Dynamic tensor descriptor (#24)

* support dynamic tensor descriptor * use buffer load OOB feature for padding case * add navi support * add int8x4 inference kernel Co-authored-by: Chao Liu <chao@ixt-rack-81.local.lan> Co-authored-by: Jing Zhang <jizhan@amd.com>

Dynamic tensor descriptor (#24)
* support dynamic tensor descriptor * use buffer load OOB feature for padding case * add navi support * add int8x4 inference kernel Co-authored-by: Chao Liu <chao@ixt-rack-81.local.lan> Co-authored-by: Jing Zhang <jizhan@amd.com>
fcbb9788 · Chao Liu · GitHub · bbcb67d0 · fcbb9788 · fcbb9788
Unverified Commit fcbb9788 authored Mar 25, 2021 by Chao Liu Committed by GitHub Mar 25, 2021
20 changed files
--- a/composable_kernel/include/utility/statically_indexed_array.hpp
+++ b/composable_kernel/include/utility/statically_indexed_array.hpp
--- a/composable_kernel/include/utility/tuple.hpp
+++ b/composable_kernel/include/utility/tuple.hpp
--- a/composable_kernel/include/utility/tuple_helper.hpp
+++ b/composable_kernel/include/utility/tuple_helper.hpp
--- a/composable_kernel/include/utility/type.hpp
+++ b/composable_kernel/include/utility/type.hpp
--- a/composable_kernel/include/utility/utility.hpp
+++ b/composable_kernel/include/utility/utility.hpp
--- a/driver/include/conv_common.hpp
+++ b/driver/include/conv_common.hpp
--- a/driver/include/device_convolution_backward_data_implicit_gemm_v1r1_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_convolution_backward_data_implicit_gemm_v1r1_nchw_kcyx_nkhw.hpp
--- a/driver/include/device_convolution_backward_data_implicit_gemm_v4r1_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_convolution_backward_data_implicit_gemm_v4r1_nchw_kcyx_nkhw.hpp
--- a/driver/include/device_convolution_backward_data_implicit_gemm_v5r1_nhwc_kyxc_nhwk.hpp
+++ b/driver/include/device_convolution_backward_data_implicit_gemm_v5r1_nhwc_kyxc_nhwk.hpp
--- a/driver/include/device_convolution_implicit_gemm_v4r1_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_convolution_implicit_gemm_v4r1_nchw_kcyx_nkhw.hpp
--- a/driver/include/device_convolution_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_convolution_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
--- a/driver/include/device_convolution_forward_implicit_gemm_v4r4_nhwc_kyxc_nhwk.hpp
+++ b/driver/include/device_convolution_forward_implicit_gemm_v4r4_nhwc_kyxc_nhwk.hpp
--- a/driver/include/device_dynamic_convolution_forward_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_dynamic_convolution_forward_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
--- a/driver/include/device_dynamic_convolution_forward_implicit_gemm_v4r4_nhwc_kyxc_nhwk.hpp
+++ b/driver/include/device_dynamic_convolution_forward_implicit_gemm_v4r4_nhwc_kyxc_nhwk.hpp
--- a/driver/include/device_dynamic_convolution_forward_implicit_gemm_v5r1_nchw_kcyx_nkhw.hpp
+++ b/driver/include/device_dynamic_convolution_forward_implicit_gemm_v5r1_nchw_kcyx_nkhw.hpp
--- a/driver/include/host_conv.hpp
+++ b/driver/include/host_conv.hpp
--- a/driver/include/host_tensor.hpp
+++ b/driver/include/host_tensor.hpp
--- a/driver/src/conv_bwd_data_driver.cpp
+++ b/driver/src/conv_bwd_data_driver.cpp
--- a/driver/src/conv_bwd_data_driver.cu
+++ b/driver/src/conv_bwd_data_driver.cu
-conv_bwd_data_driver.cpp
\ No newline at end of file
--- a/driver/src/conv_driver.cpp
+++ b/driver/src/conv_driver.cpp