This is because SSR write data is hardwired to the bidirectional data FIFO output. Therefore, on reads, the write data bits may change irrespective of when a read request is pending. This instability is benign, but causes the payload-wide assertion to fail.
This PR, together with https://github.com/pulp-platform/common_cells/pull/219, fixes this issue by masking stability assertion on the write data and mask inside stream_xbar and stream_omega_net and then conditionally asserting write data and mask stability on reads and atomics in snitch_tcdm_interconnect.
A more general discussion is maybe in order on whether SSRs should invest additional logic to instead mask write data on reads, but we should first fix the bug and then ponder design improvements.
https://github.com/pulp-platform/common_cells/pull/200, recently included by a dependency update, may trigger false-positive TCDM stability assertion errors in some cases when using SSRs.
This is because SSR write data is hardwired to the bidirectional data FIFO output. Therefore, on reads, the write data bits may change irrespective of when a read request is pending. This instability is benign, but causes the payload-wide assertion to fail.
This PR, together with https://github.com/pulp-platform/common_cells/pull/219, fixes this issue by masking stability assertion on the write data and mask inside
stream_xbarandstream_omega_netand then conditionally asserting write data and mask stability on reads and atomics insnitch_tcdm_interconnect.A more general discussion is maybe in order on whether SSRs should invest additional logic to instead mask write data on reads, but we should first fix the bug and then ponder design improvements.
TODO:
common_cellsrelease.common_cellsdependency.