[SVE] Fall back on DAG ISel at -O0 when encountering scalable types

At the moment we use Global ISel by default at -O0, however it is
currently not capable of dealing with scalable vectors for two
reasons:

1. The register banks know nothing about SVE registers.
2. The LLT (Low Level Type) class knows nothing about scalable
   vectors.

For now, the easiest way to avoid users hitting issues when using
the SVE ACLE is to fall back on normal DAG ISel when encountering
instructions that operate on scalable vector types.

I've added a couple of RUN lines to existing SVE tests to ensure
we can compile at -O0. I've also added some new tests to

  CodeGen/AArch64/GlobalISel/arm64-fallback.ll

that demonstrate we correctly fallback to DAG ISel at -O0 when
lowering formal arguments or translating instructions that involve
scalable vector types.

Differential Revision: https://reviews.llvm.org/D81557

diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h
index a85a24f..f180b27 100644 (file)
--- a/llvm/include/llvm/CodeGen/TargetLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetLowering.h
@@ -516,6 +516,10 @@ public:
     return PredictableSelectIsExpensive;
   }
 
+  virtual bool fallBackToDAGISel(const Instruction &Inst) const {
+    return false;
+  }
+
   /// If a branch or a select condition is skewed in one direction by more than
   /// this factor, it is very likely to be predicted correctly.
   virtual BranchProbability getPredictableBranchThreshold() const;

diff --git a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
index cd6d51f..fae7387 100644 (file)
--- a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -2195,6 +2195,10 @@ bool IRTranslator::translate(const Instruction &Inst) {
   else
     EntryBuilder->setDebugLoc(DebugLoc());
 
+  auto &TLI = *MF->getSubtarget().getTargetLowering();
+  if (TLI.fallBackToDAGISel(Inst))
+    return false;
+
   switch (Inst.getOpcode()) {
 #define HANDLE_INST(NUM, OPCODE, CLASS)                                        \
   case Instruction::OPCODE:                                                    \

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 6f430d7..8eefbe6 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -14642,3 +14642,14 @@ bool AArch64TargetLowering::shouldLocalize(
   }
   return TargetLoweringBase::shouldLocalize(MI, TTI);
 }
+
+bool AArch64TargetLowering::fallBackToDAGISel(const Instruction &Inst) const {
+  if (isa<ScalableVectorType>(Inst.getType()))
+    return true;
+
+  for (unsigned i = 0; i < Inst.getNumOperands(); ++i)
+    if (isa<ScalableVectorType>(Inst.getOperand(i)->getType()))
+      return true;
+
+  return false;
+}

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index 0c0be2a..3baae53 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -702,6 +702,9 @@ public:
                                                  bool isVarArg) const override;
   /// Used for exception handling on Win64.
   bool needsFixedCatchObjects() const override;
+
+  bool fallBackToDAGISel(const Instruction &Inst) const override;
+
 private:
   /// Keep a pointer to the AArch64Subtarget around so that we can
   /// make the right decision when generating code for different targets.

diff --git a/llvm/lib/Target/AArch64/GISel/AArch64CallLowering.cpp b/llvm/lib/Target/AArch64/GISel/AArch64CallLowering.cpp
index 1cfe368..7903299 100644 (file)
--- a/llvm/lib/Target/AArch64/GISel/AArch64CallLowering.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64CallLowering.cpp
@@ -438,6 +438,9 @@ bool AArch64CallLowering::lowerFormalArguments(
   SmallVector<ArgInfo, 8> SplitArgs;
   unsigned i = 0;
   for (auto &Arg : F.args()) {
+    if (isa<ScalableVectorType>(Arg.getType()))
+      return false;
+
     if (DL.getTypeStoreSize(Arg.getType()).isZero())
       continue;
 

diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll
index 17e3a5a..ca628fa 100644 (file)
--- a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll
@@ -219,3 +219,23 @@ entry:
   tail call void asm sideeffect "", "imr,imr,~{memory}"(i32 %x, i32 %y)
   ret void
 }
+
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to lower arguments{{.*}}scalable_arg
+; FALLBACK-WITH-REPORT-OUT-LABEL: scalable_arg
+define <vscale x 16 x i8> @scalable_arg(<vscale x 16 x i1> %pred, i8* %addr) #1 {
+  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.ld1.nxv16i8(<vscale x 16 x i1> %pred, i8* %addr)
+  ret <vscale x 16 x i8> %res
+}
+
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to translate instruction{{.*}}scalable_call
+; FALLBACK-WITH-REPORT-OUT-LABEL: scalable_call
+define <vscale x 16 x i8> @scalable_call(i8* %addr) #1 {
+  %pred = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 0)
+  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.ld1.nxv16i8(<vscale x 16 x i1> %pred, i8* %addr)
+  ret <vscale x 16 x i8> %res
+}
+
+attributes #1 = { "target-features"="+sve" }
+
+declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 %pattern)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.ld1.nxv16i8(<vscale x 16 x i1>, i8*)

diff --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-ld1.ll b/llvm/test/CodeGen/AArch64/sve-intrinsics-ld1.ll
index 928883d..30d6eeb 100644 (file)
--- a/llvm/test/CodeGen/AArch64/sve-intrinsics-ld1.ll
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-ld1.ll
@@ -1,4 +1,5 @@
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+; RUN: llc -O0 -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
 
 ;
 ; LD1B

diff --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-st1.ll b/llvm/test/CodeGen/AArch64/sve-intrinsics-st1.ll
index 512644f..9c297bf 100644 (file)
--- a/llvm/test/CodeGen/AArch64/sve-intrinsics-st1.ll
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-st1.ll
@@ -1,4 +1,5 @@
 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s
+; RUN: llc -O0 -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
 ; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
 
 ; WARN-NOT: warning