mirror of
git://gcc.gnu.org/git/gcc.git
synced 2025-03-23 00:41:25 +08:00
Use plain -fopenacc to enable OpenACC kernels processing
gcc/ * tree-parloops.c (create_parallel_loop, gen_parallel_loop) (parallelize_loops): In OpenACC kernels mode, set n_threads to zero. (pass_parallelize_loops::gate): In OpenACC kernels mode, gate on flag_openacc. * tree-ssa-loop.c (gate_oacc_kernels): Likewise. gcc/testsuite/ * c-c++-common/goacc/kernels-counter-vars-function-scope.c: Adjust to -ftree-parallelize-loops/-fopenacc changes. * c-c++-common/goacc/kernels-double-reduction-n.c: Likewise. * c-c++-common/goacc/kernels-double-reduction.c: Likewise. * c-c++-common/goacc/kernels-loop-2.c: Likewise. * c-c++-common/goacc/kernels-loop-3.c: Likewise. * c-c++-common/goacc/kernels-loop-g.c: Likewise. * c-c++-common/goacc/kernels-loop-mod-not-zero.c: Likewise. * c-c++-common/goacc/kernels-loop-n.c: Likewise. * c-c++-common/goacc/kernels-loop-nest.c: Likewise. * c-c++-common/goacc/kernels-loop.c: Likewise. * c-c++-common/goacc/kernels-one-counter-var.c: Likewise. * c-c++-common/goacc/kernels-reduction.c: Likewise. * gfortran.dg/goacc/kernels-loop-inner.f95: Likewise. * gfortran.dg/goacc/kernels-loops-adjacent.f95: Likewise. libgomp/ * oacc-parallel.c (GOACC_parallel_keyed): Initialize dims. * plugin/plugin-nvptx.c (nvptx_exec): Provide default values for dims. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-2.c: Adjust to -ftree-parallelize-loops/-fopenacc changes. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-3.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-3.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-4.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-5.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-6.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-collapse.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-g.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-mod-not-zero.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-n.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop-nest.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-loop.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-reduction.c: Likewise. From-SVN: r233634
This commit is contained in:
Thomas Schwinge
Thomas Schwinge
parent
43331dfbb8
commit
f99c355797
@ -1,3 +1,12 @@
|
||||
2016-02-23 Thomas Schwinge <thomas@codesourcery.com>
|
||||
|
||||
* tree-parloops.c (create_parallel_loop, gen_parallel_loop)
|
||||
(parallelize_loops): In OpenACC kernels mode, set n_threads to
|
||||
zero.
|
||||
(pass_parallelize_loops::gate): In OpenACC kernels mode, gate on
|
||||
flag_openacc.
|
||||
* tree-ssa-loop.c (gate_oacc_kernels): Likewise.
|
||||
|
||||
2016-02-23 Richard Biener <rguenther@suse.de>
|
||||
|
||||
* mem-stats.h (struct mem_usage): Use PRIu64 for printing size_t.
|
||||
|
||||
@ -1,3 +1,21 @@
|
||||
2016-02-23 Thomas Schwinge <thomas@codesourcery.com>
|
||||
|
||||
* c-c++-common/goacc/kernels-counter-vars-function-scope.c: Adjust
|
||||
to -ftree-parallelize-loops/-fopenacc changes.
|
||||
* c-c++-common/goacc/kernels-double-reduction-n.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-double-reduction.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-2.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-3.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-g.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-mod-not-zero.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-n.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop-nest.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-loop.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-one-counter-var.c: Likewise.
|
||||
* c-c++-common/goacc/kernels-reduction.c: Likewise.
|
||||
* gfortran.dg/goacc/kernels-loop-inner.f95: Likewise.
|
||||
* gfortran.dg/goacc/kernels-loops-adjacent.f95: Likewise.
|
||||
|
||||
2016-02-23 Rainer Orth <ro@CeBiTec.Uni-Bielefeld.DE>
|
||||
|
||||
* gcc.target/i386/chkp-hidden-def.c: Require alias support.
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -51,4 +50,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -34,4 +33,4 @@ foo (unsigned int n)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -34,4 +33,4 @@ foo (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -67,4 +66,4 @@ main (void)
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.1" 1 "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.2" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 3 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -45,5 +44,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,6 +1,5 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-g" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -13,5 +12,4 @@
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -49,4 +48,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -52,5 +51,4 @@ foo (COUNTERTYPE n)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -36,4 +35,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -52,5 +51,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -50,5 +49,4 @@ main (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
/* { dg-additional-options "-O2" } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
|
||||
/* { dg-additional-options "-fdump-tree-optimized" } */
|
||||
|
||||
@ -32,5 +31,4 @@ foo (void)
|
||||
/* Check that the loop has been split off into a function. */
|
||||
/* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(32," 1 "parloops1" } } */
|
||||
|
||||
/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
! { dg-additional-options "-O2" }
|
||||
! { dg-additional-options "-ftree-parallelize-loops=32" }
|
||||
|
||||
program main
|
||||
implicit none
|
||||
|
||||
@ -1,5 +1,4 @@
|
||||
! { dg-additional-options "-O2" }
|
||||
! { dg-additional-options "-ftree-parallelize-loops=10" }
|
||||
|
||||
program main
|
||||
implicit none
|
||||
|
||||
@ -2016,7 +2016,8 @@ transform_to_exit_first_loop (struct loop *loop,
|
||||
/* Create the parallel constructs for LOOP as described in gen_parallel_loop.
|
||||
LOOP_FN and DATA are the arguments of GIMPLE_OMP_PARALLEL.
|
||||
NEW_DATA is the variable that should be initialized from the argument
|
||||
of LOOP_FN. N_THREADS is the requested number of threads. */
|
||||
of LOOP_FN. N_THREADS is the requested number of threads, which can be 0 if
|
||||
that number is to be determined later. */
|
||||
|
||||
static void
|
||||
create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
|
||||
@ -2049,6 +2050,7 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
|
||||
basic_block paral_bb = single_pred (bb);
|
||||
gsi = gsi_last_bb (paral_bb);
|
||||
|
||||
gcc_checking_assert (n_threads != 0);
|
||||
t = build_omp_clause (loc, OMP_CLAUSE_NUM_THREADS);
|
||||
OMP_CLAUSE_NUM_THREADS_EXPR (t)
|
||||
= build_int_cst (integer_type_node, n_threads);
|
||||
@ -2221,7 +2223,8 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
|
||||
}
|
||||
|
||||
/* Generates code to execute the iterations of LOOP in N_THREADS
|
||||
threads in parallel.
|
||||
threads in parallel, which can be 0 if that number is to be determined
|
||||
later.
|
||||
|
||||
NITER describes number of iterations of LOOP.
|
||||
REDUCTION_LIST describes the reductions existent in the LOOP. */
|
||||
@ -2318,6 +2321,7 @@ gen_parallel_loop (struct loop *loop,
|
||||
else
|
||||
m_p_thread=MIN_PER_THREAD;
|
||||
|
||||
gcc_checking_assert (n_threads != 0);
|
||||
many_iterations_cond =
|
||||
fold_build2 (GE_EXPR, boolean_type_node,
|
||||
nit, build_int_cst (type, m_p_thread * n_threads));
|
||||
@ -3177,7 +3181,7 @@ oacc_entry_exit_ok (struct loop *loop,
|
||||
static bool
|
||||
parallelize_loops (bool oacc_kernels_p)
|
||||
{
|
||||
unsigned n_threads = flag_tree_parallelize_loops;
|
||||
unsigned n_threads;
|
||||
bool changed = false;
|
||||
struct loop *loop;
|
||||
struct loop *skip_loop = NULL;
|
||||
@ -3199,6 +3203,13 @@ parallelize_loops (bool oacc_kernels_p)
|
||||
if (cfun->has_nonlocal_label)
|
||||
return false;
|
||||
|
||||
/* For OpenACC kernels, n_threads will be determined later; otherwise, it's
|
||||
the argument to -ftree-parallelize-loops. */
|
||||
if (oacc_kernels_p)
|
||||
n_threads = 0;
|
||||
else
|
||||
n_threads = flag_tree_parallelize_loops;
|
||||
|
||||
gcc_obstack_init (&parloop_obstack);
|
||||
reduction_info_table_type reduction_list (10);
|
||||
|
||||
@ -3361,7 +3372,13 @@ public:
|
||||
{}
|
||||
|
||||
/* opt_pass methods: */
|
||||
virtual bool gate (function *) { return flag_tree_parallelize_loops > 1; }
|
||||
virtual bool gate (function *)
|
||||
{
|
||||
if (oacc_kernels_p)
|
||||
return flag_openacc;
|
||||
else
|
||||
return flag_tree_parallelize_loops > 1;
|
||||
}
|
||||
virtual unsigned int execute (function *);
|
||||
opt_pass * clone () { return new pass_parallelize_loops (m_ctxt); }
|
||||
void set_pass_param (unsigned int n, bool param)
|
||||
|
||||
@ -148,7 +148,7 @@ make_pass_tree_loop (gcc::context *ctxt)
|
||||
static bool
|
||||
gate_oacc_kernels (function *fn)
|
||||
{
|
||||
if (flag_tree_parallelize_loops <= 1)
|
||||
if (!flag_openacc)
|
||||
return false;
|
||||
|
||||
tree oacc_function_attr = get_oacc_fn_attrib (fn->decl);
|
||||
@ -230,10 +230,9 @@ public:
|
||||
virtual bool gate (function *)
|
||||
{
|
||||
return (optimize
|
||||
/* Don't bother doing anything if the program has errors. */
|
||||
&& !seen_error ()
|
||||
&& flag_openacc
|
||||
&& flag_tree_parallelize_loops > 1);
|
||||
/* Don't bother doing anything if the program has errors. */
|
||||
&& !seen_error ());
|
||||
}
|
||||
|
||||
}; // class pass_ipa_oacc
|
||||
|
||||
@ -1,3 +1,35 @@
|
||||
2016-02-23 Thomas Schwinge <thomas@codesourcery.com>
|
||||
|
||||
* oacc-parallel.c (GOACC_parallel_keyed): Initialize dims.
|
||||
* plugin/plugin-nvptx.c (nvptx_exec): Provide default values for
|
||||
dims.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-2.c: Adjust to
|
||||
-ftree-parallelize-loops/-fopenacc changes.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-3.c: Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-2.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-3.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-4.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-5.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq-6.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-and-seq.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-collapse.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-g.c: Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-mod-not-zero.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-n.c: Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop-nest.c:
|
||||
Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-loop.c: Likewise.
|
||||
* testsuite/libgomp.oacc-c-c++-common/kernels-reduction.c:
|
||||
Likewise.
|
||||
|
||||
2016-02-22 Cesar Philippidis <cesar@codesourcery.com>
|
||||
|
||||
* testsuite/libgomp.oacc-c-c++-common/vprop.c: New test.
|
||||
|
||||
@ -103,6 +103,10 @@ GOACC_parallel_keyed (int device, void (*fn) (void *),
|
||||
return;
|
||||
}
|
||||
|
||||
/* Default: let the runtime choose. */
|
||||
for (i = 0; i != GOMP_DIM_MAX; i++)
|
||||
dims[i] = 0;
|
||||
|
||||
va_start (ap, kinds);
|
||||
/* TODO: This will need amending when device_type is implemented. */
|
||||
while ((tag = va_arg (ap, unsigned)) != 0)
|
||||
|
||||
@ -894,9 +894,21 @@ nvptx_exec (void (*fn), size_t mapnum, void **hostaddrs, void **devaddrs,
|
||||
/* Initialize the launch dimensions. Typically this is constant,
|
||||
provided by the device compiler, but we must permit runtime
|
||||
values. */
|
||||
for (i = 0; i != 3; i++)
|
||||
if (targ_fn->launch->dim[i])
|
||||
dims[i] = targ_fn->launch->dim[i];
|
||||
int seen_zero = 0;
|
||||
for (i = 0; i != GOMP_DIM_MAX; i++)
|
||||
{
|
||||
if (targ_fn->launch->dim[i])
|
||||
dims[i] = targ_fn->launch->dim[i];
|
||||
if (!dims[i])
|
||||
seen_zero = 1;
|
||||
}
|
||||
|
||||
if (seen_zero)
|
||||
{
|
||||
for (i = 0; i != GOMP_DIM_MAX; i++)
|
||||
if (!dims[i])
|
||||
dims[i] = /* TODO */ 32;
|
||||
}
|
||||
|
||||
/* This reserves a chunk of a pre-allocated page of memory mapped on both
|
||||
the host and the device. HP is a host pointer to the new chunk, and DP is
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N (1024 * 512)
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N (1024 * 512)
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 32
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 100
|
||||
|
||||
@ -1,5 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
/* { dg-additional-options "-g" } */
|
||||
|
||||
#include "kernels-loop.c"
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N ((1024 * 512) + 1)
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N ((1024 * 512) + 1)
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N 1000
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define N (1024 * 512)
|
||||
|
||||
@ -1,6 +1,3 @@
|
||||
/* { dg-do run } */
|
||||
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#define n 10000
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user