Index: compiler-rt/lib/tsan/rtl/tsan_interface_ann.cpp
===================================================================
--- compiler-rt/lib/tsan/rtl/tsan_interface_ann.cpp
+++ compiler-rt/lib/tsan/rtl/tsan_interface_ann.cpp
@@ -286,6 +286,16 @@
   ThreadIgnoreEnd(thr);
 }
 
+void INTERFACE_ATTRIBUTE AnnotateAllAtomicBegin(char *f, int l) {
+  SCOPED_ANNOTATION(AnnotateAllAtomicBegin);
+  ThreadAllAtomicBegin(thr, pc);
+}
+
+void INTERFACE_ATTRIBUTE AnnotateAllAtomicEnd(char *f, int l) {
+  SCOPED_ANNOTATION(AnnotateAllAtomicEnd);
+  ThreadAllAtomicEnd(thr);
+}
+
 void INTERFACE_ATTRIBUTE AnnotateIgnoreSyncBegin(char *f, int l) {
   SCOPED_ANNOTATION(AnnotateIgnoreSyncBegin);
   ThreadIgnoreSyncBegin(thr, pc);
Index: compiler-rt/lib/tsan/rtl/tsan_rtl.h
===================================================================
--- compiler-rt/lib/tsan/rtl/tsan_rtl.h
+++ compiler-rt/lib/tsan/rtl/tsan_rtl.h
@@ -94,6 +94,7 @@
 // FastState (from most significant bit):
 //   ignore          : 1
 //   tid             : kTidBits
+//   allAtomics      : 1
 //   unused          : -
 //   history_size    : 3
 //   epoch           : kClkBits
@@ -141,6 +142,10 @@
   void ClearIgnoreBit() { x_ &= ~kIgnoreBit; }
   bool GetIgnoreBit() const { return (s64)x_ < 0; }
 
+  void SetAllAtomicBit() { x_ |= kAllAtomicBit; }
+  void ClearAllAtomicBit() { x_ &= ~kAllAtomicBit; }
+  bool GetAllAtomicBit() const { return x_ & kAllAtomicBit; }
+
   void SetHistorySize(int hs) {
     CHECK_GE(hs, 0);
     CHECK_LE(hs, 7);
@@ -166,6 +171,8 @@
 
  private:
   friend class Shadow;
+  static const u64 kAllAtomicShift = 6 + kClkBits;
+  static const u64 kAllAtomicBit = 1ull << kAllAtomicShift;
   static const int kTidShift = 64 - kTidBits - 1;
   static const u64 kIgnoreBit = 1ull << 63;
   static const u64 kFreedBit = 1ull << 63;
@@ -216,6 +223,11 @@
     DCHECK_EQ(IsAtomic(), kIsAtomic);
   }
 
+  void UpgradeAtomic(bool kIsAtomic) {
+    if (kIsAtomic)
+      x_ |= kAtomicBit;
+  }
+
   bool IsAtomic() const {
     return x_ & kAtomicBit;
   }
@@ -385,6 +397,7 @@
   // We do not distinguish beteween ignoring reads and writes
   // for better performance.
   int ignore_reads_and_writes;
+  int all_atomic;
   atomic_sint32_t pending_signals;
   int ignore_sync;
   int suppress_reports;
@@ -752,6 +765,8 @@
 
 void ThreadIgnoreBegin(ThreadState *thr, uptr pc);
 void ThreadIgnoreEnd(ThreadState *thr);
+void ThreadAllAtomicBegin(ThreadState *thr, uptr pc);
+void ThreadAllAtomicEnd(ThreadState *thr);
 void ThreadIgnoreSyncBegin(ThreadState *thr, uptr pc);
 void ThreadIgnoreSyncEnd(ThreadState *thr);
 
Index: compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
===================================================================
--- compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
+++ compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
@@ -844,7 +844,7 @@
   Shadow cur(fast_state);
   cur.SetAddr0AndSizeLog(addr & 7, kAccessSizeLog);
   cur.SetWrite(kAccessIsWrite);
-  cur.SetAtomic(kIsAtomic);
+  cur.UpgradeAtomic(kIsAtomic);
 
   if (LIKELY(ContainsSameAccess(shadow_mem, cur.raw(),
       thr->fast_synch_epoch, kAccessIsWrite))) {
@@ -858,8 +858,8 @@
     cur.IncrementEpoch();
   }
 
-  MemoryAccessImpl1(thr, addr, kAccessSizeLog, kAccessIsWrite, kIsAtomic,
-      shadow_mem, cur);
+  MemoryAccessImpl1(thr, addr, kAccessSizeLog, kAccessIsWrite, cur.IsAtomic(),
+                    shadow_mem, cur);
 }
 
 // Called by MemoryAccessRange in tsan_rtl_thread.cpp
@@ -1041,6 +1041,29 @@
   }
 }
 
+void ThreadAllAtomicBegin(ThreadState *thr, uptr pc) {
+  DPrintf("#%d: ThreadAllAtomicBegin\n", thr->tid);
+  thr->all_atomic++;
+  CHECK_GT(thr->all_atomic, 0);
+  thr->fast_state.SetAllAtomicBit();
+  /*#if !SANITIZER_GO
+    if (pc && !ctx->after_multithreaded_fork)
+      thr->mop_ignore_set.Add(CurrentStackId(thr, pc));
+  #endif*/
+}
+
+void ThreadAllAtomicEnd(ThreadState *thr) {
+  DPrintf("#%d: ThreadAllAtomicEnd\n", thr->tid);
+  CHECK_GT(thr->all_atomic, 0);
+  thr->all_atomic--;
+  if (thr->all_atomic == 0) {
+    thr->fast_state.ClearAllAtomicBit();
+    /*#if !SANITIZER_GO
+        thr->mop_ignore_set.Reset();
+    #endif*/
+  }
+}
+
 #if !SANITIZER_GO
 extern "C" SANITIZER_INTERFACE_ATTRIBUTE
 uptr __tsan_testonly_shadow_stack_current_size() {
Index: openmp/tools/archer/ompt-tsan.cpp
===================================================================
--- openmp/tools/archer/ompt-tsan.cpp
+++ openmp/tools/archer/ompt-tsan.cpp
@@ -173,6 +173,12 @@
 AnnotateIgnoreWritesBegin(const char *file, int line) {}
 void __attribute__((weak)) AnnotateIgnoreWritesEnd(const char *file, int line) {
 }
+void __attribute__((weak)) AnnotateAllAtomicBegin(const char *file, int line) {
+  AnnotateIgnoreWritesBegin(file, line);
+}
+void __attribute__((weak)) AnnotateAllAtomicEnd(const char *file, int line) {
+  AnnotateIgnoreWritesEnd(file, line);
+}
 void __attribute__((weak))
 AnnotateNewMemory(const char *file, int line, const volatile void *cv,
                   size_t size) {}
@@ -199,6 +205,13 @@
 // Resume checking for racy writes.
 #define TsanIgnoreWritesEnd() AnnotateIgnoreWritesEnd(__FILE__, __LINE__)
 
+// Promote all memory accesses to be atomic between here and the next
+// TsanAllAtomicEnd.
+#define TsanAllAtomicBegin() AnnotateAllAtomicBegin(__FILE__, __LINE__)
+
+// Resume checking for racy writes.
+#define TsanAllAtomicEnd() AnnotateAllAtomicEnd(__FILE__, __LINE__)
+
 // We don't really delete the clock for now
 #define TsanDeleteClock(cv)
 
@@ -728,7 +741,7 @@
         // 2. execution of another task.
         // For the latter case we will re-enable tracking in task_switch.
         Data->InBarrier = true;
-        TsanIgnoreWritesBegin();
+        TsanAllAtomicBegin();
       }
 
       break;
@@ -761,7 +774,7 @@
       if (hasReductionCallback < ompt_set_always) {
         // We want to track writes after the barrier again.
         Data->InBarrier = false;
-        TsanIgnoreWritesEnd();
+        TsanAllAtomicEnd();
       }
 
       char BarrierIndex = Data->BarrierIndex;
@@ -816,7 +829,7 @@
   case ompt_scope_begin:
     switch (kind) {
     case ompt_sync_region_reduction:
-      TsanIgnoreWritesBegin();
+      TsanAllAtomicBegin();
       break;
     default:
       break;
@@ -825,7 +838,7 @@
   case ompt_scope_end:
     switch (kind) {
     case ompt_sync_region_reduction:
-      TsanIgnoreWritesEnd();
+      TsanAllAtomicEnd();
       break;
     default:
       break;
@@ -927,7 +940,7 @@
   if (hasReductionCallback < ompt_set_always && FromTask->InBarrier) {
     // We want to ignore writes in the runtime code during barriers,
     // but not when executing tasks with user code!
-    TsanIgnoreWritesEnd();
+    TsanAllAtomicEnd();
   }
 
   // The late fulfill happens after the detached task finished execution
@@ -972,7 +985,7 @@
   // Legacy handling for missing reduction callback
   if (hasReductionCallback < ompt_set_always && ToTask->InBarrier) {
     // We re-enter runtime code which currently performs a barrier.
-    TsanIgnoreWritesBegin();
+    TsanAllAtomicBegin();
   }
 
   // task suspended
@@ -1101,6 +1114,8 @@
                    (void (*)(const char *, int, const volatile void *)));
   findTsanFunction(AnnotateIgnoreWritesBegin, (void (*)(const char *, int)));
   findTsanFunction(AnnotateIgnoreWritesEnd, (void (*)(const char *, int)));
+  findTsanFunction(AnnotateAllAtomicBegin, (void (*)(const char *, int)));
+  findTsanFunction(AnnotateAllAtomicEnd, (void (*)(const char *, int)));
   findTsanFunction(
       AnnotateNewMemory,
       (void (*)(const char *, int, const volatile void *, size_t)));
Index: openmp/tools/archer/tests/races/reduction-race.c
===================================================================
--- /dev/null
+++ openmp/tools/archer/tests/races/reduction-race.c
@@ -0,0 +1,42 @@
+/*
+ * reduction-race.c -- Archer testcase
+ */
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+//
+// See tools/archer/LICENSE.txt for details.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+// RUN: %libarcher-compile-and-run-race | FileCheck %s
+// RUN: %libarcher-compile-and-run-race-noserial | FileCheck %s
+// REQUIRES: tsan
+#include <omp.h>
+#include <stdio.h>
+
+int main(int argc, char *argv[]) {
+  int var = 0;
+
+#pragma omp parallel num_threads(8) shared(var)
+  {
+#pragma omp master
+    var++;
+#pragma omp for reduction(+ : var)
+    for (int i = 0; i < 100; i++)
+      var++;
+  }
+
+  int error = (var != 101);
+  fprintf(stderr, "DONE\n");
+  return error;
+}
+
+// CHECK: WARNING: ThreadSanitizer: data race
+// CHECK-NEXT:   {{(Write|Read)}} of size 4
+// CHECK-NEXT: #0 {{.*}}parallel-simple.c:23
+// CHECK:   Previous write of size 4
+// CHECK-NEXT: #0 {{.*}}parallel-simple.c:23
+// CHECK: DONE
+// CHECK: ThreadSanitizer: reported 1 warnings