889faabe78
The handling of overlapped structure mapping in CGOpenMPRuntime.cpp can
lead to redundant zero-sized mapping nodes at runtime. This patch fixes
it using a combination of approaches: trivially adjacent struct members
won't have a mapping node created between them, and for more complicated
cases (inheritance) the physical layout of the struct/class is used to
make sure that elements aren't missed.
I've introduced a new class to track the state whilst iterating over the
struct. This reduces a bit of redundancy in the code (accumulating
CombinedInfo both during and after the loop), which I think is a bit
neater.
Before:
omptarget --> Entry 0: Base=0x00007fff8d483830, Begin=0x00007fff8d483830, Size=48, Type=0x20, Name=unknown
omptarget --> Entry 1: Base=0x00007fff8d483830, Begin=0x00007fff8d483830, Size=0, Type=0x1000000000003, Name=unknown
omptarget --> Entry 2: Base=0x00007fff8d483830, Begin=0x00007fff8d483834, Size=0, Type=0x1000000000003, Name=unknown
omptarget --> Entry 3: Base=0x00007fff8d483830, Begin=0x00007fff8d483838, Size=0, Type=0x1000000000003, Name=unknown
omptarget --> Entry 4: Base=0x00007fff8d483830, Begin=0x00007fff8d48383c, Size=20, Type=0x1000000000003, Name=unknown
omptarget --> Entry 5: Base=0x00007fff8d483830, Begin=0x00007fff8d483854, Size=0, Type=0x1000000000003, Name=unknown
omptarget --> Entry 6: Base=0x00007fff8d483830, Begin=0x00007fff8d483858, Size=0, Type=0x1000000000003, Name=unknown
omptarget --> Entry 7: Base=0x00007fff8d483830, Begin=0x00007fff8d48385c, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 8: Base=0x00007fff8d483830, Begin=0x00007fff8d483830, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 9: Base=0x00007fff8d483830, Begin=0x00007fff8d483834, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 10: Base=0x00007fff8d483830, Begin=0x00007fff8d483838, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 11: Base=0x00007fff8d483840, Begin=0x00005e7665275130, Size=32, Type=0x1000000000013, Name=unknown
omptarget --> Entry 12: Base=0x00007fff8d483830, Begin=0x00007fff8d483850, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 13: Base=0x00007fff8d483830, Begin=0x00007fff8d483854, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 14: Base=0x00007fff8d483830, Begin=0x00007fff8d483858, Size=4, Type=0x1000000000003, Name=unknown
After:
omptarget --> Entry 0: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f562e0, Size=48, Type=0x20, Name=unknown
omptarget --> Entry 1: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f562ec, Size=20, Type=0x1000000000003, Name=unknown
omptarget --> Entry 2: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f5630c, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 3: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f562e0, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 4: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f562e4, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 5: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f562e8, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 6: Base=0x00007fffd0f562f0, Begin=0x000058b6013fb130, Size=32, Type=0x1000000000013, Name=unknown
omptarget --> Entry 7: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f56300, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 8: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f56304, Size=4, Type=0x1000000000003, Name=unknown
omptarget --> Entry 9: Base=0x00007fffd0f562e0, Begin=0x00007fffd0f56308, Size=4, Type=0x1000000000003, Name=unknown
For code:
#include <cstdlib>
#include <cstdio>
struct S {
int x;
int y;
int z;
int *p1;
int *p2;
};
struct T : public S {
int a;
int b;
int c;
};
int main() {
T v;
v.p1 = (int*) calloc(8, sizeof(int));
v.p2 = (int*) calloc(8, sizeof(int));
#pragma omp target map(tofrom: v, v.x, v.y, v.z, v.p1[:8], v.a, v.b, v.c)
{
v.x++;
v.y += 2;
v.z += 3;
v.p1[0] += 4;
v.a += 7;
v.b += 5;
v.c += 6;
}
return 0;
}
51 lines
1.9 KiB
C++
51 lines
1.9 KiB
C++
// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp -emit-llvm %s -o - | FileCheck %s
|
|
// expected-no-diagnostics
|
|
|
|
template<typename C>
|
|
struct S {
|
|
C x;
|
|
C y;
|
|
char z; // Hidden padding after here...
|
|
};
|
|
|
|
template<typename C>
|
|
struct T : public S<C> {
|
|
C a;
|
|
C b;
|
|
C c;
|
|
};
|
|
|
|
int main() {
|
|
T<int> v;
|
|
|
|
#pragma omp target map(tofrom: v, v.y, v.z, v.a)
|
|
{
|
|
v.y++;
|
|
v.z += 2;
|
|
v.a += 3;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
// CHECK: [[CSTSZ:@.+]] = private {{.*}}constant [7 x i64] [i64 0, i64 0, i64 0, i64 0, i64 4, i64 1, i64 4]
|
|
// CHECK: [[CSTTY:@.+]] = private {{.*}}constant [7 x i64] [i64 [[#0x20]], i64 [[#0x1000000000003]], i64 [[#0x1000000000003]], i64 [[#0x1000000000003]], i64 [[#0x1000000000003]], i64 [[#0x1000000000003]], i64 [[#0x1000000000003]]]
|
|
|
|
// CHECK-DAG: call i32 @__tgt_target_kernel(ptr @{{.+}}, i64 -1, i32 -1, i32 0, ptr @.{{.+}}.region_id, ptr [[ARGS:%.+]])
|
|
// CHECK-DAG: [[KSIZE:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 4
|
|
// CHECK-DAG: store ptr [[SZBASE:%.+]], ptr [[KSIZE]], align 8
|
|
// CHECK-DAG: [[SZBASE]] = getelementptr inbounds [7 x i64], ptr [[SIZES:%[^,]*]], i32 0, i32 0
|
|
|
|
// Fill four non-constant size elements here: the whole struct size, the region
|
|
// covering v.x, the region covering padding after v.z and the region covering
|
|
// v.b and v.c.
|
|
|
|
// CHECK-DAG: [[STR:%.+]] = getelementptr inbounds [7 x i64], ptr [[SIZES]], i32 0, i32 0
|
|
// CHECK-DAG: store i64 %{{.+}}, ptr [[STR]], align 8
|
|
// CHECK-DAG: [[X:%.+]] = getelementptr inbounds [7 x i64], ptr [[SIZES]], i32 0, i32 1
|
|
// CHECK-DAG: store i64 %{{.+}}, ptr [[X]], align 8
|
|
// CHECK-DAG: [[PAD:%.+]] = getelementptr inbounds [7 x i64], ptr [[SIZES]], i32 0, i32 2
|
|
// CHECK-DAG: store i64 %{{.+}}, ptr [[PAD]], align 8
|
|
// CHECK-DAG: [[BC:%.+]] = getelementptr inbounds [7 x i64], ptr [[SIZES]], i32 0, i32 3
|
|
// CHECK-DAG: store i64 %{{.+}}, ptr [[BC]], align 8
|