mlir

Currently, Grand Central will output multiline YAML description strings as one line, e.g., "foo\nbar\baz". However, the LLVM YAML library has support for instead emitting this in "block scala" format: https://llvm.org/docs/YamlIO.html#block-scalars. Change FIRRTL's Grand Central pass to do block scalar output of description strings for better readability of the output YAML.

Once implemented,

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