diff options
author | Thomas Schwinge <tschwinge@baylibre.com> | 2024-03-07 13:18:23 +0100 |
---|---|---|
committer | Thomas Schwinge <tschwinge@baylibre.com> | 2024-03-08 16:35:28 +0100 |
commit | 37078f241a22c45db6380c5e9a79b4d08054bb3d (patch) | |
tree | a7be05757c13fdb30cc466e7c0fc318d4f59e2d9 /gcc | |
parent | ab70addf560e18210d238edfd605fc91fcce9df1 (diff) | |
download | gcc-37078f241a22c45db6380c5e9a79b4d08054bb3d.zip gcc-37078f241a22c45db6380c5e9a79b4d08054bb3d.tar.gz gcc-37078f241a22c45db6380c5e9a79b4d08054bb3d.tar.bz2 |
nvptx: 'cuDeviceGetCount' failure is fatal
Per commit 683f11843974f0bdf42f79cdcbb0c2b43c7b81b0
"OpenMP: Move omp requires checks to libgomp", we're now using 'return -1'
from 'GOMP_OFFLOAD_get_num_devices' for 'omp_requires_mask' purposes. This
missed that via 'nvptx_get_num_devices', we could also 'return -1' for
'cuDeviceGetCount' failure. Before, this meant (in 'gomp_target_init') to
silently ignore the plugin/device -- which also has been doubtful behavior.
Let's instead turn 'cuDeviceGetCount' failure into a fatal error, similar to
other errors during device initialization.
libgomp/
* plugin/plugin-nvptx.c (nvptx_get_num_devices):
'cuDeviceGetCount' failure is fatal.
Diffstat (limited to 'gcc')
0 files changed, 0 insertions, 0 deletions