This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[gomp4] remove goacc locking
- From: Nathan Sidwell <nathan at acm dot org>
- To: GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: Mon, 28 Sep 2015 11:56:09 -0400
- Subject: [gomp4] remove goacc locking
- Authentication-results: sourceware.org; auth=none
I've committed this to remove the now no longer needed lock and unlock builtins
and related infrastructure.
nathan
2015-09-28 Nathan Sidwell <nathan@codesourcery.com>
* target.def (GOACC_LOCK): Delete hook.
* doc/tm.texi.in (TARGET_GOACC_LOCK): Delete.
* doc/tm.texi: Rebuilt.
* targhooks.h (default_goacc_lock): Delete.
* internal-fn.def (GOACC_LOCK, GOACC_UNLOCK, GOACC_LOCK_INIT): Delete.
* internal-fn.c (expand_GOACC_LOCK, expand_GOACC_UNLOCK,
expand_GOACC_LOCK_INIT): Delete.
* omp-low.c (lower_oacc_reductions): Remove locking.
(execute_oacc_transform): Remove lock transforming.
(default_goacc_lock): Delete.
* config/nvptx/nvptx-protos.h (nvptx_expand_oacc_lock): Delete.
* config/nvptx/nvptx.md (oacc_lock, oacc_unlock, oacc_lock_init):
Delete.
(nvptx_spin_lock, nvptx_spin_reset): Delete.
* config/nvptx/nvptx.c (LOCK_GLOBAL, LOCK_SHARED, LOCK_MAX): Delete.
(lock_names, lock_space, lock_level, lock_used): Delete.
(force_global_locks): Delete.
(nvptx_option_override): Do not initialize lock syms.
(nvptx_expand_oacc_lock): Delete.
(nvptx_file_end): Do not finalize locks.
(TARGET_GOACC_LOCK): Delete.
Index: internal-fn.def
===================================================================
--- internal-fn.def (revision 228200)
+++ internal-fn.def (working copy)
@@ -81,13 +81,6 @@ DEF_INTERNAL_FN (UNIQUE, ECF_NOTHROW | E
DEF_INTERNAL_FN (GOACC_DIM_SIZE, ECF_CONST | ECF_NOTHROW | ECF_LEAF, ".")
DEF_INTERNAL_FN (GOACC_DIM_POS, ECF_PURE | ECF_NOTHROW | ECF_LEAF, ".")
-/* LOCK, UNLOCK & LOCK_INIT operate a mutex used for reductions. The first
- argument is the compute dimension of the reduction and the second
- argument is a loop identifer. */
-DEF_INTERNAL_FN (GOACC_LOCK, ECF_NOTHROW | ECF_LEAF, "..")
-DEF_INTERNAL_FN (GOACC_UNLOCK, ECF_NOTHROW | ECF_LEAF, "..")
-DEF_INTERNAL_FN (GOACC_LOCK_INIT, ECF_NOTHROW | ECF_LEAF, "..")
-
/* REDUCTION_SETUP, REDUCTION_INIT, REDUCTION_FINI and REDUCTION_TEARDOWN
together define a generic interface to support gang, worker and vector
reductions. All of the functions take the following form
Index: config/nvptx/nvptx-protos.h
===================================================================
--- config/nvptx/nvptx-protos.h (revision 228200)
+++ config/nvptx/nvptx-protos.h (working copy)
@@ -34,7 +34,6 @@ extern const char *nvptx_section_for_dec
#ifdef RTX_CODE
extern void nvptx_expand_oacc_fork (unsigned);
extern void nvptx_expand_oacc_join (unsigned);
-extern void nvptx_expand_oacc_lock (rtx, int);
extern void nvptx_expand_call (rtx, rtx);
extern rtx nvptx_expand_compare (rtx);
extern const char *nvptx_ptx_type_from_mode (machine_mode, bool);
Index: config/nvptx/nvptx.md
===================================================================
--- config/nvptx/nvptx.md (revision 228200)
+++ config/nvptx/nvptx.md (working copy)
@@ -1371,36 +1371,6 @@
return asms[INTVAL (operands[1])];
})
-(define_expand "oacc_lock"
- [(unspec_volatile:SI [(match_operand:SI 0 "const_int_operand" "")
- (match_operand:SI 1 "const_int_operand" "")]
- UNSPECV_LOCK)]
- ""
-{
- nvptx_expand_oacc_lock (operands[0], 0);
- DONE;
-})
-
-(define_expand "oacc_unlock"
- [(unspec_volatile:SI [(match_operand:SI 0 "const_int_operand" "")
- (match_operand:SI 1 "const_int_operand" "")]
- UNSPECV_LOCK)]
- ""
-{
- nvptx_expand_oacc_lock (operands[0], +1);
- DONE;
-})
-
-(define_expand "oacc_lock_init"
- [(unspec_volatile:SI [(match_operand:SI 0 "const_int_operand" "")
- (match_operand:SI 1 "const_int_operand" "")]
- UNSPECV_LOCK)]
- ""
-{
- nvptx_expand_oacc_lock (operands[0], -1);
- DONE;
-})
-
(define_insn "nvptx_fork"
[(unspec_volatile:SI [(match_operand:SI 0 "const_int_operand" "")]
UNSPECV_FORK)]
@@ -1588,23 +1558,3 @@
UNSPECV_MEMBAR)]
""
"%.\\tmembar%B0;")
-
-;; spin lock and reset
-(define_insn "nvptx_spin_lock"
- [(parallel
- [(set (match_operand:SI 2 "register_operand" "=R")
- (unspec_volatile:SI [(match_operand:SI 0 "memory_operand" "m")
- (match_operand:SI 1 "const_int_operand" "i")]
- UNSPECV_LOCK))
- (set (match_operand:BI 3 "register_operand" "=R") (const_int 0))
- (label_ref (match_operand 4 "" ""))])]
- ""
- "%4:\\tatom%R1.cas.b32\\t%2, %0, 0, 1;\\n\\t\\tsetp.ne.u32\\t%3, %2, 0;\\n\\t@%3\\tbra.uni\\t%4;")
-
-(define_insn "nvptx_spin_reset"
- [(set (match_operand:SI 2 "register_operand" "=R")
- (unspec_volatile:SI [(match_operand:SI 0 "memory_operand" "m")
- (match_operand:SI 1 "const_int_operand" "i")]
- UNSPECV_LOCK))]
- ""
- "%.\\tatom%R1.exch.b32\\t%2, %0, 0;")
Index: config/nvptx/nvptx.c
===================================================================
--- config/nvptx/nvptx.c (revision 228200)
+++ config/nvptx/nvptx.c (working copy)
@@ -122,21 +122,6 @@ static unsigned worker_bcast_align;
#define worker_bcast_name "__worker_bcast"
static GTY(()) rtx worker_bcast_sym;
-/* Global and shared lock variables. Allocated at end of compilation,
- if used. Again, PTX lacks common blocks, so we can't share across
- compilations. */
-#define LOCK_GLOBAL 0
-#define LOCK_SHARED 1
-#define LOCK_MAX 2
-static const char *const lock_names[] = {"__global_lock", "__shared_lock"};
-static const unsigned lock_space[] = {ADDR_SPACE_GLOBAL, ADDR_SPACE_SHARED};
-static const unsigned lock_level[] = {BARRIER_GLOBAL, BARRIER_SHARED};
-static GTY(()) rtx lock_syms[LOCK_MAX];
-static bool lock_used[LOCK_MAX];
-
-/* FIXME: Temporary workaround for worker locks. */
-static bool force_global_locks = true;
-
/* Size of buffer needed for worker reductions. This has to be
disjoing from the worker broadcast array, as both may be live
concurrently. */
@@ -208,9 +193,6 @@ nvptx_option_override (void)
worker_red_sym = gen_rtx_SYMBOL_REF (Pmode, worker_red_name);
worker_red_align = GET_MODE_ALIGNMENT (SImode) / BITS_PER_UNIT;
-
- for (unsigned ix = LOCK_MAX; ix--;)
- lock_syms[ix] = gen_rtx_SYMBOL_REF (Pmode, lock_names[ix]);
}
/* Return the mode to be used when declaring a ptx object for OBJ.
@@ -1271,44 +1253,6 @@ nvptx_expand_oacc_join (unsigned mode)
nvptx_emit_joining (GOMP_DIM_MASK (mode), false);
}
-/* Expander for reduction locking and unlocking. We expect SRC to be
- gang or worker level. */
-
-void
-nvptx_expand_oacc_lock (rtx src, int direction)
-{
- unsigned HOST_WIDE_INT kind;
- rtx pat;
-
- kind = INTVAL (src) == GOMP_DIM_GANG ? LOCK_GLOBAL : LOCK_SHARED;
- kind = force_global_locks ? LOCK_GLOBAL : kind;
- lock_used[kind] = true;
-
- rtx mem = gen_rtx_MEM (SImode, lock_syms[kind]);
- rtx space = GEN_INT (lock_space[kind]);
- rtx barrier = NULL_RTX;
- rtx tmp = gen_reg_rtx (SImode);
-
- if (direction >= 0)
- barrier = gen_nvptx_membar (GEN_INT (lock_level[kind]));
-
- if (direction > 0)
- emit_insn (barrier);
- if (!direction)
- {
- rtx_code_label *label = gen_label_rtx ();
-
- LABEL_NUSES (label)++;
- pat = gen_nvptx_spin_lock (mem, space, tmp, gen_reg_rtx (BImode), label);
- }
- else
- /* We can use reset for both unlock and initialization. */
- pat = gen_nvptx_spin_reset (mem, space, tmp);
- emit_insn (pat);
- if (!direction)
- emit_insn (barrier);
-}
-
/* Generate instruction(s) to unpack a 64 bit object into 2 32 bit
objects. */
@@ -4103,16 +4047,6 @@ nvptx_file_end (void)
worker_red_align,
worker_red_name, worker_red_hwm);
}
-
- /* Emit lock variables. */
- for (unsigned ix = LOCK_MAX; ix--;)
- if (lock_used[ix])
- {
- fprintf (asm_out_file, "// BEGIN VAR DEF: %s\n", lock_names[ix]);
- fprintf (asm_out_file, "%s .u32 %s;\n",
- nvptx_section_from_addr_space (lock_space[ix]),
- lock_names[ix]);
- }
}
/* Expander for the shuffle builtins. */
@@ -4930,9 +4864,6 @@ nvptx_use_anchors_for_symbol (const_rtx
#undef TARGET_GOACC_FORK_JOIN
#define TARGET_GOACC_FORK_JOIN nvptx_xform_fork_join
-#undef TARGET_GOACC_LOCK
-#define TARGET_GOACC_LOCK nvptx_xform_lock
-
#undef TARGET_GOACC_REDUCTION
#define TARGET_GOACC_REDUCTION nvptx_goacc_reduction
Index: internal-fn.c
===================================================================
--- internal-fn.c (revision 228200)
+++ internal-fn.c (working copy)
@@ -2026,45 +2026,6 @@ expand_GOACC_DIM_POS (gcall *ARG_UNUSED
#endif
}
-static void
-expand_GOACC_LOCK (gcall *ARG_UNUSED (stmt))
-{
-#ifdef HAVE_oacc_lock
- rtx dim = expand_normal (gimple_call_arg (stmt, 0));
- rtx id = expand_normal (gimple_call_arg (stmt, 1));
-
- emit_insn (gen_oacc_lock (dim, id));
-#else
- gcc_unreachable ();
-#endif
-}
-
-static void
-expand_GOACC_UNLOCK (gcall *ARG_UNUSED (stmt))
-{
-#ifdef HAVE_oacc_unlock
- rtx dim = expand_normal (gimple_call_arg (stmt, 0));
- rtx id = expand_normal (gimple_call_arg (stmt, 1));
-
- emit_insn (gen_oacc_unlock (dim, id));
-#else
- gcc_unreachable ();
-#endif
-}
-
-static void
-expand_GOACC_LOCK_INIT (gcall *ARG_UNUSED (stmt))
-{
-#ifdef HAVE_oacc_lock_init
- rtx dim = expand_normal (gimple_call_arg (stmt, 0));
- rtx id = expand_normal (gimple_call_arg (stmt, 1));
-
- emit_insn (gen_oacc_lock_init (dim, id));
-#else
- gcc_unreachable ();
-#endif
-}
-
/* This should get expanded in oacc_transform. */
static void
Index: omp-low.c
===================================================================
--- omp-low.c (revision 228200)
+++ omp-low.c (working copy)
@@ -4718,14 +4718,11 @@ expand_oacc_get_thread_num (gimple_seq *
before-loop forking sequence in FORK_SEQ and the after-loop joining
sequence to JOIN_SEQ. The general form of these sequences is
- GOACC_LOCK_INIT
GOACC_REDUCTION_SETUP
GOACC_FORK
GOACC_REDUCTION_INIT
...
- GOACC_LOCK
GOACC_REDUCTION_FINI
- GOACC_UNLOCK
GOACC_JOIN
GOACC_REDUCTION_TEARDOWN. */
@@ -4833,30 +4830,12 @@ lower_oacc_reductions (location_t loc, t
}
/* Now stitch things together. */
- if (count)
- {
- gcall *init = gimple_build_call_internal
- (IFN_GOACC_LOCK_INIT, 2, level, lid);
- gimple_seq_add_stmt (fork_seq, init);
- }
gimple_seq_add_seq (fork_seq, before_fork);
if (fork)
gimple_seq_add_stmt (fork_seq, fork);
gimple_seq_add_seq (fork_seq, after_fork);
- if (count)
- {
- gcall *init = gimple_build_call_internal
- (IFN_GOACC_LOCK, 2, level, lid);
- gimple_seq_add_stmt (join_seq, init);
- }
gimple_seq_add_seq (join_seq, before_join);
- if (count)
- {
- gcall *init = gimple_build_call_internal
- (IFN_GOACC_UNLOCK, 2, level, lid);
- gimple_seq_add_stmt (join_seq, init);
- }
if (join)
gimple_seq_add_stmt (join_seq, join);
gimple_seq_add_seq (join_seq, after_join);
@@ -14914,13 +14893,6 @@ execute_oacc_transform ()
rescan = 0;
break;
- case IFN_GOACC_LOCK:
- case IFN_GOACC_UNLOCK:
- case IFN_GOACC_LOCK_INIT:
- if (targetm.goacc.lock (call, dims, ifn_code))
- rescan = -1;
- break;
-
case IFN_GOACC_REDUCTION_SETUP:
case IFN_GOACC_REDUCTION_INIT:
case IFN_GOACC_REDUCTION_FINI:
@@ -15026,37 +14998,6 @@ default_goacc_fork_join (gcall *ARG_UNUS
}
return false;
-}
-
-/* Default lock/unlock early expander. Delete the function calls if
- there is no RTL expander. */
-
-bool
-default_goacc_lock (gcall *ARG_UNUSED (call), const int*ARG_UNUSED (dims),
- unsigned ifn_code)
-{
- switch (ifn_code)
- {
- case IFN_GOACC_LOCK:
-#ifndef HAVE_oacc_lock
- return true;
-#endif
- break;
- case IFN_GOACC_UNLOCK:
-#ifndef HAVE_oacc_unlock
- return true;
-#endif
- break;
- case IFN_GOACC_LOCK_INIT:
-#ifndef HAVE_oacc_lock_init
- return true;
-#endif
- break;
- default:
- gcc_unreachable ();
- }
-
- return false;
}
/* Default goacc.reduction early expander.
Index: target.def
===================================================================
--- target.def (revision 228200)
+++ target.def (working copy)
@@ -1671,16 +1671,6 @@ bool, (gcall *call, const int dims[], bo
default_goacc_fork_join)
DEFHOOK
-(lock,
-"This hook should convert IFN_GOACC_LOCK, IFN_GOACC_UNLOCK,\n\
-IFN_GOACC_LOCK_INIT function calls to target-specific gimple. It is\n\
-executed during the oacc_xform pass. It should return true, if the\n\
-functions should be deleted. The default hook returns true, if there\n\
-are no RTL expanders for them.",
-bool, (gcall *call, const int dims[], unsigned ifn_code),
-default_goacc_lock)
-
-DEFHOOK
(reduction,
"This hook is used by the oacc_transform pass to expand calls to the\n\
internal functions @var{GOACC_REDUCTION_SETUP},\n\
Index: doc/tm.texi
===================================================================
--- doc/tm.texi (revision 228200)
+++ doc/tm.texi (working copy)
@@ -5768,14 +5768,6 @@ pass. It should return true, if the fun
default hook returns true, if there are no RTL expanders for them.
@end deftypefn
-@deftypefn {Target Hook} bool TARGET_GOACC_LOCK (gcall *@var{call}, const int @var{dims[]}, unsigned @var{ifn_code})
-This hook should convert IFN_GOACC_LOCK, IFN_GOACC_UNLOCK,
-IFN_GOACC_LOCK_INIT function calls to target-specific gimple. It is
-executed during the oacc_xform pass. It should return true, if the
-functions should be deleted. The default hook returns true, if there
-are no RTL expanders for them.
-@end deftypefn
-
@deftypefn {Target Hook} bool TARGET_GOACC_REDUCTION (gcall *@var{call})
This hook is used by the oacc_transform pass to expand calls to the
internal functions @var{GOACC_REDUCTION_SETUP},
Index: doc/tm.texi.in
===================================================================
--- doc/tm.texi.in (revision 228200)
+++ doc/tm.texi.in (working copy)
@@ -4253,8 +4253,6 @@ address; but often a machine-dependent
@hook TARGET_GOACC_FORK_JOIN
-@hook TARGET_GOACC_LOCK
-
@hook TARGET_GOACC_REDUCTION
@node Anchored Addresses
Index: targhooks.h
===================================================================
--- targhooks.h (revision 228200)
+++ targhooks.h (working copy)
@@ -111,7 +111,6 @@ extern bool default_goacc_reduction (gca
extern bool default_goacc_validate_dims (tree, int [], int);
extern unsigned default_goacc_dim_limit (unsigned);
extern bool default_goacc_fork_join (gcall *, const int [], bool);
-extern bool default_goacc_lock (gcall *, const int [], unsigned);
/* These are here, and not in hooks.[ch], because not all users of
hooks.h include tm.h, and thus we don't have CUMULATIVE_ARGS. */