4cdfee3f20
Currently parallel-loop-1.c fails at -O0 on a Quadro M1200, because one of the kernel launch configurations exceeds the resources available in the device, due to the default dimensions chosen by the runtime. This patch fixes that by taking the per-function max_threads_per_block into account when using the default dimensions. 2018-07-30 Tom de Vries <tdevries@suse.de> * plugin/plugin-nvptx.c (MIN, MAX): Redefine. (nvptx_exec): Ensure worker and vector default dims don't exceed targ_fn->max_threads_per_block. From-SVN: r263062 |
||
---|---|---|
.. | ||
config | ||
plugin | ||
testsuite | ||
acinclude.m4 | ||
aclocal.m4 | ||
affinity.c | ||
alloc.c | ||
atomic.c | ||
barrier.c | ||
ChangeLog | ||
ChangeLog.graphite | ||
config.h.in | ||
configure | ||
configure.ac | ||
configure.tgt | ||
critical.c | ||
env.c | ||
error.c | ||
fortran.c | ||
hashtab.h | ||
icv-device.c | ||
icv.c | ||
iter_ull.c | ||
iter.c | ||
libgomp_f.h.in | ||
libgomp_g.h | ||
libgomp-plugin.c | ||
libgomp-plugin.h | ||
libgomp.h | ||
libgomp.map | ||
libgomp.spec.in | ||
libgomp.texi | ||
lock.c | ||
loop_ull.c | ||
loop.c | ||
Makefile.am | ||
Makefile.in | ||
oacc-async.c | ||
oacc-cuda.c | ||
oacc-host.c | ||
oacc-init.c | ||
oacc-int.h | ||
oacc-mem.c | ||
oacc-parallel.c | ||
oacc-plugin.c | ||
oacc-plugin.h | ||
omp_lib.f90.in | ||
omp_lib.h.in | ||
omp.h.in | ||
openacc_lib.h | ||
openacc.f90 | ||
openacc.h | ||
ordered.c | ||
parallel.c | ||
priority_queue.c | ||
priority_queue.h | ||
sections.c | ||
secure_getenv.h | ||
single.c | ||
splay-tree.c | ||
splay-tree.h | ||
target.c | ||
task.c | ||
taskloop.c | ||
team.c | ||
work.c |