[AArch64] Initial Ampere1B scheduling model (llvm#81341)

The Ampere1B core is enabled with a new scheduling/pipeline model, as it
provides significant updates over the Ampere1 core; it reduces latencies
on many instructions, has some micro-ops reassigned between the XY and X
units, and provides modelling for the instructions added since Ampere1
and Ampere1A.

As this is the first model implementing the CSSC instructions, we update
the UnsupportedFeatures on all other models (that have CompleteModel
set).

Testcases are added under llvm-mca: these showed the FullFP16 feature
missing, so we are adding it in as part of this commit.

This *adds tests and additional fixes* compared to the reverted llvm#81338.

(cherry picked from commit dd1897c)

Author: ptomsich

llvm/lib/Target/AArch64/AArch64.td

@@ -837,6 +837,7 @@ include "AArch64SchedA64FX.td"
 include "AArch64SchedThunderX3T110.td"
 include "AArch64SchedTSV110.td"
 include "AArch64SchedAmpere1.td"
+include "AArch64SchedAmpere1B.td"
 include "AArch64SchedNeoverseN1.td"
 include "AArch64SchedNeoverseN2.td"
 include "AArch64SchedNeoverseV1.td"
@@ -1551,7 +1552,7 @@ def ProcessorFeatures {
                                      FeatureMTE, FeatureSSBS, FeatureRandGen,
                                      FeatureSB, FeatureSM4, FeatureSHA2,
                                      FeatureSHA3, FeatureAES, FeatureCSSC,
-                                     FeatureWFxT];
+                                     FeatureWFxT, FeatureFullFP16];
 
   // ETE and TRBE are future architecture extensions. We temporarily enable them
   // by default for users targeting generic AArch64. The extensions do not
@@ -1719,7 +1720,7 @@ def : ProcessorModel<"ampere1", Ampere1Model, ProcessorFeatures.Ampere1,
 def : ProcessorModel<"ampere1a", Ampere1Model, ProcessorFeatures.Ampere1A,
                      [TuneAmpere1A]>;
 
-def : ProcessorModel<"ampere1b", Ampere1Model, ProcessorFeatures.Ampere1B,
+def : ProcessorModel<"ampere1b", Ampere1BModel, ProcessorFeatures.Ampere1B,
                      [TuneAmpere1B]>;
 
 //===----------------------------------------------------------------------===//

llvm/lib/Target/AArch64/AArch64SchedA53.td

@@ -29,7 +29,7 @@ def CortexA53Model : SchedMachineModel {
   list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
                                                     PAUnsupported.F,
                                                     SMEUnsupported.F,
-                                                    [HasMTE]);
+                                                    [HasMTE, HasCSSC]);
 }
 
 

llvm/lib/Target/AArch64/AArch64SchedA57.td

@@ -34,7 +34,7 @@ def CortexA57Model : SchedMachineModel {
   list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
                                                     PAUnsupported.F,
                                                     SMEUnsupported.F,
-                                                    [HasMTE]);
+                                                    [HasMTE, HasCSSC]);
 }
 
 //===----------------------------------------------------------------------===//

llvm/lib/Target/AArch64/AArch64SchedA64FX.td

@@ -22,7 +22,8 @@ def A64FXModel : SchedMachineModel {
 
   list<Predicate> UnsupportedFeatures = !listconcat(SMEUnsupported.F, SVEUnsupported.F,
                                                     [HasMTE, HasMatMulInt8, HasBF16,
-                                                    HasPAuth, HasPAuthLR, HasCPA]);
+                                                    HasPAuth, HasPAuthLR, HasCPA,
+                                                    HasCSSC]);
   let FullInstRWOverlapCheck = 0;
 }