aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRichard Henderson <richard.henderson@linaro.org>2018-10-31 09:29:29 +0000
committerRichard Henderson <rth@gcc.gnu.org>2018-10-31 02:29:29 -0700
commit77f33f44baf24c22848197aa80962c003dd7b3e2 (patch)
treea1fc76d6ee8e85ab16d6ba4a95070461a6e27c8f
parent187cea947e54d08eaed2587edeb49a5cc1fe8d6a (diff)
downloadgcc-77f33f44baf24c22848197aa80962c003dd7b3e2.zip
gcc-77f33f44baf24c22848197aa80962c003dd7b3e2.tar.gz
gcc-77f33f44baf24c22848197aa80962c003dd7b3e2.tar.bz2
aarch64: Simplify LSE cas generation
The cas insn is a single insn, and if expanded properly need not be split after reload. Use the proper inputs for the insn. * config/aarch64/aarch64.c (aarch64_expand_compare_and_swap): Force oldval into the rval register for TARGET_LSE; emit the compare during initial expansion so that it may be deleted if unused. (aarch64_gen_atomic_cas): Remove. * config/aarch64/atomics.md (@aarch64_compare_and_swap<SHORT>_lse): Change =&r to +r for operand 0; use match_dup for operand 2; remove is_weak and mod_f operands as unused. Drop the split and merge with... (@aarch64_atomic_cas<SHORT>): ... this pattern's output; remove. (@aarch64_compare_and_swap<GPI>_lse): Similarly. (@aarch64_atomic_cas<GPI>): Similarly. From-SVN: r265656
-rw-r--r--gcc/ChangeLog14
-rw-r--r--gcc/config/aarch64/aarch64-protos.h1
-rw-r--r--gcc/config/aarch64/aarch64.c46
-rw-r--r--gcc/config/aarch64/atomics.md121
4 files changed, 63 insertions, 119 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 660bafb..3c764c5 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,17 @@
+2018-10-31 Richard Henderson <richard.henderson@linaro.org>
+
+ * config/aarch64/aarch64.c (aarch64_expand_compare_and_swap):
+ Force oldval into the rval register for TARGET_LSE; emit the compare
+ during initial expansion so that it may be deleted if unused.
+ (aarch64_gen_atomic_cas): Remove.
+ * config/aarch64/atomics.md (@aarch64_compare_and_swap<SHORT>_lse):
+ Change =&r to +r for operand 0; use match_dup for operand 2;
+ remove is_weak and mod_f operands as unused. Drop the split
+ and merge with...
+ (@aarch64_atomic_cas<SHORT>): ... this pattern's output; remove.
+ (@aarch64_compare_and_swap<GPI>_lse): Similarly.
+ (@aarch64_atomic_cas<GPI>): Similarly.
+
2018-10-31 Richard Biener <rguenther@suse.de>
* tree-eh.c (replace_trapping_overflow): Simplify ABS_EXPR case
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 776e869..f662533 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -563,7 +563,6 @@ rtx aarch64_load_tp (rtx);
void aarch64_expand_compare_and_swap (rtx op[]);
void aarch64_split_compare_and_swap (rtx op[]);
-void aarch64_gen_atomic_cas (rtx, rtx, rtx, rtx, rtx);
bool aarch64_atomic_ldop_supported_p (enum rtx_code);
void aarch64_gen_atomic_ldop (enum rtx_code, rtx, rtx, rtx, rtx, rtx);
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 54f5746..9d53cf9 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -14620,16 +14620,27 @@ aarch64_expand_compare_and_swap (rtx operands[])
}
if (TARGET_LSE)
- emit_insn (gen_aarch64_compare_and_swap_lse (mode, rval, mem, oldval,
- newval, is_weak, mod_s,
- mod_f));
+ {
+ /* The CAS insn requires oldval and rval overlap, but we need to
+ have a copy of oldval saved across the operation to tell if
+ the operation is successful. */
+ if (mode == QImode || mode == HImode)
+ rval = copy_to_mode_reg (SImode, gen_lowpart (SImode, oldval));
+ else if (reg_overlap_mentioned_p (rval, oldval))
+ rval = copy_to_mode_reg (mode, oldval);
+ else
+ emit_move_insn (rval, oldval);
+ emit_insn (gen_aarch64_compare_and_swap_lse (mode, rval, mem,
+ newval, mod_s));
+ aarch64_gen_compare_reg (EQ, rval, oldval);
+ }
else
emit_insn (gen_aarch64_compare_and_swap (mode, rval, mem, oldval, newval,
is_weak, mod_s, mod_f));
-
if (mode == QImode || mode == HImode)
- emit_move_insn (operands[1], gen_lowpart (mode, rval));
+ rval = gen_lowpart (mode, rval);
+ emit_move_insn (operands[1], rval);
x = gen_rtx_REG (CCmode, CC_REGNUM);
x = gen_rtx_EQ (SImode, x, const0_rtx);
@@ -14679,31 +14690,6 @@ aarch64_emit_post_barrier (enum memmodel model)
}
}
-/* Emit an atomic compare-and-swap operation. RVAL is the destination register
- for the data in memory. EXPECTED is the value expected to be in memory.
- DESIRED is the value to store to memory. MEM is the memory location. MODEL
- is the memory ordering to use. */
-
-void
-aarch64_gen_atomic_cas (rtx rval, rtx mem,
- rtx expected, rtx desired,
- rtx model)
-{
- machine_mode mode;
-
- mode = GET_MODE (mem);
-
- /* Move the expected value into the CAS destination register. */
- emit_insn (gen_rtx_SET (rval, expected));
-
- /* Emit the CAS. */
- emit_insn (gen_aarch64_atomic_cas (mode, rval, mem, desired, model));
-
- /* Compare the expected value with the value loaded by the CAS, to establish
- whether the swap was made. */
- aarch64_gen_compare_reg (EQ, rval, expected);
-}
-
/* Split a compare and swap pattern. */
void
diff --git a/gcc/config/aarch64/atomics.md b/gcc/config/aarch64/atomics.md
index bba8e9e..2266085 100644
--- a/gcc/config/aarch64/atomics.md
+++ b/gcc/config/aarch64/atomics.md
@@ -85,56 +85,50 @@
}
)
-(define_insn_and_split "@aarch64_compare_and_swap<mode>_lse"
- [(set (reg:CC CC_REGNUM) ;; bool out
- (unspec_volatile:CC [(const_int 0)] UNSPECV_ATOMIC_CMPSW))
- (set (match_operand:SI 0 "register_operand" "=&r") ;; val out
+(define_insn "@aarch64_compare_and_swap<mode>_lse"
+ [(set (match_operand:SI 0 "register_operand" "+r") ;; val out
(zero_extend:SI
- (match_operand:SHORT 1 "aarch64_sync_memory_operand" "+Q"))) ;; memory
+ (match_operand:SHORT 1 "aarch64_sync_memory_operand" "+Q"))) ;; memory
(set (match_dup 1)
(unspec_volatile:SHORT
- [(match_operand:SI 2 "aarch64_plus_operand" "rI") ;; expected
- (match_operand:SHORT 3 "aarch64_reg_or_zero" "rZ") ;; desired
- (match_operand:SI 4 "const_int_operand") ;; is_weak
- (match_operand:SI 5 "const_int_operand") ;; mod_s
- (match_operand:SI 6 "const_int_operand")] ;; mod_f
+ [(match_dup 0) ;; expected
+ (match_operand:SHORT 2 "aarch64_reg_or_zero" "rZ") ;; desired
+ (match_operand:SI 3 "const_int_operand")] ;; mod_s
UNSPECV_ATOMIC_CMPSW))]
"TARGET_LSE"
- "#"
- "&& reload_completed"
- [(const_int 0)]
- {
- aarch64_gen_atomic_cas (operands[0], operands[1],
- operands[2], operands[3],
- operands[5]);
- DONE;
- }
-)
+{
+ enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
+ if (is_mm_relaxed (model))
+ return "cas<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else if (is_mm_acquire (model) || is_mm_consume (model))
+ return "casa<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else if (is_mm_release (model))
+ return "casl<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else
+ return "casal<atomic_sfx>\t%<w>0, %<w>2, %1";
+})
-(define_insn_and_split "@aarch64_compare_and_swap<mode>_lse"
- [(set (reg:CC CC_REGNUM) ;; bool out
- (unspec_volatile:CC [(const_int 0)] UNSPECV_ATOMIC_CMPSW))
- (set (match_operand:GPI 0 "register_operand" "=&r") ;; val out
+(define_insn "@aarch64_compare_and_swap<mode>_lse"
+ [(set (match_operand:GPI 0 "register_operand" "+r") ;; val out
(match_operand:GPI 1 "aarch64_sync_memory_operand" "+Q")) ;; memory
(set (match_dup 1)
(unspec_volatile:GPI
- [(match_operand:GPI 2 "aarch64_plus_operand" "rI") ;; expect
- (match_operand:GPI 3 "aarch64_reg_or_zero" "rZ") ;; desired
- (match_operand:SI 4 "const_int_operand") ;; is_weak
- (match_operand:SI 5 "const_int_operand") ;; mod_s
- (match_operand:SI 6 "const_int_operand")] ;; mod_f
+ [(match_dup 0) ;; expected
+ (match_operand:GPI 2 "aarch64_reg_or_zero" "rZ") ;; desired
+ (match_operand:SI 3 "const_int_operand")] ;; mod_s
UNSPECV_ATOMIC_CMPSW))]
"TARGET_LSE"
- "#"
- "&& reload_completed"
- [(const_int 0)]
- {
- aarch64_gen_atomic_cas (operands[0], operands[1],
- operands[2], operands[3],
- operands[5]);
- DONE;
- }
-)
+{
+ enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
+ if (is_mm_relaxed (model))
+ return "cas<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else if (is_mm_acquire (model) || is_mm_consume (model))
+ return "casa<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else if (is_mm_release (model))
+ return "casl<atomic_sfx>\t%<w>0, %<w>2, %1";
+ else
+ return "casal<atomic_sfx>\t%<w>0, %<w>2, %1";
+})
(define_expand "atomic_exchange<mode>"
[(match_operand:ALLI 0 "register_operand" "")
@@ -610,55 +604,6 @@
return "swpal<atomic_sfx>\t%<w>2, %<w>0, %1";
})
-;; Atomic compare-and-swap: HI and smaller modes.
-
-(define_insn "@aarch64_atomic_cas<mode>"
- [(set (match_operand:SI 0 "register_operand" "+&r") ;; out
- (zero_extend:SI
- (match_operand:SHORT 1 "aarch64_sync_memory_operand" "+Q"))) ;; memory.
- (set (match_dup 1)
- (unspec_volatile:SHORT
- [(match_dup 0)
- (match_operand:SHORT 2 "aarch64_reg_or_zero" "rZ") ;; value.
- (match_operand:SI 3 "const_int_operand" "")] ;; model.
- UNSPECV_ATOMIC_CAS))]
- "TARGET_LSE && reload_completed"
-{
- enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
- if (is_mm_relaxed (model))
- return "cas<atomic_sfx>\t%<w>0, %<w>2, %1";
- else if (is_mm_acquire (model) || is_mm_consume (model))
- return "casa<atomic_sfx>\t%<w>0, %<w>2, %1";
- else if (is_mm_release (model))
- return "casl<atomic_sfx>\t%<w>0, %<w>2, %1";
- else
- return "casal<atomic_sfx>\t%<w>0, %<w>2, %1";
-})
-
-;; Atomic compare-and-swap: SI and larger modes.
-
-(define_insn "@aarch64_atomic_cas<mode>"
- [(set (match_operand:GPI 0 "register_operand" "+&r") ;; out
- (match_operand:GPI 1 "aarch64_sync_memory_operand" "+Q")) ;; memory.
- (set (match_dup 1)
- (unspec_volatile:GPI
- [(match_dup 0)
- (match_operand:GPI 2 "aarch64_reg_or_zero" "rZ") ;; value.
- (match_operand:SI 3 "const_int_operand" "")] ;; model.
- UNSPECV_ATOMIC_CAS))]
- "TARGET_LSE && reload_completed"
-{
- enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
- if (is_mm_relaxed (model))
- return "cas<atomic_sfx>\t%<w>0, %<w>2, %1";
- else if (is_mm_acquire (model) || is_mm_consume (model))
- return "casa<atomic_sfx>\t%<w>0, %<w>2, %1";
- else if (is_mm_release (model))
- return "casl<atomic_sfx>\t%<w>0, %<w>2, %1";
- else
- return "casal<atomic_sfx>\t%<w>0, %<w>2, %1";
-})
-
;; Atomic load-op: Load data, operate, store result, keep data.
(define_insn "@aarch64_atomic_load<atomic_ldop><mode>"