ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-13 09:45:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add a scale op, related instances and examples (#1242)

Browse Source 
* Add a scale op

* Update the element op

* Add instances

* Add an example

* Add a client example

* Add a flag check

* Revert flag check addition

* Fix flag check

* Update d strides in example

* Update d strides in client example

* Apply suggestions from code review

Update copyright header

Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

* Move the example

* Move the client example

* Update element op

* Update example with the new element op

* Add scalar layout

* Update example

* Update kernel for scalar Ds

* Revert kernel changes

* Update element op

* Update example to use scales' pointers

* Format

* Update instances

* Update client example

* Move element op to unary elements

* Update element op to work with values instead of pointers

* Update instances to take element op as an argument

* Update examples to use random scale values

---------

Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
This commit is contained in:
Rostyslav Geyyer
2024-06-04 19:28:15 -05:00
committed by GitHub
parent 2cab8d39e3
commit cb0645bedc
13 changed files with 1150 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/CMakeLists.txt Normal file
View File

@@ -0,0 +1,5 @@
# ONLY XDL_KERNELS
set(GROUPED_CONV3D_FWD_CONVSCALE
xdl/device_grouped_conv3d_fwd_xdl_convscale_ndhwgc_gkzyxc_ndhwgk_f8_instance.cpp)
add_instance_library(device_grouped_conv3d_fwd_convscale_instance ${GROUPED_CONV3D_FWD_CONVSCALE})

62
library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/xdl/device_grouped_conv3d_fwd_xdl_convscale_ndhwgc_gkzyxc_ndhwgk_f8_instance.cpp Normal file
View File

@@ -0,0 +1,62 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_outelementop_instance.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using ConvScale = ck::tensor_operation::element_wise::ConvScale;
void add_device_grouped_conv3d_fwd_xdl_convscale_ndhwgc_gkzyxc_ndhwgk_f8_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
F8,
F8,
ck::Tuple<>,
F8,
PassThrough,
PassThrough,
ConvScale,
F8,
F8>>>& instances)
{
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_outelementop_f8_instances<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
ConvFwdDefault,
ConvScale>{});
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_outelementop_f8_instances<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
ConvFwd1x1P0,
ConvScale>{});
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_outelementop_f8_instances<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
ConvFwd1x1S1P0,
ConvScale>{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck