merge main into amd-staging

Change-Id: Id0b4149c9d730a84fc55bc3ed2bf205f54788576

Author: ronlieb

bolt/docs/CommandLineArgumentReference.md

@@ -0,0 +1,149 @@
+#!/usr/bin/env python3
+# A tool to parse the output of `llvm-bolt --help-hidden` and update the
+# documentation in CommandLineArgumentReference.md automatically.
+# Run from the directory in which this file is located to update the docs.
+
+import subprocess
+from textwrap import wrap
+
+LINE_LIMIT = 80
+
+
+def wrap_text(text, indent, limit=LINE_LIMIT):
+    wrapped_lines = wrap(text, width=limit - len(indent))
+    wrapped_text = ("\n" + indent).join(wrapped_lines)
+    return wrapped_text
+
+
+def add_info(sections, section, option, description):
+    indent = "  "
+    wrapped_description = "\n".join(
+        [
+            wrap_text(line, indent) if len(line) > LINE_LIMIT else line
+            for line in description
+        ]
+    )
+    sections[section].append((option, indent + wrapped_description))
+
+
+def parse_bolt_options(output):
+    section_headers = [
+        "Generic options:",
+        "Output options:",
+        "BOLT generic options:",
+        "BOLT optimization options:",
+        "BOLT options in relocation mode:",
+        "BOLT instrumentation options:",
+        "BOLT printing options:",
+    ]
+
+    sections = {key: [] for key in section_headers}
+    current_section, prev_section = None, None
+    option, description = None, []
+
+    for line in output.split("\n"):
+        cleaned_line = line.strip()
+
+        if cleaned_line.casefold() in map(str.casefold, section_headers):
+            if prev_section != None:  # Save last option from prev section
+                add_info(sections, current_section, option, description)
+                option, description = None, []
+
+            cleaned_line = cleaned_line.split()
+            # Apply lowercase to all words except the first one
+            cleaned_line = [cleaned_line[0]] + [
+                word.lower() for word in cleaned_line[1:]
+            ]
+            # Join the words back together into a string
+            cleaned_line = " ".join(cleaned_line)
+
+            current_section = cleaned_line
+            prev_section = current_section
+            continue
+
+        if cleaned_line.startswith("-"):
+            if option and description:
+                # Join description lines, adding an extra newline for
+                # sub-options that start with '='
+                add_info(sections, current_section, option, description)
+                option, description = None, []
+
+            parts = cleaned_line.split("  ", 1)
+            if len(parts) > 1:
+                option = parts[0].strip()
+                descr = parts[1].strip()
+                descr = descr[2].upper() + descr[3:]
+                description = [descr]
+                if option.startswith("--print") or option.startswith("--time"):
+                    current_section = "BOLT printing options:"
+                elif prev_section != None:
+                    current_section = prev_section
+            continue
+
+        if cleaned_line.startswith("="):
+            parts = cleaned_line.split(maxsplit=1)
+            # Split into two parts: sub-option and description
+            if len(parts) == 2:
+                # Rejoin with a single space
+                cleaned_line = parts[0] + " " + parts[1].rstrip()
+            description.append(cleaned_line)
+        elif cleaned_line:  # Multiline description continuation
+            description.append(cleaned_line)
+
+    add_info(sections, current_section, option, description)
+    return sections
+
+
+def generate_markdown(sections):
+    markdown_lines = [
+        "# BOLT - a post-link optimizer developed to speed up large applications\n",
+        "## SYNOPSIS\n",
+        "`llvm-bolt <executable> [-o outputfile] <executable>.bolt "
+        "[-data=perf.fdata] [options]`\n",
+        "## OPTIONS",
+    ]
+
+    for section, options in sections.items():
+        markdown_lines.append(f"\n### {section}")
+        if section == "BOLT instrumentation options:":
+            markdown_lines.append(
+                f"\n`llvm-bolt <executable> -instrument"
+                " [-o outputfile] <instrumented-executable>`"
+            )
+        for option, desc in options:
+            markdown_lines.append(f"\n- `{option}`\n")
+            # Split description into lines to handle sub-options
+            desc_lines = desc.split("\n")
+            for line in desc_lines:
+                if line.startswith("="):
+                    # Sub-option: correct formatting with bullet
+                    sub_option, sub_desc = line[1:].split(" ", 1)
+                    markdown_lines.append(f"  - `{sub_option}`: {sub_desc[4:]}")
+                else:
+                    # Regular line of description
+                    if line[2:].startswith("<"):
+                        line = line.replace("<", "").replace(">", "")
+                    markdown_lines.append(f"{line}")
+
+    return "\n".join(markdown_lines)
+
+
+def main():
+    try:
+        help_output = subprocess.run(
+            ["llvm-bolt", "--help-hidden"], capture_output=True, text=True, check=True
+        ).stdout
+    except subprocess.CalledProcessError as e:
+        print("Failed to execute llvm-bolt --help:")
+        print(e)
+        return
+
+    sections = parse_bolt_options(help_output)
+    markdown = generate_markdown(sections)
+
+    with open("CommandLineArgumentReference.md", "w") as md_file:
+        md_file.write(markdown)
+
+
+if __name__ == "__main__":
+    main()

bolt/docs/generate_doc.py

@@ -352,7 +352,7 @@ static cl::opt<bool> CreateDebugNames(
 
 static cl::opt<bool>
     DebugSkeletonCu("debug-skeleton-cu",
-                    cl::desc("prints out offsetrs for abbrev and debu_info of "
+                    cl::desc("prints out offsets for abbrev and debug_info of "
                              "Skeleton CUs that get patched."),
                     cl::ZeroOrMore, cl::Hidden, cl::init(false),
                     cl::cat(BoltCategory));

bolt/lib/Rewrite/DWARFRewriter.cpp

@@ -23,4 +23,4 @@ on the Clang forums:
   https://discourse.llvm.org/c/clang/
 
 If you find a bug in Clang, please file it in the LLVM bug tracker:
-  http://llvm.org/bugs/
+  https://github.com/llvm/llvm-project/issues

clang/README.txt

@@ -4430,9 +4430,9 @@ To generate SPIR-V binaries, Clang uses the external ``llvm-spirv`` tool from th
 Prior to the generation of SPIR-V binary with Clang, ``llvm-spirv``
 should be built or installed. Please refer to `the following instructions
 <https://github.com/KhronosGroup/SPIRV-LLVM-Translator#build-instructions>`_
-for more details. Clang will expect the ``llvm-spirv`` executable to
-be present in the ``PATH`` environment variable. Clang uses ``llvm-spirv``
-with `the widely adopted assembly syntax package
+for more details. Clang will look for ``llvm-spirv-<LLVM-major-version>`` and
+``llvm-spirv`` executables, in this order, in the ``PATH`` environment variable.
+Clang uses ``llvm-spirv`` with `the widely adopted assembly syntax package
 <https://github.com/KhronosGroup/SPIRV-LLVM-Translator/#build-with-spirv-tools>`_.
 
 `The versioning

clang/docs/UsersManual.rst

@@ -3135,17 +3135,42 @@ alpha.unix
 alpha.unix.BlockInCriticalSection (C)
 """""""""""""""""""""""""""""""""""""
 Check for calls to blocking functions inside a critical section.
-Applies to: ``lock, unlock, sleep, getc, fgets, read, recv, pthread_mutex_lock,``
-`` pthread_mutex_unlock, mtx_lock, mtx_timedlock, mtx_trylock, mtx_unlock, lock_guard, unique_lock``
+Blocking functions detected by this checker: ``sleep, getc, fgets, read, recv``.
+Critical section handling functions modelled by this checker: ``lock, unlock, pthread_mutex_lock, pthread_mutex_trylock, pthread_mutex_unlock, mtx_lock, mtx_timedlock, mtx_trylock, mtx_unlock, lock_guard, unique_lock``.
 
 .. code-block:: c
 
- void test() {
-   std::mutex m;
-   m.lock();
-   sleep(3); // warn: a blocking function sleep is called inside a critical
-             //       section
-   m.unlock();
+ void pthread_lock_example(pthread_mutex_t *m) {
+   pthread_mutex_lock(m); // note: entering critical section here
+   sleep(10); // warn: Call to blocking function 'sleep' inside of critical section
+   pthread_mutex_unlock(m);
+ }
+
+.. code-block:: cpp
+
+ void overlapping_critical_sections(mtx_t *m1, std::mutex &m2) {
+   std::lock_guard lg{m2}; // note: entering critical section here
+   mtx_lock(m1); // note: entering critical section here
+   sleep(10); // warn: Call to blocking function 'sleep' inside of critical section
+   mtx_unlock(m1);
+   sleep(10); // warn: Call to blocking function 'sleep' inside of critical section
+             // still inside of the critical section of the std::lock_guard
+ }
+
+**Limitations**
+
+* The ``trylock`` and ``timedlock`` versions of acquiring locks are currently assumed to always succeed.
+  This can lead to false positives.
+
+.. code-block:: c
+
+ void trylock_example(pthread_mutex_t *m) {
+   if (pthread_mutex_trylock(m) == 0) { // assume trylock always succeeds
+     sleep(10); // warn: Call to blocking function 'sleep' inside of critical section
+     pthread_mutex_unlock(m);
+   } else {
+     sleep(10); // false positive: Incorrect warning about blocking function inside critical section.
+   }
  }
 
 .. _alpha-unix-Chroot:

clang/docs/analyzer/checkers.rst

@@ -97,14 +97,6 @@ template <typename T> class CustomizableOptional {
   template <typename U> T value_or(U &&alt) && {
     return has_value() ? std::move(operator*()) : std::forward<U>(alt);
   }
-
-  // Allow conversion to std::optional<T>.
-  explicit operator std::optional<T> &() const & {
-    return *this ? **this : std::optional<T>();
-  }
-  explicit operator std::optional<T> &&() const && {
-    return *this ? std::move(**this) : std::optional<T>();
-  }
 };
 
 template <typename T>

clang/include/clang/Basic/CustomizableOptional.h

@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 #include "SPIRV.h"
 #include "CommonArgs.h"
+#include "clang/Basic/Version.h"
 #include "clang/Driver/Compilation.h"
 #include "clang/Driver/Driver.h"
 #include "clang/Driver/InputInfo.h"
@@ -32,8 +33,15 @@ void SPIRV::constructTranslateCommand(Compilation &C, const Tool &T,
 
   CmdArgs.append({"-o", Output.getFilename()});
 
-  const char *Exec =
-      C.getArgs().MakeArgString(T.getToolChain().GetProgramPath("llvm-spirv"));
+  // Try to find "llvm-spirv-<LLVM_VERSION_MAJOR>". Otherwise, fall back to
+  // plain "llvm-spirv".
+  using namespace std::string_literals;
+  auto VersionedTool = "llvm-spirv-"s + std::to_string(LLVM_VERSION_MAJOR);
+  std::string ExeCand = T.getToolChain().GetProgramPath(VersionedTool.c_str());
+  if (!llvm::sys::fs::can_execute(ExeCand))
+    ExeCand = T.getToolChain().GetProgramPath("llvm-spirv");
+
+  const char *Exec = C.getArgs().MakeArgString(ExeCand);
   C.addCommand(std::make_unique<Command>(JA, T, ResponseFileSupport::None(),
                                          Exec, CmdArgs, Input, Output));
 }

clang/lib/Driver/ToolChains/SPIRV.cpp

@@ -246,6 +246,27 @@ bool doesClauseApplyToDirective(OpenACCDirectiveKind DirectiveKind,
       return false;
     }
 
+  case OpenACCClauseKind::DeviceType:
+  case OpenACCClauseKind::DType:
+    switch (DirectiveKind) {
+    case OpenACCDirectiveKind::Parallel:
+    case OpenACCDirectiveKind::Serial:
+    case OpenACCDirectiveKind::Kernels:
+    case OpenACCDirectiveKind::Data:
+    case OpenACCDirectiveKind::Init:
+    case OpenACCDirectiveKind::Shutdown:
+    case OpenACCDirectiveKind::Set:
+    case OpenACCDirectiveKind::Update:
+    case OpenACCDirectiveKind::Loop:
+    case OpenACCDirectiveKind::Routine:
+    case OpenACCDirectiveKind::ParallelLoop:
+    case OpenACCDirectiveKind::SerialLoop:
+    case OpenACCDirectiveKind::KernelsLoop:
+      return true;
+    default:
+      return false;
+    }
+
   default:
     // Do nothing so we can go to the 'unimplemented' diagnostic instead.
     return true;

clang/lib/Sema/SemaOpenACC.cpp

@@ -36,15 +36,15 @@ ssize_t read(int fd, void *buf, size_t count);
 ssize_t recv(int sockfd, void *buf, size_t len, int flags);
 
 struct pthread_mutex_t;
-void pthread_mutex_lock(pthread_mutex_t *mutex);
-void pthread_mutex_trylock(pthread_mutex_t *mutex);
-void pthread_mutex_unlock(pthread_mutex_t *mutex);
+int pthread_mutex_lock(pthread_mutex_t *mutex);
+int pthread_mutex_trylock(pthread_mutex_t *mutex);
+int pthread_mutex_unlock(pthread_mutex_t *mutex);
 
 struct mtx_t;
-void mtx_lock(mtx_t *mutex);
-void mtx_timedlock(mtx_t *mutex);
-void mtx_trylock(mtx_t *mutex);
-void mtx_unlock(mtx_t *mutex);
+int mtx_lock(mtx_t *mutex);
+int mtx_timedlock(mtx_t *mutex);
+int mtx_trylock(mtx_t *mutex);
+int mtx_unlock(mtx_t *mutex);
 
 // global params for dummy function calls
 FILE *stream;
@@ -292,3 +292,20 @@ void testBlockInCriticalSectionUniqueLockNested() {
   testBlockInCriticalSectionUniqueLock(); // expected-note {{Calling 'testBlockInCriticalSectionUniqueLock'}}
   sleep(1); // no-warning
 }
+
+void testTrylockCurrentlyFalsePositive(pthread_mutex_t *m) {
+                                       // expected-note@+4 {{Assuming the condition is true}}
+                                       // expected-note@+3 {{Taking true branch}}
+                                       // expected-note@+2 {{Assuming the condition is false}}
+                                       // expected-note@+1 {{Taking false branch}}
+  if (pthread_mutex_trylock(m) == 0) { // expected-note 2 {{Entering critical section here}}
+                                       // FIXME: we are entering the critical section only in the true branch
+    sleep(10); // expected-warning {{Call to blocking function 'sleep' inside of critical section}}
+               // expected-note@-1 {{Call to blocking function 'sleep' inside of critical section}}
+    pthread_mutex_unlock(m);
+  } else {
+    sleep(10); // expected-warning {{Call to blocking function 'sleep' inside of critical section}}
+               // expected-note@-1 {{Call to blocking function 'sleep' inside of critical section}}
+               // FIXME: this is a false positive, the lock was not acquired
+  }
+}

clang/test/Analysis/block-in-critical-section.cpp

@@ -0,0 +1,22 @@
+// RUN: %clang_cc1 -verify %s
+// expected-no-diagnostics
+
+/* WG14 N1464: ???
+ * Creation of complex value
+ */
+
+// The paper is about the CMPLX macros, which Clang supports via the
+// __builtin_complex builtin function. Test the basic functionality.
+_Static_assert(__builtin_complex(5.0, 2.0) == 5.0 + 1.0j * 2.0, "");
+_Static_assert(__builtin_complex(5.0f, 2.0f) == 5.0f + 1.0j * 2.0f, "");
+_Static_assert(__builtin_complex(5.0L, 2.0L) == 5.0L + 1.0j * 2.0L, "");
+
+// Test the edge case involving NaN or infinity.
+#define INF(type) (type)__builtin_inf()
+#define NAN(type) (type)__builtin_nan("")
+_Static_assert(__builtin_complex(5.0f, INF(float)) != 5.0f + 1.0j * INF(float), "");
+_Static_assert(__builtin_complex(5.0, INF(double)) != 5.0 + 1.0j * INF(double), "");
+_Static_assert(__builtin_complex(5.0L, INF(long double)) != 5.0L + 1.0j * INF(long double), "");
+_Static_assert(__builtin_complex(5.0f, NAN(float)) != 5.0f + 1.0j * NAN(float), "");
+_Static_assert(__builtin_complex(5.0, NAN(double)) != 5.0 + 1.0j * NAN(double), "");
+_Static_assert(__builtin_complex(5.0L, NAN(long double)) != 5.0L + 1.0j * NAN(long double), "");

clang/test/C/C11/n1464.c

@@ -135,6 +135,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx10-1-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx10_1_generic -DFAMILY=GFX10
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx10-3-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx10_3_generic -DFAMILY=GFX10
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx11-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx11_generic -DFAMILY=GFX11
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx12-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx12_generic -DFAMILY=GFX12
 
 // ARCH-GCN-DAG: #define FP_FAST_FMA 1
 

clang/test/Driver/amdgpu-macros.cl

@@ -119,6 +119,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx10-1-generic %s 2>&1 | FileCheck --check-prefix=GFX10_1_GENERIC %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx10-3-generic %s 2>&1 | FileCheck --check-prefix=GFX10_3_GENERIC %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx11-generic %s 2>&1 | FileCheck --check-prefix=GFX11_GENERIC %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx12-generic %s 2>&1 | FileCheck --check-prefix=GFX12_GENERIC %s
 
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
@@ -170,3 +171,4 @@
 // GFX10_1_GENERIC:   "-target-cpu" "gfx10-1-generic"
 // GFX10_3_GENERIC:   "-target-cpu" "gfx10-3-generic"
 // GFX11_GENERIC:     "-target-cpu" "gfx11-generic"
+// GFX12_GENERIC:     "-target-cpu" "gfx12-generic"