psoni2628 updated this revision to Diff 442595.
psoni2628 added a comment.
- Remove discouraged else after return
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D129149/new/
https://reviews.llvm.org/D129149
Files:
clang/lib/CodeGen/CGStmtOpenMP.cpp
clang/test/OpenMP/irbuilder_simd.cpp
clang/test/OpenMP/irbuilder_simdlen.cpp
llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
Index: llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
===================================================================
--- llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
+++ llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
@@ -1794,6 +1794,39 @@
}));
}
+TEST_F(OpenMPIRBuilderTest, ApplySimdlen) {
+ OpenMPIRBuilder OMPBuilder(*M);
+
+ CanonicalLoopInfo *CLI = buildSingleLoopFunction(DL, OMPBuilder, 32);
+
+ // Simd-ize the loop.
+ OMPBuilder.applySimd(DL, CLI);
+ OMPBuilder.applySimdlen(DL, CLI, ConstantInt::get(Type::getInt32Ty(Ctx), 3));
+
+ OMPBuilder.finalize();
+ EXPECT_FALSE(verifyModule(*M, &errs()));
+
+ PassBuilder PB;
+ FunctionAnalysisManager FAM;
+ PB.registerFunctionAnalyses(FAM);
+ LoopInfo &LI = FAM.getResult<LoopAnalysis>(*F);
+
+ const std::vector<Loop *> &TopLvl = LI.getTopLevelLoops();
+ EXPECT_EQ(TopLvl.size(), 1u);
+
+ Loop *L = TopLvl.front();
+ EXPECT_TRUE(findStringMetadataForLoop(L, "llvm.loop.parallel_accesses"));
+ EXPECT_TRUE(getBooleanLoopAttribute(L, "llvm.loop.vectorize.enable"));
+ EXPECT_EQ(getIntLoopAttribute(L, "llvm.loop.vectorize.width"), 3);
+
+ // Check for llvm.access.group metadata attached to the printf
+ // function in the loop body.
+ BasicBlock *LoopBody = CLI->getBody();
+ EXPECT_TRUE(any_of(*LoopBody, [](Instruction &I) {
+ return I.getMetadata("llvm.access.group") != nullptr;
+ }));
+}
+
TEST_F(OpenMPIRBuilderTest, UnrollLoopFull) {
OpenMPIRBuilder OMPBuilder(*M);
Index: llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
===================================================================
--- llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -2881,6 +2881,15 @@
BoolConst})});
}
+void OpenMPIRBuilder::applySimdlen(DebugLoc, CanonicalLoopInfo *CanonicalLoop,
+ llvm::ConstantInt *Simdlen) {
+ LLVMContext &Ctx = Builder.getContext();
+ addLoopMetadata(
+ CanonicalLoop,
+ MDNode::get(Ctx, {MDString::get(Ctx, "llvm.loop.vectorize.width"),
+ ConstantAsMetadata::get(Simdlen)}));
+}
+
/// Create the TargetMachine object to query the backend for optimization
/// preferences.
///
Index: llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
===================================================================
--- llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
+++ llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
@@ -603,6 +603,14 @@
/// \param Loop The loop to simd-ize.
void applySimd(DebugLoc DL, CanonicalLoopInfo *Loop);
+ /// Add metadata for simdlen to a simd loop.
+ ///
+ /// \param DL Debug location for instructions added by unrolling.
+ /// \param Loop The simd loop.
+ /// \param Simdlen The Simdlen length to apply to the simd loop.
+ void applySimdlen(DebugLoc DL, CanonicalLoopInfo *Loop,
+ llvm::ConstantInt *Simdlen);
+
/// Generator for '#omp flush'
///
/// \param Loc The location where the flush directive was encountered
Index: clang/test/OpenMP/irbuilder_simdlen.cpp
===================================================================
--- /dev/null
+++ clang/test/OpenMP/irbuilder_simdlen.cpp
@@ -0,0 +1,72 @@
+// RUN: %clang_cc1 -no-opaque-pointers -fopenmp-enable-irbuilder -verify -fopenmp -fopenmp-version=45 -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
+// expected-no-diagnostics
+
+struct S {
+ int a, b;
+};
+
+struct P {
+ int a, b;
+};
+
+void simple(float *a, float *b, int *c) {
+ S s, *p;
+ P pp;
+#pragma omp simd simdlen(3)
+ for (int i = 3; i < 32; i += 5) {
+ // llvm.access.group test
+ // CHECK: %[[A_ADDR:.+]] = alloca float*, align 8
+ // CHECK: %[[B_ADDR:.+]] = alloca float*, align 8
+ // CHECK: %[[S:.+]] = alloca %struct.S, align 4
+ // CHECK: %[[P:.+]] = alloca %struct.S*, align 8
+ // CHECK: %[[I:.+]] = alloca i32, align 4
+ // CHECK: %[[TMP3:.+]] = load float*, float** %[[B_ADDR:.+]], align 8, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[TMP4:.+]] = load i32, i32* %[[I:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[IDXPROM:.+]] = sext i32 %[[TMP4:.+]] to i64
+ // CHECK-NEXT: %[[ARRAYIDX:.+]] = getelementptr inbounds float, float* %[[TMP3:.+]], i64 %[[IDXPROM:.+]]
+ // CHECK-NEXT: %[[TMP5:.+]] = load float, float* %[[ARRAYIDX:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[A2:.+]] = getelementptr inbounds %struct.S, %struct.S* %[[S:.+]], i32 0, i32 0
+ // CHECK-NEXT: %[[TMP6:.+]] = load i32, i32* %[[A2:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[CONV:.+]] = sitofp i32 %[[TMP6:.+]] to float
+ // CHECK-NEXT: %[[ADD:.+]] = fadd float %[[TMP5:.+]], %[[CONV:.+]]
+ // CHECK-NEXT: %[[TMP7:.+]] = load %struct.S*, %struct.S** %[[P:.+]], align 8, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[A3:.+]] = getelementptr inbounds %struct.S, %struct.S* %[[TMP7:.+]], i32 0, i32 0
+ // CHECK-NEXT: %[[TMP8:.+]] = load i32, i32* %[[A3:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[CONV4:.+]] = sitofp i32 %[[TMP8:.+]] to float
+ // CHECK-NEXT: %[[ADD5:.+]] = fadd float %[[ADD:.+]], %[[CONV4:.+]]
+ // CHECK-NEXT: %[[TMP9:.+]] = load float*, float** %[[A_ADDR:.+]], align 8, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[TMP10:.+]] = load i32, i32* %[[I:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // CHECK-NEXT: %[[IDXPROM6:.+]] = sext i32 %[[TMP10:.+]] to i64
+ // CHECK-NEXT: %[[ARRAYIDX7:.+]] = getelementptr inbounds float, float* %[[TMP9:.+]], i64 %[[IDXPROM6:.+]]
+ // CHECK-NEXT: store float %[[ADD5:.+]], float* %[[ARRAYIDX7:.+]], align 4, !llvm.access.group ![[META3:[0-9]+]]
+ // llvm.loop test
+ // CHECK: %[[OMP_LOOPDOTNEXT:.+]] = add nuw i32 %[[OMP_LOOPDOTIV:.+]], 1
+ // CHECK-NEXT: br label %omp_loop.header, !llvm.loop ![[META4:[0-9]+]]
+ a[i] = b[i] + s.a + p->a;
+ }
+
+#pragma omp simd
+ for (int j = 3; j < 32; j += 5) {
+ // test if unique access groups were used for a second loop
+ // CHECK: %[[A22:.+]] = getelementptr inbounds %struct.P, %struct.P* %[[PP:.+]], i32 0, i32 0
+ // CHECK-NEXT: %[[TMP14:.+]] = load i32, i32* %[[A22:.+]], align 4, !llvm.access.group ![[META8:[0-9]+]]
+ // CHECK-NEXT: %[[TMP15:.+]] = load i32*, i32** %[[C_ADDR:.+]], align 8, !llvm.access.group ![[META8:[0-9]+]]
+ // CHECK-NEXT: %[[TMP16:.+]] = load i32, i32* %[[J:.+]], align 4, !llvm.access.group ![[META8:[0-9]+]]
+ // CHECK-NEXT: %[[IDXPROM23:.+]] = sext i32 %[[TMP16:.+]] to i64
+ // CHECK-NEXT: %[[ARRAYIDX24:.+]] = getelementptr inbounds i32, i32* %[[TMP15:.+]], i64 %[[IDXPROM23:.+]]
+ // CHECK-NEXT: store i32 %[[TMP14:.+]], i32* %[[ARRAYIDX24:.+]], align 4, !llvm.access.group ![[META8:[0-9]+]]
+ // check llvm.loop metadata
+ // CHECK: %[[OMP_LOOPDOTNEXT:.+]] = add nuw i32 %[[OMP_LOOPDOTIV:.+]], 1
+ // CHECK-NEXT: br label %[[OMP_LLOP_BODY:.*]], !llvm.loop ![[META9:[0-9]+]]
+ c[j] = pp.a;
+ }
+}
+
+// CHECK: ![[META3:[0-9]+]] = distinct !{}
+// CHECK-NEXT: ![[META4]] = distinct !{![[META4]], ![[META5:[0-9]+]], ![[META6:[0-9]+]], ![[META7:[0-9]+]]}
+// CHECK-NEXT: ![[META5]] = !{!"llvm.loop.parallel_accesses", ![[META3]]}
+// CHECK-NEXT: ![[META6]] = !{!"llvm.loop.vectorize.enable", i1 true}
+// CHECK-NEXT: ![[META7]] = !{!"llvm.loop.vectorize.width", i32 3}
+// CHECK-NEXT: ![[META8:[0-9]+]] = distinct !{}
+// CHECK-NEXT: ![[META9]] = distinct !{![[META9]], ![[META10:[0-9]+]], ![[META6]]}
+// CHECK-NEXT: ![[META10]] = !{!"llvm.loop.parallel_accesses", ![[META8]]}
Index: clang/test/OpenMP/irbuilder_simd.cpp
===================================================================
--- clang/test/OpenMP/irbuilder_simd.cpp
+++ clang/test/OpenMP/irbuilder_simd.cpp
@@ -68,4 +68,4 @@
// CHECK-NEXT: ![[META6]] = !{!"llvm.loop.vectorize.enable", i1 true}
// CHECK-NEXT: ![[META7:[0-9]+]] = distinct !{}
// CHECK-NEXT: ![[META8]] = distinct !{![[META8]], ![[META9:[0-9]+]], ![[META6]]}
-// CHECK-NEXT: ![[META9]] = !{!"llvm.loop.parallel_accesses", ![[META7]]}
\ No newline at end of file
+// CHECK-NEXT: ![[META9]] = !{!"llvm.loop.parallel_accesses", ![[META7]]}
Index: clang/lib/CodeGen/CGStmtOpenMP.cpp
===================================================================
--- clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -2591,11 +2591,12 @@
}
}
-static bool isSupportedByOpenMPIRBuilder(const OMPExecutableDirective &S) {
+static bool isSupportedByOpenMPIRBuilder(const OMPSimdDirective &S) {
// Check for unsupported clauses
- if (!S.clauses().empty()) {
- // Currently no clause is supported
- return false;
+ for (OMPClause *C : S.clauses()) {
+ // Currently only simdlen clause is supported
+ if (!dyn_cast<OMPSimdlenClause>(C))
+ return false;
}
// Check if we have a statement with the ordered directive.
@@ -2639,6 +2640,13 @@
CGM.getOpenMPRuntime().getOMPBuilder();
// Add SIMD specific metadata
OMPBuilder.applySimd(DL, CLI);
+ if (const auto *C = S.getSingleClause<OMPSimdlenClause>()) {
+ RValue Len =
+ this->EmitAnyExpr(C->getSimdlen(), AggValueSlot::ignored(),
+ /*ignoreResult=*/true);
+ auto *Val = cast<llvm::ConstantInt>(Len.getScalarVal());
+ OMPBuilder.applySimdlen(DL, CLI, Val);
+ }
return;
}
};
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
