[committed][nvptx] Apply vector-partitionable routines workaround to default vl
Tom de Vries
tdevries@suse.de
Sat Jan 12 10:39:00 GMT 2019
Hi,
Make "[nvptx] Force vl32 if calling vector-partitionable routines" work as well
if vector length is set by modifying PTX_DEFAULT_VECTOR_LENGTH.
Committed to trunk.
Thanks,
- Tom
[nvptx] Apply vector-partitionable routines workaround to default vl
2019-01-11 Tom de Vries <tdevries@suse.de>
* config/nvptx/nvptx.c (nvptx_goacc_validate_dims_1): In offloading
region calling vector-partitionable routine, set default_vector_length
to WARP_SIZE.
---
gcc/config/nvptx/nvptx.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 95d72d0a4e0..1d9704543d9 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -5669,6 +5669,8 @@ nvptx_goacc_validate_dims_1 (tree decl, int dims[], int fn_level, unsigned used)
const char *vector_reason = NULL;
if (offload_region_p && has_vector_partitionable_routine_calls_p (decl))
{
+ default_vector_length = PTX_WARP_SIZE;
+
if (dims[GOMP_DIM_VECTOR] > PTX_WARP_SIZE)
{
vector_reason = G_("using vector_length (%d) due to call to"
More information about the Gcc-patches
mailing list