[Clang][OpenMP Offload] Move offload registration code to the wrapper

The final list of OpenMP offload targets becomes known only at the link time and since offload registration code depends on the targets list it makes sense to delay offload registration code generation to the link time instead of adding it to the host part of every fat object. This patch moves offload registration code generation from clang to the offload wrapper tool.

This is the last part of the OpenMP linker script elimination patch https://reviews.llvm.org/D64943

Differential Revision: https://reviews.llvm.org/D68746

llvm-svn: 374937

1 files changed, 25 insertions, 60 deletions

diff --git a/clang/test/OpenMP/target_parallel_codegen_registration.cpp b/clang/test/OpenMP/target_parallel_codegen_registration.cpp
index 380e00e55b4..61534d89891 100644
--- a/clang/test/OpenMP/target_parallel_codegen_registration.cpp
+++ b/clang/test/OpenMP/target_parallel_codegen_registration.cpp
@@ -52,13 +52,9 @@
 // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] }
 // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] }
 // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 }
-// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* }
-// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* }
 
 // TCHECK:    [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 }
 
-// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat
-
 // CHECK-DAG: [[A1:@.+]] = internal global [[SA]]
 // CHECK-DAG: [[A2:@.+]] = global [[SA]]
 // CHECK-DAG: [[B1:@.+]] = global [[SB]]
@@ -172,19 +168,11 @@
 // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00"
 // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section "omp_offloading_entries", align 1
 
-// CHECK: [[ENTBEGIN:@.+]] = external hidden constant [[ENTTY]]
-// CHECK: [[ENTEND:@.+]] = external hidden constant [[ENTTY]]
-// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8
-// CHECK: [[DEVEND:@.+]] = extern_weak constant i8
-// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]])
-// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]])
-
 // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function.
-// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [
+// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [
 // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null },
 // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null },
 // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null },
-// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }]
 
 // CHECK-NTARGET: @llvm.global_ctors = appending global [3   x { i32, void ()*, i8* }] [
 
@@ -354,12 +342,8 @@ struct ST {
 //TCHECK-DAG: define weak void @[[NAME12]](
 
 // CHECK-NTARGET-NOT: __tgt_target
-// CHECK-NTARGET-NOT: __tgt_register_lib
-// CHECK-NTARGET-NOT: __tgt_unregister_lib
 
 // TCHECK-NOT: __tgt_target
-// TCHECK-NOT: __tgt_register_lib
-// TCHECK-NOT: __tgt_unregister_lib
 
 // We have 2 initializers with priority 500
 //CHECK: define internal void [[P500]](
@@ -385,25 +369,6 @@ struct ST {
 //CHECK-NOT: call void @{{.+}}()
 //CHECK:     ret void
 
-// Check registration and unregistration
-
-//CHECK:     define internal void @.omp_offloading.requires_reg()
-//CHECK:     call void @__tgt_register_requires(i64 1)
-//CHECK:     ret void
-
-//CHECK:     define internal void @[[UNREGFN:.+]](i8* %0)
-//CHECK-SAME: comdat($[[REGFN]]) {
-//CHECK:     call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]])
-//CHECK:     ret void
-//CHECK:     declare i32 @__tgt_unregister_lib([[DSCTY]]*)
-
-//CHECK:     define linkonce hidden void @[[REGFN]]()
-//CHECK-SAME: comdat {
-//CHECK:     call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]])
-//CHECK:     call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*),
-//CHECK:     ret void
-//CHECK:     declare i32 @__tgt_register_lib([[DSCTY]]*)
-
 static __attribute__((init_priority(500))) SA a1;
 SA a2;
 SB __attribute__((init_priority(500))) b1;
@@ -436,31 +401,31 @@ int bar(int a){
 
 // Check metadata is properly generated:
 // CHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}}
 
 // TCHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}}
-// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}}
 
 #endif