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

Option becomes: -instruction-tables=`<level>`
 
The choice of `<level>` controls number of printed information.
`<level>` may be `none` (default), `normal`, `full`.
Note: If the option is used without `<label>`, default is `normal`
(legacy).

When `<level>` is `full`, additional information are:
- `<Bypass Latency>`: Latency when a bypass is implemented between
operands
  in pipelines (see SchedReadAdvance).
  - `<LLVM Opcode Name>`: mnemonic plus operands identifier.
  - `<Resources units>`: Used resources associated with LLVM Opcode.
- `<instruction comment>`: reports comment if any from source assembly.

Level `full` can be used to better check scheduling info when TableGen
is modified.
LLVM Opcode name help to find right instruction regexp to fix TableGen
Scheduling Info.

-instruction-tables=full option is validated on
AArch64/Neoverse/V1-sve-instructions.s

Follow up of MR #126703

---------

Co-authored-by: Julien Villette <julien.villette@sipearl.com>

Author: jvillette38

llvm/docs/CommandGuide/llvm-mca.rst

@@ -197,14 +197,32 @@ option specifies "``-``", then the output will also be sent to standard output.
 
   Enable all the view.
 
-.. option:: -instruction-tables
+.. option:: -instruction-tables=<level>
 
   Prints resource pressure information based on the static information
   available from the processor model. This differs from the resource pressure
   view because it doesn't require that the code is simulated. It instead prints
   the theoretical uniform distribution of resource pressure for every
   instruction in sequence.
 
+  The choice of `<level>` controls number of printed information.
+  `<level>` may be `none` (default), `normal`, `full`.
+  Note: If the option is used without `<label>`, default is `normal` (legacy).
+
+  When `<level>` is `full`, additional information are:
+  - `<Bypass Latency>`: Latency when a bypass is implemented between operands
+  in pipelines (see SchedReadAdvance).
+  - `<LLVM Opcode Name>`: mnemonic plus operands identifier.
+  - `<Resources units>`: Used resources associated with LLVM Opcode.
+  - `<instruction comment>`: reports comment if any from source assembly.
+
+  `<Resources units>` syntax can be:
+  - <Resource Name>: ReleaseAtCycle is 1.
+  - <Resource Name>[<ReleaseAtCycle>]: ReleaseAtCycle is greater than 1
+  and AcquireAtCycle is 0.
+  - <Resource Name>[<AcquireAtCycle>,<ReleaseAtCycle>]: ReleaseAtCycle
+  is greater than 1 and AcquireAtCycle is greater than 0.
+
 .. option:: -bottleneck-analysis
 
   Print information about bottlenecks that affect the throughput. This analysis

llvm/include/llvm/MC/MCSchedule.h

@@ -402,6 +402,10 @@ struct MCSchedModel {
   static unsigned getForwardingDelayCycles(ArrayRef<MCReadAdvanceEntry> Entries,
                                            unsigned WriteResourceIdx = 0);
 
+  /// Returns the bypass delay cycle for the maximum latency write cycle
+  static unsigned getBypassDelayCycles(const MCSubtargetInfo &STI,
+                                       const MCSchedClassDesc &SCDesc);
+
   /// Returns the default initialized model.
   static const MCSchedModel Default;
 };

llvm/lib/MC/MCSchedule.cpp

@@ -177,3 +177,37 @@ MCSchedModel::getForwardingDelayCycles(ArrayRef<MCReadAdvanceEntry> Entries,
 
   return std::abs(DelayCycles);
 }
+
+unsigned MCSchedModel::getBypassDelayCycles(const MCSubtargetInfo &STI,
+                                            const MCSchedClassDesc &SCDesc) {
+
+  ArrayRef<MCReadAdvanceEntry> Entries = STI.getReadAdvanceEntries(SCDesc);
+  if (Entries.empty())
+    return 0;
+
+  unsigned MaxLatency = 0;
+  unsigned WriteResourceID = 0;
+  unsigned DefEnd = SCDesc.NumWriteLatencyEntries;
+
+  for (unsigned DefIdx = 0; DefIdx != DefEnd; ++DefIdx) {
+    // Lookup the definition's write latency in SubtargetInfo.
+    const MCWriteLatencyEntry *WLEntry =
+        STI.getWriteLatencyEntry(&SCDesc, DefIdx);
+    unsigned Cycles = 0;
+    // If latency is Invalid (<0), consider 0 cycle latency
+    if (WLEntry->Cycles > 0)
+      Cycles = (unsigned)WLEntry->Cycles;
+    if (Cycles > MaxLatency) {
+      MaxLatency = Cycles;
+      WriteResourceID = WLEntry->WriteResourceID;
+    }
+  }
+
+  for (const MCReadAdvanceEntry &E : Entries) {
+    if (E.WriteResourceID == WriteResourceID)
+      return E.Cycles;
+  }
+
+  // Unable to find WriteResourceID in MCReadAdvanceEntry Entries
+  return 0;
+}