[GISel]: Add legalization support for widening bit counting operations

[aditya_nandakumar]

Summary

Added legalizerHelper code along with FileCheck based unit tests.

[arsenm]

LGTM

[aditya_nandakumar]

Thanks Matt. Submitted in r340429

lib/CodeGen/GlobalISel/LegalizerHelper.cpp

 
 LegalizerHelper::LegalizeResult
 LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
   MIRBuilder.setInstr(MI);
 
   switch (MI.getOpcode()) {
   default:
     return UnableToLegalize;
+  case TargetOpcode::G_CTTZ:
+  case TargetOpcode::G_CTTZ_ZERO_UNDEF:
+  case TargetOpcode::G_CTLZ:
+  case TargetOpcode::G_CTLZ_ZERO_UNDEF:
+  case TargetOpcode::G_CTPOP: {
+    // First ZEXT the input.
+    auto MIBZext = MIRBuilder.buildZExt(WideTy, MI.getOperand(1).getReg());
+    unsigned SrcReg = MIBZext->getOperand(0).getReg();
+    LLT CurTy = MRI.getType(MI.getOperand(0).getReg());
+    if (MI.getOpcode() == TargetOpcode::G_CTTZ) {
+      // The count is the same in the larger type except if the original
+      // value was zero.  This can be handled by setting the bit just off
+      // the top of the original type.
+      auto TopBit =
+          APInt::getOneBitSet(WideTy.getSizeInBits(), CurTy.getSizeInBits());
+      auto MIBOr = MIRBuilder.buildInstr(
+          TargetOpcode::G_OR, WideTy, MIBZext,
+          MIRBuilder.buildConstant(WideTy, TopBit.getSExtValue()));
+      SrcReg = MIBOr->getOperand(0).getReg();
+    }
+    // Perform the operation at the larger size.
+    auto MIBNewOp = MIRBuilder.buildInstr(MI.getOpcode(), WideTy, SrcReg);
+    unsigned NewReg = MIBNewOp->getOperand(0).getReg();
+    // This is already the correct result for CTPOP and CTTZs
+    if (MI.getOpcode() == TargetOpcode::G_CTLZ ||
+        MI.getOpcode() == TargetOpcode::G_CTLZ_ZERO_UNDEF) {
+      // The correct result is NewOp - (Difference in widety and current ty).
+      unsigned SizeDiff = WideTy.getSizeInBits() - CurTy.getSizeInBits();
+      auto MIBSub =
+          MIRBuilder.buildInstr(TargetOpcode::G_SUB, WideTy, MIBNewOp,
+                                MIRBuilder.buildConstant(WideTy, SizeDiff));
+      NewReg = MIBSub->getOperand(0).getReg();
+    }
+    auto &TII = *MI.getMF()->getSubtarget().getInstrInfo();
+    // Make the original instruction a trunc now, and update it's source.
+    MI.setDesc(TII.get(TargetOpcode::G_TRUNC));
+    MI.getOperand(1).setReg(NewReg);
+    MIRBuilder.recordInsertion(&MI);
+    return Legalized;
+  }
 
   case TargetOpcode::G_ADD:
   case TargetOpcode::G_AND:
   case TargetOpcode::G_MUL:
   case TargetOpcode::G_OR:
   case TargetOpcode::G_XOR:
   case TargetOpcode::G_SUB:
     // Perform operation at larger width (any extension is fine here, high bits

unittests/CodeGen/GlobalISel/LegalizerHelperTest.cpp

TEST_F(LegalizerHelperTest, LowerBitCountingCTLZ1) {
   CHECK: [[CTPOP:%[0-9]+]]:_(s8) = G_CTPOP [[Or4]]:_
   CHECK: [[Len:%[0-9]+]]:_(s8) = G_CONSTANT i8 8
   CHECK: [[Sub:%[0-9]+]]:_(s8) = G_SUB [[Len]]:_, [[CTPOP]]:_
   )";
 
   // Check
   ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
 }
+
+// CTLZ widening.
+TEST_F(LegalizerHelperTest, WidenBitCountingCTLZ) {
+  if (!TM)
+    return;
+
+  // Declare your legalization info
+  DefineLegalizerInfo(A,
+                      { getActionDefinitionsBuilder(G_CTLZ).legalFor({s16}); });
+  // Build
+  // Trunc it to s8.
+  LLT s8{LLT::scalar(8)};
+  LLT s16{LLT::scalar(16)};
+  auto MIBTrunc = B.buildTrunc(s8, Copies[0]);
+  auto MIBCTLZ = B.buildInstr(TargetOpcode::G_CTLZ, s8, MIBTrunc);
+  AInfo Info(MF->getSubtarget());
+  LegalizerHelper Helper(*MF, Info);
+  ASSERT_TRUE(Helper.widenScalar(*MIBCTLZ, 0, s16) ==
+              LegalizerHelper::LegalizeResult::Legalized);
+
+  auto CheckStr = R"(
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC
+  CHECK: [[Zext:%[0-9]+]]:_(s16) = G_ZEXT [[Trunc]]
+  CHECK: [[Ctlz:%[0-9]+]]:_(s16) = G_CTLZ [[Zext]]
+  CHECK: [[Cst8:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+  CHECK: [[Sub:%[0-9]+]]:_(s16) = G_SUB [[Ctlz]]:_, [[Cst8]]:_
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC [[Sub]]
+  )";
+
+  // Check
+  ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
+}
+
+// CTLZ_ZERO_UNDEF widening.
+TEST_F(LegalizerHelperTest, WidenBitCountingCTLZZeroUndef) {
+  if (!TM)
+    return;
+
+  // Declare your legalization info
+  DefineLegalizerInfo(
+      A, { getActionDefinitionsBuilder(G_CTLZ_ZERO_UNDEF).legalFor({s16}); });
+  // Build
+  // Trunc it to s8.
+  LLT s8{LLT::scalar(8)};
+  LLT s16{LLT::scalar(16)};
+  auto MIBTrunc = B.buildTrunc(s8, Copies[0]);
+  auto MIBCTLZ_ZU = B.buildInstr(TargetOpcode::G_CTLZ_ZERO_UNDEF, s8, MIBTrunc);
+  AInfo Info(MF->getSubtarget());
+  LegalizerHelper Helper(*MF, Info);
+  ASSERT_TRUE(Helper.widenScalar(*MIBCTLZ_ZU, 0, s16) ==
+              LegalizerHelper::LegalizeResult::Legalized);
+
+  auto CheckStr = R"(
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC
+  CHECK: [[Zext:%[0-9]+]]:_(s16) = G_ZEXT [[Trunc]]
+  CHECK: [[CtlzZu:%[0-9]+]]:_(s16) = G_CTLZ_ZERO_UNDEF [[Zext]]
+  CHECK: [[Cst8:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+  CHECK: [[Sub:%[0-9]+]]:_(s16) = G_SUB [[CtlzZu]]:_, [[Cst8]]:_
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC [[Sub]]
+  )";
+
+  // Check
+  ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
+}
+
+// CTPOP widening.
+TEST_F(LegalizerHelperTest, WidenBitCountingCTPOP) {
+  if (!TM)
+    return;
+
+  // Declare your legalization info
+  DefineLegalizerInfo(
+      A, { getActionDefinitionsBuilder(G_CTPOP).legalFor({s16}); });
+  // Build
+  // Trunc it to s8.
+  LLT s8{LLT::scalar(8)};
+  LLT s16{LLT::scalar(16)};
+  auto MIBTrunc = B.buildTrunc(s8, Copies[0]);
+  auto MIBCTPOP = B.buildInstr(TargetOpcode::G_CTPOP, s8, MIBTrunc);
+  AInfo Info(MF->getSubtarget());
+  LegalizerHelper Helper(*MF, Info);
+  ASSERT_TRUE(Helper.widenScalar(*MIBCTPOP, 0, s16) ==
+              LegalizerHelper::LegalizeResult::Legalized);
+
+  auto CheckStr = R"(
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC
+  CHECK: [[Zext:%[0-9]+]]:_(s16) = G_ZEXT [[Trunc]]
+  CHECK: [[Ctpop:%[0-9]+]]:_(s16) = G_CTPOP [[Zext]]
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC [[Ctpop]]
+  )";
+
+  // Check
+  ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
+}
+
+// CTTZ_ZERO_UNDEF widening.
+TEST_F(LegalizerHelperTest, WidenBitCountingCTTZ_ZERO_UNDEF) {
+  if (!TM)
+    return;
+
+  // Declare your legalization info
+  DefineLegalizerInfo(
+      A, { getActionDefinitionsBuilder(G_CTTZ_ZERO_UNDEF).legalFor({s16}); });
+  // Build
+  // Trunc it to s8.
+  LLT s8{LLT::scalar(8)};
+  LLT s16{LLT::scalar(16)};
+  auto MIBTrunc = B.buildTrunc(s8, Copies[0]);
+  auto MIBCTTZ_ZERO_UNDEF =
+      B.buildInstr(TargetOpcode::G_CTTZ_ZERO_UNDEF, s8, MIBTrunc);
+  AInfo Info(MF->getSubtarget());
+  LegalizerHelper Helper(*MF, Info);
+  ASSERT_TRUE(Helper.widenScalar(*MIBCTTZ_ZERO_UNDEF, 0, s16) ==
+              LegalizerHelper::LegalizeResult::Legalized);
+
+  auto CheckStr = R"(
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC
+  CHECK: [[Zext:%[0-9]+]]:_(s16) = G_ZEXT [[Trunc]]
+  CHECK: [[CttzZu:%[0-9]+]]:_(s16) = G_CTTZ_ZERO_UNDEF [[Zext]]
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC [[CttzZu]]
+  )";
+
+  // Check
+  ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
+}
+
+// CTTZ widening.
+TEST_F(LegalizerHelperTest, WidenBitCountingCTTZ) {
+  if (!TM)
+    return;
+
+  // Declare your legalization info
+  DefineLegalizerInfo(A,
+                      { getActionDefinitionsBuilder(G_CTTZ).legalFor({s16}); });
+  // Build
+  // Trunc it to s8.
+  LLT s8{LLT::scalar(8)};
+  LLT s16{LLT::scalar(16)};
+  auto MIBTrunc = B.buildTrunc(s8, Copies[0]);
+  auto MIBCTTZ = B.buildInstr(TargetOpcode::G_CTTZ, s8, MIBTrunc);
+  AInfo Info(MF->getSubtarget());
+  LegalizerHelper Helper(*MF, Info);
+  ASSERT_TRUE(Helper.widenScalar(*MIBCTTZ, 0, s16) ==
+              LegalizerHelper::LegalizeResult::Legalized);
+
+  auto CheckStr = R"(
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC
+  CHECK: [[Zext:%[0-9]+]]:_(s16) = G_ZEXT [[Trunc]]
+  CHECK: [[Cst:%[0-9]+]]:_(s16) = G_CONSTANT i16 256
+  CHECK: [[Or:%[0-9]+]]:_(s16) = G_OR [[Zext]]:_, [[Cst]]
+  CHECK: [[Cttz:%[0-9]+]]:_(s16) = G_CTTZ [[Or]]
+  CHECK: [[Trunc:%[0-9]+]]:_(s8) = G_TRUNC [[Cttz]]
+  )";
+
+  // Check
+  ASSERT_TRUE(CheckMachineFunction(*MF, CheckStr));
+}
 } // namespace