OMPRTL_NVPTX__kmpc_end_reduce_nowait,
/// Call to void __kmpc_data_sharing_init_stack();
OMPRTL_NVPTX__kmpc_data_sharing_init_stack,
+ /// Call to void __kmpc_data_sharing_init_stack_spmd();
+ OMPRTL_NVPTX__kmpc_data_sharing_init_stack_spmd,
/// Call to void* __kmpc_data_sharing_push_stack(size_t size,
/// int16_t UseSharedMemory);
OMPRTL_NVPTX__kmpc_data_sharing_push_stack,
/*RequiresDataSharing=*/Bld.getInt16(1)};
CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_spmd_kernel_init), Args);
+
+ // For data sharing, we need to initialize the stack.
+ CGF.EmitRuntimeCall(
+ createNVPTXRuntimeFunction(
+ OMPRTL_NVPTX__kmpc_data_sharing_init_stack_spmd));
+
CGF.EmitBranch(ExecuteBB);
CGF.EmitBlock(ExecuteBB);
// Wait for parallel work
syncCTAThreads(CGF);
- // For data sharing, we need to initialize the stack for workers.
- CGF.EmitRuntimeCall(
- createNVPTXRuntimeFunction(
- OMPRTL_NVPTX__kmpc_data_sharing_init_stack));
-
Address WorkFn =
CGF.CreateDefaultAlignTempAlloca(CGF.Int8PtrTy, /*Name=*/"work_fn");
Address ExecStatus =
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_data_sharing_init_stack");
break;
}
+ case OMPRTL_NVPTX__kmpc_data_sharing_init_stack_spmd: {
+ /// Build void __kmpc_data_sharing_init_stack_spmd();
+ auto *FnTy =
+ llvm::FunctionType::get(CGM.VoidTy, llvm::None, /*isVarArg*/ false);
+ RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_data_sharing_init_stack_spmd");
+ break;
+ }
case OMPRTL_NVPTX__kmpc_data_sharing_push_stack: {
// Build void *__kmpc_data_sharing_push_stack(size_t size,
// int16_t UseSharedMemory);
/// ========= In the worker function ========= ///
// CK1: {{.*}}define internal void @__omp_offloading{{.*}}test_ds{{.*}}_worker()
// CK1: call void @llvm.nvvm.barrier0()
-// CK1: call void @__kmpc_data_sharing_init_stack
+// CK1-NOT: call void @__kmpc_data_sharing_init_stack
/// ========= In the kernel function ========= ///
// CHECK: [[AA:%.+]] = load i16*, i16** [[AA_ADDR]], align
// CHECK: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK: [[B:%.+]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align
// CHECK: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l22}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l31}}(
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXEC:.+]]
//
// CHECK: [[EXEC]]
// CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l27}}(
//
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXECUTE:.+]]
//
// CHECK: [[EXECUTE]]
// CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l32}}(
//
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXECUTE:.+]]
//
// CHECK: [[EXECUTE]]
// CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l38}}(
//
// CHECK: call void @__kmpc_spmd_kernel_init(
+ // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: br label {{%?}}[[EXECUTE:.+]]
//
// CHECK: [[EXECUTE]]
// CHECK: define weak void @__omp_offloading_{{.*}}ftemplate{{.*}}_l37(
// CHECK: call void @__kmpc_spmd_kernel_init(
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call i8* @__kmpc_data_sharing_push_stack(
// CHECK-NOT: call void @__kmpc_serialized_parallel(
// CHECK: call void [[L0:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.*}})
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL1:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92,
// CHECK: {{call|invoke}} void [[OUTL2:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92,
// CHECK: {{call|invoke}} void [[OUTL3:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: store {{.+}} [[F_IN]], {{.+}}* {{.+}},
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: store {{.+}} 99, {{.+}}* [[COMB_UB:%.+]], align
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92, {{.+}}, {{.+}}, {{.+}}* [[COMB_UB]],
// CHECK: {{call|invoke}} void [[OUTL4:@.+]](
tx a[N];
short aa[N];
tx b[10];
- tx c[M][M];
+ tx c[M][M];
tx f = n;
tx l;
int k;
for(int i = 0; i < M; i++) {
for(int j = 0; j < M; j++) {
k = M;
- c[i][j] = i+j*f+k;
+ c[i][j] = i+j*f+k;
}
}
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL1:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92,
// CHECK: {{call|invoke}} void [[OUTL2:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92,
// CHECK: {{call|invoke}} void [[OUTL3:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: store {{.+}} [[F_IN]], {{.+}}* {{.+}},
// CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]],
+// CHECK: call void @__kmpc_data_sharing_init_stack_spmd
// CHECK: store {{.+}} 99, {{.+}}* [[COMB_UB:%.+]], align
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 92, {{.+}}, {{.+}}, {{.+}}* [[COMB_UB]],
// CHECK: {{call|invoke}} void [[OUTL4:@.+]](