[clang] [OpenMP] Correctly code-gen default atomic mem order (PR #97663)

[Joseph Huber via cfe-commits]

https://github.com/jhuber6 created https://github.com/llvm/llvm-project/pull/97663

Summary:
The parsing for this was implemented, but we never hooked up the default
value to the result of this clause. This patch adds the support by
making it default to the requires directive.


>From fa3561bd4d42522f07ec901c15b411f06b844490 Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Wed, 3 Jul 2024 21:44:07 -0500
Subject: [PATCH] [OpenMP] Correctly code-gen default atomic mem order

Summary:
The parsing for this was implemented, but we never hooked up the default
value to the result of this clause. This patch adds the support by
making it default to the requires directive.
---
 clang/lib/CodeGen/CGStmtOpenMP.cpp            |  2 +-
 .../requires_default_atomic_mem_order.cpp     | 46 +++++++++++++++++++
 2 files changed, 47 insertions(+), 1 deletion(-)
 create mode 100644 clang/test/OpenMP/requires_default_atomic_mem_order.cpp

diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index 76ff8f5b234da6..4d05322951d0a5 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -6555,7 +6555,7 @@ static void emitOMPAtomicExpr(CodeGenFunction &CGF, OpenMPClauseKind Kind,
 }
 
 void CodeGenFunction::EmitOMPAtomicDirective(const OMPAtomicDirective &S) {
-  llvm::AtomicOrdering AO = llvm::AtomicOrdering::Monotonic;
+  llvm::AtomicOrdering AO = CGM.getOpenMPRuntime().getDefaultMemoryOrdering();
   // Fail Memory Clause Ordering.
   llvm::AtomicOrdering FailAO = llvm::AtomicOrdering::NotAtomic;
   bool MemOrderingSpecified = false;
diff --git a/clang/test/OpenMP/requires_default_atomic_mem_order.cpp b/clang/test/OpenMP/requires_default_atomic_mem_order.cpp
new file mode 100644
index 00000000000000..90d2db4eac20c4
--- /dev/null
+++ b/clang/test/OpenMP/requires_default_atomic_mem_order.cpp
@@ -0,0 +1,46 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+// RUN: %clang_cc1 -emit-llvm -fopenmp -triple=x86_64-unknown-linux-gnu \
+// RUN:   -DORDERING=seq_cst -o - %s \
+// RUN: | FileCheck %s --check-prefix=SEQ_CST
+// RUN: %clang_cc1 -emit-llvm -fopenmp -triple=x86_64-unknown-linux-gnu \
+// RUN:   -DORDERING=acq_rel -o - %s \
+// RUN: | FileCheck %s --check-prefix=ACQ_REL
+// RUN: %clang_cc1 -emit-llvm -fopenmp -triple=x86_64-unknown-linux-gnu \
+// RUN:   -DORDERING=relaxed -o - %s \
+// RUN: | FileCheck %s --check-prefix=RELAXED
+
+#pragma omp requires atomic_default_mem_order(ORDERING)
+
+// SEQ_CST-LABEL: define dso_local void @_Z3fooPi(
+// SEQ_CST-SAME: ptr noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+// SEQ_CST-NEXT:  [[ENTRY:.*:]]
+// SEQ_CST-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
+// SEQ_CST-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8
+// SEQ_CST-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[X_ADDR]], align 8
+// SEQ_CST-NEXT:    [[TMP1:%.*]] = atomicrmw add ptr [[TMP0]], i32 1 seq_cst, align 4
+// SEQ_CST-NEXT:    call void @__kmpc_flush(ptr @[[GLOB1:[0-9]+]])
+// SEQ_CST-NEXT:    ret void
+//
+// ACQ_REL-LABEL: define dso_local void @_Z3fooPi(
+// ACQ_REL-SAME: ptr noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+// ACQ_REL-NEXT:  [[ENTRY:.*:]]
+// ACQ_REL-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
+// ACQ_REL-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8
+// ACQ_REL-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[X_ADDR]], align 8
+// ACQ_REL-NEXT:    [[TMP1:%.*]] = atomicrmw add ptr [[TMP0]], i32 1 release, align 4
+// ACQ_REL-NEXT:    call void @__kmpc_flush(ptr @[[GLOB1:[0-9]+]])
+// ACQ_REL-NEXT:    ret void
+//
+// RELAXED-LABEL: define dso_local void @_Z3fooPi(
+// RELAXED-SAME: ptr noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+// RELAXED-NEXT:  [[ENTRY:.*:]]
+// RELAXED-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
+// RELAXED-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8
+// RELAXED-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[X_ADDR]], align 8
+// RELAXED-NEXT:    [[TMP1:%.*]] = atomicrmw add ptr [[TMP0]], i32 1 monotonic, align 4
+// RELAXED-NEXT:    ret void
+//
+void foo(int *x) {
+  #pragma omp atomic update
+    *x = *x + 1;
+}