[clang] [compiler-rt] [llvm] [PGO][AMDGPU] Add basic HIP offload PGO support (PR #177665)

[Yaxun Liu via cfe-commits]

================
@@ -0,0 +1,888 @@
+//===- InstrProfilingPlatformROCm.cpp - Profile data ROCm platform -------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+extern "C" {
+#include "InstrProfiling.h"
+#include "InstrProfilingInternal.h"
+#include "InstrProfilingPort.h"
+}
+
+#include "interception/interception.h"
+// C library headers (not <cstdio> etc.): clang_rt.profile is built with
+// -nostdinc++ and avoids the C++ standard library (see profile/CMakeLists.txt).
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifdef _WIN32
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#else
+#include <pthread.h>
+#endif
+
+/* Serialize one-time HIP loader resolution and DynamicModules mutations.
+ * Inline to avoid a sanitizer_common dependency. */
+#ifdef _WIN32
+static INIT_ONCE HipLoadedOnce = INIT_ONCE_STATIC_INIT;
+static CRITICAL_SECTION DynamicModulesLock;
+static INIT_ONCE DynamicModulesLockInit = INIT_ONCE_STATIC_INIT;
+static BOOL CALLBACK initDynamicModulesLockCb(PINIT_ONCE, PVOID, PVOID *) {
+  InitializeCriticalSection(&DynamicModulesLock);
+  return TRUE;
+}
+static void lockDynamicModules(void) {
+  InitOnceExecuteOnce(&DynamicModulesLockInit, initDynamicModulesLockCb, NULL,
+                      NULL);
+  EnterCriticalSection(&DynamicModulesLock);
+}
+static void unlockDynamicModules(void) {
+  LeaveCriticalSection(&DynamicModulesLock);
+}
+#else
+static pthread_once_t HipLoadedOnce = PTHREAD_ONCE_INIT;
+static pthread_mutex_t DynamicModulesLock = PTHREAD_MUTEX_INITIALIZER;
+static void lockDynamicModules(void) {
+  pthread_mutex_lock(&DynamicModulesLock);
+}
+static void unlockDynamicModules(void) {
+  pthread_mutex_unlock(&DynamicModulesLock);
+}
+#endif
+
+static int processDeviceOffloadPrf(void *DeviceOffloadPrf, int TUIndex,
+                                   const char *Target);
+
+static int isVerboseMode() {
+  static int IsVerbose = -1;
+  if (IsVerbose == -1)
+    IsVerbose = getenv("LLVM_PROFILE_VERBOSE") != nullptr;
+  return IsVerbose;
+}
+
+/* -------------------------------------------------------------------------- */
+/*  Dynamic loading of HIP runtime symbols                                   */
+/* -------------------------------------------------------------------------- */
+
+typedef int (*hipGetSymbolAddressTy)(void **, const void *);
+typedef int (*hipMemcpyTy)(void *, const void *, size_t, int);
+typedef int (*hipModuleGetGlobalTy)(void **, size_t *, void *, const char *);
+typedef int (*hipGetDeviceCountTy)(int *);
+typedef int (*hipGetDeviceTy)(int *);
+typedef int (*hipSetDeviceTy)(int);
+
+/* Minimal hipDeviceProp_t (HIP 6.x R0600): only gcnArchName at offset 1160
+ * is read. Padded to 4096 to tolerate ABI growth. */
+typedef struct {
+  char padding[1160];
+  char gcnArchName[256];
+  char tail_padding[2680];
+} HipDevicePropMinimal;
+typedef int (*hipGetDevicePropertiesTy)(HipDevicePropMinimal *, int);
+
+static hipGetSymbolAddressTy pHipGetSymbolAddress = nullptr;
+static hipMemcpyTy pHipMemcpy = nullptr;
+static hipModuleGetGlobalTy pHipModuleGetGlobal = nullptr;
+static hipGetDeviceCountTy pHipGetDeviceCount = nullptr;
+static hipGetDeviceTy pHipGetDevice = nullptr;
+static hipSetDeviceTy pHipSetDevice = nullptr;
+static hipGetDevicePropertiesTy pHipGetDeviceProperties = nullptr;
+
+#define MAX_DEVICES 16
----------------
yxsamliu wrote:

will do

https://github.com/llvm/llvm-project/pull/177665