Skip to content
Merged
Changes from all commits
Commits
Show all changes
29 commits
Select commit Hold shift + click to select a range
95aeb56
Enable the adapted LDS B layout for Row-Major
samremes Jun 27, 2025
224959b
fix formatting
samremes Jun 27, 2025
982b672
Implement specialized col-major A LDS block descriptor
samremes Jul 1, 2025
a9c5e6a
Fix formatting
samremes Jul 1, 2025
c6ec53b
Merge remote-tracking branch 'origin/develop' into samremes/optimized…
samremes Jul 31, 2025
fa6d590
Use VecLoadSize for AK1/BK1
samremes Aug 4, 2025
c6d7306
Fix some thread access pattern values
samremes Aug 4, 2025
c3a7be0
Use GetVectorSizeA for A
samremes Aug 4, 2025
9a1ff9f
Fix formatting
samremes Aug 4, 2025
643e61a
Merge remote-tracking branch 'origin/develop' into samremes/optimized…
samremes Aug 4, 2025
e42879a
Add extra condition to avoid division by zero
samremes Aug 4, 2025
f212236
Merge branch 'develop' into samremes/optimized_lds_non_kmajor
samremes Aug 6, 2025
329d96d
Merge branch 'develop' into samremes/optimized_lds_non_kmajor
aosewski Aug 7, 2025
befc871
Merge branch 'develop' into samremes/optimized_lds_non_kmajor
aosewski Aug 11, 2025
cc83dd6
Merge branch 'develop' into samremes/optimized_lds_non_kmajor
aosewski Aug 18, 2025
3002df2
disable layout for wave32
samremes Aug 19, 2025
f9273fc
Merge remote-tracking branch 'origin/develop' into samremes/optimized…
samremes Aug 19, 2025
3b35f84
remove extra else
samremes Aug 19, 2025
67d2a60
fix formatting
samremes Aug 19, 2025
5dc1b23
Merge remote-tracking branch 'origin/develop' into samremes/optimized…
samremes Sep 30, 2025
0c7b6a2
Fix formatting
samremes Sep 30, 2025
9b96e36
Rename one remaining TileDistributionEncodingPattern2D
samremes Sep 30, 2025
d8a3066
Use integer ceil division
samremes Sep 30, 2025
e0e86b6
Merge remote-tracking branch 'origin/develop' into samremes/optimized…
aosewski Oct 9, 2025
69bccde
Merge branch 'develop' into samremes/optimized_lds_non_kmajor
samremes Oct 10, 2025
d404405
revert remod.py changes
samremes Oct 10, 2025
78b8781
also revert utility.hpp
samremes Oct 10, 2025
b62a6dd
use getA/BTileAccessPattern everywhere
samremes Oct 10, 2025
bcf76e4
use integer_divide_ceil for AK0 too
samremes Oct 13, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading
Loading