[llvm] [MCA] Extend -instruction-tables option with verbosity levels (PR #130574)

[Min-Yih Hsu via llvm-commits]

================
@@ -141,6 +241,33 @@ void InstructionInfoView::collectData(
     IIVDEntry.mayLoad = MCDesc.mayLoad();
     IIVDEntry.mayStore = MCDesc.mayStore();
     IIVDEntry.hasUnmodeledSideEffects = MCDesc.hasUnmodeledSideEffects();
+
+    if (PrintFullInfo) {
+      // Get latency with bypass
+      IIVDEntry.Bypass =
+          IIVDEntry.Latency - MCSchedModel::getBypassDelayCycles(STI, SCDesc);
+      IIVDEntry.OpcodeName = MCII.getName(Inst.getOpcode());
+      raw_string_ostream TempStream(IIVDEntry.Resources);
+      const MCWriteProcResEntry *Index = STI.getWriteProcResBegin(&SCDesc);
+      const MCWriteProcResEntry *Last = STI.getWriteProcResEnd(&SCDesc);
+      auto Sep = "";
+      for (; Index != Last; ++Index) {
+        if (!Index->ReleaseAtCycle)
+          continue;
+        const MCProcResourceDesc *MCProc =
+            SM.getProcResource(Index->ProcResourceIdx);
+        if (Index->ReleaseAtCycle > 1) {
----------------
mshockwave wrote:

> Thanks for making the update here.
> 
> > https://github.com/llvm/llvm-project/blob/main/llvm/lib/MC/MCSchedule.cpp#L97 shows that AcquireAtCycle is not considered when computing throughput.
> 
> That might be a bug? @mshockwave what do you think?

Yeah I tried to fix it but that (accounting for AcquireAtCycle or the concept of ResourceSegment in general) turns out to be more complicated than I thought: we can't just use the smallest `NumUnit / (ReleaseAtCycle - AcquireAtCycle)` to calculate the (inverse) throughput

https://github.com/llvm/llvm-project/pull/130574