deathwings602 11d5aa1ccc Add TVM codegen for MemboundOp (#35) ... * Add: interface for membound TVM kernel and test * add getAnsorCode * add evaluation, but link failed * add evaluation of kernel, but link failed * Fix: link libcuda and nvrtc * add print * Add: const for source of copy * compile and evaluate the kernel * add compute * fix gen_ansor_op.py * fix membound_TVM * format and fix CMakeLists.txt * fix memory leak Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com> Co-authored-by: huangshuhong <huangsh19@mails.tsinghua.edu.cn>		2022-09-22 18:06:45 +08:00
..
cuda_common.h	Add TVM codegen for MemboundOp (#35)	2022-09-22 18:06:45 +08:00
cuda_element_wise.h	ADD add/mul/sub/div/pow operators and CPU/CUDA kernels (#26)	2022-09-09 13:43:59 +08:00
cuda_kernel_wihtout_config.h	Fix: PerfRecord in shared pointers (#31)	2022-09-18 20:27:18 +08:00
cuda_runtime.h	Add TVM codegen for MemboundOp (#35)	2022-09-22 18:06:45 +08:00
cuda_unary.h	Add activation operators and kernels	2022-09-16 13:58:57 +08:00
cuda_utility.h	Simplify tensor transfer between CPU and CUDA (#10)	2022-08-25 11:29:16 +08:00
gbmm_g2bmm.cuh	Fix CMake USE_CUDA (#36)	2022-09-21 12:28:00 +08:00
gbmm_g2bmm.h	Fix CMake USE_CUDA (#36)	2022-09-21 12:28:00 +08:00