Give the `define_insn` rules used in lowering `cbranch<mode>4` to RTL
more descriptive and consistent names: from now on, each rule is named
after the AArch64 instruction that it generates. Also add comments to
document each rule.
gcc/ChangeLog:
* config/aarch64/aarch64.md (condjump): Rename to ...
(aarch64_bcond): ...here.
(*compare_condjump<GPI:mode>): Rename to ...
(*aarch64_bcond_wide_imm<GPI:mode>): ...here.
(aarch64_cb<optab><mode>): Rename to ...
(aarch64_cbz<optab><mode>1): ...here.
(*cb<optab><mode>1): Rename to ...
(*aarch64_tbz<optab><mode>1): ...here.
(@aarch64_tb<optab><ALLI:mode><GPI:mode>): Rename to ...
(@aarch64_tbz<optab><ALLI:mode><GPI:mode>): ...here.
(restore_stack_nonlocal): Handle rename.
(stack_protect_combined_test): Likewise.
* config/aarch64/aarch64-simd.md (cbranch<mode>4): Likewise.
* config/aarch64/aarch64-sme.md (aarch64_restore_za): Likewise.
* config/aarch64/aarch64.cc (aarch64_gen_test_and_branch): Likewise.
---
gcc/config/aarch64/aarch64-simd.md | 2 +-
gcc/config/aarch64/aarch64-sme.md | 2 +-
gcc/config/aarch64/aarch64.cc | 4 ++--
gcc/config/aarch64/aarch64.md | 21 ++++++++++++---------
4 files changed, 16 insertions(+), 13 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-simd.md
b/gcc/config/aarch64/aarch64-simd.md
index 1099e742cbf..a816f6a3cea 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -3915,41 +3915,41 @@ (define_expand "vcond_mask_<mode><v_int_equiv>"
(define_expand "cbranch<mode>4"
[(set (pc)
(if_then_else
(match_operator 0 "aarch64_equality_operator"
[(match_operand:VDQ_I 1 "register_operand")
(match_operand:VDQ_I 2 "aarch64_simd_reg_or_zero")])
(label_ref (match_operand 3 ""))
(pc)))]
"TARGET_SIMD"
{
auto code = GET_CODE (operands[0]);
rtx tmp = operands[1];
/* If comparing against a non-zero vector we have to do a comparison first
so we can have a != 0 comparison with the result. */
if (operands[2] != CONST0_RTX (<MODE>mode))
{
tmp = gen_reg_rtx (<MODE>mode);
emit_insn (gen_xor<mode>3 (tmp, operands[1], operands[2]));
}
/* For 64-bit vectors we need no reductions. */
if (known_eq (128, GET_MODE_BITSIZE (<MODE>mode)))
{
/* Always reduce using a V4SI. */
rtx reduc = gen_lowpart (V4SImode, tmp);
rtx res = gen_reg_rtx (V4SImode);
emit_insn (gen_aarch64_umaxpv4si (res, reduc, reduc));
emit_move_insn (tmp, gen_lowpart (<MODE>mode, res));
}
rtx val = gen_reg_rtx (DImode);
emit_move_insn (val, gen_lowpart (DImode, tmp));
rtx cc_reg = aarch64_gen_compare_reg (code, val, const0_rtx);
rtx cmp_rtx = gen_rtx_fmt_ee (code, DImode, cc_reg, const0_rtx);
- emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, operands[3]));
+ emit_jump_insn (gen_aarch64_bcond (cmp_rtx, cc_reg, operands[3]));
DONE;
})
;; Patterns comparing two vectors to produce a mask.
diff --git a/gcc/config/aarch64/aarch64-sme.md
b/gcc/config/aarch64/aarch64-sme.md
index c49affd0dd3..4e4ac71c5a3 100644
--- a/gcc/config/aarch64/aarch64-sme.md
+++ b/gcc/config/aarch64/aarch64-sme.md
@@ -366,42 +366,42 @@ (define_insn "aarch64_tpidr2_restore"
;; Check whether a lazy save set up by aarch64_save_za was committed
;; and restore the saved contents if so.
;;
;; Operand 0 is the address of the current function's TPIDR2 block.
(define_insn_and_split "aarch64_restore_za"
[(set (reg:DI ZA_SAVED_REGNUM)
(unspec:DI [(match_operand 0 "pmode_register_operand" "r")
(reg:DI SME_STATE_REGNUM)
(reg:DI TPIDR2_SETUP_REGNUM)
(reg:DI ZA_SAVED_REGNUM)] UNSPEC_RESTORE_ZA))
(clobber (reg:DI R0_REGNUM))
(clobber (reg:DI R14_REGNUM))
(clobber (reg:DI R15_REGNUM))
(clobber (reg:DI R16_REGNUM))
(clobber (reg:DI R17_REGNUM))
(clobber (reg:DI R18_REGNUM))
(clobber (reg:DI R30_REGNUM))
(clobber (reg:CC CC_REGNUM))]
""
"#"
"&& epilogue_completed"
[(const_int 0)]
{
auto label = gen_label_rtx ();
auto tpidr2 = gen_rtx_REG (DImode, R16_REGNUM);
emit_insn (gen_aarch64_read_tpidr2 (tpidr2));
- auto jump = emit_likely_jump_insn (gen_aarch64_cbnedi1 (tpidr2, label));
+ auto jump = emit_likely_jump_insn (gen_aarch64_cbznedi1 (tpidr2, label));
JUMP_LABEL (jump) = label;
aarch64_restore_za (operands[0]);
emit_label (label);
DONE;
}
)
;; This instruction is emitted after asms that alter ZA, in order to model
;; the effect on dataflow. The asm itself can't have ZA as an input or
;; an output, since there is no associated data type. Instead it retains
;; the original "za" clobber, which on its own would indicate that ZA
;; is dead.
;;
;; The operand is a unique identifier.
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 9e3f2885bcc..5000672e4a2 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -2872,44 +2872,44 @@ static rtx
aarch64_gen_test_and_branch (rtx_code code, rtx x, int bitnum,
rtx_code_label *label)
{
auto mode = GET_MODE (x);
if (aarch64_track_speculation)
{
auto mask = gen_int_mode (HOST_WIDE_INT_1U << bitnum, mode);
emit_insn (gen_aarch64_and3nr_compare0 (mode, x, mask));
rtx cc_reg = gen_rtx_REG (CC_NZVmode, CC_REGNUM);
rtx x = gen_rtx_fmt_ee (code, CC_NZVmode, cc_reg, const0_rtx);
- return gen_condjump (x, cc_reg, label);
+ return gen_aarch64_bcond (x, cc_reg, label);
}
- return gen_aarch64_tb (code, mode, mode,
+ return gen_aarch64_tbz (code, mode, mode,
x, gen_int_mode (bitnum, mode), label);
}
/* Consider the operation:
OPERANDS[0] = CODE (OPERANDS[1], OPERANDS[2]) + OPERANDS[3]
where:
- CODE is [SU]MAX or [SU]MIN
- OPERANDS[2] and OPERANDS[3] are constant integers
- OPERANDS[3] is a positive or negative shifted 12-bit immediate
- all operands have mode MODE
Decide whether it is possible to implement the operation using:
SUBS <tmp>, OPERANDS[1], -OPERANDS[3]
or
ADDS <tmp>, OPERANDS[1], OPERANDS[3]
followed by:
<insn> OPERANDS[0], <tmp>, [wx]zr, <cond>
where <insn> is one of CSEL, CSINV or CSINC. Return true if so.
If GENERATE_P is true, also update OPERANDS as follows:
OPERANDS[4] = -OPERANDS[3]
OPERANDS[5] = the rtl condition representing <cond>
OPERANDS[6] = <tmp>
OPERANDS[7] = 0 for CSEL, -1 for CSINV or 1 for CSINC. */
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 05d86595bb1..ba0d1cccdd0 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -740,135 +740,138 @@ (define_expand "cbranchcc4"
""
)
-(define_insn "condjump"
+;; Emit `B<cond>`, assuming that the condition is already in the CC register.
+(define_insn "aarch64_bcond"
[(set (pc) (if_then_else (match_operator 0 "aarch64_comparison_operator"
[(match_operand 1 "cc_register")
(const_int 0)])
(label_ref (match_operand 2))
(pc)))]
""
{
/* GCC's traditional style has been to use "beq" instead of "b.eq", etc.,
but the "." is required for SVE conditions. */
bool use_dot_p = GET_MODE (operands[1]) == CC_NZCmode;
if (get_attr_length (insn) == 8)
return aarch64_gen_far_branch (operands, 2, "Lbcond",
use_dot_p ? "b.%M0\\t" : "b%M0\\t");
else
return use_dot_p ? "b.%m0\\t%l2" : "b%m0\\t%l2";
}
[(set_attr "type" "branch")
(set (attr "length")
(if_then_else (and (ge (minus (match_dup 2) (pc)) (const_int -1048576))
(lt (minus (match_dup 2) (pc)) (const_int 1048572)))
(const_int 4)
(const_int 8)))
(set (attr "far_branch")
(if_then_else (and (ge (minus (match_dup 2) (pc)) (const_int -1048576))
(lt (minus (match_dup 2) (pc)) (const_int 1048572)))
(const_int 0)
(const_int 1)))]
)
;; For a 24-bit immediate CST we can optimize the compare for equality
;; and branch sequence from:
;; mov x0, #imm1
;; movk x0, #imm2, lsl 16 /* x0 contains CST. */
;; cmp x1, x0
;; b<ne,eq> .Label
;; into the shorter:
;; sub x0, x1, #(CST & 0xfff000)
;; subs x0, x0, #(CST & 0x000fff)
;; b<ne,eq> .Label
-(define_insn_and_split "*compare_condjump<GPI:mode>"
+(define_insn_and_split "*aarch64_bcond_wide_imm<GPI:mode>"
[(set (pc) (if_then_else (EQL (match_operand:GPI 0 "register_operand" "r")
(match_operand:GPI 1 "aarch64_imm24" "n"))
(label_ref:P (match_operand 2))
(pc)))]
"!aarch64_move_imm (INTVAL (operands[1]), <GPI:MODE>mode)
&& !aarch64_plus_operand (operands[1], <GPI:MODE>mode)
&& !reload_completed"
"#"
"&& true"
[(const_int 0)]
{
HOST_WIDE_INT lo_imm = UINTVAL (operands[1]) & 0xfff;
HOST_WIDE_INT hi_imm = UINTVAL (operands[1]) & 0xfff000;
rtx tmp = gen_reg_rtx (<GPI:MODE>mode);
emit_insn (gen_add<GPI:mode>3 (tmp, operands[0], GEN_INT (-hi_imm)));
emit_insn (gen_add<GPI:mode>3_compare0 (tmp, tmp, GEN_INT (-lo_imm)));
rtx cc_reg = gen_rtx_REG (CC_NZmode, CC_REGNUM);
rtx cmp_rtx = gen_rtx_fmt_ee (<EQL:CMP>, <GPI:MODE>mode,
cc_reg, const0_rtx);
- emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, operands[2]));
+ emit_jump_insn (gen_aarch64_bcond (cmp_rtx, cc_reg, operands[2]));
DONE;
}
)
-(define_insn "aarch64_cb<optab><mode>1"
+;; For an EQ/NE comparison against zero, emit `CBZ`/`CBNZ`
+(define_insn "aarch64_cbz<optab><mode>1"
[(set (pc) (if_then_else (EQL (match_operand:GPI 0 "register_operand" "r")
(const_int 0))
(label_ref (match_operand 1))
(pc)))]
"!aarch64_track_speculation"
{
if (get_attr_length (insn) == 8)
return aarch64_gen_far_branch (operands, 1, "Lcb", "<inv_cb>\\t%<w>0, ");
else
return "<cbz>\\t%<w>0, %l1";
}
[(set_attr "type" "branch")
(set (attr "length")
(if_then_else (and (ge (minus (match_dup 1) (pc)) (const_int -1048576))
(lt (minus (match_dup 1) (pc)) (const_int 1048572)))
(const_int 4)
(const_int 8)))
(set (attr "far_branch")
(if_then_else (and (ge (minus (match_dup 2) (pc)) (const_int -1048576))
(lt (minus (match_dup 2) (pc)) (const_int 1048572)))
(const_int 0)
(const_int 1)))]
)
-(define_insn "*cb<optab><mode>1"
+;; For an LT/GE comparison against zero, emit `TBZ`/`TBNZ`
+(define_insn "*aarch64_tbz<optab><mode>1"
[(set (pc) (if_then_else (LTGE (match_operand:ALLI 0 "register_operand" "r")
(const_int 0))
(label_ref (match_operand 1))
(pc)))
(clobber (reg:CC CC_REGNUM))]
"!aarch64_track_speculation"
{
if (get_attr_length (insn) == 8)
{
if (get_attr_far_branch (insn) == 1)
return aarch64_gen_far_branch (operands, 1, "Ltb",
"<inv_tb>\\t%<w>0, <sizem1>, ");
else
{
char buf[64];
uint64_t val = ((uint64_t) 1)
<< (GET_MODE_SIZE (<MODE>mode) * BITS_PER_UNIT - 1);
sprintf (buf, "tst\t%%<w>0, %" PRId64, val);
output_asm_insn (buf, operands);
return "<bcond>\t%l1";
}
}
else
return "<tbz>\t%<w>0, <sizem1>, %l1";
}
[(set_attr "type" "branch")
(set (attr "length")
(if_then_else (and (ge (minus (match_dup 1) (pc)) (const_int -32768))
(lt (minus (match_dup 1) (pc)) (const_int 32764)))
(const_int 4)
(const_int 8)))
(set (attr "far_branch")
(if_then_else (and (ge (minus (match_dup 1) (pc)) (const_int -1048576))
(lt (minus (match_dup 1) (pc)) (const_int 1048572)))
(const_int 0)
(const_int 1)))]
)
;; -------------------------------------------------------------------
;; Test bit and branch
;; -------------------------------------------------------------------
@@ -891,42 +894,42 @@ (define_expand "tbranch_<code><mode>3"
operands[1]);
})
-(define_insn "@aarch64_tb<optab><ALLI:mode><GPI:mode>"
+(define_insn "@aarch64_tbz<optab><ALLI:mode><GPI:mode>"
[(set (pc) (if_then_else (EQL
(zero_extract:GPI
(match_operand:ALLI 0 "register_operand" "r")
(const_int 1)
(match_operand 1
"aarch64_simd_shift_imm_<ALLI:mode>" "n"))
(const_int 0))
(label_ref (match_operand 2))
(pc)))
(clobber (reg:CC CC_REGNUM))]
"!aarch64_track_speculation"
{
if (get_attr_length (insn) == 8)
{
if (get_attr_far_branch (insn) == 1)
return aarch64_gen_far_branch (operands, 2, "Ltb",
"<inv_tb>\\t%<ALLI:w>0, %1, ");
else
{
operands[1] = GEN_INT (HOST_WIDE_INT_1U << UINTVAL (operands[1]));
return "tst\t%<ALLI:w>0, %1\;<bcond>\t%l2";
}
}
else
return "<tbz>\t%<ALLI:w>0, %1, %l2";
}
[(set_attr "type" "branch")
(set (attr "length")
(if_then_else (and (ge (minus (match_dup 2) (pc)) (const_int -32768))
(lt (minus (match_dup 2) (pc)) (const_int 32764)))
(const_int 4)
(const_int 8)))
(set (attr "far_branch")
(if_then_else (and (ge (minus (match_dup 2) (pc)) (const_int -1048576))
(lt (minus (match_dup 2) (pc)) (const_int 1048572)))
(const_int 0)
(const_int 1)))]
)
@@ -1287,53 +1290,53 @@ (define_expand "save_stack_nonlocal"
(define_expand "restore_stack_nonlocal"
[(set (match_operand 0 "register_operand" "")
(match_operand 1 "memory_operand" ""))]
""
{
rtx stack_slot = adjust_address (operands[1], Pmode, 0);
emit_move_insn (operands[0], stack_slot);
if (aarch64_gcs_enabled ())
{
/* Restore GCS with code like
mov x16, 1
chkfeat x16
tbnz x16, 0, .L_done
ldr tmp1, [%1, 8]
mrs tmp2, gcspr_el0
subs tmp2, tmp1, tmp2
b.eq .L_done
.L_loop:
gcspopm
subs tmp2, tmp2, 8
b.ne .L_loop
.L_done: */
rtx loop_label = gen_label_rtx ();
rtx done_label = gen_label_rtx ();
rtx r16 = gen_rtx_REG (DImode, R16_REGNUM);
emit_move_insn (r16, const1_rtx);
emit_insn (gen_aarch64_chkfeat ());
emit_insn (gen_tbranch_neqi3 (r16, const0_rtx, done_label));
rtx gcs_slot = adjust_address (operands[1], Pmode, GET_MODE_SIZE
(Pmode));
rtx gcs_old = gen_reg_rtx (Pmode);
emit_move_insn (gcs_old, gcs_slot);
rtx gcs_now = gen_reg_rtx (Pmode);
emit_insn (gen_aarch64_load_gcspr (gcs_now));
emit_insn (gen_subdi3_compare1 (gcs_now, gcs_old, gcs_now));
rtx cc_reg = gen_rtx_REG (CC_NZmode, CC_REGNUM);
rtx cmp_rtx = gen_rtx_fmt_ee (EQ, DImode, cc_reg, const0_rtx);
- emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, done_label));
+ emit_jump_insn (gen_aarch64_bcond (cmp_rtx, cc_reg, done_label));
emit_label (loop_label);
emit_insn (gen_aarch64_gcspopm_xzr ());
emit_insn (gen_adddi3_compare0 (gcs_now, gcs_now, GEN_INT (-8)));
cc_reg = gen_rtx_REG (CC_NZmode, CC_REGNUM);
cmp_rtx = gen_rtx_fmt_ee (NE, DImode, cc_reg, const0_rtx);
- emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, loop_label));
+ emit_jump_insn (gen_aarch64_bcond (cmp_rtx, cc_reg, loop_label));
emit_label (done_label);
}
DONE;
})
;; -------------------------------------------------------------------
;; Subroutine calls and sibcalls
;; -------------------------------------------------------------------
@@ -8085,21 +8088,21 @@ (define_expand "stack_protect_test"
(define_expand "stack_protect_combined_test"
[(match_operand 0 "memory_operand")
(match_operand 1 "")
(match_operand 2)]
""
{
machine_mode mode = GET_MODE (operands[0]);
operands[1] = aarch64_stack_protect_canary_mem (mode, operands[1],
AARCH64_SALT_SSP_TEST);
emit_insn ((mode == DImode
? gen_stack_protect_test_di
: gen_stack_protect_test_si) (operands[0], operands[1]));
rtx cc_reg = gen_rtx_REG (CCmode, CC_REGNUM);
- emit_jump_insn (gen_condjump (gen_rtx_EQ (VOIDmode, cc_reg, const0_rtx),
+ emit_jump_insn (gen_aarch64_bcond (gen_rtx_EQ (VOIDmode, cc_reg, const0_rtx),
cc_reg, operands[2]));
DONE;
})
;; DO NOT SPLIT THIS PATTERN. It is important for security reasons that the
;; canary value does not live beyond the end of this sequence.
--
2.45.2
