[LLVM][ARM][CodeGen]Define branch instruction alignment for m85 and m7 (#109647)

Branch instruction alignments were not defined for cortex-m85 and
cortex-m7 which misses an optimisation opportunity. With this patch we
see performance improvements as high as 5% on some benchmarks with most
around 1%.

Author: nasherm

llvm/lib/Target/ARM/ARMFeatures.td

@@ -375,6 +375,9 @@ def FeaturePref32BitThumb : SubtargetFeature<"32bit", "Prefers32BitThumb", "true
 def FeaturePrefLoopAlign32 : SubtargetFeature<"loop-align", "PrefLoopLogAlignment","2",
                                               "Prefer 32-bit alignment for loops">;
 
+def FeaturePrefLoopAlign64 : SubtargetFeature<"loop-align-64", "PrefLoopLogAlignment","3",
+                                              "Prefer 64-bit alignment for loops">;
+
 def FeatureMVEVectorCostFactor1 : SubtargetFeature<"mve1beat", "MVEVectorCostFactor", "4",
                         "Model MVE instructions as a 1 beat per tick architecture">;
 

llvm/lib/Target/ARM/ARMProcessors.td

@@ -344,6 +344,7 @@ def : ProcessorModel<"cortex-m4", CortexM4Model,        [ARMv7em,
 def : ProcessorModel<"cortex-m7", CortexM7Model,        [ARMv7em,
                                                          ProcM7,
                                                          FeatureFPARMv8_D16,
+                                                         FeaturePrefLoopAlign64,
                                                          FeatureUseMIPipeliner,
                                                          FeatureUseMISched]>;
 
@@ -385,6 +386,7 @@ def : ProcessorModel<"cortex-m85", CortexM85Model,      [ARMv81mMainline,
                                                          FeatureDSP,
                                                          FeatureFPARMv8_D16,
                                                          FeaturePACBTI,
+                                                         FeaturePrefLoopAlign64,
                                                          FeatureUseMISched,
                                                          HasMVEFloatOps]>;
 

llvm/test/CodeGen/ARM/preferred-function-alignment.ll

@@ -1,14 +1,15 @@
-; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m85 < %s | FileCheck --check-prefixes=CHECK,ALIGN-16,ALIGN-CS-16 %s
+; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m85 < %s | FileCheck --check-prefixes=CHECK,ALIGN-64,ALIGN-CS-16 %s
 ; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m23 < %s | FileCheck --check-prefixes=CHECK,ALIGN-16,ALIGN-CS-16 %s
 
 ; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-a5 < %s  | FileCheck --check-prefixes=CHECK,ALIGN-32,ALIGN-CS-32 %s
 ; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m33 < %s | FileCheck --check-prefixes=CHECK,ALIGN-32,ALIGN-CS-16 %s
 ; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m55 < %s | FileCheck --check-prefixes=CHECK,ALIGN-32,ALIGN-CS-16 %s
-
+; RUN: llc -mtriple=arm-none-eabi -mcpu=cortex-m7 < %s | FileCheck --check-prefixes=CHECK,ALIGN-64,ALIGN-CS-16 %s
 
 ; CHECK-LABEL: test
 ; ALIGN-16: .p2align 1
 ; ALIGN-32: .p2align 2
+; ALIGN-64: .p2align 3
 
 define void @test() {
   ret void