shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/map_struct_ordering.cpp
Joseph Huber 4376fbd793
[OpenMP] Move OpenMP implicit argument to the end and reformat (#185989) 
Summary:
We use this `dyn_ptr` argument in Clang/OpenMP to handle the
`KernelLaunchEnvironment`. This is a per-kernel argument used to share
some information. Currenetly, it's prepended to the argument list and we
generate storage for it in the runtime.

This is bad for a few reasons:
1. It changes the ABI by shifting user arguments
2. It cannot be trivially be left uninitialized if unused
3. The runtime must allocate its own memory for it

This PR changes it to be appended instead. Additionally, space for this
is always emitted. This means the OMPIRBuilder itself will provide the
storage, we simply need to populate it in the runtime if it is used.
This means that if it's unused we don't always pay the cost and it's
easier for non-OpenMP users to ignore it.

Backward compatibility is maintained by auto-upgrading the kernel
arguments. In `libomptarget` we completely allocate a new buffer to
store this in the new format. The plugins still need to respect the old
ABI of the called device object, so we simply rotate it if it's the old
version.
2026-03-12 18:08:22 -05:00

178 lines
13 KiB
C++
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals all --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" --prefix-filecheck-ir-name _ --global-value-regex "\.offload_.*" --global-hex-value-regex ".offload_maptypes.*" --version 4
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
struct Descriptor {
int *datum;
long int x;
int xi;
long int arr[1][30];
};
int map_struct() {
Descriptor dat = Descriptor();
dat.xi = 3;
dat.arr[0][0] = 1;
// &dat, &dat, sizeof(dat), TO
// &dat.datum[0], &dat.datum[0], 10 * sizeof(int), TO
// &dat.datum, &dat.datum[0], sizeof(void*), ATTACH
#pragma omp target enter data map(to: dat.datum[:10]) map(to: dat)
// &dat, &dat, sizeof(dat), IMPLICIT | TO | FROM | PARAM
#pragma omp target
{
dat.xi = 4;
dat.datum[dat.arr[0][0]] = dat.xi;
}
// &dat, &dat, sizeof(dat), FROM
#pragma omp target exit data map(from: dat)
return dat.xi;
}
#endif
//.
// CHECK: @.offload_sizes = private unnamed_addr constant [3 x i64] [i64 264, i64 40, i64 8]
// CHECK: @.offload_maptypes = private unnamed_addr constant [3 x i64] [i64 [[#0x1]], i64 [[#0x1]], i64 [[#0x4000]]]
// CHECK: @.offload_sizes.1 = private unnamed_addr constant [2 x i64] [i64 264, i64 0]
// CHECK: @.offload_maptypes.2 = private unnamed_addr constant [2 x i64] [i64 [[#0x223]], i64 [[#0x120]]]
// CHECK: @.offload_sizes.3 = private unnamed_addr constant [1 x i64] [i64 264]
// CHECK: @.offload_maptypes.4 = private unnamed_addr constant [1 x i64] [i64 [[#0x2]]]
//.
// CHECK-LABEL: define dso_local noundef signext i32 @_Z10map_structv(
// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DAT:%.*]] = alloca [[STRUCT_DESCRIPTOR:%.*]], align 8
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [3 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [3 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [3 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS4:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS5:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS6:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS7:%.*]] = alloca [1 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS8:%.*]] = alloca [1 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS9:%.*]] = alloca [1 x ptr], align 8
// CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 8 [[DAT]], i8 0, i64 264, i1 false)
// CHECK-NEXT: [[XI:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[DAT]], i32 0, i32 2
// CHECK-NEXT: store i32 3, ptr [[XI]], align 8
// CHECK-NEXT: [[ARR:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[DAT]], i32 0, i32 3
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1 x [30 x i64]], ptr [[ARR]], i64 0, i64 0
// CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [30 x i64], ptr [[ARRAYIDX]], i64 0, i64 0
// CHECK-NEXT: store i64 1, ptr [[ARRAYIDX1]], align 8
// CHECK-NEXT: [[DATUM:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[DAT]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[DATUM]], align 8
// CHECK-NEXT: [[DATUM2:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[DAT]], i32 0, i32 0
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[DATUM2]], align 8
// CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds nuw i32, ptr [[TMP1]], i64 0
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP2]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP3]], align 8
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP4]], align 8
// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK-NEXT: store ptr [[TMP0]], ptr [[TMP5]], align 8
// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK-NEXT: store ptr [[ARRAYIDX3]], ptr [[TMP6]], align 8
// CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK-NEXT: store ptr null, ptr [[TMP7]], align 8
// CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK-NEXT: store ptr [[DATUM]], ptr [[TMP8]], align 8
// CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK-NEXT: store ptr [[ARRAYIDX3]], ptr [[TMP9]], align 8
// CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK-NEXT: store ptr null, ptr [[TMP10]], align 8
// CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK-NEXT: call void @__tgt_target_data_begin_mapper(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 3, ptr [[TMP11]], ptr [[TMP12]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP13]], align 8
// CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP14]], align 8
// CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP15]], align 8
// CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 1
// CHECK-NEXT: store ptr null, ptr [[TMP16]], align 8
// CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 1
// CHECK-NEXT: store ptr null, ptr [[TMP17]], align 8
// CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i64 0, i64 1
// CHECK-NEXT: store ptr null, ptr [[TMP18]], align 8
// CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK-NEXT: store i32 4, ptr [[TMP21]], align 4
// CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK-NEXT: store i32 2, ptr [[TMP22]], align 4
// CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK-NEXT: store ptr [[TMP19]], ptr [[TMP23]], align 8
// CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK-NEXT: store ptr [[TMP20]], ptr [[TMP24]], align 8
// CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK-NEXT: store ptr @.offload_sizes.1, ptr [[TMP25]], align 8
// CHECK-NEXT: [[TMP26:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK-NEXT: store ptr @.offload_maptypes.2, ptr [[TMP26]], align 8
// CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK-NEXT: store ptr null, ptr [[TMP27]], align 8
// CHECK-NEXT: [[TMP28:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK-NEXT: store ptr null, ptr [[TMP28]], align 8
// CHECK-NEXT: [[TMP29:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK-NEXT: store i64 0, ptr [[TMP29]], align 8
// CHECK-NEXT: [[TMP30:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK-NEXT: store i64 0, ptr [[TMP30]], align 8
// CHECK-NEXT: [[TMP31:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP31]], align 4
// CHECK-NEXT: [[TMP32:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP32]], align 4
// CHECK-NEXT: [[TMP33:%.*]] = getelementptr inbounds nuw [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK-NEXT: store i32 0, ptr [[TMP33]], align 4
// CHECK-NEXT: [[TMP34:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z10map_structv_l27.region_id, ptr [[KERNEL_ARGS]])
// CHECK-NEXT: [[TMP35:%.*]] = icmp ne i32 [[TMP34]], 0
// CHECK-NEXT: br i1 [[TMP35]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK: omp_offload.failed:
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z10map_structv_l27(ptr [[DAT]], ptr null) #[[ATTR2:[0-9]+]]
// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK: omp_offload.cont:
// CHECK-NEXT: [[TMP36:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP36]], align 8
// CHECK-NEXT: [[TMP37:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
// CHECK-NEXT: store ptr [[DAT]], ptr [[TMP37]], align 8
// CHECK-NEXT: [[TMP38:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_MAPPERS9]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP38]], align 8
// CHECK-NEXT: [[TMP39:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
// CHECK-NEXT: [[TMP40:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
// CHECK-NEXT: call void @__tgt_target_data_end_mapper(ptr @[[GLOB1]], i64 -1, i32 1, ptr [[TMP39]], ptr [[TMP40]], ptr @.offload_sizes.3, ptr @.offload_maptypes.4, ptr null, ptr null)
// CHECK-NEXT: [[XI10:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[DAT]], i32 0, i32 2
// CHECK-NEXT: [[TMP41:%.*]] = load i32, ptr [[XI10]], align 8
// CHECK-NEXT: ret i32 [[TMP41]]
//
//
// CHECK-LABEL: define internal void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z10map_structv_l27(
// CHECK-SAME: ptr noundef nonnull align 8 dereferenceable(264) [[DAT:%.*]], ptr noalias noundef [[DYN_PTR:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DAT_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[DYN_PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[DAT]], ptr [[DAT_ADDR]], align 8
// CHECK-NEXT: store ptr [[DYN_PTR]], ptr [[DYN_PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[DAT_ADDR]], align 8, !nonnull [[META4:![0-9]+]], !align [[META5:![0-9]+]]
// CHECK-NEXT: [[XI:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR:%.*]], ptr [[TMP0]], i32 0, i32 2
// CHECK-NEXT: store i32 4, ptr [[XI]], align 8
// CHECK-NEXT: [[XI1:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[TMP0]], i32 0, i32 2
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[XI1]], align 8
// CHECK-NEXT: [[DATUM:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DATUM]], align 8
// CHECK-NEXT: [[ARR:%.*]] = getelementptr inbounds nuw [[STRUCT_DESCRIPTOR]], ptr [[TMP0]], i32 0, i32 3
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1 x [30 x i64]], ptr [[ARR]], i64 0, i64 0
// CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [30 x i64], ptr [[ARRAYIDX]], i64 0, i64 0
// CHECK-NEXT: [[TMP3:%.*]] = load i64, ptr [[ARRAYIDX2]], align 8
// CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, ptr [[TMP2]], i64 [[TMP3]]
// CHECK-NEXT: store i32 [[TMP1]], ptr [[ARRAYIDX3]], align 4
// CHECK-NEXT: ret void
//
Reference in New Issue View Git Blame Copy Permalink