Merged main:b83b28779ee56236aaf8827398f889334abbd28d into amd-gfx:6670c73ea871

Local branch amd-gfx 6670c73 [AMDGPU][Waterfall] Put exec save in the loop header
Remote branch main b83b287 [RISCV] Make Zhinx and Zvfh imply Zhinxmin and Zvfhmin respectively (llvm#75735)

Author: SC llvm team

clang/lib/CodeGen/CGBuiltin.cpp

@@ -232,19 +232,19 @@ static Value *MakeBinaryAtomicValue(
 
 static Value *EmitNontemporalStore(CodeGenFunction &CGF, const CallExpr *E) {
   Value *Val = CGF.EmitScalarExpr(E->getArg(0));
-  Value *Address = CGF.EmitScalarExpr(E->getArg(1));
+  Address Addr = CGF.EmitPointerWithAlignment(E->getArg(1));
 
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
-  LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getArg(0)->getType());
+  LValue LV = CGF.MakeAddrLValue(Addr, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);
   return nullptr;
 }
 
 static Value *EmitNontemporalLoad(CodeGenFunction &CGF, const CallExpr *E) {
-  Value *Address = CGF.EmitScalarExpr(E->getArg(0));
+  Address Addr = CGF.EmitPointerWithAlignment(E->getArg(0));
 
-  LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getType());
+  LValue LV = CGF.MakeAddrLValue(Addr, E->getType());
   LV.setNontemporal(true);
   return CGF.EmitLoadOfScalar(LV, E->getExprLoc());
 }

clang/lib/Format/Format.cpp

@@ -1315,7 +1315,6 @@ static void expandPresetsBraceWrapping(FormatStyle &Expanded) {
     Expanded.BraceWrapping.AfterStruct = true;
     Expanded.BraceWrapping.AfterUnion = true;
     Expanded.BraceWrapping.AfterExternBlock = true;
-    Expanded.IndentExternBlock = FormatStyle::IEBS_AfterExternBlock;
     Expanded.BraceWrapping.SplitEmptyFunction = true;
     Expanded.BraceWrapping.SplitEmptyRecord = false;
     break;
@@ -1335,7 +1334,6 @@ static void expandPresetsBraceWrapping(FormatStyle &Expanded) {
     Expanded.BraceWrapping.AfterStruct = true;
     Expanded.BraceWrapping.AfterUnion = true;
     Expanded.BraceWrapping.AfterExternBlock = true;
-    Expanded.IndentExternBlock = FormatStyle::IEBS_AfterExternBlock;
     Expanded.BraceWrapping.BeforeCatch = true;
     Expanded.BraceWrapping.BeforeElse = true;
     Expanded.BraceWrapping.BeforeLambdaBody = true;
@@ -1350,7 +1348,6 @@ static void expandPresetsBraceWrapping(FormatStyle &Expanded) {
     Expanded.BraceWrapping.AfterObjCDeclaration = true;
     Expanded.BraceWrapping.AfterStruct = true;
     Expanded.BraceWrapping.AfterExternBlock = true;
-    Expanded.IndentExternBlock = FormatStyle::IEBS_AfterExternBlock;
     Expanded.BraceWrapping.BeforeCatch = true;
     Expanded.BraceWrapping.BeforeElse = true;
     Expanded.BraceWrapping.BeforeLambdaBody = true;
@@ -1375,7 +1372,6 @@ static void expandPresetsBraceWrapping(FormatStyle &Expanded) {
         /*SplitEmptyFunction=*/true,
         /*SplitEmptyRecord=*/true,
         /*SplitEmptyNamespace=*/true};
-    Expanded.IndentExternBlock = FormatStyle::IEBS_AfterExternBlock;
     break;
   case FormatStyle::BS_WebKit:
     Expanded.BraceWrapping.AfterFunction = true;
@@ -1909,7 +1905,6 @@ FormatStyle getMicrosoftStyle(FormatStyle::LanguageKind Language) {
   Style.BraceWrapping.AfterObjCDeclaration = true;
   Style.BraceWrapping.AfterStruct = true;
   Style.BraceWrapping.AfterExternBlock = true;
-  Style.IndentExternBlock = FormatStyle::IEBS_AfterExternBlock;
   Style.BraceWrapping.BeforeCatch = true;
   Style.BraceWrapping.BeforeElse = true;
   Style.BraceWrapping.BeforeWhile = false;

clang/test/CodeGen/Nontemporal.cpp

@@ -46,3 +46,17 @@ void test_all_sizes(void)                 // CHECK-LABEL: test_all_sizes
   vf2 = __builtin_nontemporal_load(&vf1); // CHECK: load <4 x float>{{.*}}align 16, !nontemporal
   vc2 = __builtin_nontemporal_load(&vc1); // CHECK: load <8 x i8>{{.*}}align 8, !nontemporal
 }
+
+struct S { char c[16]; };
+S x;
+
+typedef int v4si __attribute__ ((vector_size(16)));
+
+// CHECK-LABEL: define void @_Z14test_alignmentv()
+// CHECK: load <4 x i32>, ptr @x, align 1, !nontemporal
+// CHECK: store <4 x i32> %1, ptr @x, align 1, !nontemporal
+
+void test_alignment() {
+ auto t =  __builtin_nontemporal_load((v4si*)x.c);
+ __builtin_nontemporal_store(t, (v4si*)x.c);
+}

clang/unittests/Format/FormatTest.cpp

@@ -4571,6 +4571,13 @@ TEST_F(FormatTest, IndentExternBlockStyle) {
                "}",
                Style);
 
+  Style.BreakBeforeBraces = FormatStyle::BS_Allman;
+  verifyFormat("extern \"C\"\n"
+               "{\n"
+               "int i;\n"
+               "}",
+               Style);
+
   Style.BreakBeforeBraces = FormatStyle::BS_Custom;
   Style.BraceWrapping.AfterExternBlock = true;
   Style.IndentExternBlock = FormatStyle::IEBS_Indent;

compiler-rt/cmake/Modules/AddCompilerRT.cmake

@@ -670,13 +670,18 @@ macro(add_custom_libcxx name prefix)
   get_property(CXX_FLAGS CACHE CMAKE_CXX_FLAGS PROPERTY VALUE)
   set(LIBCXX_CXX_FLAGS "${LIBCXX_CXX_FLAGS} ${CXX_FLAGS}")
 
+  if(CMAKE_VERBOSE_MAKEFILE)
+    set(verbose -DCMAKE_VERBOSE_MAKEFILE=ON)
+  endif()
+
   ExternalProject_Add(${name}
     DEPENDS ${name}-clobber ${LIBCXX_DEPS}
     PREFIX ${CMAKE_CURRENT_BINARY_DIR}/${name}
     SOURCE_DIR ${LLVM_MAIN_SRC_DIR}/../runtimes
     BINARY_DIR ${prefix}
     CMAKE_ARGS ${CMAKE_PASSTHROUGH_VARIABLES}
                ${compiler_args}
+               ${verbose}
                -DCMAKE_C_FLAGS=${LIBCXX_C_FLAGS}
                -DCMAKE_CXX_FLAGS=${LIBCXX_CXX_FLAGS}
                -DCMAKE_BUILD_TYPE=Release

lldb/bindings/python/python-typemaps.swig

@@ -110,7 +110,7 @@ AND call SWIG_fail at the same time, because it will result in a double free.
         SWIG_fail;
       }
 
-      if (llvm::StringRef(type_name.get()).startswith("SB")) {
+      if (llvm::StringRef(type_name.get()).starts_with("SB")) {
         std::string error_msg = "Input type is invalid: " + type_name.get();
         PyErr_SetString(PyExc_TypeError, error_msg.c_str());
         SWIG_fail;

llvm/cmake/modules/LLVMExternalProjectUtils.cmake

@@ -319,6 +319,10 @@ function(llvm_ExternalProject_Add name source_dir)
     list(APPEND compiler_args -DCMAKE_ASM_COMPILER_TARGET=${ARG_TARGET_TRIPLE})
   endif()
 
+  if(CMAKE_VERBOSE_MAKEFILE)
+    set(verbose -DCMAKE_VERBOSE_MAKEFILE=ON)
+  endif()
+
   ExternalProject_Add(${name}
     DEPENDS ${ARG_DEPENDS} llvm-config
     ${name}-clobber
@@ -330,6 +334,7 @@ function(llvm_ExternalProject_Add name source_dir)
     CMAKE_ARGS ${${nameCanon}_CMAKE_ARGS}
                --no-warn-unused-cli
                ${compiler_args}
+               ${verbose}
                -DCMAKE_INSTALL_PREFIX=${CMAKE_INSTALL_PREFIX}
                ${sysroot_arg}
                -DLLVM_BINARY_DIR=${PROJECT_BINARY_DIR}

llvm/docs/AliasAnalysis.rst

@@ -207,7 +207,7 @@ Writing a new ``AliasAnalysis`` Implementation
 
 Writing a new alias analysis implementation for LLVM is quite straight-forward.
 There are already several implementations that you can use for examples, and the
-following information should help fill in any details.  For a examples, take a
+following information should help fill in any details.  For examples, take a
 look at the `various alias analysis implementations`_ included with LLVM.
 
 Different Pass styles

llvm/docs/ConvergentOperations.rst

@@ -607,7 +607,7 @@ those in the caller.
    only if both threads entered the function by executing converged
    dynamic instances of the call-site.
 
-This intrinsic can occur at most once in a function, and only in the the entry
+This intrinsic can occur at most once in a function, and only in the entry
 block of the function. If this intrinsic occurs in a basic block, then it must
 precede any other convergent operation in the same basic block.
 

llvm/docs/JITLink.rst

@@ -466,7 +466,7 @@ finally transferring linked memory to the executing process.
 
       Calls the ``JITLinkContext``'s ``JITLinkMemoryManager`` to allocate both
       working and target memory for the graph. As part of this process the
-      ``JITLinkMemoryManager`` will update the the addresses of all nodes
+      ``JITLinkMemoryManager`` will update the addresses of all nodes
       defined in the graph to their assigned target address.
 
       Note: This step only updates the addresses of nodes defined in this graph.

llvm/docs/LangRef.rst

@@ -1515,7 +1515,7 @@ Currently, only the following parameter attributes are defined:
     over-alignment specification through language attributes).
 
 ``allocalign``
-    The function parameter marked with this attribute is is the alignment in bytes of the
+    The function parameter marked with this attribute is the alignment in bytes of the
     newly allocated block returned by this function. The returned value must either have
     the specified alignment or be the null pointer. The return value MAY be more aligned
     than the requested alignment, but not less aligned.  Invalid (e.g. non-power-of-2)
@@ -22798,7 +22798,7 @@ Semantics:
 
 The '``llvm.vp.fcmp``' compares its first two operands according to the
 condition code given as the third operand. The operands are compared element by
-element on each enabled lane, where the the semantics of the comparison are
+element on each enabled lane, where the semantics of the comparison are
 defined :ref:`according to the condition code <fcmp_md_cc_sem>`. Masked-off
 lanes are ``poison``.
 
@@ -22856,7 +22856,7 @@ Semantics:
 
 The '``llvm.vp.icmp``' compares its first two operands according to the
 condition code given as the third operand. The operands are compared element by
-element on each enabled lane, where the the semantics of the comparison are
+element on each enabled lane, where the semantics of the comparison are
 defined :ref:`according to the condition code <icmp_md_cc_sem>`. Masked-off
 lanes are ``poison``.
 

llvm/docs/NVPTXUsage.rst

@@ -329,7 +329,7 @@ optimization pipeline before dead-code elimination.
 The NVPTX TargetMachine knows how to schedule ``NVVMReflect`` at the beginning
 of your pass manager; just use the following code when setting up your pass
 manager and the PassBuilder will use ``registerPassBuilderCallbacks`` to let
-NVPTXTargetMachine::registerPassBuilderCallbacks add the the pass to the
+NVPTXTargetMachine::registerPassBuilderCallbacks add the pass to the
 pass manager:
 
 .. code-block:: c++

llvm/docs/TableGen/ProgRef.rst

@@ -661,7 +661,7 @@ The argument values can be specified in two forms:
   argument with name ``a`` and ``a1`` will be assigned to the argument with
   name ``b``.
 
-Required arguments can alse be specified as named argument.
+Required arguments can also be specified as named argument.
 
 Note that the argument can only be specified once regardless of the way (named
 or positional) to specify and positional arguments should be put before named

llvm/include/llvm/ADT/StringRef.h

@@ -258,7 +258,9 @@ namespace llvm {
       return Length >= Prefix.Length &&
              compareMemory(Data, Prefix.Data, Prefix.Length) == 0;
     }
-    [[nodiscard]] bool startswith(StringRef Prefix) const {
+    [[nodiscard]] LLVM_DEPRECATED(
+        "Use starts_with instead",
+        "starts_with") bool startswith(StringRef Prefix) const {
       return starts_with(Prefix);
     }
 
@@ -271,7 +273,9 @@ namespace llvm {
              compareMemory(end() - Suffix.Length, Suffix.Data, Suffix.Length) ==
                  0;
     }
-    [[nodiscard]] bool endswith(StringRef Suffix) const {
+    [[nodiscard]] LLVM_DEPRECATED(
+        "Use ends_with instead",
+        "ends_with") bool endswith(StringRef Suffix) const {
       return ends_with(Suffix);
     }
 

llvm/include/llvm/Analysis/AliasAnalysis.h

@@ -64,7 +64,6 @@ class LoopInfo;
 class PreservedAnalyses;
 class TargetLibraryInfo;
 class Value;
-template <typename> class SmallPtrSetImpl;
 
 /// The possible results of an alias query.
 ///

llvm/include/llvm/Analysis/AliasAnalysisEvaluator.h

@@ -29,7 +29,6 @@
 namespace llvm {
 class AAResults;
 class Function;
-class FunctionPass;
 
 class AAEvaluator : public PassInfoMixin<AAEvaluator> {
   int64_t FunctionCount = 0;

llvm/include/llvm/Analysis/InstructionSimplify.h

@@ -45,7 +45,6 @@ class DominatorTree;
 class Function;
 class Instruction;
 struct LoopStandardAnalysisResults;
-class MDNode;
 class Pass;
 template <class T, unsigned n> class SmallSetVector;
 class TargetLibraryInfo;

llvm/include/llvm/CodeGen/AccelTable.h

@@ -103,7 +103,6 @@
 namespace llvm {
 
 class AsmPrinter;
-class DwarfUnit;
 class DwarfDebug;
 class DwarfTypeUnit;
 class MCSymbol;

llvm/include/llvm/CodeGen/AntiDepBreaker.h

@@ -19,7 +19,6 @@
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/Support/Compiler.h"
-#include <cassert>
 #include <utility>
 #include <vector>
 

llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h

@@ -28,11 +28,9 @@
 namespace llvm {
 
 class GISelChangeObserver;
-class APFloat;
 class APInt;
 class ConstantFP;
 class GPtrAdd;
-class GStore;
 class GZExtLoad;
 class MachineIRBuilder;
 class MachineInstrBuilder;

llvm/include/llvm/Config/llvm-config.h.cmake

@@ -16,7 +16,7 @@
 
 /* Indicate that this is LLVM compiled from the amd-gfx branch. */
 #define LLVM_HAVE_BRANCH_AMD_GFX
-#define LLVM_MAIN_REVISION 484113
+#define LLVM_MAIN_REVISION 484145
 
 /* Define if LLVM_ENABLE_DUMP is enabled */
 #cmakedefine LLVM_ENABLE_DUMP

llvm/include/llvm/IR/IntrinsicsRISCV.td

@@ -702,7 +702,7 @@ let TargetPrefix = "riscv" in {
                      LLVMMatchType<2>, LLVMMatchType<2>],
                     [ImmArg<ArgIndex<4>>,ImmArg<ArgIndex<6>>, IntrNoMem, IntrHasSideEffects]>,
                     RISCVVIntrinsic {
-    let VLOperand = 6;
+    let VLOperand = 5;
   }
   // For Saturating binary operations.
   // The destination vector type is NOT the same as first source vector.
@@ -1879,3 +1879,4 @@ let TargetPrefix = "riscv" in {
 //===----------------------------------------------------------------------===//
 include "llvm/IR/IntrinsicsRISCVXTHead.td"
 include "llvm/IR/IntrinsicsRISCVXsf.td"
+include "llvm/IR/IntrinsicsRISCVXCV.td"

llvm/include/llvm/IR/IntrinsicsRISCVXCV.td

@@ -0,0 +1,37 @@
+//===- IntrinsicsRISCVXCV.td - CORE-V intrinsics -----------*- tablegen -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines all of the CORE-V vendor intrinsics for RISC-V.
+//
+//===----------------------------------------------------------------------===//
+
+class ScalarCoreVBitManipGprGprIntrinsic
+    : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+                            [IntrNoMem, IntrSpeculatable]>;
+
+class ScalarCoreVBitManipGprIntrinsic
+    : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty],
+                            [IntrNoMem, IntrSpeculatable]>;
+
+let TargetPrefix = "riscv" in {
+  def int_riscv_cv_bitmanip_extract : ScalarCoreVBitManipGprGprIntrinsic;
+  def int_riscv_cv_bitmanip_extractu : ScalarCoreVBitManipGprGprIntrinsic;
+  def int_riscv_cv_bitmanip_bclr : ScalarCoreVBitManipGprGprIntrinsic;
+  def int_riscv_cv_bitmanip_bset : ScalarCoreVBitManipGprGprIntrinsic;
+
+  def int_riscv_cv_bitmanip_insert
+    : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+                            [IntrNoMem, IntrSpeculatable]>;
+
+  def int_riscv_cv_bitmanip_clb : ScalarCoreVBitManipGprIntrinsic;
+
+  def int_riscv_cv_bitmanip_bitrev
+    : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+                            [IntrNoMem, IntrWillReturn, IntrSpeculatable,
+                            ImmArg<ArgIndex<1>>, ImmArg<ArgIndex<2>>]>;
+} // TargetPrefix = "riscv"

llvm/lib/CodeGen/AsmPrinter/DebugLocStream.h

@@ -18,7 +18,6 @@ namespace llvm {
 class AsmPrinter;
 class DbgVariable;
 class DwarfCompileUnit;
-class MachineInstr;
 class MCSymbol;
 
 /// Byte stream of .debug_loc entries.

llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h

@@ -25,7 +25,6 @@
 #include "llvm/CodeGen/LexicalScopes.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/Support/Casting.h"
-#include <cassert>
 #include <cstdint>
 #include <memory>
 

llvm/lib/CodeGen/AsmPrinter/DwarfFile.h

@@ -28,7 +28,6 @@ class DbgLabel;
 class DINode;
 class DILocalScope;
 class DwarfCompileUnit;
-class DwarfTypeUnit;
 class DwarfUnit;
 class LexicalScope;
 class MCSection;

llvm/lib/CodeGen/MachineStableHash.cpp

@@ -14,7 +14,6 @@
 #include "llvm/CodeGen/MachineStableHash.h"
 #include "llvm/ADT/APFloat.h"
 #include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"

llvm/lib/IR/Metadata.cpp

@@ -1566,7 +1566,7 @@ void Instruction::updateDIAssignIDMapping(DIAssignID *ID) {
            "Expect existing attachment to be mapped");
 
     auto &InstVec = InstrsIt->second;
-    auto *InstIt = std::find(InstVec.begin(), InstVec.end(), this);
+    auto *InstIt = llvm::find(InstVec, this);
     assert(InstIt != InstVec.end() &&
            "Expect instruction to be mapped to attachment");
     // The vector contains a ptr to this. If this is the only element in the