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 · bbcb67d0 · fcbb9788
Unverified Commit fcbb9788 authored Mar 25, 2021 by Chao Liu Committed by GitHub Mar 25, 2021
5 changed files
--- a/driver/src/conv_driver.cu
+++ b/driver/src/conv_driver.cu
--- a/external/half/include/half.hpp
+++ b/external/half/include/half.hpp
--- a/script/cmake-rocm3.5.sh
+++ b/script/cmake-rocm3.5.sh
--- a/script/count_vgpr.sh
+++ b/script/count_vgpr.sh
--- a/script/hipclang_opt.sh
+++ b/script/hipclang_opt.sh