OpenMP: Add convergent to more runtime functions

[arsenm]

Summary

Several of these other functions are probably also convergent, but
these two seem obviously convergent.

[ABataev]

LG, thanks!

[arsenm]

56a503bdba9c33fce4d8fe86494cfd9c0b62c88a

clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

case OMPRTL__kmpc_barrier_simple_spmd: {
     RTLFn = CGM.CreateConvergentRuntimeFunction(
         FnTy, /*Name*/ "__kmpc_barrier_simple_spmd");
     break;
   }
   case OMPRTL_NVPTX__kmpc_warp_active_thread_mask: {
     // Build int32_t __kmpc_warp_active_thread_mask(void);
     auto *FnTy =
         llvm::FunctionType::get(CGM.Int32Ty, llvm::None, /*isVarArg=*/false);
-    RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_warp_active_thread_mask");
+    RTLFn = CGM.CreateConvergentRuntimeFunction(FnTy, "__kmpc_warp_active_thread_mask");
     break;
   }
   case OMPRTL_NVPTX__kmpc_syncwarp: {
     // Build void __kmpc_syncwarp(kmp_int32 Mask);
     auto *FnTy =
         llvm::FunctionType::get(CGM.VoidTy, CGM.Int32Ty, /*isVarArg=*/false);
-    RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_syncwarp");
+    RTLFn = CGM.CreateConvergentRuntimeFunction(FnTy, "__kmpc_syncwarp");
     break;
   }
   }
   return RTLFn;
 }
 
 void CGOpenMPRuntimeNVPTX::createOffloadEntry(llvm::Constant *ID,
                                               llvm::Constant *Addr,

clang/test/OpenMP/nvptx_parallel_codegen.cpp

 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}_worker()
 // CHECK-DAG: [[OMP_EXEC_STATUS:%.+]] = alloca i8,
 // CHECK-DAG: [[OMP_WORK_FN:%.+]] = alloca i8*,
 // CHECK: store i8* null, i8** [[OMP_WORK_FN]],
 // CHECK: store i8 0, i8* [[OMP_EXEC_STATUS]],
 // CHECK: br label {{%?}}[[AWAIT_WORK:.+]]
 //
 // CHECK: [[AWAIT_WORK]]
-// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0) #[[#BARRIER_ATTRS:]]
+// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0) #[[#CONVERGENT:]]
 // CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]]
 // CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
 // store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
 // CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
 // CHECK: [[SHOULD_EXIT:%.+]] = icmp eq i8* [[WORK]], null
 // CHECK: br i1 [[SHOULD_EXIT]], label {{%?}}[[EXIT:.+]], label {{%?}}[[SEL_WORKERS:.+]]
 //
 // CHECK: [[SEL_WORKERS]]

 // CHECK: br label {{%?}}[[EXIT]]
 //
 // CHECK: [[EXIT]]
 // CHECK: ret void
 
 // CHECK: define internal void [[PARALLEL_FN4]](
 // CHECK: [[A:%.+]] = alloca i[[SZ:32|64]],
 // CHECK: store i[[SZ]] 45, i[[SZ]]* %a,
-// CHECK: call void @__kmpc_barrier(%struct.ident_t* @{{.+}}, i32 %{{.+}}) #[[#BARRIER_ATTRS]]
+// CHECK: call void @__kmpc_barrier(%struct.ident_t* @{{.+}}, i32 %{{.+}}) #[[#CONVERGENT:]]
 // CHECK: ret void
 
-// CHECK: declare void @__kmpc_barrier(%struct.ident_t*, i32) #[[#BARRIER_ATTRS]]
+// CHECK: declare void @__kmpc_barrier(%struct.ident_t*, i32) #[[#CONVERGENT]]
 
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l55}}_worker()
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l55}}(
 // CHECK-32: [[A_ADDR:%.+]] = alloca i32,
 // CHECK-64: [[A_ADDR:%.+]] = alloca i64,
 // CHECK-64: [[CONV:%.+]] = bitcast i64* [[A_ADDR]] to i32*
 // CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
 // CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
 // CHECK: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
 // CHECK: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
 // CHECK: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
 // CHECK: [[BC:%.+]] = bitcast i8* [[STACK]] to %struct._globalized_locals_ty*
 // CHECK-32: [[A:%.+]] = load i32, i32* [[A_ADDR]],
 // CHECK-64: [[A:%.+]] = load i32, i32* [[CONV]],
 // CHECK: [[GLOBAL_A_ADDR:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CHECK: store i32 [[A]], i32* [[GLOBAL_A_ADDR]],
 // CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
 // CHECK: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
 
 // CHECK-LABEL: define internal void @{{.+}}(i32* noalias %{{.+}}, i32* noalias %{{.+}}, i32* dereferenceable{{.*}})
 // CHECK:  [[CC:%.+]] = alloca i32,
-// CHECK:  [[MASK:%.+]] = call i32 @__kmpc_warp_active_thread_mask()
+// CHECK:  [[MASK:%.+]] = call i32 @__kmpc_warp_active_thread_mask(){{$}}
 // CHECK:  [[TID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
 // CHECK:  [[NUM_THREADS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
 // CHECK:  store i32 0, i32* [[CC]],
 // CHECK:  br label
 
 // CHECK:  [[CC_VAL:%.+]] = load i32, i32* [[CC]],
 // CHECK:  [[RES:%.+]] = icmp slt i32 [[CC_VAL]], [[NUM_THREADS]]
 // CHECK:  br i1 [[RES]], label
 
 // CHECK:  [[CC_VAL:%.+]] = load i32, i32* [[CC]],
 // CHECK:  [[RES:%.+]] = icmp eq i32 [[TID]], [[CC_VAL]]
 // CHECK:  br i1 [[RES]], label
 
 // CHECK:  call void @__kmpc_critical(
 // CHECK:  load i32, i32*
 // CHECK:  add nsw i32
 // CHECK:  store i32
 // CHECK:  call void @__kmpc_end_critical(
 
-// CHECK:  call void @__kmpc_syncwarp(i32 [[MASK]])
+// CHECK:  call void @__kmpc_syncwarp(i32 [[MASK]]){{$}}
 // CHECK:  [[NEW_CC_VAL:%.+]] = add nsw i32 [[CC_VAL]], 1
 // CHECK:  store i32 [[NEW_CC_VAL]], i32* [[CC]],
 // CHECK:  br label
 
-// CHECK: attributes #[[#BARRIER_ATTRS]] = {{.*}} convergent {{.*}}
+
+// CHECK: declare i32 @__kmpc_warp_active_thread_mask() #[[#CONVERGENT:]]
+// CHECK: declare void @__kmpc_syncwarp(i32) #[[#CONVERGENT:]]
+
+// CHECK: attributes #[[#CONVERGENT]] = {{.*}} convergent {{.*}}
 
 #endif