mlir

Currently when you run firtool --verbose-pass-executions, it doesn't print any information when it's in the parser. This can be confusing to a user especially for large designs where, currently, >50% of the time is spent in the parser.

Modify --verbose-pass-executions to print information about parsing.

Sample output:

# firtool Foo.fir -verbose-pass-executions -mlir-timing
[fir

Testing needed for Scalar ops where type promotion is required; cases like f32+f64.

@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