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_ROCM
Commits
d7c28884
Unverified
Commit
d7c28884
authored
Oct 18, 2024
by
Rostyslav Geyyer
Committed by
GitHub
Oct 18, 2024
Browse files
Merge branch 'develop' into lwpck-2374_2
parents
2ebaf5f1
a285d6f9
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
8 additions
and
1 deletion
+8
-1
CMakeLists.txt
CMakeLists.txt
+7
-0
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn.hpp
...f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn.hpp
+1
-1
No files found.
CMakeLists.txt
View file @
d7c28884
...
@@ -202,6 +202,13 @@ if(NOT WIN32 AND ${hip_VERSION_FLAT} GREATER 500723302)
...
@@ -202,6 +202,13 @@ if(NOT WIN32 AND ${hip_VERSION_FLAT} GREATER 500723302)
add_compile_options
(
-fno-offload-uniform-block
)
add_compile_options
(
-fno-offload-uniform-block
)
endif
()
endif
()
endif
()
endif
()
if
(
NOT WIN32 AND
${
hip_VERSION_FLAT
}
GREATER 500500000
)
check_cxx_compiler_flag
(
"-mllvm --lsr-drop-solution=1"
HAS_LSR_DROP_SOLUTION
)
if
(
HAS_LSR_DROP_SOLUTION
)
message
(
"Adding the lsr-drop-solution=1 compiler flag"
)
add_compile_options
(
"SHELL: -mllvm --lsr-drop-solution=1"
)
endif
()
endif
()
if
(
NOT WIN32 AND
${
hip_VERSION_FLAT
}
GREATER 600140090
)
if
(
NOT WIN32 AND
${
hip_VERSION_FLAT
}
GREATER 600140090
)
check_cxx_compiler_flag
(
"-mllvm -enable-post-misched=0"
HAS_ENABLE_POST_MISCHED
)
check_cxx_compiler_flag
(
"-mllvm -enable-post-misched=0"
HAS_ENABLE_POST_MISCHED
)
if
(
HAS_ENABLE_POST_MISCHED
)
if
(
HAS_ENABLE_POST_MISCHED
)
...
...
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn.hpp
View file @
d7c28884
...
@@ -46,7 +46,7 @@ using device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_comp_instances = std::tuple<
...
@@ -46,7 +46,7 @@ using device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_comp_instances = std::tuple<
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
192
,
256
,
64
,
16
,
8
,
32
,
32
,
3
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
8
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
192
,
256
,
64
,
16
,
8
,
32
,
32
,
3
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
8
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
128
,
16
,
8
,
32
,
32
,
2
,
2
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
8
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
128
,
16
,
8
,
32
,
32
,
2
,
2
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
8
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
64
,
16
,
4
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
4
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
64
,
16
,
4
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
4
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v3
>
,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
64
,
16
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
8
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Intrawave
,
BlockGemmPipelineVersion
::
v5
>
,
//
DeviceGemm_Xdl_CShuffleV3< Row, Row, Row, F8, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 128, 128, 64, 16, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 0, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v5>,
// We prefer following instance, however, existing compiler bug cause it failed to generate sanity code.
// We prefer following instance, however, existing compiler bug cause it failed to generate sanity code.
// DeviceGemm_Xdl_CShuffleV3< Row, Row, Row, F8, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 128, 128, 64, 16, 4, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 4, 0, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v5>,
// DeviceGemm_Xdl_CShuffleV3< Row, Row, Row, F8, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 128, 128, 64, 16, 4, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 4, 0, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v5>,
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
64
,
16
,
4
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
4
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Interwave
,
BlockGemmPipelineVersion
::
v1
>
DeviceGemm_Xdl_CShuffleV3
<
Row
,
Row
,
Row
,
F8
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmSpec
,
256
,
128
,
128
,
64
,
16
,
4
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
16
,
16
,
0
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
8
,
4
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
,
BlockGemmPipelineScheduler
::
Interwave
,
BlockGemmPipelineVersion
::
v1
>
...
...
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