Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
composable_kernel
Commits
360383bb
Commit
360383bb
authored
Sep 08, 2022
by
Po-Yen, Chen
Browse files
Avoid too-large block id
parent
e017a9f0
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
0 deletions
+2
-0
include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
+2
-0
No files found.
include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
View file @
360383bb
...
@@ -54,6 +54,8 @@ struct Block2TileMap
...
@@ -54,6 +54,8 @@ struct Block2TileMap
const
auto
H0
=
math
::
integer_divide_ceil
(
desc_
.
GetLength
(
Number
<
NumDim
-
2
>
{}),
HPerBlock
);
const
auto
H0
=
math
::
integer_divide_ceil
(
desc_
.
GetLength
(
Number
<
NumDim
-
2
>
{}),
HPerBlock
);
const
auto
W0
=
math
::
integer_divide_ceil
(
desc_
.
GetLength
(
Number
<
NumDim
-
1
>
{}),
WPerBlock
);
const
auto
W0
=
math
::
integer_divide_ceil
(
desc_
.
GetLength
(
Number
<
NumDim
-
1
>
{}),
WPerBlock
);
block_1d_id
=
block_1d_id
%
(
H0
*
W0
);
index_t
idx_H0
=
block_1d_id
/
W0
;
index_t
idx_H0
=
block_1d_id
/
W0
;
index_t
idx_W0
=
block_1d_id
%
W0
;
index_t
idx_W0
=
block_1d_id
%
W0
;
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment