Revision 0d43318d10e1a00cfb44aae5e396e41a438a4b46 authored by Steven Johnson on 10 January 2023, 19:23:58 UTC, committed by GitHub on 10 January 2023, 19:23:58 UTC
* Optimize Module::compile() for some edge cases

Avoid redundant `compile_to_buffer()` calls for output requests that can't possibly ever need them.

* Avoid mutation
1 parent a8d88bb
History
File Mode Size
Makefile -rw-r--r-- 4.0 KB
benchmarking_utils.h -rw-r--r-- 552 bytes
common_types.h -rw-r--r-- 381 bytes
denormal_disabler.h -rw-r--r-- 1.3 KB
halide_as_onnx_backend.py -rw-r--r-- 3.4 KB
halide_as_onnx_backend_test.py -rw-r--r-- 2.9 KB
model.cpp -rw-r--r-- 21.0 KB
model.py -rw-r--r-- 2.1 KB
model_test.py -rw-r--r-- 4.9 KB
onnx_converter.cc -rw-r--r-- 170.6 KB
onnx_converter.h -rw-r--r-- 1.4 KB
onnx_converter_generator.cc -rw-r--r-- 2.4 KB
onnx_converter_generator_test.cc -rw-r--r-- 851 bytes
onnx_converter_test.cc -rw-r--r-- 16.9 KB
test_model_proto.txt -rw-r--r-- 844 bytes

back to top