[TableGen] Emit more variant transitions

`llvm-mca` relies on the predicates to be based on `MCSchedPredicate` in order
to resolve the scheduling for variant instructions.  Otherwise, it aborts
the building of the instruction model early.

However, the scheduling model emitter in `TableGen` gives up too soon, unless
all processors use only such predicates.

In order to allow more processors to be used with `llvm-mca`, this patch
emits scheduling transitions if any processor uses these predicates.  The
transition emitted for the processors using legacy predicates is the one
specified with `NoSchedPred`, which is based on `MCSchedPredicate`.

Preferably, `llvm-mca` should instead assume a reasonable default when a
variant transition is not based on `MCSchedPredicate` for a given processor.
This issue should be revisited in the future.

Differential revision: https://reviews.llvm.org/D54648

llvm-svn: 347504

llvm/include/llvm/Target/TargetSchedule.td

@@ -373,6 +373,10 @@ class SchedPredicate<code pred> : SchedPredicateBase {
   SchedMachineModel SchedModel = ?;
   code Predicate = pred;
 }
+
+// Define a predicate to be typically used as the default case in a
+// SchedVariant.  It the SchedVariant does not use any other predicate based on
+// MCSchedPredicate, this is the default scheduling case used by llvm-mca.
 def NoSchedPred : MCSchedPredicate<TruePred>;
 
 // Associate a predicate with a list of SchedReadWrites. By default,

llvm/test/tools/llvm-mca/AArch64/CortexA57/shifted-register.s

@@ -1,7 +1,25 @@
-# RUN: not llvm-mca -march=aarch64 -mcpu=cortex-a57 -resource-pressure=false < %s 2> %t
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
-# RUN: FileCheck --input-file %t %s
+# RUN: llvm-mca -march=aarch64 -mcpu=cortex-a57 -resource-pressure=false < %s | FileCheck %s
 
   add	x0, x1, x2, lsl #3
 
-# CHECK: error
+# CHECK:      Iterations:        100
-# CHECK-SAME: unable to resolve scheduling class for write variant.
+# CHECK-NEXT: Instructions:      100
+# CHECK-NEXT: Total Cycles:      53
+# CHECK-NEXT: Total uOps:        100
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    1.89
+# CHECK-NEXT: IPC:               1.89
+# CHECK-NEXT: Block RThroughput: 0.5
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      1     0.50                        add	x0, x1, x2, lsl #3

llvm/test/tools/llvm-mca/AArch64/Cyclone/register-offset.s

@@ -1,9 +1,29 @@
-# RUN: not llvm-mca -march=aarch64 -mcpu=cyclone -resource-pressure=false < %s 2> %t
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
-# RUN: FileCheck --input-file %t %s
+# RUN: llvm-mca -march=aarch64 -mcpu=cyclone -resource-pressure=false < %s | FileCheck %s
 
   ldr	x7, [x1, #8]
   ldr	x6, [x1, x2]
   ldr	x4, [x1, x2, sxtx]
 
-# CHECK: error
+# CHECK:      Iterations:        100
-# CHECK-SAME: unable to resolve scheduling class for write variant.
+# CHECK-NEXT: Instructions:      300
+# CHECK-NEXT: Total Cycles:      156
+# CHECK-NEXT: Total uOps:        300
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    1.92
+# CHECK-NEXT: IPC:               1.92
+# CHECK-NEXT: Block RThroughput: 1.5
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     0.50    *                   ldr	x7, [x1, #8]
+# CHECK-NEXT:  1      4     0.50    *                   ldr	x6, [x1, x2]
+# CHECK-NEXT:  1      4     0.50    *                   ldr	x4, [x1, x2, sxtx]

llvm/test/tools/llvm-mca/ARM/unsupported-write-variant.s

@@ -1,4 +1,6 @@
 # RUN: not llvm-mca -march=arm -mcpu=swift -all-views=false 2>&1 < %s | FileCheck %s
+# D54648 results in this test to become valid.
+# XFAIL: *
 
 add r3, r1, r12, lsl #2
 

llvm/utils/TableGen/SubtargetEmitter.cpp

@@ -1504,9 +1504,9 @@ void collectVariantClasses(const CodeGenSchedModels &SchedModels,
       continue;
 
     if (OnlyExpandMCInstPredicates) {
-      // Ignore this variant scheduling class if transitions don't uses any
+      // Ignore this variant scheduling class no transitions use any meaningful
       // MCSchedPredicate definitions.
-      if (!all_of(SC.Transitions, [](const CodeGenSchedTransition &T) {
+      if (!any_of(SC.Transitions, [](const CodeGenSchedTransition &T) {
             return hasMCSchedPredicates(T);
           }))
         continue;
@@ -1560,6 +1560,7 @@ void SubtargetEmitter::emitSchedModelHelpersImpl(
     PE.setExpandForMC(OnlyExpandMCInstPredicates);
     for (unsigned PI : ProcIndices) {
       OS << "    ";
+
       // Emit a guard on the processor ID.
       if (PI != 0) {
         OS << (OnlyExpandMCInstPredicates
@@ -1573,11 +1574,23 @@ void SubtargetEmitter::emitSchedModelHelpersImpl(
       for (const CodeGenSchedTransition &T : SC.Transitions) {
         if (PI != 0 && !count(T.ProcIndices, PI))
           continue;
+
+        // Emit only transitions based on MCSchedPredicate, if it's the case.
+        // At least the transition specified by NoSchedPred is emitted,
+        // which becomes the default transition for those variants otherwise
+        // not based on MCSchedPredicate.
+        // FIXME: preferably, llvm-mca should instead assume a reasonable
+        // default when a variant transition is not based on MCSchedPredicate
+        // for a given processor.
+        if (OnlyExpandMCInstPredicates && !hasMCSchedPredicates(T))
+          continue;
+
         PE.setIndentLevel(3);
         emitPredicates(T, SchedModels.getSchedClass(T.ToClassIdx), PE, OS);
       }
 
       OS << "    }\n";
+
       if (PI == 0)
         break;
     }