Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/13689
Now that typeid.h lives in c10/util, the include paths should reflect that.
Reviewed By: ezyang
Differential Revision: D12912237
fbshipit-source-id: e54225f049f690de77cb6d5f417994b211a6e1fb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/13377
* Enable junk fill for the default CPU allocator. The first diff only enables this for the tests. A second diff will change the default of zero-fill to false.
* Fix tests to use 64-bit counters that IterOp and LearningRateOp demands.
* Fix kernels that uses uninitialized memory.
Reviewed By: salexspb
Differential Revision: D10866512
fbshipit-source-id: 17860e77e63a203edf46d0da0335608f77884821
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12029
In order to remove New() function in StaticContext(to remove StaticContext) and converge to the Allocator design, we'll first change the return type of New to at::DataPtr.
Reviewed By: ezyang
Differential Revision: D9889990
fbshipit-source-id: 3257c763530b987025f428741bdd2e089d11bad4
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9939
Pull Request resolved: https://github.com/facebookresearch/weakly-supervised-action-detection/pull/13
Pull Request resolved: https://github.com/pytorch/translate/pull/166
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9125
Closes https://github.com/pytorch/pytorch/pull/9125
Use inheritance for polymorphism, and remove template parameter
This is to change the templating in call sites, the core implementations will change later
Before Caffe2 Tensor class was compile-time fixed to bind to a particular device/context. With this change, we're making it a runtime property (stored inside the tensor), but preserve the same semantics. For example, one has to specify device type in order to create a Tensor - there are no uninitialized tensors. More specifically the changes are:
1. We added an extra argument *DeviceType* to most of the constructors of the tensor, e.g. (Tensor(DeviceType type)),
2. Semantics of constructor Tensor(const Tensor<SrcContext>& src, ContextForCopy* context); is changed, in this constructor, the second context is passed in to enable us to call the templated Copy function, it could be in a different context as source and target previously, now we'll enforce that the context should have same device type as src, if it is provided.
3. To preserve 'get-or-construct' semantics of Blob, we added specialized getter Blob::GetMutableTensor that verifies both that Blob contains a Tensor and that it's of a correct type
4. Specifically, Tensor type is not default-constructible any more (as we don't have unknown device tensors) and thus some of the code handling STL containers needs to change
Note: Some changes are postponed just to keep this diff a bit smaller. Please see `TODO`s.
Reviewed By: ezyang, houseroad
Differential Revision: D9024330
fbshipit-source-id: e0b8295d2dc6ebe2963383ded5af799ad17164ba
Summary:
Pull Request resolved: https://github.com/facebookresearch/weakly-supervised-action-detection/pull/13
Pull Request resolved: https://github.com/pytorch/translate/pull/166
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9125
Closes https://github.com/pytorch/pytorch/pull/9125
Use inheritance for polymorphism, and remove template parameter
This is to change the templating in call sites, the core implementations will change later
Before Caffe2 Tensor class was compile-time fixed to bind to a particular device/context. With this change, we're making it a runtime property (stored inside the tensor), but preserve the same semantics. For example, one has to specify device type in order to create a Tensor - there are no uninitialized tensors. More specifically the changes are:
1. We added an extra argument *DeviceType* to most of the constructors of the tensor, e.g. (Tensor(DeviceType type)),
2. Semantics of constructor Tensor(const Tensor<SrcContext>& src, ContextForCopy* context); is changed, in this constructor, the second context is passed in to enable us to call the templated Copy function, it could be in a different context as source and target previously, now we'll enforce that the context should have same device type as src, if it is provided.
3. To preserve 'get-or-construct' semantics of Blob, we added specialized getter Blob::GetMutableTensor that verifies both that Blob contains a Tensor and that it's of a correct type
4. Specifically, Tensor type is not default-constructible any more (as we don't have unknown device tensors) and thus some of the code handling STL containers needs to change
Note: Some changes are postponed just to keep this diff a bit smaller. Please see `TODO`s.
Reviewed By: xw285cornell
Differential Revision: D8121878
fbshipit-source-id: 4a5e9a677ba4ac82095df959851a054c81eccf81
Summary:
This reverts commit d286264fccc72bf90a2fcd7da533ecca23ce557e
bypass-lint
An infra SEV is better than not reverting this diff.
If you copy this password, see you in SEV Review!
cause_a_sev_many_files
Differential Revision: D6817719
fbshipit-source-id: 8fe0ad7aba75caaa4c3cac5e0a804ab957a1b836
Summary:
Basically, this should make windows {static_lib, shared_lib} * {static_runtime, shared_runtime} * {cpu, gpu} work. A few highlights:
(1) Updated newest protobuf.
(2) use protoc dllexport command to ensure proper symbol export.
(3) various code updates to make sure that C2 symbols are properly shown
(4) cmake file changes to make build proper
(5) option to choose static runtime and shared runtime similar to protobuf
(6) revert to visual studio 2015 as current cuda and msvc 2017 do not play well together.
Closes https://github.com/caffe2/caffe2/pull/1793
Reviewed By: dzhulgakov
Differential Revision: D6817719
Pulled By: Yangqing
fbshipit-source-id: d286264fccc72bf90a2fcd7da533ecca23ce557e
Summary:
During the team meeting today Dima and Alex mentioned that the current lambda
function causes slowdown in performance when a large number of alloc and
dealloc happen. My observation is that most of the Delete are actually direct
Delete() function pointers, so I gave it a shot to see if we can reduce
the overhead.
RawAllocDealloc is much fast already, and we observe another 5ns reduction
(12.5%). For TensorAllocDealloc of 32x32 tensors, we are observing 57ns saving
(26%). This is measured on Xeon(R) CPU E5-2660.
Also cleaned up the function interfaces of ShareExternalPointer so we have 2
functions only.
Reviewed By: salexspb, dzhulgakov
Differential Revision: D5801013
fbshipit-source-id: 7068207a43400fa3902bbb3689b3c729e839456c
