gcc/

	Backport from trunk r237857.
	2016-06-29  Jim Wilson  <jim.wilson@linaro.org>

	* config/aarch64/aarch64-cores.def (qdf24xx): Use qdf24xx tuning.
	* config/aarch64/aarch64.c (qdf24xx_addrcost_table,
	qdf24xx_regmove_cost, qdf24xx_tunings): New.
	* config/arm/aarch64-cost-tables.h (qdf24xx_extra_costs): New.
	* config/arm/arm-cores.def (qdf24xx): Use qdf24xx tuning.
	* config/arm/arm.c (arm_qdf24xx_tune): New.

	gcc/testsuite/
	Backport from trunk r237857.
	2016-06-29  Jim Wilson  <jim.wilson@linaro.org>

	* gcc.dg/asr_div1.c: Add aarch64 specific dg-options.

Change-Id: I6937b1e3ec6049a296ab700994cd79ea1c637979

6 files changed, 180 insertions, 2 deletions

diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index bc83ab45a5c..d9da2576dea 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -46,7 +46,7 @@ AARCH64_CORE("cortex-a57",  cortexa57, cortexa57, 8A,  AARCH64_FL_FOR_ARCH8 | AA
 AARCH64_CORE("cortex-a72",  cortexa72, cortexa57, 8A,  AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, "0x41", "0xd08")
 AARCH64_CORE("cortex-a73",  cortexa73, cortexa57, 8A,  AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa73, "0x41", "0xd09")
 AARCH64_CORE("exynos-m1",   exynosm1,  exynosm1,  8A,  AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, exynosm1,  "0x53", "0x001")
-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, qdf24xx,   "0x51", "0x800")
 AARCH64_CORE("thunderx",    thunderx,  thunderx,  8A,  AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx,  "0x43", "0x0a1")
 AARCH64_CORE("xgene1",      xgene1,    xgene1,    8A,  AARCH64_FL_FOR_ARCH8, xgene1, "0x50", "0x000")
 
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index a4a34b57f0e..3537aa3299c 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -250,6 +250,22 @@ static const struct cpu_addrcost_table xgene1_addrcost_table =
   0, /* imm_offset  */
 };
 
+static const struct cpu_addrcost_table qdf24xx_addrcost_table =
+{
+    {
+      1, /* hi  */
+      0, /* si  */
+      0, /* di  */
+      1, /* ti  */
+    },
+  0, /* pre_modify  */
+  0, /* post_modify  */
+  0, /* register_offset  */
+  0, /* register_sextend  */
+  0, /* register_zextend  */
+  0 /* imm_offset  */
+};
+
 static const struct cpu_addrcost_table vulcan_addrcost_table =
 {
     {
@@ -324,6 +340,15 @@ static const struct cpu_regmove_cost xgene1_regmove_cost =
   2 /* FP2FP  */
 };
 
+static const struct cpu_regmove_cost qdf24xx_regmove_cost =
+{
+  2, /* GP2GP  */
+  /* Avoid the use of int<->fp moves for spilling.  */
+  6, /* GP2FP  */
+  6, /* FP2GP  */
+  4 /* FP2FP  */
+};
+
 static const struct cpu_regmove_cost vulcan_regmove_cost =
 {
   1, /* GP2GP  */
@@ -715,6 +740,32 @@ static const struct tune_params xgene1_tunings =
   (AARCH64_EXTRA_TUNE_NONE)	/* tune_flags.  */
 };
 
+static const struct tune_params qdf24xx_tunings =
+{
+  &qdf24xx_extra_costs,
+  &qdf24xx_addrcost_table,
+  &qdf24xx_regmove_cost,
+  &generic_vector_cost,
+  &generic_branch_cost,
+  &generic_approx_modes,
+  4, /* memmov_cost  */
+  4, /* issue_rate  */
+  (AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
+   | AARCH64_FUSE_MOVK_MOVK), /* fuseable_ops  */
+  16,	/* function_align.  */
+  8,	/* jump_align.  */
+  16,	/* loop_align.  */
+  2,	/* int_reassoc_width.  */
+  4,	/* fp_reassoc_width.  */
+  1,	/* vec_reassoc_width.  */
+  2,	/* min_div_recip_mul_sf.  */
+  2,	/* min_div_recip_mul_df.  */
+  0,	/* max_case_values.  */
+  64,	/* cache_line_size.  */
+  tune_params::AUTOPREFETCHER_STRONG,	/* autoprefetcher_model.  */
+  (AARCH64_EXTRA_TUNE_NONE)		/* tune_flags.  */
+};
+
 static const struct tune_params vulcan_tunings =
 {
   &vulcan_extra_costs,
diff --git a/gcc/config/arm/aarch-cost-tables.h b/gcc/config/arm/aarch-cost-tables.h
index 8bcfcb4b934..b30c84f1656 100644
--- a/gcc/config/arm/aarch-cost-tables.h
+++ b/gcc/config/arm/aarch-cost-tables.h
@@ -537,4 +537,107 @@ const struct cpu_cost_table xgene1_extra_costs =
   }
 };
 
+const struct cpu_cost_table qdf24xx_extra_costs =
+{
+  /* ALU */
+  {
+    0,                 /* arith.  */
+    0,                 /* logical.  */
+    0,                 /* shift.  */
+    0,                 /* shift_reg.  */
+    COSTS_N_INSNS (1), /* arith_shift.  */
+    COSTS_N_INSNS (1), /* arith_shift_reg.  */
+    0,                 /* log_shift.  */
+    0,                 /* log_shift_reg.  */
+    0,                 /* extend.  */
+    0,                 /* extend_arith.  */
+    0,                 /* bfi.  */
+    0,                 /* bfx.  */
+    0,                 /* clz.  */
+    0,	               /* rev.  */
+    0,                 /* non_exec.  */
+    true               /* non_exec_costs_exec.  */
+  },
+  {
+    /* MULT SImode */
+    {
+      COSTS_N_INSNS (2),       /* simple.  */
+      COSTS_N_INSNS (2),       /* flag_setting.  */
+      COSTS_N_INSNS (2),       /* extend.  */
+      COSTS_N_INSNS (2),       /* add.  */
+      COSTS_N_INSNS (2),       /* extend_add.  */
+      COSTS_N_INSNS (4)       /* idiv.  */
+    },
+    /* MULT DImode */
+    {
+      COSTS_N_INSNS (3),       /* simple.  */
+      0,                       /* flag_setting (N/A).  */
+      COSTS_N_INSNS (3),       /* extend.  */
+      COSTS_N_INSNS (3),       /* add.  */
+      COSTS_N_INSNS (3),       /* extend_add.  */
+      COSTS_N_INSNS (9)       /* idiv.  */
+    }
+  },
+  /* LD/ST */
+  {
+    COSTS_N_INSNS (2),         /* load.  */
+    COSTS_N_INSNS (2),         /* load_sign_extend.  */
+    COSTS_N_INSNS (2),         /* ldrd.  */
+    COSTS_N_INSNS (2),         /* ldm_1st.  */
+    1,                         /* ldm_regs_per_insn_1st.  */
+    2,                         /* ldm_regs_per_insn_subsequent.  */
+    COSTS_N_INSNS (2),         /* loadf.  */
+    COSTS_N_INSNS (2),         /* loadd.  */
+    COSTS_N_INSNS (3),         /* load_unaligned.  */
+    0,                         /* store.  */
+    0,                         /* strd.  */
+    0,                         /* stm_1st.  */
+    1,                         /* stm_regs_per_insn_1st.  */
+    2,                         /* stm_regs_per_insn_subsequent.  */
+    0,                         /* storef.  */
+    0,                         /* stored.  */
+    COSTS_N_INSNS (1),         /* store_unaligned.  */
+    COSTS_N_INSNS (1),         /* loadv.  */
+    COSTS_N_INSNS (1)          /* storev.  */
+  },
+  {
+    /* FP SFmode */
+    {
+      COSTS_N_INSNS (6),      /* div.  */
+      COSTS_N_INSNS (5),       /* mult.  */
+      COSTS_N_INSNS (5),       /* mult_addsub. */
+      COSTS_N_INSNS (5),       /* fma.  */
+      COSTS_N_INSNS (3),       /* addsub.  */
+      COSTS_N_INSNS (1),       /* fpconst. */
+      COSTS_N_INSNS (1),       /* neg.  */
+      COSTS_N_INSNS (2),       /* compare.  */
+      COSTS_N_INSNS (4),       /* widen.  */
+      COSTS_N_INSNS (4),       /* narrow.  */
+      COSTS_N_INSNS (4),       /* toint.  */
+      COSTS_N_INSNS (4),       /* fromint.  */
+      COSTS_N_INSNS (2)        /* roundint.  */
+    },
+    /* FP DFmode */
+    {
+      COSTS_N_INSNS (11),      /* div.  */
+      COSTS_N_INSNS (6),       /* mult.  */
+      COSTS_N_INSNS (6),       /* mult_addsub.  */
+      COSTS_N_INSNS (6),       /* fma.  */
+      COSTS_N_INSNS (3),       /* addsub.  */
+      COSTS_N_INSNS (1),       /* fpconst.  */
+      COSTS_N_INSNS (1),       /* neg.  */
+      COSTS_N_INSNS (2),       /* compare.  */
+      COSTS_N_INSNS (4),       /* widen.  */
+      COSTS_N_INSNS (4),       /* narrow.  */
+      COSTS_N_INSNS (4),       /* toint.  */
+      COSTS_N_INSNS (4),       /* fromint.  */
+      COSTS_N_INSNS (2)        /* roundint.  */
+    }
+  },
+  /* Vector */
+  {
+    COSTS_N_INSNS (1)  /* alu.  */
+  }
+};
+
 #endif /* GCC_AARCH_COST_TABLES_H */
diff --git a/gcc/config/arm/arm-cores.def b/gcc/config/arm/arm-cores.def
index a53c7d819f5..2072e1e6f8d 100644
--- a/gcc/config/arm/arm-cores.def
+++ b/gcc/config/arm/arm-cores.def
@@ -173,7 +173,7 @@ ARM_CORE("cortex-a57",	cortexa57, cortexa57,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED
 ARM_CORE("cortex-a72",	cortexa72, cortexa57,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57)
 ARM_CORE("cortex-a73",	cortexa73, cortexa57,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a73)
 ARM_CORE("exynos-m1",	exynosm1,  exynosm1,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), exynosm1)
-ARM_CORE("qdf24xx",	qdf24xx,   cortexa57,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57)
+ARM_CORE("qdf24xx",	qdf24xx,   cortexa57,	8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), qdf24xx)
 ARM_CORE("xgene1",      xgene1,    xgene1,      8A,	ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_FOR_ARCH8A),            xgene1)
 
 /* V8 big.LITTLE implementations */
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index bf5f8242ca1..7f5ddc3e7e2 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -2052,6 +2052,29 @@ const struct tune_params arm_xgene1_tune =
   tune_params::SCHED_AUTOPREF_OFF
 };
 
+const struct tune_params arm_qdf24xx_tune =
+{
+  arm_9e_rtx_costs,
+  &qdf24xx_extra_costs,
+  NULL,                                         /* Scheduler cost adjustment.  */
+  arm_default_branch_cost,
+  &arm_default_vec_cost,			/* Vectorizer costs.  */
+  1,						/* Constant limit.  */
+  2,						/* Max cond insns.  */
+  8,						/* Memset max inline.  */
+  4,						/* Issue rate.  */
+  ARM_PREFETCH_BENEFICIAL (0, -1, 64),
+  tune_params::PREF_CONST_POOL_FALSE,
+  tune_params::PREF_LDRD_TRUE,
+  tune_params::LOG_OP_NON_SHORT_CIRCUIT_TRUE,	/* Thumb.  */
+  tune_params::LOG_OP_NON_SHORT_CIRCUIT_TRUE,	/* ARM.  */
+  tune_params::DISPARAGE_FLAGS_ALL,
+  tune_params::PREF_NEON_64_FALSE,
+  tune_params::PREF_NEON_STRINGOPS_TRUE,
+  FUSE_OPS (tune_params::FUSE_MOVW_MOVT),
+  tune_params::SCHED_AUTOPREF_FULL
+};
+
 /* Branches can be dual-issued on Cortex-A5, so conditional execution is
    less appealing.  Set max_insns_skipped to a low value.  */
 
diff --git a/gcc/testsuite/gcc.dg/asr_div1.c b/gcc/testsuite/gcc.dg/asr_div1.c
index 11b52469bcd..ac067e2023e 100644
--- a/gcc/testsuite/gcc.dg/asr_div1.c
+++ b/gcc/testsuite/gcc.dg/asr_div1.c
@@ -1,6 +1,7 @@
 /* Test division by const int generates only one shift.  */
 /* { dg-do run } */
 /* { dg-options "-O2 -fdump-rtl-combine-all" } */
+/* { dg-options "-O2 -fdump-rtl-combine-all -mtune=cortex-a53" { target aarch64*-*-* } } */
 
 extern void abort (void);