nvptx-protos.h (nvptx_hard_regno_mode_ok): Delete.
* config/nvptx/nvptx-protos.h (nvptx_hard_regno_mode_ok): Delete. * config/nvptx/nvptx.h (struct machine_function): Reimplement. Adjust all users. * config/nvptx/nvptx.c (nvptx_declare_function_name): Move stack and frame array generation earlier. (nvptx_call_args): Reimplement. (nvptx_expand_call): Adjust. (nvptx_hard_reno_mode_ok): Delete. (nvptx_reorg): Revert scan of hard regs. From-SVN: r231691
This commit is contained in:
Nathan Sidwell
parent
597a8ab9c6
commit
44c068aecb
4 changed files with 76 additions and 77 deletions
|
|
@ -1,11 +1,24 @@
|
|||
2015-12-16 Nathan Sidwell <nathan@acm.org>
|
||||
|
||||
* config/nvptx/nvptx-protos.h (nvptx_hard_regno_mode_ok): Delete.
|
||||
* config/nvptx/nvptx.h (struct machine_function):
|
||||
Reimplement. Adjust all users.
|
||||
* config/nvptx/nvptx.c (nvptx_declare_function_name): Move stack
|
||||
and frame array generation earlier.
|
||||
(nvptx_call_args): Reimplement.
|
||||
(nvptx_expand_call): Adjust.
|
||||
(nvptx_hard_reno_mode_ok): Delete.
|
||||
(nvptx_reorg): Revert scan of hard regs.
|
||||
|
||||
2015-12-16 Tom de Vries <tom@codesourcery.com>
|
||||
|
||||
* opts.c (default_options_optimization): Set fipa-pta on by default for
|
||||
fopenacc.
|
||||
* opts.c (default_options_optimization): Set fipa-pta on by
|
||||
default for fopenacc.
|
||||
* passes.def: Move kernels pass group to pass_ipa_oacc.
|
||||
* tree-pass.h (make_pass_oacc_kernels2): Remove.
|
||||
(make_pass_ipa_oacc, make_pass_ipa_oacc_kernels): Declare.
|
||||
* tree-ssa-loop.c (pass_oacc_kernels2, make_pass_oacc_kernels2): Remove.
|
||||
* tree-ssa-loop.c (pass_oacc_kernels2, make_pass_oacc_kernels2):
|
||||
Remove.
|
||||
(pass_ipa_oacc, pass_ipa_oacc_kernels): New pass.
|
||||
(make_pass_ipa_oacc, make_pass_ipa_oacc_kernels): New function.
|
||||
* tree-ssa-structalias.c (pass_ipa_pta::clone): New function.
|
||||
|
|
|
|||
|
|
@ -41,7 +41,6 @@ extern const char *nvptx_ptx_type_from_mode (machine_mode, bool);
|
|||
extern const char *nvptx_output_mov_insn (rtx, rtx);
|
||||
extern const char *nvptx_output_call_insn (rtx_insn *, rtx, rtx);
|
||||
extern const char *nvptx_output_return (void);
|
||||
extern bool nvptx_hard_regno_mode_ok (int, machine_mode);
|
||||
extern rtx nvptx_maybe_convert_symbolic_operand (rtx);
|
||||
#endif
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -147,7 +147,7 @@ static struct machine_function *
|
|||
nvptx_init_machine_status (void)
|
||||
{
|
||||
struct machine_function *p = ggc_cleared_alloc<machine_function> ();
|
||||
p->ret_reg_mode = VOIDmode;
|
||||
p->return_mode = VOIDmode;
|
||||
return p;
|
||||
}
|
||||
|
||||
|
|
@ -487,7 +487,7 @@ nvptx_strict_argument_naming (cumulative_args_t cum_v)
|
|||
static rtx
|
||||
nvptx_libcall_value (machine_mode mode, const_rtx)
|
||||
{
|
||||
if (cfun->machine->start_call == NULL_RTX)
|
||||
if (!cfun->machine->doing_call)
|
||||
/* Pretend to return in a hard reg for early uses before pseudos can be
|
||||
generated. */
|
||||
return gen_rtx_REG (mode, NVPTX_RETURN_REGNUM);
|
||||
|
|
@ -506,7 +506,7 @@ nvptx_function_value (const_tree type, const_tree ARG_UNUSED (func),
|
|||
|
||||
if (outgoing)
|
||||
{
|
||||
cfun->machine->ret_reg_mode = mode;
|
||||
cfun->machine->return_mode = mode;
|
||||
return gen_rtx_REG (mode, NVPTX_RETURN_REGNUM);
|
||||
}
|
||||
|
||||
|
|
@ -678,14 +678,14 @@ write_return_type (std::stringstream &s, bool for_proto, tree type)
|
|||
optimization-level specific, so no caller can make use of
|
||||
this data, but more importantly for us, we must ensure it
|
||||
doesn't change the PTX prototype. */
|
||||
mode = (machine_mode) cfun->machine->ret_reg_mode;
|
||||
mode = (machine_mode) cfun->machine->return_mode;
|
||||
|
||||
if (mode == VOIDmode)
|
||||
return return_in_mem;
|
||||
|
||||
/* Clear ret_reg_mode to inhibit copy of retval to non-existent
|
||||
/* Clear return_mode to inhibit copy of retval to non-existent
|
||||
retval parameter. */
|
||||
cfun->machine->ret_reg_mode = VOIDmode;
|
||||
cfun->machine->return_mode = VOIDmode;
|
||||
}
|
||||
else
|
||||
mode = promote_return (mode);
|
||||
|
|
@ -989,7 +989,18 @@ nvptx_declare_function_name (FILE *file, const char *name, const_tree decl)
|
|||
|
||||
fprintf (file, "%s", s.str().c_str());
|
||||
|
||||
if (regno_reg_rtx[OUTGOING_STATIC_CHAIN_REGNUM] != const0_rtx)
|
||||
/* Declare a local var for outgoing varargs. */
|
||||
if (cfun->machine->has_varadic)
|
||||
init_frame (file, STACK_POINTER_REGNUM,
|
||||
UNITS_PER_WORD, crtl->outgoing_args_size);
|
||||
|
||||
/* Declare a local variable for the frame. */
|
||||
HOST_WIDE_INT sz = get_frame_size ();
|
||||
if (sz || cfun->machine->has_chain)
|
||||
init_frame (file, FRAME_POINTER_REGNUM,
|
||||
crtl->stack_alignment_needed / BITS_PER_UNIT, sz);
|
||||
|
||||
if (cfun->machine->has_chain)
|
||||
fprintf (file, "\t.reg.u%d %s;\n", GET_MODE_BITSIZE (Pmode),
|
||||
reg_names[OUTGOING_STATIC_CHAIN_REGNUM]);
|
||||
|
||||
|
|
@ -1010,17 +1021,6 @@ nvptx_declare_function_name (FILE *file, const char *name, const_tree decl)
|
|||
}
|
||||
}
|
||||
|
||||
/* Declare a local var for outgoing varargs. */
|
||||
if (cfun->machine->has_call_with_varargs)
|
||||
init_frame (file, STACK_POINTER_REGNUM,
|
||||
UNITS_PER_WORD, crtl->outgoing_args_size);
|
||||
|
||||
/* Declare a local variable for the frame. */
|
||||
HOST_WIDE_INT sz = get_frame_size ();
|
||||
if (sz || cfun->machine->has_call_with_sc)
|
||||
init_frame (file, FRAME_POINTER_REGNUM,
|
||||
crtl->stack_alignment_needed / BITS_PER_UNIT, sz);
|
||||
|
||||
/* Emit axis predicates. */
|
||||
if (cfun->machine->axis_predicate[0])
|
||||
nvptx_init_axis_predicate (file,
|
||||
|
|
@ -1036,7 +1036,7 @@ nvptx_declare_function_name (FILE *file, const char *name, const_tree decl)
|
|||
const char *
|
||||
nvptx_output_return (void)
|
||||
{
|
||||
machine_mode mode = (machine_mode)cfun->machine->ret_reg_mode;
|
||||
machine_mode mode = (machine_mode)cfun->machine->return_mode;
|
||||
|
||||
if (mode != VOIDmode)
|
||||
fprintf (asm_out_file, "\tst.param%s\t[%s_out], %s;\n",
|
||||
|
|
@ -1076,20 +1076,28 @@ nvptx_get_drap_rtx (void)
|
|||
argument to the next call. */
|
||||
|
||||
static void
|
||||
nvptx_call_args (rtx arg, tree funtype)
|
||||
nvptx_call_args (rtx arg, tree fntype)
|
||||
{
|
||||
if (cfun->machine->start_call == NULL_RTX)
|
||||
if (!cfun->machine->doing_call)
|
||||
{
|
||||
cfun->machine->call_args = NULL;
|
||||
cfun->machine->funtype = funtype;
|
||||
cfun->machine->start_call = const0_rtx;
|
||||
}
|
||||
if (arg == pc_rtx)
|
||||
return;
|
||||
cfun->machine->doing_call = true;
|
||||
cfun->machine->is_varadic = false;
|
||||
cfun->machine->num_args = 0;
|
||||
|
||||
rtx_expr_list *args_so_far = cfun->machine->call_args;
|
||||
if (REG_P (arg))
|
||||
cfun->machine->call_args = alloc_EXPR_LIST (VOIDmode, arg, args_so_far);
|
||||
if (fntype && stdarg_p (fntype))
|
||||
{
|
||||
cfun->machine->is_varadic = true;
|
||||
cfun->machine->has_varadic = true;
|
||||
cfun->machine->num_args++;
|
||||
}
|
||||
}
|
||||
|
||||
if (REG_P (arg) && arg != pc_rtx)
|
||||
{
|
||||
cfun->machine->num_args++;
|
||||
cfun->machine->call_args = alloc_EXPR_LIST (VOIDmode, arg,
|
||||
cfun->machine->call_args);
|
||||
}
|
||||
}
|
||||
|
||||
/* Implement the corresponding END_CALL_ARGS hook. Clear and free the
|
||||
|
|
@ -1098,7 +1106,7 @@ nvptx_call_args (rtx arg, tree funtype)
|
|||
static void
|
||||
nvptx_end_call_args (void)
|
||||
{
|
||||
cfun->machine->start_call = NULL_RTX;
|
||||
cfun->machine->doing_call = false;
|
||||
free_EXPR_LIST_list (&cfun->machine->call_args);
|
||||
}
|
||||
|
||||
|
|
@ -1111,16 +1119,10 @@ nvptx_end_call_args (void)
|
|||
void
|
||||
nvptx_expand_call (rtx retval, rtx address)
|
||||
{
|
||||
int nargs = 0;
|
||||
rtx callee = XEXP (address, 0);
|
||||
rtx pat, t;
|
||||
rtvec vec;
|
||||
rtx varargs = NULL_RTX;
|
||||
unsigned parallel = 0;
|
||||
|
||||
for (t = cfun->machine->call_args; t; t = XEXP (t, 1))
|
||||
nargs++;
|
||||
|
||||
if (!call_insn_operand (callee, Pmode))
|
||||
{
|
||||
callee = force_reg (Pmode, callee);
|
||||
|
|
@ -1133,7 +1135,7 @@ nvptx_expand_call (rtx retval, rtx address)
|
|||
if (decl != NULL_TREE)
|
||||
{
|
||||
if (DECL_STATIC_CHAIN (decl))
|
||||
cfun->machine->has_call_with_sc = true;
|
||||
cfun->machine->has_chain = true;
|
||||
|
||||
tree attr = get_oacc_fn_attrib (decl);
|
||||
if (attr)
|
||||
|
|
@ -1154,35 +1156,31 @@ nvptx_expand_call (rtx retval, rtx address)
|
|||
}
|
||||
}
|
||||
|
||||
if (cfun->machine->funtype
|
||||
&& stdarg_p (cfun->machine->funtype))
|
||||
unsigned nargs = cfun->machine->num_args;
|
||||
if (cfun->machine->is_varadic)
|
||||
{
|
||||
varargs = gen_reg_rtx (Pmode);
|
||||
emit_move_insn (varargs, stack_pointer_rtx);
|
||||
cfun->machine->has_call_with_varargs = true;
|
||||
}
|
||||
vec = rtvec_alloc (nargs + 1 + (varargs ? 1 : 0));
|
||||
pat = gen_rtx_PARALLEL (VOIDmode, vec);
|
||||
|
||||
rtvec vec = rtvec_alloc (nargs + 1);
|
||||
rtx pat = gen_rtx_PARALLEL (VOIDmode, vec);
|
||||
int vec_pos = 0;
|
||||
|
||||
|
||||
rtx call = gen_rtx_CALL (VOIDmode, address, const0_rtx);
|
||||
rtx tmp_retval = retval;
|
||||
t = gen_rtx_CALL (VOIDmode, address, const0_rtx);
|
||||
if (retval != NULL_RTX)
|
||||
if (retval)
|
||||
{
|
||||
if (!nvptx_register_operand (retval, GET_MODE (retval)))
|
||||
tmp_retval = gen_reg_rtx (GET_MODE (retval));
|
||||
t = gen_rtx_SET (tmp_retval, t);
|
||||
call = gen_rtx_SET (tmp_retval, call);
|
||||
}
|
||||
XVECEXP (pat, 0, vec_pos++) = t;
|
||||
XVECEXP (pat, 0, vec_pos++) = call;
|
||||
|
||||
/* Construct the call insn, including a USE for each argument pseudo
|
||||
register. These will be used when printing the insn. */
|
||||
for (rtx arg = cfun->machine->call_args; arg; arg = XEXP (arg, 1))
|
||||
{
|
||||
rtx this_arg = XEXP (arg, 0);
|
||||
XVECEXP (pat, 0, vec_pos++) = gen_rtx_USE (VOIDmode, this_arg);
|
||||
}
|
||||
XVECEXP (pat, 0, vec_pos++) = gen_rtx_USE (VOIDmode, XEXP (arg, 0));
|
||||
|
||||
if (varargs)
|
||||
XVECEXP (pat, 0, vec_pos++) = gen_rtx_USE (VOIDmode, varargs);
|
||||
|
|
@ -1477,18 +1475,6 @@ nvptx_legitimate_address_p (machine_mode, rtx x, bool)
|
|||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/* Implement HARD_REGNO_MODE_OK. We barely use hard regs, but we want
|
||||
to ensure that the return register's mode isn't changed. */
|
||||
|
||||
bool
|
||||
nvptx_hard_regno_mode_ok (int regno, machine_mode mode)
|
||||
{
|
||||
if (regno != NVPTX_RETURN_REGNUM
|
||||
|| cfun == NULL || cfun->machine->ret_reg_mode == VOIDmode)
|
||||
return true;
|
||||
return mode == cfun->machine->ret_reg_mode;
|
||||
}
|
||||
|
||||
/* Machinery to output constant initializers. When beginning an
|
||||
initializer, we decide on a fragment size (which is visible in ptx
|
||||
|
|
@ -3773,7 +3759,7 @@ nvptx_reorg (void)
|
|||
|
||||
/* Mark unused regs as unused. */
|
||||
int max_regs = max_reg_num ();
|
||||
for (int i = 0; i < max_regs; i++)
|
||||
for (int i = LAST_VIRTUAL_REGISTER + 1; i < max_regs; i++)
|
||||
if (REG_N_SETS (i) == 0 && REG_N_REFS (i) == 0)
|
||||
regno_reg_rtx[i] = const0_rtx;
|
||||
|
||||
|
|
|
|||
|
|
@ -220,14 +220,15 @@ struct nvptx_args {
|
|||
#if defined HOST_WIDE_INT
|
||||
struct GTY(()) machine_function
|
||||
{
|
||||
rtx_expr_list *call_args;
|
||||
rtx start_call;
|
||||
tree funtype;
|
||||
bool has_call_with_varargs;
|
||||
bool has_call_with_sc;
|
||||
HOST_WIDE_INT outgoing_stdarg_size;
|
||||
int ret_reg_mode; /* machine_mode not defined yet. */
|
||||
rtx axis_predicate[2];
|
||||
rtx_expr_list *call_args; /* Arg list for the current call. */
|
||||
bool doing_call; /* Within a CALL_ARGS ... CALL_ARGS_END sequence. */
|
||||
bool is_varadic; /* This call is varadic */
|
||||
bool has_varadic; /* Current function has a varadic call. */
|
||||
bool has_chain; /* Current function has outgoing static chain. */
|
||||
int num_args; /* Number of args of current call. */
|
||||
int return_mode; /* Return mode of current fn.
|
||||
(machine_mode not defined yet.) */
|
||||
rtx axis_predicate[2]; /* Neutering predicates. */
|
||||
};
|
||||
#endif
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue