cc374d8056
Summary: Currently, OpenMP handles the `omp requires` clause by emitting a global constructor into the runtime for every translation unit that requires it. However, this is not a great solution because it prevents us from having a defined order in which the runtime is accessed and used. This patch changes the approach to no longer use global constructors, but to instead group the flag with the other offloading entires that we already handle. This has the effect of still registering each flag per requires TU, but now we have a single constructor that handles everything. This function removes support for the old `__tgt_register_requires` and replaces it with a warning message. We just had a recent release, and the OpenMP policy for the past four releases since we switched to LLVM is that we do not provide strict backwards compatibility between major LLVM releases now that the library is versioned. This means that a user will need to recompile if they have an old binary that relied on `register_requires` having the old behavior. It is important that we actively deprecate this, as otherwise it would not solve the problem of having no defined init and shutdown order for `libomptarget`. The problem of `libomptarget` not having a define init and shutdown order cascades into a lot of other issues so I have a strong incentive to be rid of it. It is worth noting that the current `__tgt_offload_entry` only has space for a 32-bit integer here. I am planning to overhaul these at some point as well.
202 lines
8.8 KiB
C++
202 lines
8.8 KiB
C++
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
|
|
// Test host codegen.
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK
|
|
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
|
|
|
|
// Test target codegen - host bc file has to be created first.
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix TCHECK
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix TCHECK
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK
|
|
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
|
|
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
|
|
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
|
|
|
|
|
|
|
|
// Check target registration is registered as a Ctor.
|
|
|
|
|
|
template<typename tx, typename ty>
|
|
struct TT{
|
|
tx X;
|
|
ty Y;
|
|
};
|
|
|
|
int global;
|
|
extern int global;
|
|
|
|
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;
|
|
static long *plocal;
|
|
|
|
#pragma omp target parallel loop device(global + a) depend(in: global) depend(out: a, b, cn[4])
|
|
for (int i = 0; i < 10; ++i) {
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#pragma omp target parallel loop device(global + a) nowait depend(inout: global, a, bn) if(target:a)
|
|
for (int i = 0; i < *plocal; ++i) {
|
|
static int local1;
|
|
*plocal = global;
|
|
local1 = global;
|
|
}
|
|
|
|
#pragma omp target parallel loop if(0) firstprivate(global) depend(out:global)
|
|
for (int i = 0; i < global; ++i) {
|
|
global += 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-64: [[BP1_CAST:%.+]] = bitcast i[[SZ]]* [[BP1_PTR:%.+]] to i32*
|
|
// CHECK-64: store i32 [[BP1_I32]], i32* [[BP1_CAST]],
|
|
// CHECK-32: store i32 [[BP1_I32]], i32* [[BP1_PTR:%.+]],
|
|
|
|
// CHECK-64: [[BP1_CAST:%.+]] = bitcast i[[SZ]]* [[BP1_PTR:%.+]] to i32*
|
|
// CHECK-64: store i32 [[BP1_I32]], i32* [[BP1_CAST]],
|
|
// CHECK-32: store i32 [[BP1_I32]], i32* [[BP1_PTR:%.+]],
|
|
|
|
// Create stack storage and store argument in there.
|
|
// CHECK-64: [[AA_CADDR:%.+]] = bitcast i[[SZ]]* [[AA_ADDR]] to i32*
|
|
// CHECK-64: load i32, i32* [[AA_CADDR]], align
|
|
// CHECK-32: load i32, i32* [[AA_ADDR]], align
|
|
|
|
// CHECK-64: [[BP1_CAST:%.+]] = bitcast i[[SZ]]* [[BP1_PTR:%.+]] to i32*
|
|
// CHECK-64: store i32 [[BP1_I32]], i32* [[BP1_CAST]],
|
|
// CHECK-32: store i32 [[BP1_I32]], i32* [[BP1_PTR:%.+]],
|
|
|
|
|
|
#endif
|
|
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l66
|
|
// CHECK-SAME: () #[[ATTR2:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB2:[0-9]+]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l66.omp_outlined)
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//
|
|
//// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
// SIMD-ONLY0: {{.*}}
|
|
// SIMD-ONLY1: {{.*}}
|
|
// TCHECK: {{.*}}
|