gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CUDA: various improvements

Browse Source
This commit is contained in:
Philippe Tillet
2015-08-21 13:06:20 -04:00
parent 33dac6b05a
commit 10524ebdee
25 changed files with 170 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tune/android/tune/optimize.py
View File

@@ -13,12 +13,12 @@ from numpy import cumsum
import tools
fetch_types = [sc.templates.fetching_policy_type.FETCH_FROM_GLOBAL_CONTIGUOUS,
sc.templates.fetching_policy_type.FETCH_FROM_GLOBAL_STRIDED,
fetch_types = [sc.templates.fetching_policy_type.FETCH_FROM_LOCAL,
sc.templates.fetching_policy_type.FETCH_FROM_LOCAL,
sc.templates.fetching_policy_type.FETCH_FROM_LOCAL,
sc.templates.fetching_policy_type.FETCH_FROM_LOCAL]
to_catch = (sc.OperationNotSupported, sc.LaunchOutOfResources, sc.MemObjectAllocationFailure, sc.InvalidWorkGroupSize, sc.OutOfHostMemory, sc.InvalidValue)
to_catch = (sc.OperationNotSupported, sc.OclLaunchOutOfResources, sc.CudaLaunchOutOfResources, sc.MemObjectAllocationFailure, sc.InvalidWorkGroupSize, sc.OutOfHostMemory, sc.InvalidValue)
def exhaustive(template, sizes, context):
tree, _ = tools.tree_of(template, sizes, context)