Tom de Vries 2c372e81a9 [nvptx, libgomp] Don't launch with num_workers == 0 ... When using a compiler build with: ... +#define PTX_DEFAULT_VECTOR_LENGTH PTX_CTA_SIZE +#define PTX_MAX_VECTOR_LENGTH PTX_CTA_SIZE ... and running the libgomp testsuite, we run into an execution failure in parallel-loop-1.c, due to a cuda launch failure: ... nvptx_exec: kernel f6_none_none$_omp_fn$0: launch gangs=480, workers=0, \ vectors=1024 libgomp: cuLaunchKernel error: invalid argument ... because workers == 0. The workers variable is set to 0 here in nvptx_exec: ... workers = blocks / actual_vectors; ... because actual_vectors is 1024, and blocks is 768: ... cuOccupancyMaxPotentialBlockSize: grid = 10, block = 768 ... Fix this by ensuring that workers is at least one. 2019-01-09 Tom de Vries <tdevries@suse.de> * plugin/plugin-nvptx.c (nvptx_exec): Make sure to launch with at least one worker. From-SVN: r267746		2019-01-09 00:07:45 +00:00
..
cuda	Update copyright years.	2019-01-01 13:31:55 +01:00
Makefrag.am	Update copyright years.	2019-01-01 13:31:55 +01:00
configfrag.ac	Update copyright years.	2019-01-01 13:31:55 +01:00
cuda-lib.def	[nvptx] Use CUDA driver API to select default runtime launch geometry	2018-08-13 12:04:24 +00:00
hsa_ext_finalize.h	Update copyright years.	2019-01-01 13:31:55 +01:00
plugin-hsa.c	Update copyright years.	2019-01-01 13:31:55 +01:00
plugin-nvptx.c	[nvptx, libgomp] Don't launch with num_workers == 0	2019-01-09 00:07:45 +00:00