[PATCH] D53443: [OpenMP][NVPTX] Enable default scheduling for parallel for in non-SPMD cases.
Gheorghe-Teodor Bercea via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Fri Oct 26 14:44:18 PDT 2018
gtbercea updated this revision to Diff 171352.
gtbercea added a comment.
Add test.
Repository:
rC Clang
https://reviews.llvm.org/D53443
Files:
lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
test/OpenMP/nvptx_parallel_for_codegen.cpp
Index: test/OpenMP/nvptx_parallel_for_codegen.cpp
===================================================================
--- test/OpenMP/nvptx_parallel_for_codegen.cpp
+++ test/OpenMP/nvptx_parallel_for_codegen.cpp
@@ -57,7 +57,10 @@
// CHECK: store i32 0, {{.*}} [[OMP_LB:%.+]],
// CHECK: store i32 9, {{.*}} [[OMP_UB:%.+]],
// CHECK: store i32 1, {{.*}} [[OMP_ST:%.+]],
-// CHECK: call void @__kmpc_for_static_init_4({{.*}} i32 34, {{.*}} [[OMP_LB]], {{.*}} [[OMP_UB]], {{.*}} [[OMP_ST]], i32 1, i32 1)
+// CHECK: call void @__kmpc_for_static_init_4({{.*}} i32 33, {{.*}} [[OMP_LB]], {{.*}} [[OMP_UB]], {{.*}} [[OMP_ST]], i32 1, i32 1)
+// CHECK: br label %[[OMP_DISPATCH_COND:.+]]
+
+// CHECK: [[OMP_DISPATCH_COND]]
// CHECK: [[OMP_UB_1:%.+]] = load {{.*}} [[OMP_UB]]
// CHECK: [[COMP_1:%.+]] = icmp sgt {{.*}} [[OMP_UB_1]]
// CHECK: br i1 [[COMP_1]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
@@ -74,6 +77,12 @@
// CHECK: store i32 [[COND_RES]], i32* [[OMP_UB]]
// CHECK: [[OMP_LB_1:%.+]] = load i32, i32* [[OMP_LB]]
// CHECK: store i32 [[OMP_LB_1]], i32* [[OMP_IV]]
+// CHECK: [[OMP_IV_1:%.+]] = load i32, i32* [[OMP_IV]]
+// CHECK: [[OMP_UB_3:%.+]] = load i32, i32* [[OMP_UB]]
+// CHECK: [[COMP_2:%.+]] = icmp sle i32 [[OMP_IV_1]], [[OMP_UB_3]]
+// CHECK: br i1 [[COMP_2]], label %[[DISPATCH_BODY:.+]], label %[[DISPATCH_END:.+]]
+
+// CHECK: [[DISPATCH_BODY]]
// CHECK: br label %[[OMP_INNER_FOR_COND:.+]]
// CHECK: [[OMP_INNER_FOR_COND]]
@@ -94,7 +103,20 @@
// CHECK: store i32 [[ADD_1]], i32* [[OMP_IV]]
// CHECK: br label %[[OMP_INNER_FOR_COND]]
-// CHECK: [[OMP_INNER_FOR_END]]
+// CHECK: [[OMP_INNER_FOR_COND]]
+// CHECK: br label %[[OMP_DISPATCH_INC:.+]]
+
+// CHECK: [[OMP_DISPATCH_INC]]
+// CHECK: [[OMP_LB_2:%.+]] = load i32, i32* [[OMP_LB]]
+// CHECK: [[OMP_ST_1:%.+]] = load i32, i32* [[OMP_ST]]
+// CHECK: [[ADD_2:%.+]] = add nsw i32 [[OMP_LB_2]], [[OMP_ST_1]]
+// CHECK: store i32 [[ADD_2]], i32* [[OMP_LB]]
+// CHECK: [[OMP_UB_5:%.+]] = load i32, i32* [[OMP_UB]]
+// CHECK: [[OMP_ST_2:%.+]] = load i32, i32* [[OMP_ST]]
+// CHECK: [[ADD_3:%.+]] = add nsw i32 [[OMP_UB_5]], [[OMP_ST_2]]
+// CHECK: store i32 [[ADD_3]], i32* [[OMP_UB]]
+
+// CHECK: [[DISPATCH_END]]
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -4238,16 +4238,17 @@
Chunk = CGF.EmitScalarConversion(getNVPTXNumThreads(CGF),
CGF.getContext().getIntTypeForBitwidth(32, /*Signed=*/0),
S.getIterationVariable()->getType(), S.getBeginLoc());
+ return;
}
+ CGOpenMPRuntime::getDefaultDistScheduleAndChunk(
+ CGF, S, ScheduleKind, Chunk);
}
void CGOpenMPRuntimeNVPTX::getDefaultScheduleAndChunk(
CodeGenFunction &CGF, const OMPLoopDirective &S,
OpenMPScheduleClauseKind &ScheduleKind,
llvm::Value *&Chunk) const {
- if (getExecutionMode() == CGOpenMPRuntimeNVPTX::EM_SPMD) {
- ScheduleKind = OMPC_SCHEDULE_static;
- Chunk = CGF.Builder.getIntN(CGF.getContext().getTypeSize(
- S.getIterationVariable()->getType()), 1);
- }
+ ScheduleKind = OMPC_SCHEDULE_static;
+ Chunk = CGF.Builder.getIntN(CGF.getContext().getTypeSize(
+ S.getIterationVariable()->getType()), 1);
}
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D53443.171352.patch
Type: text/x-patch
Size: 3363 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20181026/27a34d70/attachment.bin>
More information about the cfe-commits
mailing list