merge main into amd-staging

Change-Id: I583f3124faab024cb9f199f7b3c840d8a68b7cd4

Author: Jenkins

clang/lib/Format/FormatInternal.h

@@ -15,6 +15,11 @@
 #ifndef LLVM_CLANG_LIB_FORMAT_FORMATINTERNAL_H
 #define LLVM_CLANG_LIB_FORMAT_FORMATINTERNAL_H
 
+#include "clang/Basic/LLVM.h"
+#include "clang/Format/Format.h"
+#include "clang/Tooling/Core/Replacement.h"
+#include <utility>
+
 namespace clang {
 namespace format {
 namespace internal {

clang/lib/Sema/SemaChecking.cpp

@@ -5189,6 +5189,7 @@ static bool isPPC_64Builtin(unsigned BuiltinID) {
   case PPC::BI__builtin_ppc_fetch_and_andlp:
   case PPC::BI__builtin_ppc_fetch_and_orlp:
   case PPC::BI__builtin_ppc_fetch_and_swaplp:
+  case PPC::BI__builtin_ppc_rldimi:
     return true;
   }
   return false;
@@ -5290,8 +5291,10 @@ bool Sema::CheckPPCBuiltinFunctionCall(const TargetInfo &TI, unsigned BuiltinID,
   case PPC::BI__builtin_ppc_rlwnm:
     return SemaValueIsRunOfOnes(TheCall, 2);
   case PPC::BI__builtin_ppc_rlwimi:
+    return SemaBuiltinConstantArgRange(TheCall, 2, 0, 31) ||
+           SemaValueIsRunOfOnes(TheCall, 3);
   case PPC::BI__builtin_ppc_rldimi:
-    return SemaBuiltinConstantArg(TheCall, 2, Result) ||
+    return SemaBuiltinConstantArgRange(TheCall, 2, 0, 63) ||
            SemaValueIsRunOfOnes(TheCall, 3);
   case PPC::BI__builtin_ppc_addex: {
     if (SemaBuiltinConstantArgRange(TheCall, 2, 0, 3))

clang/test/CodeGen/PowerPC/builtins-ppc-xlcompat-error.c

@@ -24,13 +24,16 @@ void test_trap(void) {
   __tw(ia, ib, 0); //expected-error {{argument value 0 is outside the valid range [1, 31]}}
 }
 
+#ifdef __PPC64__
 void test_builtin_ppc_rldimi() {
   unsigned int shift;
   unsigned long long mask;
   unsigned long long res = __builtin_ppc_rldimi(ull, ull, shift, 7); // expected-error {{argument to '__builtin_ppc_rldimi' must be a constant integer}}
   res = __builtin_ppc_rldimi(ull, ull, 63, mask);                    // expected-error {{argument to '__builtin_ppc_rldimi' must be a constant integer}}
   res = __builtin_ppc_rldimi(ull, ull, 63, 0xFFFF000000000F00);      // expected-error {{argument 3 value should represent a contiguous bit field}}
+  res = __builtin_ppc_rldimi(ull, ull, 64, 0xFFFF000000000000);      // expected-error {{argument value 64 is outside the valid range [0, 63]}}
 }
+#endif
 
 void test_builtin_ppc_rlwimi() {
   unsigned int shift;
@@ -83,6 +86,10 @@ void testalignx(const void *pointer, unsigned int alignment) {
 }
 
 #ifndef __PPC64__
+unsigned long long testrldimi32() {
+  return __rldimi(ull, ui, 3, 0x7ffff8ULL); //expected-error {{this builtin is only available on 64-bit targets}}
+}
+
 long long testbpermd(long long bit_selector, long long source) {
   return __bpermd(bit_selector, source); //expected-error {{this builtin is only available on 64-bit targets}}
 }

clang/test/CodeGen/PowerPC/builtins-ppc-xlcompat-rotate.c

@@ -1,8 +1,10 @@
 // REQUIRES: powerpc-registered-target
 // RUN: %clang_cc1 -triple powerpc64-unknown-linux-gnu \
-// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s
+// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s \
+// RUN:   -check-prefixes=PPC64,CHECK
 // RUN: %clang_cc1 -triple powerpc64le-unknown-linux-gnu \
-// RUN:   -emit-llvm %s -o - -target-cpu pwr8 | FileCheck %s
+// RUN:   -emit-llvm %s -o - -target-cpu pwr8 | FileCheck %s \
+// RUN:   -check-prefixes=PPC64,CHECK
 // RUN: %clang_cc1 -triple powerpc-unknown-aix \
 // RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s
 // RUN: %clang_cc1 -triple powerpc64-unknown-aix \
@@ -11,18 +13,20 @@
 extern unsigned int ui;
 extern unsigned long long ull;
 
+#ifdef __PPC64__
 void test_builtin_ppc_rldimi() {
-  // CHECK-LABEL: test_builtin_ppc_rldimi
-  // CHECK:       %res = alloca i64, align 8
-  // CHECK-NEXT:  [[RA:%[0-9]+]] = load i64, ptr @ull, align 8
-  // CHECK-NEXT:  [[RB:%[0-9]+]] = load i64, ptr @ull, align 8
-  // CHECK-NEXT:  [[RC:%[0-9]+]] = call i64 @llvm.ppc.rldimi(i64 [[RA]], i64 [[RB]], i32 63, i64 72057593769492480)
-  // CHECK-NEXT:  store i64 [[RC]], ptr %res, align 8
-  // CHECK-NEXT:  ret void
+  // PPC64-LABEL: test_builtin_ppc_rldimi
+  // PPC64:       %res = alloca i64, align 8
+  // PPC64-NEXT:  [[RA:%[0-9]+]] = load i64, ptr @ull, align 8
+  // PPC64-NEXT:  [[RB:%[0-9]+]] = load i64, ptr @ull, align 8
+  // PPC64-NEXT:  [[RC:%[0-9]+]] = call i64 @llvm.ppc.rldimi(i64 [[RA]], i64 [[RB]], i32 63, i64 72057593769492480)
+  // PPC64-NEXT:  store i64 [[RC]], ptr %res, align 8
+  // PPC64-NEXT:  ret void
 
   /*shift = 63, mask = 0x00FFFFFFF0000000 = 72057593769492480, ~mask = 0xFF0000000FFFFFFF = -72057593769492481*/
   unsigned long long res = __builtin_ppc_rldimi(ull, ull, 63, 0x00FFFFFFF0000000);
 }
+#endif
 
 void test_builtin_ppc_rlwimi() {
   // CHECK-LABEL: test_builtin_ppc_rlwimi

clang/unittests/Format/FormatTest.cpp

@@ -11475,10 +11475,10 @@ TEST_F(FormatTest, UnderstandsNewAndDelete) {
                "void new (link p);\n"
                "void delete (link p);");
 
-  verifyFormat("{ p->delete(); }\n"
-               "{ p->new(); }",
-               "{ p->delete (); }\n"
-               "{ p->new (); }");
+  verifyFormat("p->new();\n"
+               "p->delete();",
+               "p->new ();\n"
+               "p->delete ();");
 
   FormatStyle AfterPlacementOperator = getLLVMStyle();
   AfterPlacementOperator.SpaceBeforeParens = FormatStyle::SBPO_Custom;

flang/lib/Lower/Bridge.cpp

@@ -748,7 +748,8 @@ class FirConverter : public Fortran::lower::AbstractConverter {
 
   void copyVar(mlir::Location loc, mlir::Value dst,
                mlir::Value src) override final {
-    copyVarHLFIR(loc, dst, src);
+    copyVarHLFIR(loc, Fortran::lower::SymbolBox::Intrinsic{dst},
+                 Fortran::lower::SymbolBox::Intrinsic{src});
   }
 
   void copyHostAssociateVar(
@@ -1009,10 +1010,7 @@ class FirConverter : public Fortran::lower::AbstractConverter {
       // `omp.private`'s `alloc` block. If this is the case, we return this
       // `SymbolBox::Intrinsic` value.
       if (Fortran::lower::SymbolBox v = symMap->lookupSymbol(sym))
-        return v.match(
-            [&](const Fortran::lower::SymbolBox::Intrinsic &)
-                -> Fortran::lower::SymbolBox { return v; },
-            [](const auto &) -> Fortran::lower::SymbolBox { return {}; });
+        return v;
 
       return {};
     }
@@ -1060,15 +1058,16 @@ class FirConverter : public Fortran::lower::AbstractConverter {
                const Fortran::lower::SymbolBox &rhs_sb) {
     mlir::Location loc = genLocation(sym.name());
     if (lowerToHighLevelFIR())
-      copyVarHLFIR(loc, lhs_sb.getAddr(), rhs_sb.getAddr());
+      copyVarHLFIR(loc, lhs_sb, rhs_sb);
     else
       copyVarFIR(loc, sym, lhs_sb, rhs_sb);
   }
 
-  void copyVarHLFIR(mlir::Location loc, mlir::Value dst, mlir::Value src) {
+  void copyVarHLFIR(mlir::Location loc, Fortran::lower::SymbolBox dst,
+                    Fortran::lower::SymbolBox src) {
     assert(lowerToHighLevelFIR());
-    hlfir::Entity lhs{dst};
-    hlfir::Entity rhs{src};
+    hlfir::Entity lhs{dst.getAddr()};
+    hlfir::Entity rhs{src.getAddr()};
     // Temporary_lhs is set to true in hlfir.assign below to avoid user
     // assignment to be used and finalization to be called on the LHS.
     // This may or may not be correct but mimics the current behaviour
@@ -1082,7 +1081,22 @@ class FirConverter : public Fortran::lower::AbstractConverter {
           /*keepLhsLengthInAllocatableAssignment=*/false,
           /*temporary_lhs=*/true);
     };
-    if (lhs.isAllocatable()) {
+
+    bool isBoxAllocatable = dst.match(
+        [](const fir::MutableBoxValue &box) { return box.isAllocatable(); },
+        [](const fir::FortranVariableOpInterface &box) {
+          return fir::FortranVariableOpInterface(box).isAllocatable();
+        },
+        [](const auto &box) { return false; });
+
+    bool isBoxPointer = dst.match(
+        [](const fir::MutableBoxValue &box) { return box.isPointer(); },
+        [](const fir::FortranVariableOpInterface &box) {
+          return fir::FortranVariableOpInterface(box).isPointer();
+        },
+        [](const auto &box) { return false; });
+
+    if (isBoxAllocatable) {
       // Deep copy allocatable if it is allocated.
       // Note that when allocated, the RHS is already allocated with the LHS
       // shape for copy on entry in createHostAssociateVarClone.
@@ -1097,7 +1111,7 @@ class FirConverter : public Fortran::lower::AbstractConverter {
             copyData(lhs, rhs);
           })
           .end();
-    } else if (lhs.isPointer()) {
+    } else if (isBoxPointer) {
       // Set LHS target to the target of RHS (do not copy the RHS
       // target data into the LHS target storage).
       auto loadVal = builder->create<fir::LoadOp>(loc, rhs);

flang/lib/Lower/OpenMP/DataSharingProcessor.cpp

@@ -50,6 +50,7 @@ void DataSharingProcessor::processStep2(mlir::Operation *op, bool isLoop) {
 }
 
 void DataSharingProcessor::insertDeallocs() {
+  // TODO Extend delayed privatization to include a `dealloc` region.
   for (const Fortran::semantics::Symbol *sym : privatizedSymbols)
     if (Fortran::semantics::IsAllocatable(sym->GetUltimate())) {
       converter.createHostAssociateVarCloneDealloc(*sym);
@@ -367,6 +368,7 @@ void DataSharingProcessor::doPrivatize(const Fortran::semantics::Symbol *sym) {
         symLoc, uniquePrivatizerName, symType,
         isFirstPrivate ? mlir::omp::DataSharingClauseType::FirstPrivate
                        : mlir::omp::DataSharingClauseType::Private);
+    fir::ExtendedValue symExV = converter.getSymbolExtendedValue(*sym);
 
     symTable->pushScope();
 
@@ -377,7 +379,8 @@ void DataSharingProcessor::doPrivatize(const Fortran::semantics::Symbol *sym) {
           &allocRegion, /*insertPt=*/{}, symType, symLoc);
 
       firOpBuilder.setInsertionPointToEnd(allocEntryBlock);
-      symTable->addSymbol(*sym, allocRegion.getArgument(0));
+      symTable->addSymbol(*sym,
+                          fir::substBase(symExV, allocRegion.getArgument(0)));
       symTable->pushScope();
       cloneSymbol(sym);
       firOpBuilder.create<mlir::omp::YieldOp>(
@@ -394,10 +397,12 @@ void DataSharingProcessor::doPrivatize(const Fortran::semantics::Symbol *sym) {
       mlir::Block *copyEntryBlock = firOpBuilder.createBlock(
           &copyRegion, /*insertPt=*/{}, {symType, symType}, {symLoc, symLoc});
       firOpBuilder.setInsertionPointToEnd(copyEntryBlock);
-      symTable->addSymbol(*sym, copyRegion.getArgument(0),
+      symTable->addSymbol(*sym,
+                          fir::substBase(symExV, copyRegion.getArgument(0)),
                           /*force=*/true);
       symTable->pushScope();
-      symTable->addSymbol(*sym, copyRegion.getArgument(1));
+      symTable->addSymbol(*sym,
+                          fir::substBase(symExV, copyRegion.getArgument(1)));
       auto ip = firOpBuilder.saveInsertionPoint();
       copyFirstPrivateSymbol(sym, &ip);
 

flang/test/Lower/OpenMP/delayed-privatization-allocatable-firstprivate.f90

@@ -0,0 +1,36 @@
+! Test delayed privatization for allocatables: `firstprivate`.
+
+! RUN: %flang_fc1 -emit-hlfir -fopenmp -mmlir --openmp-enable-delayed-privatization \
+! RUN:   -o - %s 2>&1 | FileCheck %s
+! RUN: bbc -emit-hlfir -fopenmp --openmp-enable-delayed-privatization -o - %s 2>&1 |\
+! RUN:   FileCheck %s
+
+subroutine delayed_privatization_allocatable
+  implicit none
+  integer, allocatable :: var1
+
+!$omp parallel firstprivate(var1)
+  var1 = 10
+!$omp end parallel
+end subroutine
+
+! CHECK-LABEL: omp.private {type = firstprivate}
+! CHECK-SAME: @[[PRIVATIZER_SYM:.*]] : [[TYPE:!fir.ref<!fir.box<!fir.heap<i32>>>]] alloc {
+
+! CHECK-NEXT: ^bb0(%[[PRIV_ARG:.*]]: [[TYPE]]):
+
+! CHECK: } copy {
+! CHECK: ^bb0(%[[PRIV_ORIG_ARG:.*]]: [[TYPE]], %[[PRIV_PRIV_ARG:.*]]: [[TYPE]]):
+
+! CHECK-NEXT:  %[[PRIV_BASE_VAL:.*]] = fir.load %[[PRIV_PRIV_ARG]]
+! CHECK-NEXT:  %[[PRIV_BASE_BOX:.*]] = fir.box_addr %[[PRIV_BASE_VAL]]
+! CHECK-NEXT:  %[[PRIV_BASE_ADDR:.*]] = fir.convert %[[PRIV_BASE_BOX]]
+! CHECK-NEXT:  %[[C0:.*]] = arith.constant 0 : i64
+! CHECK-NEXT:  %[[COPY_COND:.*]] = arith.cmpi ne, %[[PRIV_BASE_ADDR]], %[[C0]] : i64
+
+! CHECK-NEXT:  fir.if %[[COPY_COND]] {
+! CHECK-NEXT:    %[[ORIG_BASE_VAL:.*]] = fir.load %[[PRIV_ORIG_ARG]]
+! CHECK-NEXT:    %[[ORIG_BASE_ADDR:.*]] = fir.box_addr %[[ORIG_BASE_VAL]]
+! CHECK-NEXT:    %[[ORIG_BASE_LD:.*]] = fir.load %[[ORIG_BASE_ADDR]]
+! CHECK-NEXT:    hlfir.assign %[[ORIG_BASE_LD]] to %[[PRIV_BASE_BOX]] temporary_lhs
+! CHECK-NEXT:  }

flang/test/Lower/OpenMP/delayed-privatization-allocatable-private.f90

@@ -0,0 +1,43 @@
+! Test delayed privatization for allocatables: `private`.
+
+! RUN: %flang_fc1 -emit-hlfir -fopenmp -mmlir --openmp-enable-delayed-privatization \
+! RUN:   -o - %s 2>&1 | FileCheck %s
+! RUN: bbc -emit-hlfir -fopenmp --openmp-enable-delayed-privatization -o - %s 2>&1 |\
+! RUN:   FileCheck %s
+
+subroutine delayed_privatization_allocatable
+  implicit none
+  integer, allocatable :: var1
+
+!$omp parallel private(var1)
+  var1 = 10
+!$omp end parallel
+end subroutine
+
+! CHECK-LABEL: omp.private {type = private}
+! CHECK-SAME: @[[PRIVATIZER_SYM:.*]] : [[TYPE:!fir.ref<!fir.box<!fir.heap<i32>>>]] alloc {
+
+! CHECK-NEXT: ^bb0(%[[PRIV_ARG:.*]]: [[TYPE]]):
+
+! CHECK-NEXT:   %[[PRIV_ALLOC:.*]] = fir.alloca !fir.box<!fir.heap<i32>> {bindc_name = "var1", pinned, uniq_name = "_QFdelayed_privatization_allocatableEvar1"}
+
+! CHECK-NEXT:   %[[PRIV_ARG_VAL:.*]] = fir.load %[[PRIV_ARG]] : !fir.ref<!fir.box<!fir.heap<i32>>>
+! CHECK-NEXT:   %[[PRIV_ARG_BOX:.*]] = fir.box_addr %[[PRIV_ARG_VAL]] : (!fir.box<!fir.heap<i32>>) -> !fir.heap<i32>
+! CHECK-NEXT:   %[[PRIV_ARG_ADDR:.*]] = fir.convert %[[PRIV_ARG_BOX]] : (!fir.heap<i32>) -> i64
+! CHECK-NEXT:   %[[C0:.*]] = arith.constant 0 : i64
+! CHECK-NEXT:   %[[ALLOC_COND:.*]] = arith.cmpi ne, %[[PRIV_ARG_ADDR]], %[[C0]] : i64
+
+! CHECK-NEXT:   fir.if %[[ALLOC_COND]] {
+! CHECK-NEXT:     %[[PRIV_ALLOCMEM:.*]] = fir.allocmem i32 {fir.must_be_heap = true, uniq_name = "_QFdelayed_privatization_allocatableEvar1.alloc"}
+! CHECK-NEXT:     %[[PRIV_ALLOCMEM_BOX:.*]] = fir.embox %[[PRIV_ALLOCMEM]] : (!fir.heap<i32>) -> !fir.box<!fir.heap<i32>>
+! CHECK-NEXT:     fir.store %[[PRIV_ALLOCMEM_BOX]] to %[[PRIV_ALLOC]] : !fir.ref<!fir.box<!fir.heap<i32>>>
+! CHECK-NEXT:   } else {
+! CHECK-NEXT:     %[[ZERO_BITS:.*]] = fir.zero_bits !fir.heap<i32>
+! CHECK-NEXT:     %[[ZERO_BOX:.*]] = fir.embox %[[ZERO_BITS]] : (!fir.heap<i32>) -> !fir.box<!fir.heap<i32>>
+! CHECK-NEXT:     fir.store %[[ZERO_BOX]] to %[[PRIV_ALLOC]] : !fir.ref<!fir.box<!fir.heap<i32>>>
+! CHECK-NEXT:   }
+
+! CHECK-NEXT:   %[[PRIV_DECL:.*]]:2 = hlfir.declare %[[PRIV_ALLOC]]
+! CHECK-NEXT:   omp.yield(%[[PRIV_DECL]]#0 : [[TYPE]])
+
+! CHECK-NEXT: }

flang/test/Lower/OpenMP/delayed-privatization-pointer.f90

@@ -0,0 +1,31 @@
+! Test delayed privatization for pointers: `private`.
+
+! RUN: %flang_fc1 -emit-hlfir -fopenmp -mmlir --openmp-enable-delayed-privatization \
+! RUN:   -o - %s 2>&1 | FileCheck %s
+! RUN: bbc -emit-hlfir -fopenmp --openmp-enable-delayed-privatization -o - %s 2>&1 |\
+! RUN:   FileCheck %s
+
+subroutine delayed_privatization_pointer
+  implicit none
+  integer, pointer :: var1
+
+!$omp parallel firstprivate(var1)
+  var1 = 10
+!$omp end parallel
+end subroutine
+
+! CHECK-LABEL: omp.private {type = firstprivate}
+! CHECK-SAME: @[[PRIVATIZER_SYM:.*]] : [[TYPE:!fir.ref<!fir.box<!fir.ptr<i32>>>]] alloc {
+
+! CHECK-NEXT: ^bb0(%[[PRIV_ARG:.*]]: [[TYPE]]):
+
+! CHECK-NEXT:   %[[PRIV_ALLOC:.*]] = fir.alloca !fir.box<!fir.ptr<i32>> {bindc_name = "var1", pinned, uniq_name = "_QFdelayed_privatization_pointerEvar1"}
+! CHECK-NEXT:   %[[PRIV_DECL:.*]]:2 = hlfir.declare %[[PRIV_ALLOC]]
+! CHECK-NEXT:   omp.yield(%[[PRIV_DECL]]#0 : [[TYPE]])
+
+! CHECK-NEXT: } copy {
+! CHECK: ^bb0(%[[PRIV_ORIG_ARG:.*]]: [[TYPE]], %[[PRIV_PRIV_ARG:.*]]: [[TYPE]]):
+! CHECK-NEXT:    %[[ORIG_BASE_VAL:.*]] = fir.load %[[PRIV_ORIG_ARG]]
+ ! CHECK-NEXT:   fir.store %[[ORIG_BASE_VAL]] to %[[PRIV_PRIV_ARG]] : !fir.ref<!fir.box<!fir.ptr<i32>>>
+! CHECK-NEXT:   omp.yield(%[[PRIV_PRIV_ARG]] : [[TYPE]])
+! CHECK-NEXT: }