Andrew Waterman
Andrew Waterman
In #2333, we introduced warnings when the implicit clock at Mem declaration time doesn't match the implicit clock at Mem port generation time. These warnings shouldn't be emitted for combinational-read...
This isn't yet complete, and in particular the inability to directly manipulate the `rnmie` bit may be a deficiency. (As it stands, it's impossible to perform the standard pattern of...
I'm copying this from @jrahmeh's issue here: https://github.com/riscv/riscv-v-spec/issues/765 In section A.7 of the unprivileged ISA (Document Version 20191214-draft), both examples (Figures A.20 and A21) seem to be incorrect. In A.20,...
It's sometimes desirable to express that a load or store has poor temporal locality, so that the microarchitecture can optimize its use of the memory hierarchy accordingly. Temporal locality hints...
Don't merge yet; it's still early days for this extension.
See https://github.com/riscv/riscv-isa-manual/tree/wfmi
The current logic for updating the `maybe_full` flag in Queue is `when(do_enq =/= do_deq) { maybe_full := do_enq }` (which, incidentally, is the same as `maybe_full := majority(maybe_full, do_enq, !do_deq)`,...
As currently written, the definition of the `stoptime` field implies that `time` and `mtime` are handled differently: that `stoptime` affects the `time` CSR always, but only affects `mtime` when all...
The isa_extension_t enum already has 44 extensions. In not too long, the enum will grow in size to 65, when it will collide with the 'A' extension. Fix that preemptively...