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
6b0f1b2f
Commit
6b0f1b2f
authored
Apr 08, 2022
by
illsilin
Browse files
fixed some typos
parent
3b573bb9
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
3 additions
and
3 deletions
+3
-3
include/ck/tensor_operation/gpu/device/device_batched_gemm_xdl.hpp
...k/tensor_operation/gpu/device/device_batched_gemm_xdl.hpp
+1
-1
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
...k/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
+1
-1
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
...k/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
+1
-1
No files found.
include/ck/tensor_operation/gpu/device/device_batched_gemm_xdl.hpp
View file @
6b0f1b2f
...
...
@@ -46,7 +46,7 @@ __global__ void
const
ComputeBasePrtOfBatch
compute_base_ptr_of_batch_
,
const
Block2CTileMap
block_2_ctile_map
)
{
#if
(defined
(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
#if (!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
const
index_t
num_blocks_per_batch
=
__builtin_amdgcn_readfirstlane
(
get_grid_size
()
/
batch_count
);
const
index_t
g_idx
=
__builtin_amdgcn_readfirstlane
(
get_block_1d_id
()
/
num_blocks_per_batch
);
...
...
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
View file @
6b0f1b2f
...
...
@@ -42,7 +42,7 @@ __global__ void
const
CElementwiseOperation
c_element_op
,
const
Block2CTileMap
block_2_ctile_map
)
{
#if
(defined
(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
#if (!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
__shared__
char
p_shared
[
GridwiseGemm
::
GetSharedMemoryNumberOfByte
()];
GridwiseGemm
::
template
Run
<
HasMainK0BlockLoop
>(
...
...
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
View file @
6b0f1b2f
...
...
@@ -45,7 +45,7 @@ __global__ void
const
CElementwiseOperation
c_element_op
,
const
Block2CTileMap
block_2_ctile_map
)
{
#if
(defined
(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
#if (!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
__shared__
char
p_shared
[
GridwiseGemm
::
GetSharedMemoryNumberOfByte
()];
GridwiseGemm
::
template
Run
<
HasMainK0BlockLoop
>(
...
...
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