Closed hunhoffe closed 2 weeks ago
It should now be possible to also replicate the failure in the minimal-matrix-scalar-add
branch
https://github.com/Xilinx/mlir-air/pull/637 should enable the test now. There was an error in the logic for generating symbolic linkage between AIRRt dma ops and aie.device.
I believe this is fixed in the mentioned PR, so closing this issue!
From branch
debugging_matrix_scalar_add
, I am working on getting my examplemulti_core_dma
working (this file). The single core version works in this branch, but when I increase the herd size from 1x1 to 2x2, the example does not work any more.To be specific, to replicate run:
When I inspect
programming_examples/matrix_scalar_add/multi_core_dma/build/air_project/npu.air.mlir
, I notice that it looks like all of the data is only going to one core instead of being distributed to all of the cores.