From d20b5fba2b0e36374d6d25de964e84417ead0abb Mon Sep 17 00:00:00 2001
From: Tim Northover <tnorthover@apple.com>
Date: Thu, 20 Jul 2017 22:58:38 +0000
Subject: [PATCH] Recommit: GlobalISel: select G_EXTRACT and G_INSERT
 instructions on AArch64.

It revealed a bug in the Localizer pass which has now been fixed.

This includes the fix for SUBREG_TO_REG committed separately last time.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308688 91177308-0d34-0410-b5e6-96231b3b80d8
---
 .../AArch64/AArch64InstructionSelector.cpp    | 50 ++++++++++++++++-
 .../GlobalISel/select-insert-extract.mir      | 54 +++++++++++++++++++
 2 files changed, 103 insertions(+), 1 deletion(-)
 create mode 100644 test/CodeGen/AArch64/GlobalISel/select-insert-extract.mir

diff --git a/lib/Target/AArch64/AArch64InstructionSelector.cpp b/lib/Target/AArch64/AArch64InstructionSelector.cpp
index 43f3daf8a03..d32a6bd7f81 100644
--- a/lib/Target/AArch64/AArch64InstructionSelector.cpp
+++ b/lib/Target/AArch64/AArch64InstructionSelector.cpp
@@ -758,6 +758,55 @@ bool AArch64InstructionSelector::select(MachineInstr &I) const {
     constrainSelectedInstRegOperands(I, TII, TRI, RBI);
     return true;
   }
+  case TargetOpcode::G_EXTRACT: {
+    LLT SrcTy = MRI.getType(I.getOperand(1).getReg());
+    // Larger extracts are vectors, same-size extracts should be something else
+    // by now (either split up or simplified to a COPY).
+    if (SrcTy.getSizeInBits() > 64 || Ty.getSizeInBits() > 32)
+      return false;
+
+    I.setDesc(TII.get(AArch64::UBFMXri));
+    MachineInstrBuilder(MF, I).addImm(I.getOperand(2).getImm() +
+                                      Ty.getSizeInBits() - 1);
+
+    unsigned DstReg = MRI.createGenericVirtualRegister(LLT::scalar(64));
+    BuildMI(MBB, std::next(I.getIterator()), I.getDebugLoc(),
+            TII.get(AArch64::COPY))
+        .addDef(I.getOperand(0).getReg())
+        .addUse(DstReg, 0, AArch64::sub_32);
+    RBI.constrainGenericRegister(I.getOperand(0).getReg(),
+                                 AArch64::GPR32RegClass, MRI);
+    I.getOperand(0).setReg(DstReg);
+
+    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
+  }
+
+  case TargetOpcode::G_INSERT: {
+    LLT SrcTy = MRI.getType(I.getOperand(2).getReg());
+    // Larger inserts are vectors, same-size ones should be something else by
+    // now (split up or turned into COPYs).
+    if (Ty.getSizeInBits() > 64 || SrcTy.getSizeInBits() > 32)
+      return false;
+
+    I.setDesc(TII.get(AArch64::BFMXri));
+    unsigned LSB = I.getOperand(3).getImm();
+    unsigned Width = MRI.getType(I.getOperand(2).getReg()).getSizeInBits();
+    I.getOperand(3).setImm((64 - LSB) % 64);
+    MachineInstrBuilder(MF, I).addImm(Width - 1);
+
+    unsigned SrcReg = MRI.createGenericVirtualRegister(LLT::scalar(64));
+    BuildMI(MBB, I.getIterator(), I.getDebugLoc(),
+            TII.get(AArch64::SUBREG_TO_REG))
+        .addDef(SrcReg)
+        .addImm(0)
+        .addUse(I.getOperand(2).getReg())
+        .addImm(AArch64::sub_32);
+    RBI.constrainGenericRegister(I.getOperand(2).getReg(),
+                                 AArch64::GPR32RegClass, MRI);
+    I.getOperand(2).setReg(SrcReg);
+
+    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
+  }
   case TargetOpcode::G_FRAME_INDEX: {
     // allocas and G_FRAME_INDEX are only supported in addrspace(0).
     if (Ty != LLT::pointer(0, 64)) {
@@ -765,7 +814,6 @@ bool AArch64InstructionSelector::select(MachineInstr &I) const {
             << ", expected: " << LLT::pointer(0, 64) << '\n');
       return false;
     }
-
     I.setDesc(TII.get(AArch64::ADDXri));
 
     // MOs for a #0 shifted immediate.
diff --git a/test/CodeGen/AArch64/GlobalISel/select-insert-extract.mir b/test/CodeGen/AArch64/GlobalISel/select-insert-extract.mir
new file mode 100644
index 00000000000..e88e151bd24
--- /dev/null
+++ b/test/CodeGen/AArch64/GlobalISel/select-insert-extract.mir
@@ -0,0 +1,54 @@
+# RUN: llc -mtriple=aarch64-- -run-pass=instruction-select -verify-machineinstrs -global-isel %s -o - | FileCheck %s
+
+---
+# CHECK-LABEL: name: insert_gprs
+name:            insert_gprs
+legalized:       true
+regBankSelected: true
+
+body:             |
+  bb.0:
+    liveins: %x0
+
+    %0:gpr(s32) = COPY %w0
+
+    %1:gpr(s64) = G_IMPLICIT_DEF
+
+    ; CHECK:  body:
+    ; CHECK: [[TMP:%[0-9]+]] = SUBREG_TO_REG 0, %0, 15
+    ; CHECK: %2 = BFMXri %1, [[TMP]], 0, 31
+    %2:gpr(s64) = G_INSERT %1, %0, 0
+
+    ; CHECK: [[TMP:%[0-9]+]] = SUBREG_TO_REG 0, %0, 15
+    ; CHECK: %3 = BFMXri %1, [[TMP]], 51, 31
+    %3:gpr(s64) = G_INSERT %1, %0, 13
+
+    %x0 = COPY %2
+    %x1 = COPY %3
+...
+
+
+---
+# CHECK-LABEL: name: extract_gprs
+name:            extract_gprs
+legalized:       true
+regBankSelected: true
+
+body:             |
+  bb.0:
+    liveins: %x0
+
+    %0:gpr(s64) = COPY %x0
+
+    ; CHECK:  body:
+    ; CHECK: [[TMP:%[0-9]+]] = UBFMXri %0, 0, 31
+    ; CHECK: %1 = COPY [[TMP]].sub_32
+    %1:gpr(s32) = G_EXTRACT %0, 0
+
+    ; CHECK: [[TMP:%[0-9]+]] = UBFMXri %0, 13, 44
+    ; CHECK: %2 = COPY [[TMP]].sub_32
+    %2:gpr(s32) = G_EXTRACT %0, 13
+
+    %w0 = COPY %1
+    %w1 = COPY %2
+...
-- 
2.40.0