[LV] Add -scalable-vectorization=<option> flag.

This patch adds a new option to the LoopVectorizer to control how
scalable vectors can be used.

Initially, this suggests three levels to control scalable
vectorization, although other more aggressive options can be added in
the future.

The possible options are:
- Disabled:   Disables vectorization with scalable vectors.
- Enabled:    Vectorize loops using scalable vectors or fixed-width
              vectors, but favors fixed-width vectors when the cost
              is a tie.
- Preferred:  Like 'Enabled', but favoring scalable vectors when the
              cost-model is inconclusive.

Reviewed By: paulwalker-arm, vkmr

Differential Revision: https://reviews.llvm.org/D101945

diff --git a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
index bed637e..a66925e 100644 (file)
--- a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
+++ b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
@@ -96,6 +96,20 @@ public:
     FK_Enabled = 1,    ///< Forcing enabled.
   };
 
+  enum ScalableForceKind {
+    /// Not selected.
+    SK_Unspecified = -1,
+    /// Disables vectorization with scalable vectors.
+    SK_FixedWidthOnly = 0,
+    /// Vectorize loops using scalable vectors or fixed-width vectors, but favor
+    /// scalable vectors when the cost-model is inconclusive. This is the
+    /// default when the scalable.enable hint is enabled through a pragma.
+    SK_PreferScalable = 1,
+    /// Vectorize loops using scalable vectors or fixed-width  vectors, but
+    /// favor fixed-width vectors when the cost is inconclusive.
+    SK_PreferFixedWidth = 2,
+  };
+
   LoopVectorizeHints(const Loop *L, bool InterleaveOnlyWhenForced,
                      OptimizationRemarkEmitter &ORE);
 
@@ -109,7 +123,8 @@ public:
   void emitRemarkWithHints() const;
 
   ElementCount getWidth() const {
-    return ElementCount::get(Width.Value, isScalable());
+    return ElementCount::get(Width.Value,
+                             isScalableVectorizationExplicitlyEnabled());
   }
   unsigned getInterleave() const {
     if (Interleave.Value)
@@ -129,7 +144,16 @@ public:
     return (ForceKind)Force.Value;
   }
 
-  bool isScalable() const { return Scalable.Value; }
+  /// \return true if scalable vectorization has been explicitly enabled.
+  bool isScalableVectorizationExplicitlyEnabled() const {
+    return Scalable.Value == SK_PreferFixedWidth ||
+           Scalable.Value == SK_PreferScalable;
+  }
+
+  /// \return true if scalable vectorization has been explicitly disabled.
+  bool isScalableVectorizationDisabled() const {
+    return Scalable.Value == SK_FixedWidthOnly;
+  }
 
   /// If hints are provided that force vectorization, use the AlwaysPrint
   /// pass name to force the frontend to print the diagnostic.

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index 69d7554..59b2aa9 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -48,6 +48,23 @@ static cl::opt<unsigned> PragmaVectorizeSCEVCheckThreshold(
     cl::desc("The maximum number of SCEV checks allowed with a "
              "vectorize(enable) pragma"));
 
+// FIXME: When scalable vectorization is stable enough, change the default
+// to SK_PreferFixedWidth.
+static cl::opt<LoopVectorizeHints::ScalableForceKind> ScalableVectorization(
+    "scalable-vectorization", cl::init(LoopVectorizeHints::SK_FixedWidthOnly),
+    cl::Hidden,
+    cl::desc("Control whether the compiler can use scalable vectors to "
+             "vectorize a loop"),
+    cl::values(
+        clEnumValN(LoopVectorizeHints::SK_FixedWidthOnly, "off",
+                   "Scalable vectorization is disabled."),
+        clEnumValN(LoopVectorizeHints::SK_PreferFixedWidth, "on",
+                   "Scalable vectorization is available, but favor fixed-width "
+                   "vectorization when the cost is inconclusive."),
+        clEnumValN(LoopVectorizeHints::SK_PreferScalable, "preferred",
+                   "Scalable vectorization is available and favored when the "
+                   "cost is inconclusive.")));
+
 /// Maximum vectorization interleave count.
 static const unsigned MaxInterleaveFactor = 16;
 
@@ -77,8 +94,8 @@ LoopVectorizeHints::LoopVectorizeHints(const Loop *L,
       Force("vectorize.enable", FK_Undefined, HK_FORCE),
       IsVectorized("isvectorized", 0, HK_ISVECTORIZED),
       Predicate("vectorize.predicate.enable", FK_Undefined, HK_PREDICATE),
-      Scalable("vectorize.scalable.enable", false, HK_SCALABLE), TheLoop(L),
-      ORE(ORE) {
+      Scalable("vectorize.scalable.enable", SK_Unspecified, HK_SCALABLE),
+      TheLoop(L), ORE(ORE) {
   // Populate values with existing loop metadata.
   getHintsFromMetadata();
 
@@ -86,6 +103,16 @@ LoopVectorizeHints::LoopVectorizeHints(const Loop *L,
   if (VectorizerParams::isInterleaveForced())
     Interleave.Value = VectorizerParams::VectorizationInterleave;
 
+  if ((LoopVectorizeHints::ScalableForceKind)Scalable.Value == SK_Unspecified)
+    // If the width is set, but the metadata says nothing about the scalable
+    // property, then assume it concerns only a fixed-width UserVF.
+    // If width is not set, the flag takes precedence.
+    Scalable.Value = Width.Value ? SK_FixedWidthOnly : ScalableVectorization;
+  else if (ScalableVectorization == SK_FixedWidthOnly)
+    // If the flag is set to disable any use of scalable vectors, override the
+    // loop hint.
+    Scalable.Value = SK_FixedWidthOnly;
+
   if (IsVectorized.Value != 1)
     // If the vectorization width and interleaving count are both 1 then
     // consider the loop to have been already vectorized because there's

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 5bccd7d..a4edca3 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5648,6 +5648,12 @@ LoopVectorizationCostModel::getMaxLegalScalableVF(unsigned MaxSafeElements) {
     return ElementCount::getScalable(0);
   }
 
+  if (Hints->isScalableVectorizationDisabled()) {
+    reportVectorizationInfo("Scalable vectorization is explicitly disabled",
+                            "ScalableVectorizationDisabled", ORE, TheLoop);
+    return ElementCount::getScalable(0);
+  }
+
   auto MaxScalableVF = ElementCount::getScalable(
       std::numeric_limits<ElementCount::ScalarTy>::max());
 

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll b/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll
index 3eb0eef..d93e5b8 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -force-target-instruction-cost=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-target-instruction-cost=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s 2>&1 | FileCheck %s
 
 ; This test currently fails when the LV calculates a maximums safe
 ; distance for scalable vectors, because the code to eliminate the tail is

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/first-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/AArch64/first-order-recurrence.ll
index 2e2754c..a88b960 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/first-order-recurrence.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/first-order-recurrence.ll
@@ -1,5 +1,5 @@
-; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF1
-; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=2 -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF2
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=1 -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF1
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=2 -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF2
 
 ; We vectorize this first order recurrence, with a set of insertelements for
 ; each unrolled part. Make sure these insertelements are generated in-order,

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
index f4114fe..7d6469f 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: asserts
-; RUN: opt -loop-vectorize -force-vector-interleave=1 -S -debug < %s 2>%t | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-vector-interleave=1 -S -debug-only=loop-vectorize < %s 2>%t | FileCheck %s
 ; RUN: cat %t | FileCheck %s --check-prefix=CHECK-COST
 
 target triple = "aarch64-unknown-linux-gnu"

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
index 8fa057f..2bbc6df 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
@@ -1,4 +1,4 @@
-; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -instcombine -mattr=+sve -mtriple aarch64-unknown-linux-gnu < %s | FileCheck %s
+; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -instcombine -mattr=+sve -mtriple aarch64-unknown-linux-gnu -scalable-vectorization=on < %s | FileCheck %s
 
 define void @vec_load(i64 %N, double* nocapture %a, double* nocapture readonly %b) {
 ; CHECK-LABEL: @vec_load

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
index 7b410dd..e45c535 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -loop-vectorize -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S 2>%t | FileCheck %s -check-prefix=CHECK
+; RUN: opt < %s -loop-vectorize -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S -scalable-vectorization=on 2>%t | FileCheck %s -check-prefix=CHECK
 ; RUN: cat %t | FileCheck %s -check-prefix=CHECK-REMARK
 
 ; Reduction can be vectorized

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
index 69748f0..48c2fd9 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -enable-strict-reductions -S | FileCheck %s -check-prefix=CHECK
+; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -enable-strict-reductions -S | FileCheck %s -check-prefix=CHECK
 
 define float @fadd_strict(float* noalias nocapture readonly %a, i64 %n) {
 ; CHECK-LABEL: @fadd_strict

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-analysis.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-analysis.ll
index 6fe5464..2213fde 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-analysis.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-analysis.ll
@@ -1,6 +1,8 @@
 ; REQUIRES: asserts
-; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_ON
-; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize -vectorizer-maximize-bandwidth < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_ON_MAXBW
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize -scalable-vectorization=on        < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_ON
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize -scalable-vectorization=preferred < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_PREFERRED
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize -scalable-vectorization=off       < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_DISABLED
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -force-target-instruction-cost=1 -loop-vectorize -S -debug-only=loop-vectorize -vectorizer-maximize-bandwidth -scalable-vectorization=on < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK_SCALABLE_ON_MAXBW
 
 ; Test that the MaxVF for the following loop, that has no dependence distances,
 ; is calculated as vscale x 4 (max legal SVE vector size) or vscale x 16
@@ -8,6 +10,8 @@
 define void @test0(i32* %a, i8* %b, i32* %c) {
 ; CHECK: LV: Checking a loop in "test0"
 ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 4
+; CHECK_SCALABLE_PREFERRED: LV: Found feasible scalable VF = vscale x 4
+; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF
 ; CHECK_SCALABLE_ON_MAXBW: LV: Found feasible scalable VF = vscale x 16
 entry:
   br label %loop
@@ -35,6 +39,8 @@ exit:
 define void @test1(i32* %a, i8* %b) {
 ; CHECK: LV: Checking a loop in "test1"
 ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 4
+; CHECK_SCALABLE_PREFERRED: LV: Found feasible scalable VF = vscale x 4
+; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF
 ; CHECK_SCALABLE_ON_MAXBW: LV: Found feasible scalable VF = vscale x 4
 entry:
   br label %loop
@@ -63,6 +69,8 @@ exit:
 define void @test2(i32* %a, i8* %b) {
 ; CHECK: LV: Checking a loop in "test2"
 ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 2
+; CHECK_SCALABLE_PREFERRED: LV: Found feasible scalable VF = vscale x 2
+; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF
 ; CHECK_SCALABLE_ON_MAXBW: LV: Found feasible scalable VF = vscale x 2
 entry:
   br label %loop
@@ -91,6 +99,8 @@ exit:
 define void @test3(i32* %a, i8* %b) {
 ; CHECK: LV: Checking a loop in "test3"
 ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 1
+; CHECK_SCALABLE_PREFERRED: LV: Found feasible scalable VF = vscale x 1
+; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF
 ; CHECK_SCALABLE_ON_MAXBW: LV: Found feasible scalable VF = vscale x 1
 entry:
   br label %loop
@@ -120,6 +130,8 @@ exit:
 define void @test4(i32* %a, i32* %b) {
 ; CHECK: LV: Checking a loop in "test4"
 ; CHECK_SCALABLE_ON-NOT: LV: Found feasible scalable VF
+; CHECK_SCALABLE_PREFERRED-NOT: LV: Found feasible scalable VF
+; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF
 ; CHECK_SCALABLE_ON_MAXBW-NOT: LV: Found feasible scalable VF
 entry:
   br label %loop

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll
index 33d75e0..a29cf18 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll
@@ -1,8 +1,8 @@
 ; REQUIRES: asserts
-; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -loop-vectorize -S < %s 2>&1 | FileCheck %s
-; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck --check-prefix=CHECK-DBG %s
-; RUN: opt -mtriple=aarch64-none-linux-gnu -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck --check-prefix=CHECK-NO-SVE %s
-; RUN: opt -mtriple=aarch64-none-linux-gnu -loop-vectorize -force-target-supports-scalable-vectors=true -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck --check-prefix=CHECK-NO-MAX-VSCALE %s
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -loop-vectorize -S -scalable-vectorization=on < %s 2>&1 | FileCheck %s
+; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S -scalable-vectorization=on < %s 2>&1 | FileCheck --check-prefix=CHECK-DBG %s
+; RUN: opt -mtriple=aarch64-none-linux-gnu -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S -scalable-vectorization=on < %s 2>&1 | FileCheck --check-prefix=CHECK-NO-SVE %s
+; RUN: opt -mtriple=aarch64-none-linux-gnu -loop-vectorize -force-target-supports-scalable-vectors=true -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S -scalable-vectorization=on < %s 2>&1 | FileCheck --check-prefix=CHECK-NO-MAX-VSCALE %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
index ad6f42b..79cb349 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve < %s -S | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -scalable-vectorization=on < %s -S | FileCheck %s
 
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
index 2536c6c..3054f3a 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
 
 define void @cond_inv_load_i32i32i16(i32* noalias nocapture %a, i32* noalias nocapture readonly %cond, i16* noalias nocapture readonly %inv, i64 %n) {
 ; CHECK-LABEL: @cond_inv_load_i32i32i16

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-extract-last-veclane.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-extract-last-veclane.ll
index 56a53a5..d6c509f 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-extract-last-veclane.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-extract-last-veclane.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
index 58f683c..5738019 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -scalable-vectorization=on -o - | FileCheck %s
 
 define void @gather_nxv4i32_ind64(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) {
 ; CHECK-LABEL: @gather_nxv4i32_ind64

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
index 192d181..fff09c8 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
@@ -1,4 +1,4 @@
-; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine < %s -S | FileCheck %s
+; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -scalable-vectorization=on -dce -instcombine < %s -S | FileCheck %s
 
 ; Test that we can add on the induction variable
 ;   for (long long i = 0; i < n; i++) {

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
index a12ec7f..2c6741b 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
@@ -1,4 +1,4 @@
-; RUN: opt -S -loop-vectorize -mattr=+sve -mtriple aarch64-linux-gnu < %s | FileCheck %s
+; RUN: opt -S -loop-vectorize -scalable-vectorization=on -mattr=+sve -mtriple aarch64-linux-gnu < %s | FileCheck %s
 
 define void @invariant_load(i64 %n, i32* noalias nocapture %a, i32* nocapture readonly %b) {
 ; CHECK-LABEL: @invariant_load

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
index e804dd3..8327e09 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
@@ -1,4 +1,4 @@
-; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S <%s | FileCheck %s
+; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -scalable-vectorization=on -dce -instcombine -S <%s | FileCheck %s
 
 define void @stride7_i32(i32* noalias nocapture %dst, i64 %n) {
 ; CHECK-LABEL: @stride7_i32(

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
index 9988bfd..a2864a1 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -scalable-vectorization=on -o - | FileCheck %s
 
 define void @mloadstore_f32(float* noalias nocapture %a, float* noalias nocapture readonly %b, i64 %n) {
 ; CHECK-LABEL: @mloadstore_f32

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-type-conv.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-type-conv.ll
index 221a6a6..eb87f77 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-type-conv.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-type-conv.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -dce -instcombine < %s -S | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine < %s -S | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
index ab45cd8..cd7fa7e 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
@@ -10,7 +10,7 @@
 
 ; The test checks if the mask is being correctly created, reverted and used
 
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
index c439270..002dadd 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
@@ -4,7 +4,7 @@
 ;  for (int i = N-1; i >= 0; --i)
 ;    a[i] = b[i] + 1.0;
 
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
 
 define void @vector_reverse_f64(i64 %N, double* %a, double* %b) #0{
 ; CHECK-LABEL: @vector_reverse_f64

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
index 353ad64..2745e95 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
@@ -1,4 +1,4 @@
-; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S < %s | FileCheck %s
+; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -scalable-vectorization=on -dce -instcombine -S < %s | FileCheck %s
 
 ; Ensure that we can vectorize loops such as:
 ;   int *ptr = c;

diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/scalable-vf-hint.ll b/llvm/test/Transforms/LoopVectorize/RISCV/scalable-vf-hint.ll
index 69f0073..57c612e 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/RISCV/scalable-vf-hint.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/scalable-vf-hint.ll
@@ -1,5 +1,5 @@
 ; RUN: opt -mtriple=riscv64 -mattr=+m,+experimental-v -loop-vectorize \
-; RUN:   -riscv-v-vector-bits-max=512 -S < %s 2>&1 \
+; RUN:   -riscv-v-vector-bits-max=512 -S -scalable-vectorization=on < %s 2>&1 \
 ; RUN:   | FileCheck %s
 
 ; void test(int *a, int *b, int N) {

diff --git a/llvm/test/Transforms/LoopVectorize/metadata-width.ll b/llvm/test/Transforms/LoopVectorize/metadata-width.ll
index 1dc51ca..7b60bc7 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/metadata-width.ll
+++ b/llvm/test/Transforms/LoopVectorize/metadata-width.ll
@@ -1,4 +1,5 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -dce -instcombine -S -scalable-vectorization=on | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -dce -instcombine -S -scalable-vectorization=preferred | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 
@@ -65,11 +66,37 @@ for.end:                                          ; preds = %for.body, %entry
   ret void
 }
 
+; Test that when only the width property is specified, and not the scalable.enable flag,
+; that the hint defaults to 'scalable.enable = false'.
+
+; CHECK-LABEL: @test4(
+; CHECK: store <8 x i32>
+; CHECK: ret void
+define void @test4(i32* nocapture %a, i32 %n) #0 {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+  store i32 42, i32* %arrayidx, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !6
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
 attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
 
-!0 = !{!0, !1}
+!0 = !{!0, !1, !5}
 !1 = !{!"llvm.loop.vectorize.width", i32 8}
 !2 = !{!2, !1, !3}
 !3 = !{!"llvm.loop.vectorize.scalable.enable", i32 1}
 !4 = !{!4, !1, !5}
 !5 = !{!"llvm.loop.vectorize.scalable.enable", i32 0}
+!6 = !{!6, !7}
+!7 = !{!"llvm.loop.vectorize.width", i32 8}

diff --git a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll
index 0a6925d..c42bb33 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: asserts
-; RUN: opt < %s  -passes='loop-vectorize' -force-vector-width=2 -force-target-supports-scalable-vectors=true -enable-epilogue-vectorization -epilogue-vectorization-force-VF=2 --debug-only=loop-vectorize -S 2>&1 | FileCheck %s
+; RUN: opt < %s  -passes='loop-vectorize' -force-vector-width=2 -force-target-supports-scalable-vectors=true -enable-epilogue-vectorization -epilogue-vectorization-force-VF=2 --debug-only=loop-vectorize -S -scalable-vectorization=on 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-n32:64-v256:256:256-v512:512:512"
 

diff --git a/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
index bbcc553..0e660a9 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
@@ -1,5 +1,5 @@
-; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF1
-; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=2 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF2
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF1
+; RUN: opt -loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=2 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF2
 
 ; void recurrence_1(int *a, int *b, int n) {
 ;   for(int i = 0; i < n; i++)

diff --git a/llvm/test/Transforms/LoopVectorize/scalable-loop-unpredicated-body-scalar-tail.ll b/llvm/test/Transforms/LoopVectorize/scalable-loop-unpredicated-body-scalar-tail.ll
index 3d845e6..93715c2 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/scalable-loop-unpredicated-body-scalar-tail.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-loop-unpredicated-body-scalar-tail.ll
@@ -1,5 +1,5 @@
-; RUN: opt -S -loop-vectorize -instcombine -force-vector-interleave=1 -force-vector-width=4 -force-target-supports-scalable-vectors=true < %s | FileCheck %s --check-prefix=CHECKUF1
-; RUN: opt -S -loop-vectorize -instcombine -force-vector-interleave=2 -force-vector-width=4 -force-target-supports-scalable-vectors=true < %s | FileCheck %s --check-prefix=CHECKUF2
+; RUN: opt -S -loop-vectorize -instcombine -force-vector-interleave=1 -force-vector-width=4 -force-target-supports-scalable-vectors=true -scalable-vectorization=on < %s | FileCheck %s --check-prefix=CHECKUF1
+; RUN: opt -S -loop-vectorize -instcombine -force-vector-interleave=2 -force-vector-width=4 -force-target-supports-scalable-vectors=true -scalable-vectorization=on < %s | FileCheck %s --check-prefix=CHECKUF2
 
 ; CHECKUF1: for.body.preheader:
 ; CHECKUF1-DAG: %wide.trip.count = zext i32 %N to i64

diff --git a/llvm/test/Transforms/LoopVectorize/scalable-reduction-inloop.ll b/llvm/test/Transforms/LoopVectorize/scalable-reduction-inloop.ll
index 03af7b3..efa7080 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/scalable-reduction-inloop.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-reduction-inloop.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -loop-vectorize -force-target-supports-scalable-vectors=true -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-target-supports-scalable-vectors=true -scalable-vectorization=on -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 

diff --git a/llvm/test/Transforms/LoopVectorize/scalable-vf-hint.ll b/llvm/test/Transforms/LoopVectorize/scalable-vf-hint.ll
index f99d87f..6f5a591 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/scalable-vf-hint.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-vf-hint.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: asserts
-; RUN: opt -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S -scalable-vectorization=on < %s 2>&1 | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"