[PowerPC] 64-bit large code-model support for toc-data

This patch adds support for toc-data for 64-bit large code-model.
The sequence ADDIStocHA8/ADDItocL8 is used to access the data
directly from the TOC.
When emitting the instruction ADDIStocHA8, we check if the symbol
has toc-data attribute before creating a toc entry for it.
When emitting the instruction ADDItocL8, we use the LA8 instruction
to load the address.

Author: Zaara Syeda

llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp

@@ -1157,21 +1157,21 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
 
     MCSymbolRefExpr::VariantKind VK = GetVKForMO(MO);
 
-    // If the symbol isn't toc-data then use the TOC on AIX.
+    // If the symbol does not have the toc-data attribute, then we create the
+    // TOC entry on AIX. If the toc-data attribute is used, the TOC entry
+    // contains the data rather than the address of the MOSymbol.
     // Map the global address operand to be a reference to the TOC entry we
     // will synthesize later. 'TOCEntry' is a label used to reference the
     // storage allocated in the TOC which contains the address of 'MOSymbol'.
-    // If the toc-data attribute is used, the TOC entry contains the data
-    // rather than the address of the MOSymbol.
     if (![](const MachineOperand &MO) {
           if (!MO.isGlobal())
             return false;
 
-          const GlobalVariable *GV = dyn_cast<GlobalVariable>(MO.getGlobal());
-          if (!GV)
-            return false;
+          if (const GlobalVariable *GV =
+                  dyn_cast<GlobalVariable>(MO.getGlobal()))
+            return GV->hasAttribute("toc-data");
 
-          return GV->hasAttribute("toc-data");
+          return false;
         }(MO)) {
       MOSymbol = lookUpOrCreateTOCEntry(MOSymbol, getTOCEntryTypeForMO(MO), VK);
     }
@@ -1301,8 +1301,9 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
 
     unsigned Op = MI->getOpcode();
 
-    // Change the opcode to load address for tocdata
-    TmpInst.setOpcode(Op == PPC::ADDItocL8 ? PPC::ADDI8 : PPC::LA);
+    // Change the opcode to load address for toc data.
+    unsigned NewOp64 = IsAIX ? PPC::LA8 : PPC::ADDI8;
+    TmpInst.setOpcode(Op == PPC::ADDItocL8 ? NewOp64 : PPC::LA);
 
     const MachineOperand &MO = MI->getOperand(2);
     assert((Op == PPC::ADDItocL8)
@@ -1316,8 +1317,7 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
 
     const MCExpr *Exp = MCSymbolRefExpr::create(
         MOSymbol,
-        Op == PPC::ADDItocL8 ? MCSymbolRefExpr::VK_PPC_TOC_LO
-                             : MCSymbolRefExpr::VK_PPC_L,
+        IsAIX ? MCSymbolRefExpr::VK_PPC_L : MCSymbolRefExpr::VK_PPC_TOC_LO,
         OutContext);
 
     TmpInst.getOperand(2) = MCOperand::createExpr(Exp);

llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp

@@ -6143,10 +6143,10 @@ void PPCDAGToDAGISel::Select(SDNode *N) {
            " ELF/AIX or 32-bit AIX in the following.");
 
     // Transforms the ISD::TOC_ENTRY node for 32-bit AIX large code model mode,
-    // or 64-bit medium (ELF-only), or large (ELF and AIX) code model code that
-    // does not conain TOC data symbols.
+    // 64-bit medium (ELF-only), or large (ELF and AIX) code model code that
+    // does not contain TOC data symbols.
     // We generate two instructions as described below. The first source
-    // operand is a symbol reference. If it must be referenced via the toc
+    // operand is a symbol reference. If it must be referenced via the TOC
     // according to Subtarget, we generate:
     // [32-bit AIX]
     //   LWZtocL(@sym, ADDIStocHA(%r2, @sym))
@@ -6159,7 +6159,7 @@ void PPCDAGToDAGISel::Select(SDNode *N) {
     // [32-bit AIX]
     //   ADDItocL(ADDIStocHA(%x2, @sym), @sym)
     // [64-bit AIX]
-    //   Currently not supported.
+    //   ADDItocL8(ADDIStocHA8(%x2, @sym), @sym)
 
     SDValue GA = N->getOperand(0);
     SDValue TOCbase = N->getOperand(1);
@@ -6171,12 +6171,9 @@ void PPCDAGToDAGISel::Select(SDNode *N) {
     // On AIX, if the symbol has the toc-data attribute it will be defined
     // in the TOC entry, so we use an ADDItocL/ADDItocL8.
     if (isAIXABI && hasTocDataAttr(GA)) {
-      if (isPPC64)
-        report_fatal_error(
-            "64-bit large code model toc-data not yet supported");
-
-      ReplaceNode(N, CurDAG->getMachineNode(PPC::ADDItocL, dl, VT,
-                                            SDValue(Tmp, 0), GA));
+      ReplaceNode(
+          N, CurDAG->getMachineNode(isPPC64 ? PPC::ADDItocL8 : PPC::ADDItocL,
+                                    dl, VT, SDValue(Tmp, 0), GA));
       return;
     }
 
@@ -7777,6 +7774,10 @@ void PPCDAGToDAGISel::PeepholePPC64() {
       Flags = PPCII::MO_TLSLD_LO;
       break;
     case PPC::ADDItocL8:
+      // Skip the following peephole optimizations for ADDItocL8 on AIX which
+      // is used for toc-data access.
+      if (Subtarget->isAIXABI())
+        continue;
       Flags = PPCII::MO_TOC_LO;
       break;
     }

llvm/lib/Target/PowerPC/PPCInstrInfo.cpp

@@ -4438,6 +4438,12 @@ bool PPCInstrInfo::isDefMIElgibleForForwarding(MachineInstr &DefMI,
   if (Opc != PPC::ADDItocL8 && Opc != PPC::ADDI && Opc != PPC::ADDI8)
     return false;
 
+  // Skip the optimization of transformTo[NewImm|Imm]FormFedByAdd for ADDItocL8
+  // on AIX which is used for toc-data access. TODO: Follow up to see if it can
+  // apply for AIX toc-data as well.
+  if (Opc == PPC::ADDItocL8 && Subtarget.isAIX())
+    return false;
+
   assert(DefMI.getNumOperands() >= 3 &&
          "Add inst must have at least three operands");
   RegMO = &DefMI.getOperand(1);

llvm/lib/Target/PowerPC/PPCInstrInfo.td

@@ -3346,7 +3346,7 @@ def ADDIStocHA : PPCEmitTimePseudo<(outs gprc:$rD), (ins gprc_nor0:$reg, tocentr
                        "#ADDIStocHA",
                        [(set i32:$rD,
                          (PPCtoc_entry i32:$reg, tglobaladdr:$disp))]>;
-// TOC Data Transform AIX
+// TOC Data Transform on AIX
 def ADDItoc : PPCEmitTimePseudo<(outs gprc:$rD), (ins tocentry32:$disp, gprc:$reg),
                    "#ADDItoc",
                    [(set i32:$rD,

llvm/test/CodeGen/PowerPC/toc-data.ll

@@ -16,6 +16,10 @@
 ; RUN:     -stop-before=ppc-vsx-copy | FileCheck %s --check-prefix CHECK32LARGE
 ; RUN: llc -mtriple powerpc-ibm-aix-xcoff -code-model=large -verify-machineinstrs < %s | FileCheck %s --check-prefix TEST32LARGE
 
+; RUN: llc -mtriple powerpc64-ibm-aix-xcoff -code-model=large -verify-machineinstrs < %s \
+; RUN:     -stop-before=ppc-vsx-copy | FileCheck %s --check-prefix CHECK64LARGE
+; RUN: llc -mtriple powerpc64-ibm-aix-xcoff -code-model=large -verify-machineinstrs < %s | FileCheck %s --check-prefix TEST64LARGE
+
 ; Global variables i and f have the toc-data attribute.
 ; In the following functions, those writing to or reading from
 ; variables i and f should use the toc-data access pattern.
@@ -63,6 +67,17 @@ define dso_local void @write_int(i32 signext %in) {
 ; TEST32LARGE-NEXT:	la 4, i[TD]@l(4)
 ; TEST32LARGE-NEXT:	stw 3, 0(4)
 
+
+; CHECK64LARGE: name:            write_int
+; CHECK64LARGE:      %[[SCRATCH1:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, @i
+; CHECK64LARGE-NEXT: %[[SCRATCH2:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDItocL8 killed %[[SCRATCH1]], @i
+; CHECK64LARGE-NEXT: STW8 %{{[0-9]+}}, 0, killed %[[SCRATCH2]] :: (store (s32) into @i)
+
+; TEST64LARGE:         .write_int:
+; TEST64LARGE:          addis 4, i[TD]@u(2)
+; TEST64LARGE-NEXT:	la 4, i[TD]@l(4)
+; TEST64LARGE-NEXT:	stw 3, 0(4)
+
 define dso_local i64 @read_ll() {
   entry:
     %0 = load i64, ptr @ll, align 8
@@ -98,6 +113,15 @@ define dso_local i64 @read_ll() {
 ; TEST32LARGE-NEXT:	lwz 3, 0(4)
 ; TEST32LARGE-NEXT:	lwz 4, 4(4)
 
+; CHECK64LARGE: name:            read_ll
+; CHECK64LARGE: %[[SCRATCH1:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, @ll
+; CHECK64LARGE: LDtocL @ll, killed %[[SCRATCH1]] :: (load (s64) from got)
+
+; TEST64LARGE:         .read_ll:
+; TEST64LARGE:          addis 3, L..C0@u(2)
+; TEST64LARGE-NEXT:	ld 3, L..C0@l(3)
+; TEST64LARGE-NEXT:	ld 3, 0(3)
+
 define dso_local float @read_float() {
   entry:
     %0 = load float, ptr @f, align 4
@@ -134,6 +158,18 @@ define dso_local float @read_float() {
 ; TEST32LARGE-NEXT:	la 3, f[TD]@l(3)
 ; TEST32LARGE-NEXT:	lfs 1, 0(3)
 
+
+; CHECK64LARGE: name:            read_float
+; CHECK64LARGE:      %[[SCRATCH1:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, @f
+; CHECK64LARGE-NEXT: %[[SCRATCH2:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDItocL8 killed %[[SCRATCH1]], @f
+; CHECK64LARGE-NEXT: LFS 0, killed %[[SCRATCH2]] :: (dereferenceable load (s32) from @f)
+
+
+; TEST64LARGE:         .read_float:
+; TEST64LARGE:          addis 3, f[TD]@u(2)
+; TEST64LARGE-NEXT:	la 3, f[TD]@l(3)
+; TEST64LARGE-NEXT:	lfs 1, 0(3)
+
 define dso_local void @write_double(double %in) {
   entry:
     store double %in, ptr @d, align 8
@@ -167,6 +203,15 @@ define dso_local void @write_double(double %in) {
 ; TEST32LARGE-NEXT:	lwz 3, L..C1@l(3)
 ; TEST32LARGE-NEXT:	stfd 1, 0(3)
 
+; CHECK64LARGE: name:            write_double
+; CHECK64LARGE: %[[SCRATCH1:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, @d
+; CHECK64LARGE: LDtocL @d, killed %[[SCRATCH1]] :: (load (s64) from got)
+
+; TEST64LARGE:         .write_double:
+; TEST64LARGE:          addis 3, L..C1@u(2)
+; TEST64LARGE-NEXT:	ld 3, L..C1@l(3)
+; TEST64LARGE-NEXT:	stfd 1, 0(3)
+
 define dso_local nonnull ptr @addr() {
   entry:
     ret ptr @i
@@ -237,4 +282,26 @@ define dso_local nonnull ptr @addr() {
 ; TEST32LARGE-NEXT:      .globl f[TD]
 ; TEST32LARGE-NOT:       .tc f[TE],f[RW]
 
+; CHECK64LARGE: name:            addr
+; CHECK64LARGE:      %[[SCRATCH1:[0-9]+]]:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, @i
+; CHECK64LARGE-NEXT: %[[SCRATCH2:[0-9]+]]:g8rc = ADDItocL8 killed %[[SCRATCH1]], @i
+; CHECK64LARGE-NEXT: $x3 = COPY %[[SCRATCH2]]
+
+; TEST64LARGE:         .addr:
+; TEST64LARGE:          addis 3, i[TD]@u(2)
+; TEST64LARGE:          la 3, i[TD]@l(3)
+
+; TEST64LARGE:         .toc
+; TEST64LARGE:           .tc ll[TE],ll[RW]
+; TEST64LARGE-NOT:       .csect ll[TD]
+; TEST64LARGE:           .tc d[TE],d[RW]
+; TEST64LARGE-NOT:       .csect d[TD],2
+; TEST64LARGE:           .csect i[TD],2
+; TEST64LARGE-NEXT:      .globl  i[TD]
+; TEST64LARGE-NEXT:      .align  2
+; TEST64LARGE-NOT:       .tc i[TE],i[RW]
+; TEST64LARGE:           .csect f[TD],2
+; TEST64LARGE-NEXT:      .globl f[TD]
+; TEST64LARGE-NOT:       .tc f[TE],f[RW]
+
 attributes #0 = { "toc-data" }