Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/50191
DISC is a e2e flow, including both compiler side and runtime side. For
runtime side, we have different targeting environments (e.g. tensorflow,
pytorch, or sometimes even a standalone binary). In order to simplify
the design of the compiler side, we design a Runtime Abstraction Layer
(RAL) to sperate the compiler side and runtime side. Thus the compiler
side only need to target RAL itself and it is the responsibility of RAL
to handle the differences between different targeting environments.
One of the most important functions of RAL is to manage stateful
resources. To this end, it provides a context object, and hides all
stateful operations behind this context, thus the compiler side itself
doesn't need to care about the resource initialization. For example, a
kernel must be loaded before it can be launched on GPU. However, the
loading operation should only be taken once during the whole lifetime of
the context in order to achieve the best performance. Based on the
initialization-free interfaces provided by RAL, compiler side can focus
on its core optimization logic and lets the RAL to manage the resource
status.
The context mentioned above is passed as a parameter to the entry
function and all RAL APIs should always use the context as their first
argument. This CR also provides a pass to help to ensure this property.
The pass rewrites the entry function to make sure their first argument
is the context. For entry function, the pass also rewrites its inputs
and outputs. To be concrete, all the original inputs and outputs of the
entry function are received from and sent to RAL through a sequence of
RAL API calls correspondingly. The motivation behind this is to hide the
implementation details of I/Os. This design may also potentially enable
partial execution of the compiled module when some of the inputs are
ready.
Copybara import of the project:
--
c4f20a89aed71181e75bcc5265723b88bde23240 by Wenyi Zhao <reyizero@gmail.com>:
[MLIR][DISC] Add RAL (Runtime abstraction layer) Dialect
DISC is a e2e flow, including both compiler side and runtime side. For
runtime side, we have different targeting environments (e.g. tensorflow,
pytorch, or sometimes even a standalone binary). In order to simplify
the design of the compiler side, we design a Runtime Abstraction Layer
(RAL) to sperate the compiler side and runtime side. Thus the compiler
side only need to target RAL itself and it is the responsibility of RAL
to handle the differences between different targeting environments.
One of the most important functions of RAL is to manage stateful
resources. To this end, it provides a context object, and hides all
stateful operations behind this context, thus the compiler side itself
doesn't need to care about the resource initialization. For example, a
kernel must be loaded before it can be launched on GPU. However, the
loading operation should only be taken once during the whole lifetime of
the context in order to achieve the best performance. Based on the
initialization-free interfaces provided by RAL, compiler side can focus
on its core optimization logic and lets the RAL to manage the resource
status.
The context mentioned above is passed as a parameter to the entry
function and all RAL APIs should always use the context as their first
argument. This CR also provides a pass to help to ensure this property.
The pass rewrites the entry function to make sure their first argument
is the context. For entry function, the pass also rewrites its inputs
and outputs. To be concrete, all the original inputs and outputs of the
entry function are received from and sent to RAL through a sequence of
RAL API calls correspondingly. The motivation behind this is to hide the
implementation details of I/Os. This design may also potentially enable
partial execution of the compiled module when some of the inputs are
ready.
--
1991d4f80ab6087943956e1c0fec4940a22ab08d by Wenyi Zhao <reyizero@gmail.com>:
fix
PiperOrigin-RevId: 379317586
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/49970
1, add hlo-to-lhlo support for DynamicReshape and DynamicBroadcastInDim
2, add a flag `convert-to-lmhlo-only` to seperate following two case:
- hlo-to-lhlo only. Simply lowers all mhlo ops to their lmhlo
counterparts, do not apply any optimization (e.g. elide any
buffer copy). Buffer optimization is not easy in dynamic
shape world especially when involving control flow, thus we
leave this to another dedicated pass.
- hlo-to-lhlo-or-memref-directly. Lowers some metadata-only mhlo
ops (e.g. reshape) to memref dialect directly and Lowers others
to their lmhlo counterparts.
Copybara import of the project:
--
562bd65a368f6194405c4ae6900e3b4388a5ec03 by Wenyi Zhao <reyizero@gmail.com>:
[MLIR][DISC] bufferize DynamicReshape and DynamicBroadcastInDim
1, add hlo-to-lhlo support for DynamicReshape and DynamicBroadcastInDim
2, add a flag `convert-to-lmhlo-only` to seperate following two case:
- hlo-to-lhlo only. Simply lowers all mhlo ops to their lmhlo
counterparts, do not apply any optimization (e.g. elide any
buffer copy). Buffer optimization is not easy in dynamic
shape world especially when involving control flow, thus we
leave this to another dedicated pass.
- hlo-to-lhlo-or-memref-directly. Lowers some metadata-only mhlo
ops (e.g. reshape) to memref dialect directly and Lowers others
to their lmhlo counterparts.
PiperOrigin-RevId: 377603395
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/49598
This PR implements logic for lowering memref.tensor_load ops that are
inserted during `mhlo-legalize-to-lmhlo`
Copybara import of the project:
--
80eb377af4e02182e1aecc943a41ca5d7d1c2100 by Wenyi Zhao <reyizero@gmail.com>:
[MLIR][DISC] legalize tensor_load inserted during hlo-to-lhlo conversion
This PR implements logic for lowering memref.tensor_load ops that are
inserted during `mhlo-legalize-to-lmhlo`.
--
ac452fe3dcd591211cd5c59be9189fe2f7153b41 by Wenyi Zhao <reyizero@gmail.com>:
minor fix
--
6b36017f8632a06adbc3e05a62975fa641d0260f by Wenyi Zhao <reyizero@gmail.com>:
minor refine
--
846005cc76d0033112e47825c2e9a97790b6925f by Wenyi Zhao <reyizero@gmail.com>:
minor fix
--
f6a4becaa287d5ca323b2d152a4d0ae053730fd9 by Wenyi Zhao <reyizero@gmail.com>:
fix
--
5555749f60f7fce8f57962860ef65efccf0362ba by Wenyi Zhao <reyizero@gmail.com>:
fix
--
8873b9b6d9315c1199ca9f7c133ecf377ecd2fa6 by Wenyi Zhao <reyizero@gmail.com>:
fix
PiperOrigin-RevId: 376942547
The maximum supported target rank of 5 is sufficient for all operations but
`select`. Make the maximum target rank configurable in the rank specialization.
This reduces the number of generated kernels for operations that don't require
it.
PiperOrigin-RevId: 376822496
Rename `gentbl` to `gentbl_cc_library` to make it clearer which kind of rule is
ultimately used.
Update `gentbl_*` macros to take `tbl_outs` options as a list rather a
whitespace-separated string and remove the related string handling.
PiperOrigin-RevId: 373406352
Add a pass to cluster unranked C/HLO operations in one
`chlo.rank_specialization_cluster` op. The C/HLO operations are moved to the
body of the operation. Later passes can use this to rank-specialize all these
operations together.
PiperOrigin-RevId: 373336725
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/48667
Added RegionBranchOpInterfaces to lmhlo operations that use regions.
This is needed, since the bufferization features in MLIR have to reason about the control flow within these operations.
Copybara import of the project:
--
572fd7d850a46630b812da84e9094280f89f259e by Julian Gross <julian.gross@dfki.de>:
Added RegionBranchOpInterfaces to lmhlo operations.
PiperOrigin-RevId: 372070825
These targets are now identical as all registration is explicit.
Temporarily leaving the old target as a (deprecated) alias while
changes propagate.
PiperOrigin-RevId: 366513211
- Extract verification of source target pairs attached to collective permute into a common
helper function and use that to verify both MHLO and LMHLO variants.
- Change MlirGpuTestBase::ParseMlirModule to allow returning back a failure, and use
that to update the mlir_gpu_compile_test to check the new behavior.
PiperOrigin-RevId: 362156962
For now, the pass only reifies the required shape computations. Moving
broadcasts will follow to allow for fusion across them.
PiperOrigin-RevId: 362033715
- XLA:HLO -> LMHLO conversion drops all token arguments and return values, however
custom calls that users write still expect to get buffer pointers for these token types.
- To be able to support this, add an optional call target argument mapping attribute to
LMHLO custom calls. When this attribute is present, it indicates the number of
arguments and returns that the custom call expects and also indicates which LMHLO
arg() or output() maps to which arg or result number of the custom call.
PiperOrigin-RevId: 358826664
This is the preferred name for the Bazel repository when included from
another project.
Note: These hardcoded "external/" includes are a horrible hack that we
can hopefully get rid of soon with more robust Bazel tablegen rules.
PiperOrigin-RevId: 350810768
For floating point operations, this uses std.pow.
For integer operations, this lowers to a loop.
This adds a dependency on scf.
PiperOrigin-RevId: 348537232
Chris Jones
Wenyi Zhao
A. Unique TensorFlower
Mehdi Amini
Jacques Pienaar
Rahul Joshi
Alex Zinenko
Itai Zukerman
dfki-jugr
Geoffrey Martin-Noble
Russell Power
Adrian Kuegel
Stephan Herhut
Alexander Belyaev
Tres Popp
Phoenix Meadowlark