| cf04f92c340b6fb0207eb780959a12fa03356f77 |
|
14-Feb-2018 |
Sanjoy Das <sanjoy@google.com> |
Improve type safety around float constants
Instead of passing floating point constants to the vector support library as
compiler-side floats, pass them as APFloats instead. This reduces the duration
during which these constants are semantically represented as floats on the host
side and are subject to fast-math-like behavior. This is especially important
in cases where the exact bit representation of the floating point constant is
significant, but also makes progress towards ensuring that e.g. build XLA with
-ffast-math does not change the IR we generate.
PiperOrigin-RevId: 185611301
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| 465a45cd3b717908ecbae72b824c91f44c2cdce0 |
|
13-Feb-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Implement vectorized Log in LLVM IR
This was the last vectorized intrinsic for which we had to call into
C++ so also remove the associated machinery.
PiperOrigin-RevId: 185482962
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| 68a7f292b324e08fefd2c47dde444720db361f4d |
|
07-Feb-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Assert more thoroughly on preconditions in VectorSupportlibrary
No behavior change intended.
PiperOrigin-RevId: 184797003
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| 9b08301f474bb1175acf6ef77e6eb2b6552339ba |
|
07-Feb-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Add an LLVM IR implementation of Exp
This lets us avoid the usual set of issues that crop up when XLA generated code
has to call into C++.
PiperOrigin-RevId: 184793093
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| 5bfd3e3c9433492aa4aed97d2a8a6c9284bdd77e |
|
07-Feb-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Use VectorSupportLibrary for LLVM IR implementation of tanh
No behavioral change intended; this is only refactoring.
VectorSupportLibrary was added after the LLVM IR implementation of tanh so the
tanh implementation was not using VectorSupportLibrary.
The main impetus for this change is that I'm about to add LLVM IR
implementations of Exp and Log, and those are going to use VectorSupportLibrary.
I did not want to have an inconsistency between the tanh and exp, log.
PiperOrigin-RevId: 184774860
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| c7e7c84a699981a9d277bf95aa44cff4a625614f |
|
04-Jan-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Cleanups to VectorSupportLibrary, TargetMachineFeatures and DotOpEmitter
- Move VectorSupportLibrary to under service/cpu since it is specific to the
CPU backend.
- Use TargetMachineFeatures to infer the vector width in DotOpEmitter
- Move the kAvxVectorSize magic constant into TargetMachineFeatures
PiperOrigin-RevId: 180740693
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| e372c01ef212590394085fc241f7a8c387810132 |
|
03-Jan-2018 |
Sanjoy Das <sanjoy@google.com> |
Automated g4 rollback of changelist 180622078
PiperOrigin-RevId: 180628481
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|
| 5f8d582514de3f1dcf0c42ff2cb6675a53682026 |
|
03-Jan-2018 |
Sanjoy Das <sanjoy@google.com> |
[XLA:CPU] Cleanups to VectorSupportLibrary, TargetMachineFeatures and DotOpEmitter
- Move VectorSupportLibrary to under service/cpu since it is specific to the
CPU backend.
- Use TargetMachineFeatures to infer the vector width in DotOpEmitter
- Move the kAvxVectorSize magic constant into TargetMachineFeatures
PiperOrigin-RevId: 180622078
/external/tensorflow/tensorflow/compiler/xla/service/cpu/vector_support_library.cc
|