Compile for gfx908 and gfx90a (#130)

* adding compilation for multiple targets

* fix build

* clean

* update Jekinsfile

* update readme

* update Jenkins

* use ck::half_t instead of ushort for bf16

* rename enum classes

* clean

* rename

* clean

example/09_convnd_fwd/README.md

@@ -1,39 +1,6 @@
-# Instructions for ```convnd_fwd_xdl``` Example
+# Instructions for ```example_convnd_fwd_xdl```
 
-## Docker script
-```bash
-docker run                                                                   \
--it                                                                          \
---rm                                                                         \
---privileged                                                                 \
---group-add sudo                                                             \
--w /root/workspace                                                           \
--v ${PATH_TO_LOCAL_WORKSPACE}:/root/workspace                                \
-rocm/tensorflow:rocm4.3.1-tf2.6-dev                                          \
-/bin/bash
-```
-
-## Build ```convnd_fwd_xdl```
-```bash
-mkdir build && cd build
-```
-
-```bash
-# Need to specify target ID, example below is gfx908
-cmake                                                                  \
--D BUILD_DEV=OFF                                                       \
--D CMAKE_BUILD_TYPE=Release                                            \
--D CMAKE_CXX_FLAGS="-DCK_AMD_GPU_GFX908 --amdgpu-target=gfx908 -O3 "   \
--D CMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc                              \
--D CMAKE_PREFIX_PATH=/opt/rocm                                         \
-..
-```
-
-```bash
- make -j convnd_fwd_xdl
-```
-
-## Run ```convnd_fwd_xdl```
+## Run ```example_convnd_fwd_xdl```
 ```bash
 #arg1: verification (0=no, 1=yes)
 #arg2: initialization (0=no init, 1=integer value, 2=decimal value)
@@ -47,7 +14,7 @@ cmake                                                                  \
 # <dilations>, (ie Dy, Dx for 2D)
 # <left padding>, (ie LeftPy, LeftPx for 2D)
 # <right padding>, (ie RightPy, RightPx for 2D)
-./example/convnd_fwd_xdl 0 1 100
+./bin/example_convnd_fwd_xdl 0 1 100
 ```
 
 Result (MI100 @ 1087Mhz, 33.4TFlops peak FP32)

example/09_convnd_fwd/convnd_fwd_xdl.cpp

@@ -26,7 +26,7 @@ using WeiElementOp = ck::tensor_operation::element_wise::PassThrough;
 using OutElementOp = ck::tensor_operation::element_wise::PassThrough;
 
 static constexpr auto ConvFwdDefault =
-    ck::tensor_operation::device::ConvolutionForwardSpecialization_t::Default;
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::Default;
 
 using DeviceConvFwdBasePtr =
     ck::tensor_operation::device::DeviceConvFwdPtr<InElementOp, WeiElementOp, OutElementOp>;