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
4361cffd
"driver/src/conv_driver.cpp" did not exist on "52c3fe05be9b6cfc0602918bf3f5177cf6713290"
Unverified
Commit
4361cffd
authored
Dec 02, 2021
by
Chao Liu
Committed by
GitHub
Dec 02, 2021
Browse files
Update README.md
update readme for example/3_conv_xdl
parent
7b24b5f0
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
14 additions
and
13 deletions
+14
-13
example/3_conv_xdl/README.md
example/3_conv_xdl/README.md
+14
-13
No files found.
example/3_conv_xdl/README.md
View file @
4361cffd
# Instructions for ```
gemm
_xdl``` Example
# Instructions for ```
conv
_xdl``` Example
## Docker script
```
bash
...
...
@@ -13,7 +13,7 @@ rocm/tensorflow:rocm4.3.1-tf2.6-dev \
/bin/bash
```
## Build ```
gemm
_xdl```
## Build ```
conv
_xdl```
```
bash
mkdir
build
&&
cd
build
```
...
...
@@ -30,27 +30,28 @@ cmake \
```
```
bash
make
-j
gemm
_xdl
make
-j
conv
_xdl
```
## Run ```
gemm
_xdl```
## Run ```
conv
_xdl```
```
bash
#arg1: verification (0=no, 1=yes)
#arg2: initialization (0=no init, 1=integer value, 2=decimal value)
#arg3: run kernel # of times (>1)
./example/gemm_xdl 0 1 5
#arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, RightPx
./example/conv_xdl 0 1 5
```
Result (MI100 @ 1087Mhz, 133.5TFlops peak FP16)
```
a_m_k
: dim
2
, lengths {
3840, 4096}, strides {4096, 1
}
b_k_n
: dim
2
, lengths {
4096, 4096}, strides {1, 4096
}
c_m_n
: dim
2
, lengths {
3840, 4096}, strides {4096, 1
}
arg.a_grid_desc_k0_m_k1_{
512, 3840
, 8}
arg.b_grid_desc_k0_n_k1_{
512, 409
6, 8}
arg.c_grid_desc_m_n_{
3840, 409
6}
launch_and_time_kernel: grid_dim {
480
, 1, 1}, block_dim {256, 1, 1}
in_n_c_hi_wi
: dim
4
, lengths {
128, 192, 71, 71}, strides {967872, 1, 13632, 192
}
wei_k_c_y_x
: dim
4
, lengths {
256, 192, 3, 3}, strides {1728, 1, 576, 192
}
out_n_k_ho_wo
: dim
4
, lengths {
128, 256, 36, 36}, strides {331776, 1, 9216, 256
}
arg.a_grid_desc_k0_m_k1_{
216, 165888
, 8}
arg.b_grid_desc_k0_n_k1_{
216, 25
6, 8}
arg.c_grid_desc_m_n_{
165888, 25
6}
launch_and_time_kernel: grid_dim {
1296
, 1, 1}, block_dim {256, 1, 1}
Warm up
Start running 5 times...
Perf: 1.
19685
ms, 10
7.657
TFlops,
78.8501
GB/s
Perf: 1.
43206
ms, 10
2.486
TFlops,
232.947
GB/s
```
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