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;
}
152 lines
8.3 KiB
C++
152 lines
8.3 KiB
C++
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
///==========================================================================///
|
|
// RUN: %clang_cc1 -DCK35 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK35 --check-prefix CK35-64
|
|
// RUN: %clang_cc1 -DCK35 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK35 --check-prefix CK35-64
|
|
// RUN: %clang_cc1 -DCK35 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK35 --check-prefix CK35-32
|
|
// RUN: %clang_cc1 -DCK35 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK35 --check-prefix CK35-32
|
|
|
|
// RUN: %clang_cc1 -DCK35 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY32 %s
|
|
// RUN: %clang_cc1 -DCK35 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY32 %s
|
|
// RUN: %clang_cc1 -DCK35 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY32 %s
|
|
// RUN: %clang_cc1 -DCK35 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY32 %s
|
|
// SIMD-ONLY32-NOT: {{__kmpc|__tgt}}
|
|
#ifdef CK35
|
|
|
|
class S {
|
|
public:
|
|
S(double &b) : b(b) {}
|
|
int a;
|
|
double &b;
|
|
void foo();
|
|
};
|
|
|
|
// CK35-DAG: [[SIZE_TO:@.+]] = private {{.*}}constant [3 x i64] [i64 0, i64 0, i64 8]
|
|
// TARGET_PARAM = 0x20
|
|
// MEMBER_OF_1 | TO = 0x1000000000001
|
|
// MEMBER_OF_1 | PTR_AND_OBJ | TO = 0x1000000000011
|
|
// CK35-DAG: [[MTYPE_TO:@.+]] = {{.+}}constant [3 x i64] [i64 [[#0x20]], i64 [[#0x1000000000001]], i64 [[#0x1000000000011]]]
|
|
// CK35-DAG: [[SIZE_FROM:@.+]] = private {{.*}}constant [2 x i64] [i64 0, i64 8]
|
|
// TARGET_PARAM = 0x20
|
|
// MEMBER_OF_1 | PTR_AND_OBJ | FROM = 0x1000000000012
|
|
// CK35-DAG: [[MTYPE_FROM:@.+]] = {{.+}}constant [2 x i64] [i64 [[#0x20]], i64 [[#0x1000000000012]]]
|
|
|
|
void ref_map() {
|
|
double b;
|
|
S s(b);
|
|
|
|
// CK35-DAG: call i32 @__tgt_target_kernel(ptr @{{.+}}, i64 -1, i32 -1, i32 0, ptr @.{{.+}}.region_id, ptr [[ARGS:%.+]])
|
|
// CK35-DAG: [[BPARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 2
|
|
// CK35-DAG: store ptr [[BPGEP:%.+]], ptr [[BPARG]]
|
|
// CK35-DAG: [[PARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 3
|
|
// CK35-DAG: store ptr [[PGEP:%.+]], ptr [[PARG]]
|
|
// CK35-DAG: [[SARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 4
|
|
// CK35-DAG: store ptr [[SIZES:%.+]], ptr [[SARG]]
|
|
// CK35-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
|
|
// CK35-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
|
|
// CK35-DAG: [[SIZES]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
|
|
|
|
// pass TARGET_PARAM {&s, &s, ((ptr)(&s+1)-(ptr)&s)}
|
|
|
|
// CK35-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
|
|
// CK35-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
|
|
// CK35-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
|
|
|
|
|
|
// CK35-DAG: store ptr [[S_ADDR:%.+]], ptr [[BP0]],
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[P0]],
|
|
// CK35-DAG: store i64 [[S_SIZE:%.+]], ptr [[S0]],
|
|
|
|
// CK35-DAG: [[S_SIZE]] = sdiv exact i64 [[SZ:%.+]], ptrtoint (ptr getelementptr (i8, ptr null, i32 1) to i64)
|
|
// CK35-DAG: [[SZ]] = sub i64 [[S_1_INTPTR:%.+]], [[S_INTPTR:%.+]]
|
|
// CK35-DAG: [[S_1_INTPTR]] = ptrtoint ptr [[S_1_VOID:%.+]] to i64
|
|
// CK35-DAG: [[S_INTPTR]] = ptrtoint ptr [[S_VOID:%.+]] to i64
|
|
// CK35-DAG: [[S_1:%.+]] = getelementptr %class.S, ptr [[S_ADDR]], i32 1
|
|
|
|
// pass MEMBER_OF_1 | TO {&s, &s, ((ptr)(&s.a+1)-(ptr)&s)} to copy the data of s.a.
|
|
|
|
// CK35-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
|
|
// CK35-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
|
|
// CK35-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
|
|
|
|
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[BP1]],
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[P1]],
|
|
// CK35-DAG: store i64 [[A_SIZE:%.+]], ptr [[S1]],
|
|
|
|
// CK35-DAG: [[A_SIZE]] = sdiv exact i64 [[SZ:%.+]], ptrtoint (ptr getelementptr (i8, ptr null, i32 1) to i64)
|
|
// CK35-DAG: [[SZ]] = sub i64 [[B_BEGIN_INTPTR:%.+]], [[S_INTPTR:%.+]]
|
|
// CK35-DAG: [[S_INTPTR]] = ptrtoint ptr [[S_VOID:%.+]] to i64
|
|
// CK35-DAG: [[B_BEGIN_INTPTR]] = ptrtoint ptr [[B_BEGIN_VOID:%.+]] to i64
|
|
// CK35-DAG: [[B_ADDR:%.+]] = getelementptr inbounds nuw %class.S, ptr [[S_ADDR]], i32 0, i32 1
|
|
|
|
// pass MEMBER_OF_1 | PTR_AND_OBJ | TO {&s, &s.b, 8|4} to copy the data of s.b.
|
|
|
|
// CK35-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
|
|
// CK35-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
|
|
|
|
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[BP2]],
|
|
// CK35-DAG: store ptr [[B_ADDR:%.+]], ptr [[P2]],
|
|
|
|
// CK35-DAG: [[B_ADDR]] = load ptr, ptr [[B_REF:%.+]], align {{[0-9]+}}, !nonnull !{{[0-9]+}}, !align !{{[0-9]+}}
|
|
// CK35-DAG: [[B_REF]] = getelementptr inbounds nuw %class.S, ptr [[S_ADDR]], i32 0, i32 1
|
|
|
|
#pragma omp target map(to: s, s.b)
|
|
s.foo();
|
|
|
|
// CK35 : call void
|
|
|
|
// CK35-DAG: call i32 @__tgt_target_kernel(ptr @{{.+}}, i64 -1, i32 -1, i32 0, ptr @.{{.+}}.region_id, ptr [[ARGS:%.+]])
|
|
// CK35-DAG: [[BPARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 2
|
|
// CK35-DAG: store ptr [[BPGEP:%.+]], ptr [[BPARG]]
|
|
// CK35-DAG: [[PARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 3
|
|
// CK35-DAG: store ptr [[PGEP:%.+]], ptr [[PARG]]
|
|
// CK35-DAG: [[SARG:%.+]] = getelementptr inbounds {{.+}}[[ARGS]], i32 0, i32 4
|
|
// CK35-DAG: store ptr [[SIZES:%.+]], ptr [[SARG]]
|
|
// CK35-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
|
|
// CK35-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
|
|
// CK35-DAG: [[SIZES]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
|
|
|
|
// pass TARGET_PARAM {&s, &s.b, ((ptr)(&s.b+1)-(ptr)&s.b)}
|
|
|
|
// CK35-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
|
|
// CK35-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
|
|
// CK35-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
|
|
|
|
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[BP0]],
|
|
// CK35-DAG: store ptr [[SB_ADDR:%.+]], ptr [[P0]],
|
|
// CK35-DAG: store i64 [[B_SIZE:%.+]], ptr [[S0]],
|
|
|
|
// CK35-DAG: [[B_SIZE]] = sdiv exact i64 [[SZ:%.+]], ptrtoint (ptr getelementptr (i8, ptr null, i32 1) to i64)
|
|
// CK35-DAG: [[SZ]] = sub i64 [[SB_1_INTPTR:%.+]], [[SB_INTPTR:%.+]]
|
|
// CK35-DAG: [[SB_1_INTPTR]] = ptrtoint ptr [[SB_1_VOID:%.+]] to i64
|
|
// CK35-DAG: [[SB_INTPTR]] = ptrtoint ptr [[SB_VOID:%.+]] to i64
|
|
// CK35-DAG: [[SB_ADDR:%.+]] = getelementptr inbounds nuw %class.S, ptr [[S_ADDR]], i32 0, i32 1
|
|
// CK35-DAG: [[SB_1:%.+]] = getelementptr ptr, ptr [[SB_ADDR]], i{{.+}} 1
|
|
|
|
// pass MEMBER_OF_1 | PTR_AND_OBJ | FROM {&s, &s.b, 8|4} to copy the data of s.c.
|
|
|
|
// CK35-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
|
|
// CK35-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
|
|
|
|
|
|
// CK35-DAG: store ptr [[S_ADDR]], ptr [[BP1]],
|
|
// CK35-DAG: store ptr [[B_ADDR:%.+]], ptr [[P1]],
|
|
|
|
// CK35-DAG: [[B_ADDR]] = load ptr, ptr [[SB_ADDR]],
|
|
|
|
#pragma omp target map(from: s.b)
|
|
s.foo();
|
|
}
|
|
|
|
#endif // CK35
|
|
#endif
|