cuda-samples/bin/x86_64/linux/release/APM_simpleCooperativeGroups.txt
2023-03-01 01:41:29 +00:00

15 lines
492 B
Plaintext

Launching a single block with 64 threads...
Sum of all ranks 0..63 in threadBlockGroup is 2016 (expected 2016)
Now creating 4 groups, each of size 16 threads:
Sum of all ranks 0..15 in this tiledPartition16 group is 120 (expected 120)
Sum of all ranks 0..15 in this tiledPartition16 group is 120 (expected 120)
Sum of all ranks 0..15 in this tiledPartition16 group is 120 (expected 120)
Sum of all ranks 0..15 in this tiledPartition16 group is 120 (expected 120)
...Done.