[SVE][Inline-Asm] Add constraints for SVE predicate registers

Summary:
Adds the following inline asm constraints for SVE:
  - Upl: One of the low eight SVE predicate registers, P0 to P7 inclusive
  - Upa: SVE predicate register with full range, P0 to P15

Reviewers: t.p.northover, sdesmalen, rovka, momchil.velikov, cameron.mcinally, greened, rengolin

Reviewed By: rovka

Subscribers: javed.absar, tschuett, rkruppe, psnobl, cfe-commits, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D66524

llvm-svn: 371967

6 files changed, 81 insertions, 1 deletions

diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index e6c1bf10298..87e1b971605 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -3825,6 +3825,8 @@ AArch64:
 - ``w``: A 32, 64, or 128-bit floating-point, SIMD or SVE vector register.
 - ``x``: Like w, but restricted to registers 0 to 15 inclusive.
 - ``y``: Like w, but restricted to SVE vector registers Z0 to Z7 inclusive.
+- ``Upl``: One of the low eight SVE predicate registers (P0 to P7)
+- ``Upa``: Any of the SVE predicate registers (P0 to P15)
 
 AMDGPU:
 
diff --git a/llvm/lib/IR/InlineAsm.cpp b/llvm/lib/IR/InlineAsm.cpp
index 99da7caaccf..fd732f9eda8 100644
--- a/llvm/lib/IR/InlineAsm.cpp
+++ b/llvm/lib/IR/InlineAsm.cpp
@@ -181,6 +181,16 @@ bool InlineAsm::ConstraintInfo::Parse(StringRef Str,
       // FIXME: For now assuming these are 2-character constraints.
       pCodes->push_back(StringRef(I+1, 2));
       I += 3;
+    } else if (*I == '@') {
+      // Multi-letter constraint
+      ++I;
+      unsigned char C = static_cast<unsigned char>(*I);
+      assert(isdigit(C) && "Expected a digit!");
+      int N = C - '0';
+      assert(N > 0 && "Found a zero letter constraint!");
+      ++I;
+      pCodes->push_back(StringRef(I, N));
+      I += N;
     } else {
       // Single letter constraint.
       pCodes->push_back(StringRef(I, 1));
diff --git a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
index 21048998edf..c9ab3e37b57 100644
--- a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
+++ b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
@@ -618,6 +618,8 @@ bool AArch64AsmPrinter::PrintAsmOperand(const MachineInstr *MI, unsigned OpNum,
     const TargetRegisterClass *RegClass;
     if (AArch64::ZPRRegClass.contains(Reg)) {
       RegClass = &AArch64::ZPRRegClass;
+    } else if (AArch64::PPRRegClass.contains(Reg)) {
+      RegClass = &AArch64::PPRRegClass;
     } else {
       RegClass = &AArch64::FPR128RegClass;
       AltName = AArch64::vreg;
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 7d466feeac9..84b4e97420c 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -5837,6 +5837,21 @@ const char *AArch64TargetLowering::LowerXConstraint(EVT ConstraintVT) const {
   return "r";
 }
 
+enum PredicateConstraint {
+  Upl,
+  Upa,
+  Invalid
+};
+
+PredicateConstraint parsePredicateConstraint(StringRef Constraint) {
+  PredicateConstraint P = PredicateConstraint::Invalid;
+  if (Constraint == "Upa")
+    P = PredicateConstraint::Upa;
+  if (Constraint == "Upl")
+    P = PredicateConstraint::Upl;
+  return P;
+}
+
 /// getConstraintType - Given a constraint letter, return the type of
 /// constraint it is for this target.
 AArch64TargetLowering::ConstraintType
@@ -5866,7 +5881,9 @@ AArch64TargetLowering::getConstraintType(StringRef Constraint) const {
     case 'S': // A symbolic address
       return C_Other;
     }
-  }
+  } else if (parsePredicateConstraint(Constraint) !=
+             PredicateConstraint::Invalid)
+      return C_RegisterClass;
   return TargetLowering::getConstraintType(Constraint);
 }
 
@@ -5897,6 +5914,10 @@ AArch64TargetLowering::getSingleConstraintMatchWeight(
   case 'z':
     weight = CW_Constant;
     break;
+  case 'U':
+    if (parsePredicateConstraint(constraint) != PredicateConstraint::Invalid)
+      weight = CW_Register;
+    break;
   }
   return weight;
 }
@@ -5941,6 +5962,14 @@ AArch64TargetLowering::getRegForInlineAsmConstraint(
         return std::make_pair(0U, &AArch64::ZPR_3bRegClass);
       break;
     }
+  } else {
+    PredicateConstraint PC = parsePredicateConstraint(Constraint);
+    if (PC != PredicateConstraint::Invalid) {
+      assert(VT.isScalableVector());
+      bool restricted = (PC == PredicateConstraint::Upl);
+      return restricted ? std::make_pair(0U, &AArch64::PPR_3bRegClass)
+                          : std::make_pair(0U, &AArch64::PPRRegClass);
+    }
   }
   if (StringRef("{cc}").equals_lower(Constraint))
     return std::make_pair(unsigned(AArch64::NZCV), &AArch64::CCRRegClass);
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
index 53fdfa5ea42..a1212a866d2 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -2507,6 +2507,17 @@ void AArch64InstrInfo::copyPhysReg(MachineBasicBlock &MBB,
     return;
   }
 
+  // Copy a Predicate register by ORRing with itself.
+  if (AArch64::PPRRegClass.contains(DestReg) &&
+      AArch64::PPRRegClass.contains(SrcReg)) {
+    assert(Subtarget.hasSVE() && "Unexpected SVE register.");
+    BuildMI(MBB, I, DL, get(AArch64::ORR_PPzPP), DestReg)
+      .addReg(SrcReg) // Pg
+      .addReg(SrcReg)
+      .addReg(SrcReg, getKillRegState(KillSrc));
+    return;
+  }
+
   // Copy a Z register by ORRing with itself.
   if (AArch64::ZPRRegClass.contains(DestReg) &&
       AArch64::ZPRRegClass.contains(SrcReg)) {
diff --git a/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll b/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll
index 2ebb0830810..ad1093028c1 100644
--- a/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll
@@ -8,6 +8,7 @@ target triple = "aarch64-none-linux-gnu"
 ; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
 ; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
 ; CHECK: [[ARG4:%[0-9]+]]:zpr_3b = COPY [[ARG1]]
+; CHECK: INLINEASM {{.*}} [[ARG4]]
 define <vscale x 16 x i8> @test_svadd_i8(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm) {
   %1 = tail call <vscale x 16 x i8> asm "add $0.b, $1.b, $2.b", "=w,w,y"(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm)
   ret <vscale x 16 x i8> %1
@@ -18,6 +19,7 @@ define <vscale x 16 x i8> @test_svadd_i8(<vscale x 16 x i8> %Zn, <vscale x 16 x
 ; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
 ; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
 ; CHECK: [[ARG4:%[0-9]+]]:zpr_4b = COPY [[ARG1]]
+; CHECK: INLINEASM {{.*}} [[ARG4]]
 define <vscale x 2 x i64> @test_svsub_i64(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm) {
   %1 = tail call <vscale x 2 x i64> asm "sub $0.d, $1.d, $2.d", "=w,w,x"(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm)
   ret <vscale x 2 x i64> %1
@@ -28,6 +30,7 @@ define <vscale x 2 x i64> @test_svsub_i64(<vscale x 2 x i64> %Zn, <vscale x 2 x
 ; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
 ; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
 ; CHECK: [[ARG4:%[0-9]+]]:zpr_3b = COPY [[ARG1]]
+; CHECK: INLINEASM {{.*}} [[ARG4]]
 define <vscale x 8 x half> @test_svfmul_f16(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
   %1 = tail call <vscale x 8 x half> asm "fmul $0.h, $1.h, $2.h", "=w,w,y"(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
   ret <vscale x 8 x half> %1
@@ -38,7 +41,30 @@ define <vscale x 8 x half> @test_svfmul_f16(<vscale x 8 x half> %Zn, <vscale x 8
 ; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
 ; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
 ; CHECK: [[ARG4:%[0-9]+]]:zpr_4b = COPY [[ARG1]]
+; CHECK: INLINEASM {{.*}} [[ARG4]]
 define <vscale x 4 x float> @test_svfmul_f(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm) {
   %1 = tail call <vscale x 4 x float> asm "fmul $0.s, $1.s, $2.s", "=w,w,x"(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm)
   ret <vscale x 4 x float> %1
 }
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z1
+; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG3:%[0-9]+]]:ppr = COPY $p0
+; CHECK: [[ARG4:%[0-9]+]]:ppr_3b = COPY [[ARG3]]
+; CHECK: INLINEASM {{.*}} [[ARG4]]
+define <vscale x 8 x half> @test_svfadd_f16(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
+  %1 = tail call <vscale x 8 x half> asm "fadd $0.h, $1/m, $2.h, $3.h", "=w,@3Upl,w,w"(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
+  ret <vscale x 8 x half> %1
+}
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG2:%[0-9]+]]:ppr = COPY $p0
+; CHECK: [[ARG3:%[0-9]+]]:ppr = COPY [[ARG2]]
+; CHECK: [[ARG4:%[0-9]+]]:zpr = COPY [[ARG1]]
+; CHECK: INLINEASM {{.*}} [[ARG3]]
+define <vscale x 4 x i32> @test_incp(<vscale x 16 x i1> %Pg, <vscale x 4 x i32> %Zn) {
+  %1 = tail call <vscale x 4 x i32> asm "incp $0.s, $1", "=w,@3Upa,0"(<vscale x 16 x i1> %Pg, <vscale x 4 x i32> %Zn)
+  ret <vscale x 4 x i32> %1
+}