squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Update generator.py

Browse Source 
stop generating analytical conv kernels to reduce kernel number
This commit is contained in:
Haicheng Wu 2022-05-08 21:47:15 -04:00 committed by GitHub
parent 6023038bae
commit 1604ebaf10
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tools/library/scripts/generator.py
View File

@ -344,8 +344,9 @@ def CreateConv2dOperator(manifest, layout, tile_descriptions, data_type, alignme
# one exceptional case
# iterator algorithm (analytic and optimized)
iterator_algorithms = [IteratorAlgorithm.Analytic, IteratorAlgorithm.Optimized]
#iterator_algorithms = [IteratorAlgorithm.Analytic, IteratorAlgorithm.Optimized]
iterator_algorithms = [IteratorAlgorithm.Optimized]
# by default, only generate the largest tile size, largest alignment, and optimized iterator
if manifest.kernel_filter == '':
tile_descriptions = [tile_descriptions[0],]
@ -526,7 +527,8 @@ def CreateConv3dOperator(manifest, layout, tile_descriptions, data_type, alignme
alignment_c = min(8, alignment)
# iterator algorithm (analytic and optimized)
iterator_algorithms = [IteratorAlgorithm.Analytic, IteratorAlgorithm.Optimized]
#iterator_algorithms = [IteratorAlgorithm.Analytic, IteratorAlgorithm.Optimized]
iterator_algorithms = [IteratorAlgorithm.Optimized]
# by default, only generate the largest tile size and optimized iterators
if manifest.kernel_filter == '':