDP_STP_QREGS), /* tune_flags. */
- &xgene1_prefetch_tune
+ &xgene1_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params qdf24xx_tunings =
@@ -1763,7 +1786,9 @@ static const struct tune_params qdf24xx_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
AARCH64_EXTRA_TUNE_RENAME_LOAD_REGS, /* tune_flags. */
- &qdf24xx_prefetch_tune
+ &qdf24xx_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
/* Tuning structure for the Qualcomm Saphira core. Default to falkor values
@@ -1799,7 +1824,9 @@ static const struct tune_params saphira_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params thunderx2t99_tunings =
@@ -1833,7 +1860,9 @@ static const struct tune_params thunderx2t99_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &thunderx2t99_prefetch_tune
+ &thunderx2t99_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params thunderx3t110_tunings =
@@ -1867,7 +1896,9 @@ static const struct tune_params thunderx3t110_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &thunderx3t110_prefetch_tune
+ &thunderx3t110_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params neoversen1_tunings =
@@ -1900,7 +1931,9 @@ static const struct tune_params neoversen1_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params ampere1_tunings =
@@ -1936,8 +1969,10 @@ static const struct tune_params ampere1_tunings =
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NO_LDP_COMBINE), /* tune_flags. */
- &ere1_prefetch_tune
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ &ere1_prefetch_tune,
+ tune_params::LDP_POLICY_ALIGNED, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALIGNED /* stp_policy_model. */
};
static const struct tune_params ampere1a_tunings =
@@ -1974,8 +2009,10 @@ static const struct tune_params ampere1a_tunings =
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NO_LDP_COMBINE), /* tune_flags. */
- &ere1_prefetch_tune
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ &ere1_prefetch_tune,
+ tune_params::LDP_POLICY_ALIGNED, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALIGNED /* stp_policy_model. */
};
static const advsimd_vec_cost neoversev1_advsimd_vector_cost =
@@ -2156,7 +2193,9 @@ static const struct tune_params neoversev1_tunings =
| AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
| AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT
| AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const sve_vec_cost neoverse512tvb_sve_vector_cost =
@@ -2293,7 +2332,9 @@ static const struct tune_params neoverse512tvb_tunings =
(AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
| AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
| AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const advsimd_vec_cost neoversen2_advsimd_vector_cost =
@@ -2483,7 +2524,9 @@ static const struct tune_params neoversen2_tunings =
| AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
| AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
| AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const advsimd_vec_cost neoversev2_advsimd_vector_cost =
@@ -2673,7 +2716,9 @@ static const struct tune_params neoversev2_tunings =
| AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
| AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
| AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT), /* tune_flags. */
- &generic_prefetch_tune
+ &generic_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
static const struct tune_params a64fx_tunings =
@@ -2706,7 +2751,9 @@ static const struct tune_params a64fx_tunings =
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
- &a64fx_prefetch_tune
+ &a64fx_prefetch_tune,
+ tune_params::LDP_POLICY_ALWAYS, /* ldp_policy_model. */
+ tune_params::STP_POLICY_ALWAYS /* stp_policy_model. */
};
/* Support for fine-grained override of the tuning structures. */
@@ -17819,6 +17866,36 @@ aarch64_parse_tune (const char *to_parse, const struct processor **res)
return AARCH_PARSE_INVALID_ARG;
}
+/* Parse a command-line -param=aarch64-ldp-policy= parameter. VALUE is
+ the value of the parameter. */
+
+static void
+aarch64_parse_ldp_policy (enum aarch64_ldp_policy value,
+ struct tune_params* tune)
+{
+ if (value == LDP_POLICY_ALWAYS)
+ tune->ldp_policy_model = tune_params::LDP_POLICY_ALWAYS;
+ else if (value == LDP_POLICY_NEVER)
+ tune->ldp_policy_model = tune_params::LDP_POLICY_NEVER;
+ else if (value == LDP_POLICY_ALIGNED)
+ tune->ldp_policy_model = tune_params::LDP_POLICY_ALIGNED;
+}
+
+/* Parse a command-line -param=aarch64-stp-policy= parameter. VALUE is
+ the value of the parameter. */
+
+static void
+aarch64_parse_stp_policy (enum aarch64_stp_policy value,
+ struct tune_params* tune)
+{
+ if (value == STP_POLICY_ALWAYS)
+ tune->stp_policy_model = tune_params::STP_POLICY_ALWAYS;
+ else if (value == STP_POLICY_NEVER)
+ tune->stp_policy_model = tune_params::STP_POLICY_NEVER;
+ else if (value == STP_POLICY_ALIGNED)
+ tune->stp_policy_model = tune_params::STP_POLICY_ALIGNED;
+}
+
/* Parse TOKEN, which has length LENGTH to see if it is an option
described in FLAG. If it is, return the index bit for that fusion type.
If not, error (printing OPTION_NAME) and return zero. */
@@ -18167,6 +18244,14 @@ aarch64_override_options_internal (struct gcc_options *opts)
aarch64_parse_override_string (opts->x_aarch64_override_tune_string,
&aarch64_tune_params);
+ if (opts->x_aarch64_ldp_policy_param)
+ aarch64_parse_ldp_policy (opts->x_aarch64_ldp_policy_param,
+ &aarch64_tune_params);
+
+ if (opts->x_aarch64_stp_policy_param)
+ aarch64_parse_stp_policy (opts->x_aarch64_stp_policy_param,
+ &aarch64_tune_params);
+
/* This target defaults to strict volatile bitfields. */
if (opts->x_flag_strict_volatile_bitfields < 0 && abi_version_at_least (2))
opts->x_flag_strict_volatile_bitfields = 1;
@@ -26457,6 +26542,43 @@ aarch64_mergeable_load_pair_p (machine_mode mode, rtx mem1, rtx mem2)
return aarch64_check_consecutive_mems (&mem1, &mem2, nullptr);
}
+/* Return true if MEM agrees with the ldp-stp policy model.
+ Otherwise, false. */
+
+bool
+aarch64_mem_ok_with_ldpstp_policy_model (rtx mem, bool load, machine_mode mode)
+{
+ /* If we have LDP_POLICY_NEVER, reject the load pair. */
+ if (load
+ && aarch64_tune_params.ldp_policy_model == tune_params::LDP_POLICY_NEVER)
+ return false;
+
+ /* If we have STP_POLICY_NEVER, reject the store pair. */
+ if (!load
+ && aarch64_tune_params.stp_policy_model == tune_params::STP_POLICY_NEVER)
+ return false;
+
+ /* If we have LDP_POLICY_ALIGNED,
+ do not emit the load pair unless the alignment is checked to be
+ at least double the alignment of the type. */
+ if (load
+ && aarch64_tune_params.ldp_policy_model == tune_params::LDP_POLICY_ALIGNED
+ && !optimize_function_for_size_p (cfun)
+ && MEM_ALIGN (mem) < 2 * GET_MODE_ALIGNMENT (mode))
+ return false;
+
+ /* If we have STP_POLICY_ALIGNED,
+ do not emit the store pair unless the alignment is checked to be
+ at least double the alignment of the type. */
+ if (!load
+ && aarch64_tune_params.stp_policy_model == tune_params::STP_POLICY_ALIGNED
+ && !optimize_function_for_size_p (cfun)
+ && MEM_ALIGN (mem) < 2 * GET_MODE_ALIGNMENT (mode))
+ return false;
+
+ return true;
+}
+
/* Given OPERANDS of consecutive load/store, check if we can merge
them into ldp/stp. LOAD is true if they are load instructions.
MODE is the mode of memory operands. */
@@ -26468,20 +26590,6 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
enum reg_class rclass_1, rclass_2;
rtx mem_1, mem_2, reg_1, reg_2;
- /* Allow the tuning structure to disable LDP instruction formation
- from combining instructions (e.g., in peephole2).
- TODO: Implement fine-grained tuning control for LDP and STP:
- 1. control policies for load and store separately;
- 2. support the following policies:
- - default (use what is in the tuning structure)
- - always
- - never
- - aligned (only if the compiler can prove that the
- load will be aligned to 2 * element_size) */
- if (load && (aarch64_tune_params.extra_tuning_flags
- & AARCH64_EXTRA_TUNE_NO_LDP_COMBINE))
- return false;
-
if (load)
{
mem_1 = operands[1];
@@ -26506,13 +26614,8 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
if (MEM_VOLATILE_P (mem_1) || MEM_VOLATILE_P (mem_2))
return false;
- /* If we have SImode and slow unaligned ldp,
- check the alignment to be at least 8 byte. */
- if (mode == SImode
- && (aarch64_tune_params.extra_tuning_flags
- & AARCH64_EXTRA_TUNE_SLOW_UNALIGNED_LDPW)
- && !optimize_size
- && MEM_ALIGN (mem_1) < 8 * BITS_PER_UNIT)
+ /* Check if mem_1 is ok with the ldp-stp policy model. */
+ if (!aarch64_mem_ok_with_ldpstp_policy_model (mem_1, load, mode))
return false;
/* Check if the addresses are in the form of [base+offset]. */
@@ -26729,13 +26832,8 @@ aarch64_operands_adjust_ok_for_ldpstp (rtx *operands, bool load,
if (offvals[0] % msize != offvals[2] % msize)
return false;
- /* If we have SImode and slow unaligned ldp,
- check the alignment to be at least 8 byte. */
- if (mode == SImode
- && (aarch64_tune_params.extra_tuning_flags
- & AARCH64_EXTRA_TUNE_SLOW_UNALIGNED_LDPW)
- && !optimize_size
- && MEM_ALIGN (mem[0]) < 8 * BITS_PER_UNIT)
+ /* Check if mem[0] is ok with the ldp-stp policy model. */
+ if (!aarch64_mem_ok_with_ldpstp_policy_model (mem[0], load, mode))
return false;
return true;
@@ -337,3 +337,41 @@ Constant memset size in bytes from which to start using MOPS sequence.
-param=aarch64-vect-unroll-limit=
Target Joined UInteger Var(aarch64_vect_unroll_limit) Init(4) Param
Limit how much the autovectorizer may unroll a loop.
+
+-param=aarch64-ldp-policy=
+Target Joined Var(aarch64_ldp_policy_param) Enum(aarch64_ldp_policy) Init(LDP_POLICY_DEFAULT) Param
+--param=aarch64-ldp-policy=[default|always|never|aligned] Fine-grained policy for load pairs.
+
+Enum
+Name(aarch64_ldp_policy) Type(enum aarch64_ldp_policy) UnknownError(unknown aarch64_ldp_policy mode %qs)
+
+EnumValue
+Enum(aarch64_ldp_policy) String(default) Value(LDP_POLICY_DEFAULT)
+
+EnumValue
+Enum(aarch64_ldp_policy) String(always) Value(LDP_POLICY_ALWAYS)
+
+EnumValue
+Enum(aarch64_ldp_policy) String(never) Value(LDP_POLICY_NEVER)
+
+EnumValue
+Enum(aarch64_ldp_policy) String(aligned) Value(LDP_POLICY_ALIGNED)
+
+-param=aarch64-stp-policy=
+Target Joined Var(aarch64_stp_policy_param) Enum(aarch64_stp_policy) Init(STP_POLICY_DEFAULT) Param
+--param=aarch64-stp-policy=[default|always|never|aligned] Fine-grained policy for store pairs.
+
+Enum
+Name(aarch64_stp_policy) Type(enum aarch64_stp_policy) UnknownError(unknown aarch64_stp_policy mode %qs)
+
+EnumValue
+Enum(aarch64_stp_policy) String(default) Value(STP_POLICY_DEFAULT)
+
+EnumValue
+Enum(aarch64_stp_policy) String(always) Value(STP_POLICY_ALWAYS)
+
+EnumValue
+Enum(aarch64_stp_policy) String(never) Value(STP_POLICY_NEVER)
+
+EnumValue
+Enum(aarch64_stp_policy) String(aligned) Value(STP_POLICY_ALIGNED)
@@ -16508,6 +16508,26 @@ Use both Advanced SIMD and SVE. Prefer SVE when the costs are deemed equal.
@end table
The default value is 0.
+@item aarch64-ldp-policy
+Fine-grained policy for load pairs.
+With @option{--param=aarch64-ldp-policy=default}, use the policy of the
+tuning structure. This is the current default.
+With @option{--param=aarch64-ldp-policy=always}, emit ldp regardless
+of alignment.
+With @option{--param=aarch64-ldp-policy=never}, do not emit ldp.
+With @option{--param=aarch64-ldp-policy=aligned}, emit ldp only if the
+source pointer is aligned to at least double the alignment of the type.
+
+@item aarch64-stp-policy
+Fine-grained policy for store pairs.
+With @option{--param=aarch64-stp-policy=default}, use the policy of the
+tuning structure. This is the current default.
+With @option{--param=aarch64-stp-policy=always}, emit stp regardless
+of alignment.
+With @option{--param=aarch64-stp-policy=never}, do not emit stp.
+With @option{--param=aarch64-stp-policy=aligned}, emit stp only if the
+source pointer is aligned to at least double the alignment of the type.
+
@item aarch64-loop-vect-issue-rate-niters
The tuning for some AArch64 CPUs tries to take both latencies and issue
rates into account when deciding whether a loop should be vectorized
deleted file mode 100644
@@ -1,11 +0,0 @@
-/* { dg-options "-O3 -mtune=ampere1" } */
-
-long
-foo (long a[])
-{
- return a[0] + a[1];
-}
-
-/* We should see two ldrs instead of one ldp. */
-/* { dg-final { scan-assembler {\tldr\t} } } */
-/* { dg-final { scan-assembler-not {\tldp\t} } } */
new file mode 100644
@@ -0,0 +1,66 @@
+/* { dg-options "-O2 --param=aarch64-ldp-policy=aligned -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define LDP_TEST_ALIGNED(TYPE) \
+TYPE ldp_aligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[0]; \
+ a_1 = arr[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[0]; \
+ a_1 = a[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE ldp_aligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[100]; \
+ a_1 = arr[101]; \
+ a_2 = arr[102]; \
+ a_3 = arr[103]; \
+ a_4 = arr[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+#define LDP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[100]; \
+ a_1 = a[101]; \
+ a_2 = a[102]; \
+ a_3 = a[103]; \
+ a_4 = a[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+LDP_TEST_ALIGNED(int32_t);
+LDP_TEST_ALIGNED(int64_t);
+LDP_TEST_ALIGNED(v4si);
+LDP_TEST_UNALIGNED(int32_t);
+LDP_TEST_UNALIGNED(int64_t);
+LDP_TEST_UNALIGNED(v4si);
+LDP_TEST_ADJUST_ALIGNED(int32_t);
+LDP_TEST_ADJUST_ALIGNED(int64_t);
+LDP_TEST_ADJUST_UNALIGNED(int32_t);
+LDP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "ldp\tw\[0-9\]+, w\[0-9\]" 3 } } */
+/* { dg-final { scan-assembler-times "ldp\tx\[0-9\]+, x\[0-9\]" 3 } } */
+/* { dg-final { scan-assembler-times "ldp\tq\[0-9\]+, q\[0-9\]" 1 } } */
+
new file mode 100644
@@ -0,0 +1,66 @@
+/* { dg-options "-O2 --param=aarch64-ldp-policy=always -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define LDP_TEST_ALIGNED(TYPE) \
+TYPE ldp_aligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[0]; \
+ a_1 = arr[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[0]; \
+ a_1 = a[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE ldp_aligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[100]; \
+ a_1 = arr[101]; \
+ a_2 = arr[102]; \
+ a_3 = arr[103]; \
+ a_4 = arr[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+#define LDP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[100]; \
+ a_1 = a[101]; \
+ a_2 = a[102]; \
+ a_3 = a[103]; \
+ a_4 = a[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+LDP_TEST_ALIGNED(int32_t);
+LDP_TEST_ALIGNED(int64_t);
+LDP_TEST_ALIGNED(v4si);
+LDP_TEST_UNALIGNED(int32_t);
+LDP_TEST_UNALIGNED(int64_t);
+LDP_TEST_UNALIGNED(v4si);
+LDP_TEST_ADJUST_ALIGNED(int32_t);
+LDP_TEST_ADJUST_ALIGNED(int64_t);
+LDP_TEST_ADJUST_UNALIGNED(int32_t);
+LDP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "ldp\tw\[0-9\]+, w\[0-9\]" 6 } } */
+/* { dg-final { scan-assembler-times "ldp\tx\[0-9\]+, x\[0-9\]" 6 } } */
+/* { dg-final { scan-assembler-times "ldp\tq\[0-9\]+, q\[0-9\]" 2 } } */
+
new file mode 100644
@@ -0,0 +1,66 @@
+/* { dg-options "-O2 --param=aarch64-ldp-policy=never -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define LDP_TEST_ALIGNED(TYPE) \
+TYPE ldp_aligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[0]; \
+ a_1 = arr[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_##TYPE(char* ptr){ \
+ TYPE a_0, a_1; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[0]; \
+ a_1 = a[1]; \
+ return a_0 + a_1; \
+}
+
+#define LDP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE ldp_aligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ a_0 = arr[100]; \
+ a_1 = arr[101]; \
+ a_2 = arr[102]; \
+ a_3 = arr[103]; \
+ a_4 = arr[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+#define LDP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE ldp_unaligned_adjust_##TYPE(char* ptr){ \
+ TYPE a_0, a_1, a_2, a_3, a_4; \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a_0 = a[100]; \
+ a_1 = a[101]; \
+ a_2 = a[102]; \
+ a_3 = a[103]; \
+ a_4 = a[110]; \
+ return a_0 + a_1 + a_2 + a_3 + a_4; \
+}
+
+LDP_TEST_ALIGNED(int32_t);
+LDP_TEST_ALIGNED(int64_t);
+LDP_TEST_ALIGNED(v4si);
+LDP_TEST_UNALIGNED(int32_t);
+LDP_TEST_UNALIGNED(int64_t);
+LDP_TEST_UNALIGNED(v4si);
+LDP_TEST_ADJUST_ALIGNED(int32_t);
+LDP_TEST_ADJUST_ALIGNED(int64_t);
+LDP_TEST_ADJUST_UNALIGNED(int32_t);
+LDP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "ldp\tw\[0-9\]+, w\[0-9\]" 0 } } */
+/* { dg-final { scan-assembler-times "ldp\tx\[0-9\]+, x\[0-9\]" 0 } } */
+/* { dg-final { scan-assembler-times "ldp\tq\[0-9\]+, q\[0-9\]" 0 } } */
+
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-options "-O2 --param=aarch64-stp-policy=aligned -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define STP_TEST_ALIGNED(TYPE) \
+TYPE *stp_aligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[0] = x; \
+ arr[1] = x; \
+ return arr; \
+}
+
+#define STP_TEST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[0] = x; \
+ a[1] = x; \
+ return a; \
+}
+
+#define STP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE *stp_aligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[100] = x; \
+ arr[101] = x; \
+ arr[102] = x; \
+ arr[103] = x; \
+ return arr; \
+}
+
+#define STP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[100] = x; \
+ a[101] = x; \
+ a[102] = x; \
+ a[103] = x; \
+ return a; \
+}
+
+STP_TEST_ALIGNED(int32_t);
+STP_TEST_ALIGNED(int64_t);
+STP_TEST_ALIGNED(v4si);
+STP_TEST_UNALIGNED(int32_t);
+STP_TEST_UNALIGNED(int64_t);
+STP_TEST_UNALIGNED(v4si);
+STP_TEST_ADJUST_ALIGNED(int32_t);
+STP_TEST_ADJUST_ALIGNED(int64_t);
+STP_TEST_ADJUST_UNALIGNED(int32_t);
+STP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "stp\tw\[0-9\]+, w\[0-9\]" 3 } } */
+/* { dg-final { scan-assembler-times "stp\tx\[0-9\]+, x\[0-9\]" 3 } } */
+/* { dg-final { scan-assembler-times "stp\tq\[0-9\]+, q\[0-9\]" 1 } } */
+
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-options "-O2 --param=aarch64-stp-policy=always -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define STP_TEST_ALIGNED(TYPE) \
+TYPE *stp_aligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[0] = x; \
+ arr[1] = x; \
+ return arr; \
+}
+
+#define STP_TEST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[0] = x; \
+ a[1] = x; \
+ return a; \
+}
+
+#define STP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE *stp_aligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[100] = x; \
+ arr[101] = x; \
+ arr[102] = x; \
+ arr[103] = x; \
+ return arr; \
+}
+
+#define STP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[100] = x; \
+ a[101] = x; \
+ a[102] = x; \
+ a[103] = x; \
+ return a; \
+}
+
+STP_TEST_ALIGNED(int32_t);
+STP_TEST_ALIGNED(int64_t);
+STP_TEST_ALIGNED(v4si);
+STP_TEST_UNALIGNED(int32_t);
+STP_TEST_UNALIGNED(int64_t);
+STP_TEST_UNALIGNED(v4si);
+STP_TEST_ADJUST_ALIGNED(int32_t);
+STP_TEST_ADJUST_ALIGNED(int64_t);
+STP_TEST_ADJUST_UNALIGNED(int32_t);
+STP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "stp\tw\[0-9\]+, w\[0-9\]" 6 } } */
+/* { dg-final { scan-assembler-times "stp\tx\[0-9\]+, x\[0-9\]" 6 } } */
+/* { dg-final { scan-assembler-times "stp\tq\[0-9\]+, q\[0-9\]" 2 } } */
+
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-options "-O2 --param=aarch64-stp-policy=never -mcpu=generic" } */
+
+#include <stdlib.h>
+#include <stdint.h>
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+#define STP_TEST_ALIGNED(TYPE) \
+TYPE *stp_aligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[0] = x; \
+ arr[1] = x; \
+ return arr; \
+}
+
+#define STP_TEST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[0] = x; \
+ a[1] = x; \
+ return a; \
+}
+
+#define STP_TEST_ADJUST_ALIGNED(TYPE) \
+TYPE *stp_aligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ arr[100] = x; \
+ arr[101] = x; \
+ arr[102] = x; \
+ arr[103] = x; \
+ return arr; \
+}
+
+#define STP_TEST_ADJUST_UNALIGNED(TYPE) \
+TYPE *stp_unaligned_adjust_##TYPE(char* ptr, TYPE x){ \
+ TYPE *arr = (TYPE*) ((uintptr_t)ptr & ~(2 * 8 * _Alignof(TYPE) - 1)); \
+ TYPE *a = arr+1; \
+ a[100] = x; \
+ a[101] = x; \
+ a[102] = x; \
+ a[103] = x; \
+ return a; \
+}
+
+STP_TEST_ALIGNED(int32_t);
+STP_TEST_ALIGNED(int64_t);
+STP_TEST_ALIGNED(v4si);
+STP_TEST_UNALIGNED(int32_t);
+STP_TEST_UNALIGNED(int64_t);
+STP_TEST_UNALIGNED(v4si);
+STP_TEST_ADJUST_ALIGNED(int32_t);
+STP_TEST_ADJUST_ALIGNED(int64_t);
+STP_TEST_ADJUST_UNALIGNED(int32_t);
+STP_TEST_ADJUST_UNALIGNED(int64_t);
+
+/* { dg-final { scan-assembler-times "stp\tw\[0-9\]+, w\[0-9\]" 0 } } */
+/* { dg-final { scan-assembler-times "stp\tx\[0-9\]+, x\[0-9\]" 0 } } */
+/* { dg-final { scan-assembler-times "stp\tq\[0-9\]+, q\[0-9\]" 0 } } */
+