pytorch/c10/core
Iurii Zdebskyi 5b9f55f33f Enable Add, sub, mul, and div on CPU for bfloat16 type. (#22851)
Summary:
Enable Add, sub, mul, and div on CPU for bfloat16 type.
Tested via unit tests.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22851

Differential Revision: D16256757

Pulled By: izdeby

fbshipit-source-id: 8b62f7581fc0ca0d2cff48ab40d877a9fcf70a5b
2019-08-08 12:34:25 -07:00
..
impl Fix deviceCount on FakeGuardImpl. (#18745) 2019-04-04 09:23:36 -07:00
Allocator.cpp unify c2 and TH allocator (#16892) 2019-02-12 21:16:34 -08:00
Allocator.h remove needless ## in REGISTER_ALLOCATOR definition. (#19261) 2019-04-18 22:44:09 -07:00
Backend.h refactor registerStoragePyTypeObject (#20467) 2019-05-14 18:22:33 -07:00
CopyBytes.cpp Remove TensorImpl -> context_base dependency (#14658) 2018-12-07 16:23:46 -08:00
CopyBytes.h Move files to/from c10/core and c10/util (#15316) 2019-01-10 16:22:22 -08:00
CPUAllocator.cpp Improve CPUAllocator OOM message (#20618) 2019-05-17 16:14:49 -07:00
CPUAllocator.h Fix spelling errors (#21665) 2019-06-13 15:21:55 -07:00
DefaultDtype.cpp Move TensorOptions, DefaultTensorOptions to c10 2018-12-06 15:59:04 -08:00
DefaultDtype.h Move TensorOptions, DefaultTensorOptions to c10 2018-12-06 15:59:04 -08:00
DefaultTensorOptions.h Move files to/from c10/core and c10/util (#15316) 2019-01-10 16:22:22 -08:00
Device.cpp Use Device instead of Backend in TensorIterator (#20690) 2019-05-24 12:14:08 -07:00
Device.h Use Device instead of Backend in TensorIterator (#20690) 2019-05-24 12:14:08 -07:00
DeviceGuard.h pin_memory malloc now uses existing context if available. (#22229) 2019-07-16 10:18:30 -07:00
DeviceType.cpp Add XLA / TPU device type, backend type and type id (#16763) 2019-02-05 12:56:44 -08:00
DeviceType.h move const defs of DeviceType to DeviceType.h (#19185) 2019-04-16 20:02:21 -07:00
Layout.h Add MKL-DNN Tensor (#17748) 2019-04-08 21:41:38 -07:00
MemoryFormat.h Adding memory_format to empty and empty_like operators (#20558) 2019-06-26 11:48:27 -07:00
QScheme.h Add set_quantizer_ for QTensor (#21852) 2019-06-18 19:50:12 -07:00
Scalar.cpp Move Scalar and ScalarType to c10/core 2018-11-27 12:59:36 -08:00
Scalar.h Rename AT_FORALL_SCALAR_TYPES_WITH_COMPLEX to AT_FORALL_SCALAR_TYPES_WITH_COMPLEX_AND_STUBS 2019-07-31 08:17:17 -07:00
ScalarType.h Enable Add, sub, mul, and div on CPU for bfloat16 type. (#22851) 2019-08-08 12:34:25 -07:00
Storage.cpp Move Storage and StorageImpl to c10 2018-11-27 12:59:48 -08:00
Storage.h Materialize a non-default device for C2 legacy storage. (#18605) 2019-04-11 13:50:41 -07:00
StorageImpl.cpp Move Storage and StorageImpl to c10 2018-11-27 12:59:48 -08:00
StorageImpl.h Implement reference counting for shared IPC CUDA tensors (#16854) 2019-03-25 10:24:38 -07:00
Stream.cpp Move files to/from c10/core and c10/util (#15316) 2019-01-10 16:22:22 -08:00
Stream.h Replace AT_CHECK with TORCH_CHECK [shard 8/10] 2019-05-15 08:05:56 -07:00
StreamGuard.h Move files to/from c10/core and c10/util (#15316) 2019-01-10 16:22:22 -08:00
TensorImpl.cpp Channels last stored in tensor (#23391) 2019-08-05 11:50:29 -07:00
TensorImpl.h Channels last stored in tensor (#23391) 2019-08-05 11:50:29 -07:00
TensorOptions.cpp Move files to/from c10/core and c10/util (#15316) 2019-01-10 16:22:22 -08:00
TensorOptions.h Enable assignment for QTensor in pytorch frontend (#19676) 2019-04-24 16:05:34 -07:00
TensorTypeId.cpp Better stringification of dispatch keys in error messages (#21809) 2019-06-19 11:44:24 -07:00
TensorTypeId.h Better stringification of dispatch keys in error messages (#21809) 2019-06-19 11:44:24 -07:00
TensorTypeIdRegistration.cpp Better stringification of dispatch keys in error messages (#21809) 2019-06-19 11:44:24 -07:00
TensorTypeIdRegistration.h Better stringification of dispatch keys in error messages (#21809) 2019-06-19 11:44:24 -07:00
thread_pool.cpp Fix init_thread calls in thread pool initialization (#20848) 2019-05-24 01:14:31 -07:00
thread_pool.h Native ATen/Parallel backend (#20087) 2019-05-28 01:40:54 -07:00
UndefinedTensorImpl.cpp Change is_variable() to check existence of AutogradMeta, and remove is_variable_ (#19139) 2019-04-11 14:03:33 -07:00
UndefinedTensorImpl.h Enforce same input tensor storage in VariableType functions (#16305) 2019-02-11 13:33:12 -08:00
WrapDimMinimal.h Followup to #17049: change more instances of RuntimeError to IndexError 2019-02-25 15:34:22 -08:00