[AArch64] Disconnect FeatureUseScalarIncVL from FeatureSVE2.

FeatureUseScalarIncVL is a tuning feature, used to control whether addvl or
add+cnt is used. It was previously added as a dependency for FeatureSVE2, an
architecture feature but this can be seen as a layering violation. The main
disadvantage is that -use-scalar-inc-vl cannot be used without disabling sve2
and all dependant features.

This patch attempt to break that, enabling the feature if SVE2 or SME is
present and the use-scalar-inc-vl is not otherwise specified, but not requiring
a hard dependency between the two. (Unfortunately I had to check if the value
was present in the features string to check that).

It also inverts the meaning of the feature to DontUseScalarIncVL, so that the
default state is to use addvl, hopefully the more sensible default going
forward.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64Features.td

@@ -358,12 +358,9 @@ def FeatureTHE : ExtensionWithMArch<"the", "THE", "FEAT_THE",
 //  Armv9.0 Architecture Extensions
 //===----------------------------------------------------------------------===//
 
-def FeatureUseScalarIncVL : SubtargetFeature<"use-scalar-inc-vl",
-  "UseScalarIncVL", "true", "Prefer inc/dec over add+cnt">;
-
 def FeatureSVE2 : ExtensionWithMArch<"sve2", "SVE2", "FEAT_SVE2",
   "Enable Scalable Vector Extension 2 (SVE2) instructions",
-  [FeatureSVE, FeatureUseScalarIncVL]>;
+  [FeatureSVE]>;
 
 def FeatureSVE2AES : ExtensionWithMArch<"sve2-aes", "SVE2AES",
   "FEAT_SVE_AES, FEAT_SVE_PMULL128",
@@ -403,7 +400,7 @@ def FeatureRME : Extension<"rme", "RME", "FEAT_RME",
   "Enable Realm Management Extension">;
 
 def FeatureSME : ExtensionWithMArch<"sme", "SME", "FEAT_SME",
-  "Enable Scalable Matrix Extension (SME)", [FeatureBF16, FeatureUseScalarIncVL]>;
+  "Enable Scalable Matrix Extension (SME)", [FeatureBF16]>;
 
 def FeatureSMEF64F64 : ExtensionWithMArch<"sme-f64f64", "SMEF64F64", "FEAT_SME_F64F64",
   "Enable Scalable Matrix Extension (SME) F64F64 instructions", [FeatureSME]>;
@@ -797,6 +794,9 @@ def FeatureUseFixedOverScalableIfEqualCost: SubtargetFeature<"use-fixed-over-sca
   "UseFixedOverScalableIfEqualCost", "true",
   "Prefer fixed width loop vectorization over scalable if the cost-model assigns equal costs">;
 
+def FeatureDontUseScalarIncVL : SubtargetFeature<"dont-use-scalar-inc-vl",
+  "DontUseScalarIncVL", "true", "Prefer add+cnt over inc/dec">;
+
 //===----------------------------------------------------------------------===//
 // Architectures.
 //

llvm/lib/Target/AArch64/AArch64InstrInfo.td

@@ -375,9 +375,9 @@ def UseNegativeImmediates
     : Predicate<"false">, AssemblerPredicate<(all_of (not FeatureNoNegativeImmediates)),
                                              "NegativeImmediates">;
 
-def UseScalarIncVL : Predicate<"Subtarget->useScalarIncVL()">;
+def UseScalarIncVL : Predicate<"!Subtarget->dontUseScalarIncVL()">;
 
-def NoUseScalarIncVL : Predicate<"!Subtarget->useScalarIncVL()">;
+def NoUseScalarIncVL : Predicate<"Subtarget->dontUseScalarIncVL()">;
 
 def UseSVEFPLD1R : Predicate<"!Subtarget->noSVEFPLD1R()">;
 

llvm/lib/Target/AArch64/AArch64Subtarget.cpp

@@ -335,6 +335,13 @@ void AArch64Subtarget::initializeProperties(bool HasMinSize) {
 
   if (AArch64MinimumJumpTableEntries.getNumOccurrences() > 0 || !HasMinSize)
     MinimumJumpTableEntries = AArch64MinimumJumpTableEntries;
+
+  // If only SVE is present (not SVE2 or SME) and DontUseScalarIncVL is not
+  // otherwise set, enable it by default.
+  if (!hasSVE2() && !hasSME()) {
+    if (!getFeatureString().contains("dont-use-scalar-inc-vl"))
+      DontUseScalarIncVL = true;
+  }
 }
 
 AArch64Subtarget::AArch64Subtarget(const Triple &TT, StringRef CPU,

llvm/test/CodeGen/AArch64/sve-intrinsics-counting-elems-i32.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s -check-prefix=NO_SCALAR_INC
-; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+use-scalar-inc-vl < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=-dont-use-scalar-inc-vl < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
 
 ; INCB

llvm/test/CodeGen/AArch64/sve-intrinsics-counting-elems.ll

@@ -1,8 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
-; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+use-scalar-inc-vl < %s | FileCheck %s -check-prefix=USE_SCALAR_INC
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=-dont-use-scalar-inc-vl < %s | FileCheck %s -check-prefix=USE_SCALAR_INC
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s -check-prefix=USE_SCALAR_INC
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -force-streaming < %s | FileCheck %s -check-prefix=USE_SCALAR_INC
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 -mattr=+dont-use-scalar-inc-vl < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -mattr=+dont-use-scalar-inc-vl -force-streaming < %s | FileCheck %s
 
 ;
 ; CNTB

llvm/test/CodeGen/AArch64/sve-vl-arith.ll

@@ -1,7 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -verify-machineinstrs < %s | FileCheck %s -check-prefix=NO_SCALAR_INC
-; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+use-scalar-inc-vl -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=-dont-use-scalar-inc-vl -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 -mattr=+dont-use-scalar-inc-vl -verify-machineinstrs < %s | FileCheck %s -check-prefix=NO_SCALAR_INC
 
 define <vscale x 8 x i16> @inch_vec(<vscale x 8 x i16> %a) {
 ; NO_SCALAR_INC-LABEL: inch_vec: