onnxruntime
Reduce amount of compiled CUDA device code
#6118
Merged

Reduce amount of compiled CUDA device code #6118

edgchen1 merged 12 commits into master from edgchen1/cuda_kernel_h
edgchen1
edgchen1 Move CudaKernel definition into a separate header file.
df838a61
edgchen1 Replace include of cuda_common.h with cuda_kernel.h in header files c…
f5eeaf20
edgchen1 Fix build issues for onnxruntime_providers_cuda.
530690a1
edgchen1 Fix build.
e7cfa771
edgchen1 Include cuda_fwd.h instead of cuda_kernel.h in cuda_execution_provide…
3de23731
edgchen1 Add cuda_kernel.h to amd_hipify.py exclusion list.
239be5e2
edgchen1 Add rocm_kernel.h, updates.
bb2c9edc
edgchen1 Fix ROCM build.
cb33f6cb
edgchen1 edgchen1 added core runtime
edgchen1 edgchen1 requested a review from pranavsharma pranavsharma 5 years ago
edgchen1 edgchen1 requested a review from suffiank suffiank 5 years ago
edgchen1 edgchen1 requested a review from SherlockNoMad SherlockNoMad 5 years ago
edgchen1 edgchen1 requested a review from weixingzhang weixingzhang 5 years ago
edgchen1 edgchen1 requested a review 5 years ago
edgchen1 edgchen1 requested a review from snnn snnn 5 years ago
edgchen1 Exclude fallback_cpu_capability.h/cc from minimal build.
8b5ab2d9
edgchen1 Fix typo.
274a7232
edgchen1 edgchen1 requested a review from HectorSVC HectorSVC 5 years ago
yuslepukhin
yuslepukhin
yuslepukhin commented on 2020-12-14
yuslepukhin
yuslepukhin commented on 2020-12-14
HectorSVC
HectorSVC commented on 2020-12-14
HectorSVC
HectorSVC commented on 2020-12-14
edgchen1 Remove redundant includes of op_kernel.h.
a1f6878e
edgchen1
edgchen1 Remove another redundant include.
ac73c1fa
jessebenson
jessebenson approved these changes on 2020-12-14
HectorSVC
HectorSVC approved these changes on 2020-12-14
edgchen1 edgchen1 merged 9810b9e0 into master 5 years ago
edgchen1 edgchen1 deleted the edgchen1/cuda_kernel_h branch 5 years ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone