Fixes #6130.

Signed-Off By: Vivek Khandelwal <[email protected]>

This commit adds mapping from `onnx.pad` op to `torch.pad` op. Currently
it does not support `a...

This adds initial support for Dedup to handle deduping classes and
objects. For the most part, ...

The logic here is very similar to the conversion for AdaptiveAvgPool1d
#2661 with a few modific...

Signed-Off By: Vivek Khandelwal <[email protected]>

convolution with [time,batch,channel] ordering, as opposed to the
default [batch, channel, time...

https://github.com/nod-ai/SHARK-Turbine/issues/312

Set PyTorch and TorchVision version to nightly release 2024-01-22.

Signed-Off By: Vivek Khand...

Signed-off-by: Gaurav Shukla <[email protected]>

Fix the build after llvm-project 8f90e6937a (e.g.
https://green.lab.llvm.org/green/job/coverage...

Clear 'dutModuleNames' and 'dutPrefix' along with the other members before running the pass.

As more than 400 tests are currently failing for the Sparc target, it
makes little sense to tes...

Fixes https://github.com/llvm/torch-mlir/issues/2764

In the case of OPT, there are ConstantO...

https://github.com/nod-ai/SHARK-Turbine/issues/331

Currently transposed convolution is not handled correctly by
`TorchToTosa`. This PR allows tran...

When inlining and flattening FIRRTL instances, create `dbg.scope`
operations to track informati...

Ignore these flags as they are currently not supported by flang.
Also re-enable pr43808.f90 tes...

FileCheck line assumed that repo and commitHash were filled in, which
they wouldn't be if GitPyt...

Avoids introducing implicit dependencies on header files which may or
may not be generated. (GPU...

Introduced in 704cfdaf0893fa4078ab744a915a56367282dcaa of @wu-s-john

g++ compiler error:

...

A lot of this functionality was replaced by the ESI runtime.

Users can either explicitly specify metadata or it can be automatically generated.

[https://github.com/nod-ai/SHARK-Turbine/issues/328](url)

---------

Co-authored-by: Dave L...

Overly specific docs can get stale easily. It looks like
https://llvm.github.io/torch-mlir/pack...

Oops... didn't run these tests!

Xilinx Runtime Shell (XRT) support for exposing the MMIO header and
manifest over MMIO. XRT is ...

Probe<Integer> shouldn't complain about nested "reference" types.

This is a re-write of comb loop detection pass. It simplifies the pass to use DFS
over a reach...

* [Comb] Handle type aliases in `comb.concat`

* [Comb] Add regression test (#5772)

* [Comb...

This commit adds support for gather op in the onnx pipeline.
https://github.com/nod-ai/SHARK-Tu...

Added verification logic to the abstract_interpreter_lib_gen.py

Also made some unit tests

...

The tests is not catching the intended semantic errors and will
stop failing when the following ...

Closes nod-ai/SHARK-Turbine#349

https://github.com/llvm/llvm-project/pull/74676 changes some predefined
target OS macros on Appl...

In f377b27ba0ab8fe69a26e13b73101003ad30c1de a bunch more tests were
added and one of those is fa...

This fixes O(N^2) compile time regression in OrOp(and other logical operations) canonicalizers. ...

Adds a MMIO service implementation for CosimBSP. Doesn't actually fulfill any service requests, ...

Fix warning about holding on to MLIR ops. Service generator instances
get held through a C++/Py...

LowerSignatures creates anonymous bound wires as a place holder but these didn't get proper name...

We can make the per-tensor version of the operation to the dequantize
operation via marking wit...

We can map the per_tensor case to the `torch.aten.quantize_per_linear`
operation. In this case ...

This PR add torch-to-tosa lowering support for AtenLinalgVectorNormOp

e2e test:
python -m e2...

Turns out the LLDB builder class defaults to `jobs="%(jobs)s"`
which expects every worker to hav...

Add support for the MMIO ESI service to PyCDE. Most implementations of this service will embed t...

Enable 'ccache' cached builds.

Changed 'write' to 'req' on the CIRCT side without updating the PyCDE
side. Fixed.

Helps improve debuggablity of the design.

This patch makes changes required in litsupport/* to support running
llvm testsuite on windows ...

Since ESI hardware embeds the manifest, lower the zlib-compressed version of it to a module to b...

Currently, can only request a single 32-bit register. In the future,
we'll add the ability to r...

This reverts commit 34489a17f06df6af09219fd5527c16fbcba556d6.

Self-hosted runners were disabled in our repo, so none of our builds are
being picked up. Going...

If the simulation attempts to send more responses than there are
outstanding requests, log an er...

The 'esi-cosim' script starts a simulation, waits for it to start, then
executes the 'inner' co...