16a385ba21
We already created a versioned `__tgt_kernel_arguments` struct but it
was only briefly used and its content was passed in isolation anyway.
This makes it hard to add more information in the future. With this
patch we fully embrace the struct as means to pass information from the
compiler to the plugin as part of a kernel launch.
The patch also extends and renames the struct, bumping the version
number to 2. Version 1 entries are auto-upgraded. This is in preparation
for "bare" kernel launches, per kernel dynamic shared memory, CUDA/HIP
lowering, etc.
The `__tgt_target_kernel_nowait` interface was deprecated as it was
unused. Once we actually implement support for something like that, we
can add an appropriate API.
Note: Only plugins with the `launch_kernel` interface are now supported.
That means that a new clang won't be able to use an old runtime.
An old clang can still use the new runtime since the libomptarget
interface did not change.
Differential Revision: https://reviews.llvm.org/D141232
130 lines
7.9 KiB
C++
130 lines
7.9 KiB
C++
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-targets=x86_64-pc-linux-gnu \
|
|
// RUN: -x c++ -triple x86_64-unknown-linux-gnu -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s
|
|
|
|
// expected-no-diagnostics
|
|
|
|
// CHECK: @.offload_sizes = private unnamed_addr constant [4 x i64] [i64 12, i64 4, i64 4, i64 4]
|
|
// CHECK-NOT: @.offload_sizes = private unnamed_addr constant [4 x i64] [i64 0, i64 4, i64 4, i64 4]
|
|
|
|
// CHECK-LABEL: define {{[^@]+}}@_Z3foov(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[B:%.*]] = alloca [[CLASS_B:%.*]], align 4
|
|
// CHECK-NEXT: call void @_ZN1BC1Eii(ptr noundef nonnull align 4 dereferenceable(12) [[B]], i32 noundef 2, i32 noundef 3)
|
|
// CHECK-NEXT: call void @_ZN1B3runEv(ptr noundef nonnull align 4 dereferenceable(12) [[B]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
class A {
|
|
protected:
|
|
int X;
|
|
int Y;
|
|
|
|
public:
|
|
A (int x, int y) : X { x }, Y { y } { };
|
|
};
|
|
|
|
class B : public A {
|
|
using A::X;
|
|
using A::Y;
|
|
public:
|
|
int res;
|
|
// CHECK-LABEL: define {{[^@]+}}@_ZN1BC1Eii(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
|
|
// CHECK-NEXT: [[X_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[Y_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
|
|
// CHECK-NEXT: store i32 [[X:%.*]], ptr [[X_ADDR]], align 4
|
|
// CHECK-NEXT: store i32 [[Y:%.*]], ptr [[Y_ADDR]], align 4
|
|
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[X_ADDR]], align 4
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[Y_ADDR]], align 4
|
|
// CHECK-NEXT: call void @_ZN1BC2Eii(ptr noundef nonnull align 4 dereferenceable(12) [[THIS1]], i32 noundef [[TMP0]], i32 noundef [[TMP1]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
B (int x, int y) : A(x,y), res{0} {}
|
|
// CHECK-LABEL: define {{[^@]+}}@_ZN1B3runEv(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
|
|
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x ptr], align 8
|
|
// CHECK-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x ptr], align 8
|
|
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x ptr], align 8
|
|
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
|
|
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
|
|
// CHECK-NEXT: [[RES:%.*]] = getelementptr inbounds [[CLASS_B:%.*]], ptr [[THIS1]], i32 0, i32 1
|
|
// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds [[CLASS_A:%.*]], ptr [[THIS1]], i32 0, i32 0
|
|
// CHECK-NEXT: [[Y:%.*]] = getelementptr inbounds [[CLASS_A]], ptr [[THIS1]], i32 0, i32 1
|
|
// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK-NEXT: store ptr [[THIS1]], ptr [[TMP0]], align 8
|
|
// CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK-NEXT: store ptr [[THIS1]], ptr [[TMP1]], align 8
|
|
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP2]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
|
|
// CHECK-NEXT: store ptr [[THIS1]], ptr [[TMP3]], align 8
|
|
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
|
|
// CHECK-NEXT: store ptr [[RES]], ptr [[TMP4]], align 8
|
|
// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP5]], align 8
|
|
// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
|
|
// CHECK-NEXT: store ptr [[THIS1]], ptr [[TMP6]], align 8
|
|
// CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
|
|
// CHECK-NEXT: store ptr [[X]], ptr [[TMP7]], align 8
|
|
// CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP8]], align 8
|
|
// CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
|
|
// CHECK-NEXT: store ptr [[THIS1]], ptr [[TMP9]], align 8
|
|
// CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 3
|
|
// CHECK-NEXT: store ptr [[Y]], ptr [[TMP10]], align 8
|
|
// CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP11]], align 8
|
|
// CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
|
|
// CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
|
|
// CHECK-NEXT: store i32 2, ptr [[TMP14]], align 4
|
|
// CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
|
|
// CHECK-NEXT: store i32 4, ptr [[TMP15]], align 4
|
|
// CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
|
|
// CHECK-NEXT: store ptr [[TMP12]], ptr [[TMP16]], align 8
|
|
// CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
|
|
// CHECK-NEXT: store ptr [[TMP13]], ptr [[TMP17]], align 8
|
|
// CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
|
|
// CHECK-NEXT: store ptr @.offload_sizes, ptr [[TMP18]], align 8
|
|
// CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
|
|
// CHECK-NEXT: store ptr @.offload_maptypes, ptr [[TMP19]], align 8
|
|
// CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP20]], align 8
|
|
// CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
|
|
// CHECK-NEXT: store ptr null, ptr [[TMP21]], align 8
|
|
// CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
|
|
// CHECK-NEXT: store i64 0, ptr [[TMP22]], align 8
|
|
// CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
|
|
// CHECK-NEXT: store i64 0, ptr [[TMP23]], align 8
|
|
// CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
|
|
// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP24]], align 4
|
|
// CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
|
|
// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP25]], align 4
|
|
// CHECK-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
|
|
// CHECK-NEXT: store i32 0, ptr [[TMP26]], align 4
|
|
// CHECK-NEXT: [[TMP27:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 -1, i32 0, ptr @.__omp_offloading_{{.*}}__ZN1B3runEv_{{.*}}.region_id, ptr [[KERNEL_ARGS]])
|
|
// CHECK-NEXT: [[TMP28:%.*]] = icmp ne i32 [[TMP27]], 0
|
|
// CHECK-NEXT: br i1 [[TMP28]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
|
|
// CHECK: omp_offload.failed:
|
|
// CHECK-NEXT: call void @__omp_offloading_{{.*}}__ZN1B3runEv_{{.*}}(ptr [[THIS1]]) #[[ATTR3:[0-9]+]]
|
|
// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT]]
|
|
// CHECK: omp_offload.cont:
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void run (void) {
|
|
#pragma omp target
|
|
res = X + Y;
|
|
}
|
|
};
|
|
|
|
void foo() {
|
|
B b(2, 3);
|
|
b.run();
|
|
}
|