InfiniTensor/include/core
kilinchange 0dc5347089
memory_allocator (#103)
* - add LazyAllocator class
- calculate memory consumption at present

* - basic function of lazy_allocator, remaining test

* - modify LazyAllocator

* - modify InfiniTensor to fit LazyAllocator

* - add setDataBlob
- modify alignment
- fix GraphObj::dataMalloc

* - modified alignment value(64bytes -> 8bytes)
- fix LazyAllocator::getPtr()
- some dubug codes and commonts
- do alignment by chaning size instead of tailAddr

* - fix some problem

* - translate chinese comments to english

* - format codes

* - fix test

* - code format

* - modify codes as YdrMaser and bitzyz suggested

* - code format

* - modify codes as constroy suggested

* - codes format

* - modify alignment on cuda

* - code format

* - add test_lazy_allocator
- fix tests where not add input tensor into graph.tensors
- fix tests where init tensor's data before calling graph->dataMallocate()

* - code format

* - remove gpu runtime in test_lazy_allocator

* - fix test_lazy_allocator: remove cuda include

* - add test

* - code format

* - add ifdef for test of allocator

* - code format

* - fix test: remove unused ifdef

* - fix bang test

* - code format

* Merge branch 'master' into dcj/memory_allocator

* fix: fix cuda conv_fp16 run fail

* fix bang_runtime.cc and cuda_runtime.cc

* - update mkl code

* - fix codes for mkl

* - code format

* - remove unused commented codes
- add an empty line at the end of the blob.cc

---------

Co-authored-by: zhangyunze <z13785159769@163.com>
2023-08-13 13:39:35 +08:00
..
blob.h Support bang c kernel wanghailu 0927 (#43) 2022-09-30 11:01:52 +08:00
common.h Add ConvTransposedNHWC (#67) 2023-03-01 14:15:02 +08:00
constants.h Dev for 202303ddl (#66) 2023-04-18 15:10:33 +08:00
data_type.h 支持fp16 dtype (#96) 2023-08-02 16:38:16 +08:00
dummy_mutator.h Add search engine (#64) 2023-02-12 18:27:52 +08:00
graph.h memory_allocator (#103) 2023-08-13 13:39:35 +08:00
graph_handler.h refactor(core): 添加新的 `OpType` 定义 (#99) 2023-08-07 11:17:05 +08:00
graph_match.h ADD: sub graph replacement. (#56) 2023-04-17 13:09:07 +08:00
hash.h Dev for 202303ddl (#66) 2023-04-18 15:10:33 +08:00
kernel.h refactor(core): 添加新的 `OpType` 定义 (#99) 2023-08-07 11:17:05 +08:00
lazy_allocator.h memory_allocator (#103) 2023-08-13 13:39:35 +08:00
mutator.h ADD: add mkl runtime for intel cpu , and add mkl kernel for matmul/conv/convtransposed. (#61) 2023-03-27 21:28:49 +08:00
object.h Dev for 202303ddl (#66) 2023-04-18 15:10:33 +08:00
op_type.h refactor(core): 添加新的 `OpType` 定义 (#99) 2023-08-07 11:17:05 +08:00
operator.h refactor(core): 添加新的 `OpType` 定义 (#99) 2023-08-07 11:17:05 +08:00
perf_engine.h Dev for 202303ddl (#66) 2023-04-18 15:10:33 +08:00
ref.h Dev for 202303ddl (#66) 2023-04-18 15:10:33 +08:00
runtime.h refactor(core): 添加新的 `OpType` 定义 (#99) 2023-08-07 11:17:05 +08:00
search_engine.h Add search engine (#64) 2023-02-12 18:27:52 +08:00
tensor.h memory_allocator (#103) 2023-08-13 13:39:35 +08:00
tensor_base.h ADD: sub graph replacement. (#56) 2023-04-17 13:09:07 +08:00