sfantao updated this revision to Diff 34869. sfantao added a comment. Update code to use implicit parameters for the captured variables using `GenerateOpenMPCapturedStmtFunction`, similarly to what is done to other directives.
`UseOnlyReferences` boolean was added to `GenerateOpenMPCapturedStmtFunction`, given that for target regions, all the captures need to be references, VAT sizes included. `UseOnlyReferences` is set to false by default and only set to true when emitting a target directive. http://reviews.llvm.org/D12871 Files: lib/CodeGen/CGOpenMPRuntime.cpp lib/CodeGen/CGOpenMPRuntime.h lib/CodeGen/CGStmtOpenMP.cpp lib/CodeGen/CodeGenFunction.h test/OpenMP/target_codegen.cpp
Index: test/OpenMP/target_codegen.cpp =================================================================== --- /dev/null +++ test/OpenMP/target_codegen.cpp @@ -0,0 +1,606 @@ +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s +// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s +// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s +// expected-no-diagnostics +#ifndef HEADER +#define HEADER + +// CHECK-DAG: [[TT:%.+]] = type { i64, i8 } +// CHECK-DAG: [[S1:%.+]] = type { double } + +// We have 8 target regions, but only 7 that actually will generate offloading +// code, only 6 will have mapped arguments, and only 4 have all-constant map +// sizes. + +// CHECK-DAG: [[SIZET2:@.+]] = private unnamed_addr constant [1 x i{{32|64}}] [i[[SZ:32|64]] 2] +// CHECK-DAG: [[MAPT2:@.+]] = private unnamed_addr constant [1 x i32] [i32 3] +// CHECK-DAG: [[SIZET3:@.+]] = private unnamed_addr constant [2 x i[[SZ]]] [i[[SZ]] 4, i[[SZ]] 2] +// CHECK-DAG: [[MAPT3:@.+]] = private unnamed_addr constant [2 x i32] [i32 3, i32 3] +// CHECK-DAG: [[MAPT4:@.+]] = private unnamed_addr constant [9 x i32] [i32 3, i32 3, i32 1, i32 3, i32 3, i32 1, i32 1, i32 3, i32 3] +// CHECK-DAG: [[SIZET5:@.+]] = private unnamed_addr constant [3 x i[[SZ]]] [i[[SZ]] 4, i[[SZ]] 2, i[[SZ]] 40] +// CHECK-DAG: [[MAPT5:@.+]] = private unnamed_addr constant [3 x i32] [i32 3, i32 3, i32 3] +// CHECK-DAG: [[SIZET6:@.+]] = private unnamed_addr constant [4 x i[[SZ]]] [i[[SZ]] 4, i[[SZ]] 2, i[[SZ]] 1, i[[SZ]] 40] +// CHECK-DAG: [[MAPT6:@.+]] = private unnamed_addr constant [4 x i32] [i32 3, i32 3, i32 3, i32 3] +// CHECK-DAG: [[MAPT7:@.+]] = private unnamed_addr constant [5 x i32] [i32 3, i32 3, i32 1, i32 1, i32 3] +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 +// CHECK-DAG: @{{.*}} = private constant i8 0 + +template<typename tx, typename ty> +struct TT{ + tx X; + ty Y; +}; + +// CHECK: define {{.*}}[[FOO:@.+]]( +int foo(int n) { + int a = 0; + short aa = 0; + float b[10]; + float bn[n]; + double c[5][10]; + double cn[5][n]; + TT<long long, char> d; + + // CHECK: br label %[[TRY:[^,]+]] + // CHECK: [[TRY]] + // CHECK: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 0, i8** null, i8** null, i[[SZ]]* null, i32* null) + // CHECK-NEXT: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 + // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL:[^,]+]], label %[[END:[^,]+]] + // CHECK: [[FAIL]] + // CHECK: call void [[HVT0:@.+]]() + // CHECK-NEXT: br label %[[END]] + // CHECK: [[END]] + #pragma omp target + { + } + + // CHECK: call void [[HVT1:@.+]](i32* {{[^,]+}}) + #pragma omp target if(0) + { + a += 1; + } + + // CHECK: br label %[[TRY:[^,]+]] + // CHECK: [[TRY]] + // CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 1, i8** [[BP:%[^,]+]], i8** [[P:%[^,]+]], i[[SZ]]* getelementptr inbounds ([1 x i[[SZ]]], [1 x i[[SZ]]]* [[SIZET2]], i32 0, i32 0), i32* getelementptr inbounds ([1 x i32], [1 x i32]* [[MAPT2]], i32 0, i32 0)) + // CHECK-DAG: [[BP]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[BPR:%[^,]+]], i32 0, i32 0 + // CHECK-DAG: [[P]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[PR:%[^,]+]], i32 0, i32 0 + // CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[BPR]], i32 0, i32 [[IDX0:[0-9]+]] + // CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[PR]], i32 0, i32 [[IDX0]] + // CHECK-DAG: store i8* [[BP0:%[^,]+]], i8** [[BPADDR0]] + // CHECK-DAG: store i8* [[P0:%[^,]+]], i8** [[PADDR0]] + // CHECK-DAG: [[BP0]] = bitcast i16* %{{.+}} to i8* + // CHECK-DAG: [[P0]] = bitcast i16* %{{.+}} to i8* + + // CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 + // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL:[^,]+]], label %[[END:[^,]+]] + // CHECK: [[FAIL]] + // CHECK: call void [[HVT2:@.+]](i16* {{[^,]+}}) + // CHECK-NEXT: br label %[[END]] + // CHECK: [[END]] + #pragma omp target if(1) + { + aa += 1; + } + + // CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 10 + // CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] + // CHECK: [[TRY]] + // CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 2, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i[[SZ]]* getelementptr inbounds ([2 x i[[SZ]]], [2 x i[[SZ]]]* [[SIZET3]], i32 0, i32 0), i32* getelementptr inbounds ([2 x i32], [2 x i32]* [[MAPT3]], i32 0, i32 0)) + // CHECK-DAG: [[BPR]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[BP:%[^,]+]], i32 0, i32 0 + // CHECK-DAG: [[PR]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[P:%[^,]+]], i32 0, i32 0 + + // CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[BP]], i32 0, i32 0 + // CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[P]], i32 0, i32 0 + // CHECK-DAG: store i8* [[BP0:%[^,]+]], i8** [[BPADDR0]] + // CHECK-DAG: store i8* [[P0:%[^,]+]], i8** [[PADDR0]] + // CHECK-DAG: [[BP0]] = bitcast i32* %{{.+}} to i8* + // CHECK-DAG: [[P0]] = bitcast i32* %{{.+}} to i8* + + // CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[BP]], i32 0, i32 1 + // CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[P]], i32 0, i32 1 + // CHECK-DAG: store i8* [[BP1:%[^,]+]], i8** [[BPADDR1]] + // CHECK-DAG: store i8* [[P1:%[^,]+]], i8** [[PADDR1]] + // CHECK-DAG: [[BP1]] = bitcast i16* %{{.+}} to i8* + // CHECK-DAG: [[P1]] = bitcast i16* %{{.+}} to i8* + + // CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 + // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL]], label %[[END:[^,]+]] + // CHECK: [[FAIL]] + // CHECK: call void [[HVT3:@.+]]({{[^,]+}}, {{[^,]+}}) + // CHECK-NEXT: br label %[[END]] + // CHECK: [[END]] + #pragma omp target if(n>10) + { + a += 1; + aa += 1; + } + + // We capture 3 VLA sizes in this target region + // CHECK: store i[[SZ]] [[BNELEMSIZE:%.+]], i[[SZ]]* [[VLA0:%[^,]+]] + // CHECK: store i[[SZ]] 5, i[[SZ]]* [[VLA1:%[^,]+]] + // CHECK: store i[[SZ]] [[CNELEMSIZE1:%.+]], i[[SZ]]* [[VLA2:%[^,]+]] + + // CHECK: [[BNSIZE:%.+]] = mul nuw i[[SZ]] 4, [[BNELEMSIZE:%.+]] + // CHECK: [[CNELEMSIZE2:%.+]] = mul nuw i[[SZ]] 5, [[CNELEMSIZE1]] + // CHECK: [[CNSIZE:%.+]] = mul nuw i[[SZ]] 8, [[CNELEMSIZE2]] + + // CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 20 + // CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] + // CHECK: [[TRY]] + // CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 9, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i[[SZ]]* [[SR:%[^,]+]], i32* getelementptr inbounds ([9 x i32], [9 x i32]* [[MAPT4]], i32 0, i32 0)) + // CHECK-DAG: [[BPR]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP:%[^,]+]], i32 0, i32 0 + // CHECK-DAG: [[PR]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P:%[^,]+]], i32 0, i32 0 + // CHECK-DAG: [[SR]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S:%[^,]+]], i32 0, i32 0 + + // CHECK-DAG: [[SADDR0:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX0:[0-9]+]] + // CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX0]] + // CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX0]] + // CHECK-DAG: [[SADDR1:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX1:[0-9]+]] + // CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX1]] + // CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX1]] + // CHECK-DAG: [[SADDR2:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX2:[0-9]+]] + // CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX2]] + // CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX2]] + // CHECK-DAG: [[SADDR3:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX3:[0-9]+]] + // CHECK-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX3]] + // CHECK-DAG: [[PADDR3:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX3]] + // CHECK-DAG: [[SADDR4:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX4:[0-9]+]] + // CHECK-DAG: [[BPADDR4:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX4]] + // CHECK-DAG: [[PADDR4:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX4]] + // CHECK-DAG: [[SADDR5:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX5:[0-9]+]] + // CHECK-DAG: [[BPADDR5:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX5]] + // CHECK-DAG: [[PADDR5:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX5]] + // CHECK-DAG: [[SADDR6:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX6:[0-9]+]] + // CHECK-DAG: [[BPADDR6:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX6]] + // CHECK-DAG: [[PADDR6:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX6]] + // CHECK-DAG: [[SADDR7:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX7:[0-9]+]] + // CHECK-DAG: [[BPADDR7:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX7]] + // CHECK-DAG: [[PADDR7:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX7]] + // CHECK-DAG: [[SADDR8:%.+]] = getelementptr inbounds [9 x i[[SZ]]], [9 x i[[SZ]]]* [[S]], i32 0, i32 [[IDX8:[0-9]+]] + // CHECK-DAG: [[BPADDR8:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[BP]], i32 0, i32 [[IDX8]] + // CHECK-DAG: [[PADDR8:%.+]] = getelementptr inbounds [9 x i8*], [9 x i8*]* [[P]], i32 0, i32 [[IDX8]] + + // The names below are not necessarily consistent with the names used for the + // addresses above as some are repeated. + // CHECK-DAG: [[BP0:%[^,]+]] = bitcast i[[SZ]]* [[VLA0]] to i8* + // CHECK-DAG: [[P0:%[^,]+]] = bitcast i[[SZ]]* [[VLA0]] to i8* + // CHECK-DAG: store i8* [[BP0]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P0]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] {{4|8}}, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP1:%[^,]+]] = bitcast i[[SZ]]* [[VLA1]] to i8* + // CHECK-DAG: [[P1:%[^,]+]] = bitcast i[[SZ]]* [[VLA1]] to i8* + // CHECK-DAG: store i8* [[BP1]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P1]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] {{4|8}}, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP2:%[^,]+]] = bitcast i[[SZ]]* [[VLA2]] to i8* + // CHECK-DAG: [[P2:%[^,]+]] = bitcast i[[SZ]]* [[VLA2]] to i8* + // CHECK-DAG: store i8* [[BP2]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P2]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] {{4|8}}, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP3:%[^,]+]] = bitcast i32* %{{.+}} to i8* + // CHECK-DAG: [[P3:%[^,]+]] = bitcast i32* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP3]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P3]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] 4, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP4:%[^,]+]] = bitcast [10 x float]* %{{.+}} to i8* + // CHECK-DAG: [[P4:%[^,]+]] = bitcast [10 x float]* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP4]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P4]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] 40, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP5:%[^,]+]] = bitcast float* %{{.+}} to i8* + // CHECK-DAG: [[P5:%[^,]+]] = bitcast float* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP5]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P5]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] [[BNSIZE]], i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP6:%[^,]+]] = bitcast [5 x [10 x double]]* %{{.+}} to i8* + // CHECK-DAG: [[P6:%[^,]+]] = bitcast [5 x [10 x double]]* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP6]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P6]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] 400, i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP7:%[^,]+]] = bitcast double* %{{.+}} to i8* + // CHECK-DAG: [[P7:%[^,]+]] = bitcast double* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP7]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P7]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] [[CNSIZE]], i[[SZ]]* {{%[^,]+}} + + // CHECK-DAG: [[BP8:%[^,]+]] = bitcast [[TT]]* %{{.+}} to i8* + // CHECK-DAG: [[P8:%[^,]+]] = bitcast [[TT]]* %{{.+}} to i8* + // CHECK-DAG: store i8* [[BP8]], i8** {{%[^,]+}} + // CHECK-DAG: store i8* [[P8]], i8** {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] {{12|16}}, i[[SZ]]* {{%[^,]+}} + + // CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 + // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL]], label %[[END:[^,]+]] + // CHECK: [[FAIL]] + // CHECK: call void [[HVT4:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) + // CHECK-NEXT: br label %[[END]] + // CHECK: [[END]] + #pragma omp target if(n>20) + { + a += 1; + b[2] += 1.0; + bn[3] += 1.0; + c[1][2] += 1.0; + cn[1][3] += 1.0; + d.X += 1; + d.Y += 1; + } + + return a; +} + +// Check that the offloading functions are emitted and that the arguments are +// correct and loaded correctly for the target regions in foo(). + +// CHECK: define internal void [[HVT0]]() + +// CHECK: define internal void [[HVT1]](i32* dereferenceable(4) %{{.+}}) +// Create stack storage and store argument in there. +// CHECK: [[A_ADDR:%.+]] = alloca i32*, align +// CHECK: store i32* %{{.+}}, i32** [[A_ADDR]], align +// CHECK: [[A_ADDR2:%.+]] = load i32*, i32** [[A_ADDR]], align +// CHECK: load i32, i32* [[A_ADDR2]], align + +// CHECK: define internal void [[HVT2]](i16* dereferenceable(2) %{{.+}}) +// Create stack storage and store argument in there. +// CHECK: [[AA_ADDR:%.+]] = alloca i16*, align +// CHECK: store i16* %{{.+}}, i16** [[AA_ADDR]], align +// CHECK: [[AA_ADDR2:%.+]] = load i16*, i16** [[AA_ADDR]], align +// CHECK: load i16, i16* [[AA_ADDR2]], align + +// CHECK: define internal void [[HVT3]] +// Create stack storage and store argument in there. +// CHECK-DAG: [[A_ADDR:%.+]] = alloca i32*, align +// CHECK-DAG: [[AA_ADDR:%.+]] = alloca i16*, align +// CHECK-DAG: store i32* %{{.+}}, i32** [[A_ADDR]], align +// CHECK-DAG: store i16* %{{.+}}, i16** [[AA_ADDR]], align +// CHECK-DAG: [[A_ADDR2:%.+]] = load i32*, i32** [[A_ADDR]], align +// CHECK-DAG: [[AA_ADDR2:%.+]] = load i16*, i16** [[AA_ADDR]], align +// CHECK-DAG: load i32, i32* [[A_ADDR2]], align +// CHECK-DAG: load i16, i16* [[AA_ADDR2]], align + +// CHECK: define internal void [[HVT4]] +// Create local storage for each capture. +// CHECK-DAG: [[LOCAL_A:%.+]] = alloca i32* +// CHECK-DAG: [[LOCAL_B:%.+]] = alloca [10 x float]* +// CHECK-DAG: [[LOCAL_VLA1:%.+]] = alloca i[[SZ]]* +// CHECK-DAG: [[LOCAL_BN:%.+]] = alloca float* +// CHECK-DAG: [[LOCAL_C:%.+]] = alloca [5 x [10 x double]]* +// CHECK-DAG: [[LOCAL_VLA2:%.+]] = alloca i[[SZ]]* +// CHECK-DAG: [[LOCAL_VLA3:%.+]] = alloca i[[SZ]]* +// CHECK-DAG: [[LOCAL_CN:%.+]] = alloca double* +// CHECK-DAG: [[LOCAL_D:%.+]] = alloca [[TT]]* +// CHECK-DAG: store i32* [[ARG_A:%.+]], i32** [[LOCAL_A]] +// CHECK-DAG: store [10 x float]* [[ARG_B:%.+]], [10 x float]** [[LOCAL_B]] +// CHECK-DAG: store i[[SZ]]* [[ARG_VLA1:%.+]], i[[SZ]]** [[LOCAL_VLA1]] +// CHECK-DAG: store float* [[ARG_BN:%.+]], float** [[LOCAL_BN]] +// CHECK-DAG: store [5 x [10 x double]]* [[ARG_C:%.+]], [5 x [10 x double]]** [[LOCAL_C]] +// CHECK-DAG: store i[[SZ]]* [[ARG_VLA2:%.+]], i[[SZ]]** [[LOCAL_VLA2]] +// CHECK-DAG: store i[[SZ]]* [[ARG_VLA3:%.+]], i[[SZ]]** [[LOCAL_VLA3]] +// CHECK-DAG: store double* [[ARG_CN:%.+]], double** [[LOCAL_CN]] +// CHECK-DAG: store [[TT]]* [[ARG_D:%.+]], [[TT]]** [[LOCAL_D]] + +// CHECK-DAG: [[REF_A:%.+]] = load i32*, i32** [[LOCAL_A]], +// CHECK-DAG: [[REF_B:%.+]] = load [10 x float]*, [10 x float]** [[LOCAL_B]], +// CHECK-DAG: [[REF_VLA1:%.+]] = load i[[SZ]]*, i[[SZ]]** [[LOCAL_VLA1]], +// CHECK-DAG: [[VAL_VLA1:%.+]] = load i[[SZ]], i[[SZ]]* [[REF_VLA1]], +// CHECK-DAG: [[REF_BN:%.+]] = load float*, float** [[LOCAL_BN]], +// CHECK-DAG: [[REF_C:%.+]] = load [5 x [10 x double]]*, [5 x [10 x double]]** [[LOCAL_C]], +// CHECK-DAG: [[REF_VLA2:%.+]] = load i[[SZ]]*, i[[SZ]]** [[LOCAL_VLA2]], +// CHECK-DAG: [[VAL_VLA2:%.+]] = load i[[SZ]], i[[SZ]]* [[REF_VLA2]], +// CHECK-DAG: [[REF_VLA3:%.+]] = load i[[SZ]]*, i[[SZ]]** [[LOCAL_VLA3]], +// CHECK-DAG: [[VAL_VLA3:%.+]] = load i[[SZ]], i[[SZ]]* [[REF_VLA3]], +// CHECK-DAG: [[REF_CN:%.+]] = load double*, double** [[LOCAL_CN]], +// CHECK-DAG: [[REF_D:%.+]] = load [[TT]]*, [[TT]]** [[LOCAL_D]], + +// Use captures. +// CHECK-DAG: load i32, i32* [[REF_A]] +// CHECK-DAG: getelementptr inbounds [10 x float], [10 x float]* [[REF_B]], i[[SZ]] 0, i[[SZ]] 2 +// CHECK-DAG: getelementptr inbounds float, float* [[REF_BN]], i[[SZ]] 3 +// CHECK-DAG: getelementptr inbounds [5 x [10 x double]], [5 x [10 x double]]* [[REF_C]], i[[SZ]] 0, i[[SZ]] 1 +// CHECK-DAG: getelementptr inbounds double, double* [[REF_CN]], i[[SZ]] %{{.+}} +// CHECK-DAG: getelementptr inbounds [[TT]], [[TT]]* [[REF_D]], i32 0, i32 0 + +template<typename tx> +tx ftemplate(int n) { + tx a = 0; + short aa = 0; + tx b[10]; + + #pragma omp target if(n>40) + { + a += 1; + aa += 1; + b[2] += 1; + } + + return a; +} + +static +int fstatic(int n) { + int a = 0; + short aa = 0; + char aaa = 0; + int b[10]; + + #pragma omp target if(n>50) + { + a += 1; + aa += 1; + aaa += 1; + b[2] += 1; + } + + return a; +} + +struct S1 { + double a; + + int r1(int n){ + int b = n+1; + short int c[2][n]; + + #pragma omp target if(n>60) + { + this->a = (double)b + 1.5; + c[1][1] = ++a; + } + + return c[1][1] + (int)b; + } +}; + +// CHECK: define {{.*}}@{{.*}}bar{{.*}} +int bar(int n){ + int a = 0; + + // CHECK: call {{.*}}i32 [[FOO]](i32 {{.*}}) + a += foo(n); + + S1 S; + // CHECK: call {{.*}}i32 [[FS1:@.+]]([[S1]]* {{.*}}, i32 {{.*}}) + a += S.r1(n); + + // CHECK: call {{.*}}i32 [[FSTATIC:@.+]](i32 {{.*}}) + a += fstatic(n); + + // CHECK: call {{.*}}i32 [[FTEMPLATE:@.+]](i32 {{.*}}) + a += ftemplate<int>(n); + + return a; +} + +// +// CHECK: define {{.*}}[[FS1]] +// +// We capture 2 VLA sizes in this target region +// CHECK: store i[[SZ]] 2, i[[SZ]]* [[VLA0:%[^,]+]] +// CHECK: store i[[SZ]] [[CELEMSIZE1:%.+]], i[[SZ]]* [[VLA1:%[^,]+]] +// CHECK: [[CELEMSIZE2:%.+]] = mul nuw i[[SZ]] 2, [[CELEMSIZE1]] +// CHECK: [[CSIZE:%.+]] = mul nuw i[[SZ]] 2, [[CELEMSIZE2]] + +// CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 60 +// CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] +// CHECK: [[TRY]] +// CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 5, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i[[SZ]]* [[SR:%[^,]+]], i32* getelementptr inbounds ([5 x i32], [5 x i32]* [[MAPT7]], i32 0, i32 0)) +// CHECK-DAG: [[BPR]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[BP:%.+]], i32 0, i32 0 +// CHECK-DAG: [[PR]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[P:%.+]], i32 0, i32 0 +// CHECK-DAG: [[SR]] = getelementptr inbounds [5 x i[[SZ]]], [5 x i[[SZ]]]* [[S:%.+]], i32 0, i32 0 +// CHECK-DAG: [[SADDR0:%.+]] = getelementptr inbounds [5 x i[[SZ]]], [5 x i[[SZ]]]* [[S]], i32 [[IDX0:[0-9]+]] +// CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[BP]], i32 [[IDX0]] +// CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[P]], i32 [[IDX0]] +// CHECK-DAG: [[SADDR1:%.+]] = getelementptr inbounds [5 x i[[SZ]]], [5 x i[[SZ]]]* [[S]], i32 [[IDX1:[0-9]+]] +// CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[BP]], i32 [[IDX1]] +// CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[P]], i32 [[IDX1]] +// CHECK-DAG: [[SADDR2:%.+]] = getelementptr inbounds [5 x i[[SZ]]], [5 x i[[SZ]]]* [[S]], i32 [[IDX2:[0-9]+]] +// CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[BP]], i32 [[IDX2]] +// CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[P]], i32 [[IDX2]] +// CHECK-DAG: [[SADDR3:%.+]] = getelementptr inbounds [5 x i[[SZ]]], [5 x i[[SZ]]]* [[S]], i32 [[IDX3:[0-9]+]] +// CHECK-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[BP]], i32 [[IDX3]] +// CHECK-DAG: [[PADDR3:%.+]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[P]], i32 [[IDX3]] + +// The names below are not necessarily consistent with the names used for the +// addresses above as some are repeated. +// CHECK-DAG: [[BP0:%[^,]+]] = bitcast i[[SZ]]* [[VLA0]] to i8* +// CHECK-DAG: [[P0:%[^,]+]] = bitcast i[[SZ]]* [[VLA0]] to i8* +// CHECK-DAG: store i8* [[BP0]], i8** {{%[^,]+}} +// CHECK-DAG: store i8* [[P0]], i8** {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] {{4|8}}, i[[SZ]]* {{%[^,]+}} + +// CHECK-DAG: [[BP1:%[^,]+]] = bitcast i[[SZ]]* [[VLA1]] to i8* +// CHECK-DAG: [[P1:%[^,]+]] = bitcast i[[SZ]]* [[VLA1]] to i8* +// CHECK-DAG: store i8* [[BP1]], i8** {{%[^,]+}} +// CHECK-DAG: store i8* [[P1]], i8** {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] {{4|8}}, i[[SZ]]* {{%[^,]+}} + +// CHECK-DAG: [[BP2:%[^,]+]] = bitcast i32* %{{.+}} to i8* +// CHECK-DAG: [[P2:%[^,]+]] = bitcast i32* %{{.+}} to i8* +// CHECK-DAG: store i8* [[BP2]], i8** {{%[^,]+}} +// CHECK-DAG: store i8* [[P2]], i8** {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] 4, i[[SZ]]* {{%[^,]+}} + +// CHECK-DAG: [[BP3:%[^,]+]] = bitcast [[S1]]* %{{.+}} to i8* +// CHECK-DAG: [[P3:%[^,]+]] = bitcast [[S1]]* %{{.+}} to i8* +// CHECK-DAG: store i8* [[BP3]], i8** {{%[^,]+}} +// CHECK-DAG: store i8* [[P3]], i8** {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] 8, i[[SZ]]* {{%[^,]+}} + +// CHECK-DAG: [[BP4:%[^,]+]] = bitcast i16* %{{.+}} to i8* +// CHECK-DAG: [[P4:%[^,]+]] = bitcast i16* %{{.+}} to i8* +// CHECK-DAG: store i8* [[BP4]], i8** {{%[^,]+}} +// CHECK-DAG: store i8* [[P4]], i8** {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] [[CSIZE]], i[[SZ]]* {{%[^,]+}} + +// CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 +// CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL]], label %[[END:[^,]+]] +// CHECK: [[FAIL]] +// CHECK: call void [[HVT7:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) +// CHECK-NEXT: br label %[[END]] +// CHECK: [[END]] + +// +// CHECK: define {{.*}}[[FSTATIC]] +// +// CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 50 +// CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] +// CHECK: [[TRY]] +// CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 4, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i[[SZ]]* getelementptr inbounds ([4 x i[[SZ]]], [4 x i[[SZ]]]* [[SIZET6]], i32 0, i32 0), i32* getelementptr inbounds ([4 x i32], [4 x i32]* [[MAPT6]], i32 0, i32 0)) +// CHECK-DAG: [[BPR]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[BP:%.+]], i32 0, i32 0 +// CHECK-DAG: [[PR]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[P:%.+]], i32 0, i32 0 + +// CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[BP]], i32 0, i32 0 +// CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[P]], i32 0, i32 0 +// CHECK-DAG: store i8* [[BP0:%[^,]+]], i8** [[BPADDR0]] +// CHECK-DAG: store i8* [[P0:%[^,]+]], i8** [[PADDR0]] +// CHECK-DAG: [[BP0]] = bitcast i32* %{{.+}} to i8* +// CHECK-DAG: [[P0]] = bitcast i32* %{{.+}} to i8* + +// CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[BP]], i32 0, i32 1 +// CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[P]], i32 0, i32 1 +// CHECK-DAG: store i8* [[BP1:%[^,]+]], i8** [[BPADDR1]] +// CHECK-DAG: store i8* [[P1:%[^,]+]], i8** [[PADDR1]] +// CHECK-DAG: [[BP1]] = bitcast i16* %{{.+}} to i8* +// CHECK-DAG: [[P1]] = bitcast i16* %{{.+}} to i8* + +// CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[BP]], i32 0, i32 2 +// CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[P]], i32 0, i32 2 +// CHECK-DAG: store i8* [[BP2:%[^,]+]], i8** [[BPADDR2]] +// CHECK-DAG: store i8* [[P2:%[^,]+]], i8** [[PADDR2]] + +// CHECK-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[BP]], i32 0, i32 3 +// CHECK-DAG: [[PADDR3:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[P]], i32 0, i32 3 +// CHECK-DAG: store i8* [[BP3:%[^,]+]], i8** [[BPADDR3]] +// CHECK-DAG: store i8* [[P3:%[^,]+]], i8** [[PADDR3]] +// CHECK-DAG: [[BP3]] = bitcast [10 x i32]* %{{.+}} to i8* +// CHECK-DAG: [[P3]] = bitcast [10 x i32]* %{{.+}} to i8* + +// CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 +// CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL]], label %[[END:[^,]+]] +// CHECK: [[FAIL]] +// CHECK: call void [[HVT6:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) +// CHECK-NEXT: br label %[[END]] +// CHECK: [[END]] + +// +// CHECK: define {{.*}}[[FTEMPLATE]] +// +// CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 40 +// CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] +// CHECK: [[TRY]] +// CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i[[SZ]]* getelementptr inbounds ([3 x i[[SZ]]], [3 x i[[SZ]]]* [[SIZET5]], i32 0, i32 0), i32* getelementptr inbounds ([3 x i32], [3 x i32]* [[MAPT5]], i32 0, i32 0)) +// CHECK-DAG: [[BPR]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[BP:%.+]], i32 0, i32 0 +// CHECK-DAG: [[PR]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[P:%.+]], i32 0, i32 0 + +// CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[BP]], i32 0, i32 0 +// CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[P]], i32 0, i32 0 +// CHECK-DAG: store i8* [[BP0:%[^,]+]], i8** [[BPADDR0]] +// CHECK-DAG: store i8* [[P0:%[^,]+]], i8** [[PADDR0]] +// CHECK-DAG: [[BP0]] = bitcast i32* %{{.+}} to i8* +// CHECK-DAG: [[P0]] = bitcast i32* %{{.+}} to i8* + +// CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[BP]], i32 0, i32 1 +// CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[P]], i32 0, i32 1 +// CHECK-DAG: store i8* [[BP1:%[^,]+]], i8** [[BPADDR1]] +// CHECK-DAG: store i8* [[P1:%[^,]+]], i8** [[PADDR1]] +// CHECK-DAG: [[BP1]] = bitcast i16* %{{.+}} to i8* +// CHECK-DAG: [[P1]] = bitcast i16* %{{.+}} to i8* + +// CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[BP]], i32 0, i32 2 +// CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[P]], i32 0, i32 2 +// CHECK-DAG: store i8* [[BP2:%[^,]+]], i8** [[BPADDR2]] +// CHECK-DAG: store i8* [[P2:%[^,]+]], i8** [[PADDR2]] +// CHECK-DAG: [[BP2]] = bitcast [10 x i32]* %{{.+}} to i8* +// CHECK-DAG: [[P2]] = bitcast [10 x i32]* %{{.+}} to i8* + +// CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 +// CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL]], label %[[END:[^,]+]] +// CHECK: [[FAIL]] +// CHECK: call void [[HVT5:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}) +// CHECK-NEXT: br label %[[END]] +// CHECK: [[END]] + +// Check that the offloading functions are emitted and that the arguments are +// correct and loaded correctly for the target regions of the callees of bar(). + +// CHECK: define internal void [[HVT7]] +// Create local storage for each capture. +// CHECK-DAG: [[LOCAL_THIS:%.+]] = alloca [[S1]]* +// CHECK-DAG: [[LOCAL_B:%.+]] = alloca i32* +// CHECK-DAG: [[LOCAL_VLA1:%.+]] = alloca i[[SZ]]* +// CHECK-DAG: [[LOCAL_VLA2:%.+]] = alloca i[[SZ]]* +// CHECK-DAG: [[LOCAL_C:%.+]] = alloca i16* +// CHECK-DAG: store [[S1]]* [[ARG_THIS:%.+]], [[S1]]** [[LOCAL_THIS]] +// CHECK-DAG: store i32* [[ARG_B:%.+]], i32** [[LOCAL_B]] +// CHECK-DAG: store i[[SZ]]* [[ARG_VLA1:%.+]], i[[SZ]]** [[LOCAL_VLA1]] +// CHECK-DAG: store i[[SZ]]* [[ARG_VLA2:%.+]], i[[SZ]]** [[LOCAL_VLA2]] +// CHECK-DAG: store i16* [[ARG_C:%.+]], i16** [[LOCAL_C]] +// Store captures in the context. +// CHECK-DAG: [[REF_THIS:%.+]] = load [[S1]]*, [[S1]]** [[LOCAL_THIS]], +// CHECK-DAG: [[REF_B:%.+]] = load i32*, i32** [[LOCAL_B]], +// CHECK-DAG: [[REF_VLA1:%.+]] = load i[[SZ]]*, i[[SZ]]** [[LOCAL_VLA1]], +// CHECK-DAG: [[VAL_VLA1:%.+]] = load i[[SZ]], i[[SZ]]* [[REF_VLA1]], +// CHECK-DAG: [[REF_VLA2:%.+]] = load i[[SZ]]*, i[[SZ]]** [[LOCAL_VLA2]], +// CHECK-DAG: [[VAL_VLA2:%.+]] = load i[[SZ]], i[[SZ]]* [[REF_VLA2]], +// CHECK-DAG: [[REF_C:%.+]] = load i16*, i16** [[LOCAL_C]], +// Use captures. +// CHECK-DAG: getelementptr inbounds [[S1]], [[S1]]* [[REF_THIS]], i32 0, i32 0 +// CHECK-DAG: load i32, i32* [[REF_B]] +// CHECK-DAG: getelementptr inbounds i16, i16* [[REF_C]], i[[SZ]] %{{.+}} + + +// CHECK: define internal void [[HVT6]] +// Create local storage for each capture. +// CHECK-DAG: [[LOCAL_A:%.+]] = alloca i32* +// CHECK-DAG: [[LOCAL_AA:%.+]] = alloca i16* +// CHECK-DAG: [[LOCAL_AAA:%.+]] = alloca i8* +// CHECK-DAG: [[LOCAL_B:%.+]] = alloca [10 x i32]* +// CHECK-DAG: store i32* [[ARG_A:%.+]], i32** [[LOCAL_A]] +// CHECK-DAG: store i16* [[ARG_AA:%.+]], i16** [[LOCAL_AA]] +// CHECK-DAG: store i8* [[ARG_AAA:%.+]], i8** [[LOCAL_AAA]] +// CHECK-DAG: store [10 x i32]* [[ARG_B:%.+]], [10 x i32]** [[LOCAL_B]] +// Store captures in the context. +// CHECK-DAG: [[REF_A:%.+]] = load i32*, i32** [[LOCAL_A]], +// CHECK-DAG: [[REF_AA:%.+]] = load i16*, i16** [[LOCAL_AA]], +// CHECK-DAG: [[REF_AAA:%.+]] = load i8*, i8** [[LOCAL_AAA]], +// CHECK-DAG: [[REF_B:%.+]] = load [10 x i32]*, [10 x i32]** [[LOCAL_B]], +// Use captures. +// CHECK-DAG: load i32, i32* [[REF_A]] +// CHECK-DAG: load i16, i16* [[REF_AA]] +// CHECK-DAG: load i8, i8* [[REF_AAA]] +// CHECK-DAG: getelementptr inbounds [10 x i32], [10 x i32]* [[REF_B]], i[[SZ]] 0, i[[SZ]] 2 + +// CHECK: define internal void [[HVT5]] +// Create local storage for each capture. +// CHECK-DAG: [[LOCAL_A:%.+]] = alloca i32* +// CHECK-DAG: [[LOCAL_AA:%.+]] = alloca i16* +// CHECK-DAG: [[LOCAL_B:%.+]] = alloca [10 x i32]* +// CHECK-DAG: store i32* [[ARG_A:%.+]], i32** [[LOCAL_A]] +// CHECK-DAG: store i16* [[ARG_AA:%.+]], i16** [[LOCAL_AA]] +// CHECK-DAG: store [10 x i32]* [[ARG_B:%.+]], [10 x i32]** [[LOCAL_B]] +// Store captures in the context. +// CHECK-DAG: [[REF_A:%.+]] = load i32*, i32** [[LOCAL_A]], +// CHECK-DAG: [[REF_AA:%.+]] = load i16*, i16** [[LOCAL_AA]], +// CHECK-DAG: [[REF_B:%.+]] = load [10 x i32]*, [10 x i32]** [[LOCAL_B]], +// Use captures. +// CHECK-DAG: load i32, i32* [[REF_A]] +// CHECK-DAG: load i16, i16* [[REF_AA]] +// CHECK-DAG: getelementptr inbounds [10 x i32], [10 x i32]* [[REF_B]], i[[SZ]] 0, i[[SZ]] 2 +#endif Index: lib/CodeGen/CodeGenFunction.h =================================================================== --- lib/CodeGen/CodeGenFunction.h +++ lib/CodeGen/CodeGenFunction.h @@ -2192,9 +2192,12 @@ llvm::Function *EmitCapturedStmt(const CapturedStmt &S, CapturedRegionKind K); llvm::Function *GenerateCapturedStmtFunction(const CapturedStmt &S); Address GenerateCapturedStmtArgument(const CapturedStmt &S); - llvm::Function *GenerateOpenMPCapturedStmtFunction(const CapturedStmt &S); + llvm::Function * + GenerateOpenMPCapturedStmtFunction(const CapturedStmt &S, + bool UseOnlyReferences = false); void GenerateOpenMPCapturedVars(const CapturedStmt &S, - SmallVectorImpl<llvm::Value *> &CapturedVars); + SmallVectorImpl<llvm::Value *> &CapturedVars, + bool UseOnlyReferences = false); /// \brief Perform element by element copying of arrays with type \a /// OriginalType from \a SrcAddr to \a DestAddr using copying procedure /// generated by \a CopyGen. Index: lib/CodeGen/CGStmtOpenMP.cpp =================================================================== --- lib/CodeGen/CGStmtOpenMP.cpp +++ lib/CodeGen/CGStmtOpenMP.cpp @@ -21,25 +21,37 @@ using namespace CodeGen; void CodeGenFunction::GenerateOpenMPCapturedVars( - const CapturedStmt &S, SmallVectorImpl<llvm::Value *> &CapturedVars) { + const CapturedStmt &S, SmallVectorImpl<llvm::Value *> &CapturedVars, + bool UseOnlyReferences) { const RecordDecl *RD = S.getCapturedRecordDecl(); auto CurField = RD->field_begin(); auto CurCap = S.captures().begin(); for (CapturedStmt::const_capture_init_iterator I = S.capture_init_begin(), E = S.capture_init_end(); I != E; ++I, ++CurField, ++CurCap) { if (CurField->hasCapturedVLAType()) { auto VAT = CurField->getCapturedVLAType(); - CapturedVars.push_back(VLASizeMap[VAT->getSizeExpr()]); + auto *Val = VLASizeMap[VAT->getSizeExpr()]; + // If we need to use only references, create a temporary location for the + // size of the VAT. + if (UseOnlyReferences) { + LValue LV = MakeNaturalAlignAddrLValue( + CreateMemTemp(CurField->getType(), "__vla_size_ref").getPointer(), + CurField->getType()); + EmitStoreThroughLValue(RValue::get(Val), LV); + Val = LV.getAddress().getPointer(); + } + CapturedVars.push_back(Val); } else if (CurCap->capturesThis()) CapturedVars.push_back(CXXThisValue); else CapturedVars.push_back(EmitLValue(*I).getAddress().getPointer()); } } llvm::Function * -CodeGenFunction::GenerateOpenMPCapturedStmtFunction(const CapturedStmt &S) { +CodeGenFunction::GenerateOpenMPCapturedStmtFunction(const CapturedStmt &S, + bool UseOnlyReferences) { assert( CapturedStmtInfo && "CapturedStmtInfo should be set when generating the captured function"); @@ -65,6 +77,8 @@ else { assert(I->capturesVariableArrayType()); II = &getContext().Idents.get("vla"); + if (UseOnlyReferences) + ArgType = getContext().getPointerType(ArgType); } if (ArgType->isVariablyModifiedType()) ArgType = getContext().getVariableArrayDecayedType(ArgType); @@ -102,6 +116,10 @@ if (FD->hasCapturedVLAType()) { auto *ExprArg = EmitLoadOfLValue(ArgLVal, SourceLocation()).getScalarVal(); + if (UseOnlyReferences) { + auto ExprArgRef = MakeNaturalAlignAddrLValue(ExprArg, FD->getType()); + ExprArg = EmitLoadOfLValue(ExprArgRef, SourceLocation()).getScalarVal(); + } auto VAT = FD->getCapturedVLAType(); VLASizeMap[VAT->getSizeExpr()] = ExprArg; } else if (I->capturesVariable()) { @@ -2230,8 +2248,37 @@ CGM.getOpenMPRuntime().emitInlinedDirective(*this, OMPD_atomic, CodeGen); } -void CodeGenFunction::EmitOMPTargetDirective(const OMPTargetDirective &) { - llvm_unreachable("CodeGen for 'omp target' is not supported yet."); +void CodeGenFunction::EmitOMPTargetDirective(const OMPTargetDirective &S) { + LexicalScope Scope(*this, S.getSourceRange()); + const CapturedStmt &CS = *cast<CapturedStmt>(S.getAssociatedStmt()); + + llvm::SmallVector<llvm::Value *, 16> CapturedVars; + GenerateOpenMPCapturedVars(CS, CapturedVars, /*UseOnlyReferences=*/true); + + // Emit target region as a standalone region. + auto &&CodeGen = [&CS](CodeGenFunction &CGF) { + CGF.EmitStmt(CS.getCapturedStmt()); + }; + + // Obtain the target region outlined function. + llvm::Value *Fn = + CGM.getOpenMPRuntime().emitTargetOutlinedFunction(S, CodeGen); + + // Check if we have any if clause associated with the directive. + const Expr *IfCond = nullptr; + + if (auto *C = S.getSingleClause<OMPIfClause>()) { + IfCond = C->getCondition(); + } + + // Check if we have any device clause associated with the directive. + const Expr *Device = nullptr; + if (auto *C = S.getSingleClause<OMPDeviceClause>()) { + Device = C->getDevice(); + } + + CGM.getOpenMPRuntime().emitTargetCall(*this, S, Fn, IfCond, Device, + CapturedVars); } void CodeGenFunction::EmitOMPTeamsDirective(const OMPTeamsDirective &) { Index: lib/CodeGen/CGOpenMPRuntime.h =================================================================== --- lib/CodeGen/CGOpenMPRuntime.h +++ lib/CodeGen/CGOpenMPRuntime.h @@ -154,6 +154,14 @@ // Call to kmp_int32 __kmpc_cancel(ident_t *loc, kmp_int32 global_tid, // kmp_int32 cncl_kind); OMPRTL__kmpc_cancel, + + // + // Offloading related calls + // + // Call to int32_t __tgt_target(int32_t device_id, void *host_ptr, int32_t + // arg_num, void** args_base, void **args, size_t *arg_sizes, int32_t + // *arg_types); + OMPRTL__tgt_target, }; /// \brief Values for bit flags used in the ident_t to describe the fields. @@ -716,6 +724,29 @@ /// virtual void emitCancelCall(CodeGenFunction &CGF, SourceLocation Loc, OpenMPDirectiveKind CancelRegion); + + /// \brief Emit outilined function for 'target' directive. + /// \param D Directive to emit. + /// \param CodeGen Code generation sequence for the \a D directive. + virtual llvm::Value * + emitTargetOutlinedFunction(const OMPExecutableDirective &D, + const RegionCodeGenTy &CodeGen); + + /// \brief Emit the target offloading code associated with \a D. The emitted + /// code attempts offloading the execution to the device, an the event of + /// a failure it executes the host version outlined in \a OutlinedFn. + /// \param D Directive to emit. + /// \param OutlinedFn Host version of the code to be offloaded. + /// \param IfCond Expression evaluated in if clause associated with the target + /// directive, or null if no if clause is used. + /// \param Device Expression evaluated in device clause associated with the + /// target directive, or null if no device clause is used. + /// \param CapturedVars Values captured in the current region. + virtual void emitTargetCall(CodeGenFunction &CGF, + const OMPExecutableDirective &D, + llvm::Value *OutlinedFn, const Expr *IfCond, + const Expr *Device, + ArrayRef<llvm::Value *> CapturedVars); }; } // namespace CodeGen Index: lib/CodeGen/CGOpenMPRuntime.cpp =================================================================== --- lib/CodeGen/CGOpenMPRuntime.cpp +++ lib/CodeGen/CGOpenMPRuntime.cpp @@ -41,6 +41,8 @@ /// \brief Region for constructs that do not require function outlining, /// like 'for', 'sections', 'atomic' etc. directives. InlinedRegion, + /// \brief Region with outlined function for standalone 'target' directive. + TargetRegion, }; CGOpenMPRegionInfo(const CapturedStmt &CS, @@ -204,6 +206,28 @@ CGOpenMPRegionInfo *OuterRegionInfo; }; +/// \brief API for captured statement code generation in OpenMP target +/// constructs. For this captures, implicit parameters are used instead of the +/// captured fields. +class CGOpenMPTargetRegionInfo : public CGOpenMPRegionInfo { +public: + CGOpenMPTargetRegionInfo(const CapturedStmt &CS, + const RegionCodeGenTy &CodeGen) + : CGOpenMPRegionInfo(CS, TargetRegion, CodeGen, OMPD_target) {} + + /// \brief This is unused for target regions because each starts executing + /// with a single thread. + const VarDecl *getThreadIDVariable() const override { return nullptr; } + + /// \brief Get the name of the capture helper. + StringRef getHelperName() const override { return ".omp_offloading."; } + + static bool classof(const CGCapturedStmtInfo *Info) { + return CGOpenMPRegionInfo::classof(Info) && + cast<CGOpenMPRegionInfo>(Info)->getRegionKind() == TargetRegion; + } +}; + /// \brief RAII for emitting code of OpenMP constructs. class InlinedOpenMPRegionRAII { CodeGenFunction &CGF; @@ -861,6 +885,22 @@ RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_cancel"); break; } + case OMPRTL__tgt_target: { + // Build int32_t __tgt_target(int32_t device_id, void *host_ptr, int32_t + // arg_num, void** args_base, void **args, size_t *arg_sizes, int32_t + // *arg_types); + llvm::Type *TypeParams[] = {CGM.Int32Ty, + CGM.VoidPtrTy, + CGM.Int32Ty, + CGM.VoidPtrPtrTy, + CGM.VoidPtrPtrTy, + CGM.SizeTy->getPointerTo(), + CGM.Int32Ty->getPointerTo()}; + llvm::FunctionType *FnTy = + llvm::FunctionType::get(CGM.Int32Ty, TypeParams, /*isVarArg*/ false); + RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_target"); + break; + } } return RTLFn; } @@ -2921,3 +2961,286 @@ } } } + +llvm::Value * +CGOpenMPRuntime::emitTargetOutlinedFunction(const OMPExecutableDirective &D, + const RegionCodeGenTy &CodeGen) { + const CapturedStmt &CS = *cast<CapturedStmt>(D.getAssociatedStmt()); + + CodeGenFunction CGF(CGM, true); + CGOpenMPTargetRegionInfo CGInfo(CS, CodeGen); + CodeGenFunction::CGCapturedStmtRAII CapInfoRAII(CGF, &CGInfo); + return CGF.GenerateOpenMPCapturedStmtFunction(CS, /*UseOnlyReferences=*/true); +} + +void CGOpenMPRuntime::emitTargetCall(CodeGenFunction &CGF, + const OMPExecutableDirective &D, + llvm::Value *OutlinedFn, + const Expr *IfCond, const Expr *Device, + ArrayRef<llvm::Value *> CapturedVars) { + /// \brief Values for bit flags used to specify the mapping type for + /// offloading. + enum OpenMPOffloadMappingFlags { + /// \brief Allocate memory on the device and move data from host to device. + OMP_MAP_TO = 0x01, + /// \brief Allocate memory on the device and move data from device to host. + OMP_MAP_FROM = 0x02, + }; + + enum OpenMPOffloadingReservedDeviceIDs { + /// \brief Device ID if the device was not defined, runtime should get it + /// from environment variables in the spec. + OMP_DEVICEID_UNDEF = -1, + }; + + // Fill up the arrays with the all the captured variables. + SmallVector<llvm::Value *, 16> BasePointers; + SmallVector<llvm::Value *, 16> Pointers; + SmallVector<llvm::Value *, 16> Sizes; + SmallVector<unsigned, 16> MapTypes; + + bool hasVLACaptures = false; + + const CapturedStmt &CS = *cast<CapturedStmt>(D.getAssociatedStmt()); + auto RI = CS.getCapturedRecordDecl()->field_begin(); + // auto II = CS.capture_init_begin(); + auto CV = CapturedVars.begin(); + for (CapturedStmt::const_capture_iterator CI = CS.capture_begin(), + CE = CS.capture_end(); + CI != CE; ++CI, ++RI, ++CV) { + StringRef Name; + QualType Ty; + llvm::Value *BasePointer; + llvm::Value *Pointer; + llvm::Value *Size; + unsigned MapType; + + if (CI->capturesVariableArrayType()) { + BasePointer = Pointer = *CV; + uint64_t SizeVal = + CGM.getContext().getTypeSizeInChars(RI->getType()).getQuantity(); + Size = llvm::ConstantInt::get(CGM.SizeTy, SizeVal); + + hasVLACaptures = true; + // VLA sizes don't need to be copied back from the device. + MapType = OMP_MAP_TO; + } else if (CI->capturesThis()) { + BasePointer = Pointer = *CV; + const PointerType *PtrTy = cast<PointerType>(RI->getType().getTypePtr()); + uint64_t SizeVal = CGM.getContext() + .getTypeSizeInChars(PtrTy->getPointeeType()) + .getQuantity(); + Size = llvm::ConstantInt::get(CGM.SizeTy, SizeVal); + + // Default map type. + MapType = OMP_MAP_TO | OMP_MAP_FROM; + } else { + BasePointer = Pointer = *CV; + + const ReferenceType *PtrTy = + cast<ReferenceType>(RI->getType().getTypePtr()); + QualType ElementType = PtrTy->getPointeeType(); + + if (auto *VAT = dyn_cast<VariableArrayType>(ElementType.getTypePtr())) { + auto VATInfo = CGF.getVLASize(VAT); + Size = llvm::ConstantInt::get( + CGM.SizeTy, + CGM.getContext().getTypeSizeInChars(VATInfo.second).getQuantity()); + Size = CGF.Builder.CreateNUWMul(Size, VATInfo.first); + } else { + uint64_t ElementTypeSize = + CGM.getContext().getTypeSizeInChars(ElementType).getQuantity(); + Size = llvm::ConstantInt::get(CGM.SizeTy, ElementTypeSize); + } + + // Default map type. + MapType = OMP_MAP_TO | OMP_MAP_FROM; + } + + BasePointers.push_back(BasePointer); + Pointers.push_back(Pointer); + Sizes.push_back(Size); + MapTypes.push_back(MapType); + } + + if (IfCond) { + // Check if the if clause conditional always evaluates to true or false. + // If it evaluates to false, we only need to emit the host version of the + // target region. If it evaluates to true, we can proceed with the codegen + // as if no if clause was provided. + bool CondConstant; + if (CGF.ConstantFoldsToSimpleInteger(IfCond, CondConstant)) { + if (CondConstant) { + IfCond = nullptr; + } else { + CGF.Builder.CreateCall(OutlinedFn, BasePointers); + return; + } + } + } + + // Generate the code to launch the target region. The pattern is the + // following: + // + // ... + // br IfCond (if any), omp_offload, omp_offload_fail + // + // omp_offload.try: + // ; create arrays for offloading + // error = __tgt_target(...) + // br error, omp_offload_fail, omp_offload_end + // + // omp_offload.fail: + // host_version(...) + // + // omp_offload.end: + // ... + // + + auto OffloadTryBlock = CGF.createBasicBlock("omp_offload.try"); + auto OffloadFailBlock = CGF.createBasicBlock("omp_offload.fail"); + auto ContBlock = CGF.createBasicBlock("omp_offload.end"); + + if (IfCond) + CGF.EmitBranchOnBoolExpr(IfCond, OffloadTryBlock, OffloadFailBlock, + /*TrueCount=*/0); + + CGF.EmitBlock(OffloadTryBlock); + + unsigned PointerNumVal = BasePointers.size(); + llvm::Value *PointerNum = CGF.Builder.getInt32(PointerNumVal); + llvm::Value *BasePointersArray; + llvm::Value *PointersArray; + llvm::Value *SizesArray; + llvm::Value *MapTypesArray; + + if (PointerNumVal) { + llvm::APInt PointerNumAP(32, PointerNumVal, /*isSigned=*/true); + QualType PointerArrayType = CGF.getContext().getConstantArrayType( + CGF.getContext().VoidPtrTy, PointerNumAP, ArrayType::Normal, + /*IndexTypeQuals=*/0); + + BasePointersArray = + CGF.CreateMemTemp(PointerArrayType, ".offload_baseptrs").getPointer(); + PointersArray = + CGF.CreateMemTemp(PointerArrayType, ".offload_ptrs").getPointer(); + + // If we don't have any VLA types, we can use a constant array for the map + // sizes, otherwise we need to fill up the arrays as we do for the pointers. + if (hasVLACaptures) { + QualType SizeArrayType = CGF.getContext().getConstantArrayType( + CGF.getContext().getSizeType(), PointerNumAP, ArrayType::Normal, + /*IndexTypeQuals=*/0); + SizesArray = + CGF.CreateMemTemp(SizeArrayType, ".offload_sizes").getPointer(); + } else { + // We expect all the sizes to be constant, so we collect them to create + // a constant array. + SmallVector<llvm::Constant *, 16> ConstSizes; + for (auto S : Sizes) + ConstSizes.push_back(cast<llvm::Constant>(S)); + + auto *SizesArrayInit = llvm::ConstantArray::get( + llvm::ArrayType::get(CGM.SizeTy, ConstSizes.size()), ConstSizes); + auto *SizesArrayGbl = new llvm::GlobalVariable( + CGM.getModule(), SizesArrayInit->getType(), + /*isConstant=*/true, llvm::GlobalValue::PrivateLinkage, + SizesArrayInit, ".offload_sizes"); + SizesArrayGbl->setUnnamedAddr(true); + SizesArray = SizesArrayGbl; + } + + // The map types are always constant so we don't need to generate code to + // fill arrays. Instead, we create an array constant. + llvm::Constant *MapTypesArrayInit = + llvm::ConstantDataArray::get(CGF.Builder.getContext(), MapTypes); + auto *MapTypesArrayGbl = new llvm::GlobalVariable( + CGM.getModule(), MapTypesArrayInit->getType(), + /*isConstant=*/true, llvm::GlobalValue::PrivateLinkage, + MapTypesArrayInit, ".offload_maptypes"); + MapTypesArrayGbl->setUnnamedAddr(true); + MapTypesArray = MapTypesArrayGbl; + + for (unsigned i = 0; i < PointerNumVal; ++i) { + llvm::Value *BP = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.VoidPtrTy, PointerNumVal), BasePointersArray, + 0, i); + Address BPAddr( + BP, CGM.getContext().getTypeAlignInChars(CGM.getContext().VoidPtrTy)); + CGF.Builder.CreateStore( + CGF.Builder.CreateBitCast(BasePointers[i], CGM.VoidPtrTy), BPAddr); + + llvm::Value *P = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.VoidPtrTy, PointerNumVal), PointersArray, 0, + i); + Address PAddr( + P, CGM.getContext().getTypeAlignInChars(CGM.getContext().VoidPtrTy)); + CGF.Builder.CreateStore( + CGF.Builder.CreateBitCast(Pointers[i], CGM.VoidPtrTy), PAddr); + + if (hasVLACaptures) { + llvm::Value *S = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.SizeTy, PointerNumVal), SizesArray, 0, i); + Address SAddr(S, CGM.getContext().getTypeAlignInChars( + CGM.getContext().getSizeType())); + CGF.Builder.CreateStore( + CGF.Builder.CreateIntCast(Sizes[i], CGM.SizeTy, /*isSigned=*/true), + SAddr); + } + } + + BasePointersArray = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.VoidPtrTy, PointerNumVal), BasePointersArray, + 0, 0); + PointersArray = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.VoidPtrTy, PointerNumVal), PointersArray, 0, + 0); + SizesArray = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.SizeTy, PointerNumVal), SizesArray, 0, 0); + MapTypesArray = CGF.Builder.CreateConstInBoundsGEP2_32( + llvm::ArrayType::get(CGM.Int32Ty, PointerNumVal), MapTypesArray, 0, 0); + + } else { + BasePointersArray = llvm::ConstantPointerNull::get(CGM.VoidPtrPtrTy); + PointersArray = llvm::ConstantPointerNull::get(CGM.VoidPtrPtrTy); + SizesArray = llvm::ConstantPointerNull::get(CGM.SizeTy->getPointerTo()); + MapTypesArray = llvm::ConstantPointerNull::get(CGM.Int32Ty->getPointerTo()); + } + + // On top of the arrays that were filled up, the target offloading call takes + // as arguments the device id as well as the host pointer. The host pointer + // is used by the runtime library to identify the current target region, so + // it only has to be unique and not necessarily point to anything. It could be + // the pointer to the outlined function that implements the target region, but + // we aren't using that so that the compiler doesn't need to keep that, and + // could therefore inline the host function if proven worthwhile during + // optimization. + + llvm::Value *HostPtr = new llvm::GlobalVariable( + CGM.getModule(), CGM.Int8Ty, /*isConstant=*/true, + llvm::GlobalValue::PrivateLinkage, + llvm::Constant::getNullValue(CGM.Int8Ty), ".offload_hstptr"); + + // Emit device ID if any. + llvm::Value *DeviceID; + if (Device) + DeviceID = CGF.Builder.CreateIntCast(CGF.EmitScalarExpr(Device), + CGM.Int32Ty, /*isSigned=*/true); + else + DeviceID = CGF.Builder.getInt32(OMP_DEVICEID_UNDEF); + + llvm::Value *OffloadingArgs[] = {DeviceID, HostPtr, PointerNum, + BasePointersArray, PointersArray, SizesArray, + MapTypesArray}; + auto Return = CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__tgt_target), + OffloadingArgs); + auto Error = CGF.Builder.CreateIsNotNull(Return); + CGF.Builder.CreateCondBr(Error, OffloadFailBlock, ContBlock); + + CGF.EmitBlock(OffloadFailBlock); + CGF.Builder.CreateCall(OutlinedFn, BasePointers); + CGF.EmitBranch(ContBlock); + + CGF.EmitBlock(ContBlock, /*IsFinished=*/true); + return; +}
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits