pytorch/binaries
Sicheng Stephen Jia 52175307e2 [vulkan] Allow benchmark binary to handle non-single tensor inputs/outputs for Vulkan models (#73109)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73109

This change updates the Vulkan model runner in `speed_benchmark_torch` to be able to generate inputs for models that have input/output types other than just a single tensor. Input elements are processed depending on their type.

Test Plan: Imported from OSS

Reviewed By: mikaylagawarecki

Differential Revision: D34354839

Pulled By: SS-JIA

fbshipit-source-id: 993e55372d2664fa7eddb16146deba264727f399
(cherry picked from commit 4a140202ac)
2022-02-19 01:33:51 +00:00
..
bench_gen Revert D30279364: [codemod][lint][fbcode/c*] Enable BLACK by default 2021-08-12 11:45:01 -07:00
aot_model_compiler.cc [nnc][aot_compiler] Memory formats args to aot_compiler (#72873) 2022-02-16 18:39:31 +00:00
at_launch_benchmark.cc Move intraop_launch_future from Parallel.h (#64166) 2021-10-08 09:07:35 -07:00
benchmark_args.h Back out "Revert D16469619: Add Virtual Memory and CPU percentage computation to AIBench" 2019-08-07 15:44:22 -07:00
benchmark_helper.cc [easy]Unbreak caffe2benchmarking build (#63655) 2021-08-20 12:57:27 -07:00
benchmark_helper.h use irange for loops 2 (#66746) 2021-12-10 04:26:23 -08:00
caffe2_benchmark.cc Remove dead includes in caffe2/binaries 2019-11-01 10:58:42 -07:00
CMakeLists.txt [cmake] Uncomment binaries (#71157) 2022-01-12 15:01:44 -08:00
compare_models_torch.cc Small improvements to compare_models_torch binary (#65171) 2021-09-17 08:32:45 -07:00
convert_and_benchmark.cc Fix typos, via a Levenshtein-type corrector (#31523) 2020-01-17 16:03:19 -08:00
convert_caffe_image_db.cc Guard all Caffe2 protobuf string serializations with CAFFE_ENFORCE (fixed reverted bug) (#12848) 2018-10-23 16:21:26 -07:00
convert_db.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
convert_encoded_to_raw_leveldb.cc Remove dead includes in caffe2/binaries 2019-11-01 10:58:42 -07:00
convert_image_to_tensor.cc Fix typos, via a Levenshtein-type corrector (#31523) 2020-01-17 16:03:19 -08:00
core_overhead_benchmark_gpu.cc New in StaticContext returns at::DataPtr (#12029) 2018-10-03 19:10:07 -07:00
core_overhead_benchmark.cc Lightweight at-most-once logging for API usage (#20745) 2019-05-23 23:17:59 -07:00
db_throughput.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
dump_operator_names.cc [binaries] fix dump_operator_name binary (#71246) 2022-01-20 17:33:08 +00:00
inspect_gpu.cc move flags to c10 (#12144) 2018-10-04 02:09:56 -07:00
intra_inter_benchmark.cc Update intra_inter_benchmark (#22051) 2019-06-21 23:06:27 -07:00
lite_interpreter_model_load.cc Replace AutoNonVariableTypeMode with InferenceMode in fbcode. (#55114) 2021-04-02 11:45:53 -07:00
make_cifar_db.cc [caffe2] update make_cifar_db to move the string into DB::Put() (#60692) 2021-06-25 14:02:24 -07:00
make_image_db.cc [caffe2] update make_mnist_db and make_image_db to move strings into DB::Put() (#60919) 2021-06-29 11:52:43 -07:00
make_mnist_db.cc [caffe2] update make_mnist_db and make_image_db to move strings into DB::Put() (#60919) 2021-06-29 11:52:43 -07:00
optimize_for_mobile.cc Update default ouput extension in optimize_for_mobile.cc (#45598) 2020-10-15 15:34:34 -07:00
parallel_info.cc Allow a non-OpenMP based build (#19749) 2019-05-06 19:34:48 -07:00
predictor_verifier.cc Replace c10::guts::stuff with std::stuff (#30915) 2019-12-16 13:57:19 -08:00
print_core_object_sizes_gpu.cc Remove dead includes in caffe2/binaries 2019-11-01 10:58:42 -07:00
print_registered_core_operators.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
record_function_benchmark.cc [PyTorch] Use plain old function pointer for RecordFunctionCallback (reapply) (#49408) 2020-12-15 19:16:01 -08:00
run_plan_mpi.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
run_plan.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
speed_benchmark_torch.cc [vulkan] Allow benchmark binary to handle non-single tensor inputs/outputs for Vulkan models (#73109) 2022-02-19 01:33:51 +00:00
speed_benchmark.cc Windows shared build (#13550) 2018-11-16 12:16:28 -08:00
split_db.cc Using c10 namespace across caffe2. (#12714) 2018-10-17 12:57:19 -07:00
tsv_2_proto.cc fix the deeptext issue (#14005) 2018-11-15 12:13:45 -08:00
tutorial_blob.cc IValue can store Blob (#11414) 2018-09-26 01:12:31 -07:00
zmq_feeder.cc Remove dead includes in caffe2/binaries 2019-11-01 10:58:42 -07:00