mlir

Right now the reducer considers an input to be interesting if the test exits with a non-zero exit code. This technically makes sense because you are likely trying to isolate a crash.

In practice however, it's far more common to run a lot of commands in a script to check if the current reduction exhibits interesting behaviour, for example by running the input through two unrelated chains of tool

The existing code assumes the result tensor type is the same as input type for a few aten ops like log, exp, erf. See https://github.com/llvm/torch-mlir/blob/486f95e84f587d020ba789b071b12f890510f1a1/lib/Dialect/Torch/Transforms/RefineTypes.cpp#L221-L235
This incorrect. The result tensor of these ops should always have the default dtype rather than the same as the input type. E2E tests fo

@honglh added optimized kernels for ARM32 in #432. It would be great if we could add support for bitpacked activations to them to match the AArch64 optimized bgemm kernels.

In test/create-cores/test_dma1.mlir, -aie-lower-memcpy convert

  AIE.memcpy @token0(1, 2) (%t11 : <%buf0, 0, 256>, %t22 : <%buf1, 0, 256>) : (memref<256xi32>, memref<256xi32>)
  AIE.memcpy @token1(1, 2) (%t11 : <%buf0, 0, 256>, %t33 : <%buf2, 0, 256>) : (memref<256xi32>, memref<256xi32>)

to (only shows the %t11 side)

  %2 = AIE.mem(%0) {
    %15 = AIE.dmaStart(MM2S0, ^bb1

-Let's make it easier for users to browse and find models in SHARK, by putting up hyperlink in the text part of the model's name (i.e BERT, Albert, Alexnet, etc) which links to their respective tank model directory (e.g bert link, albert link, [alexne