Skip to content

[Offload] Initial support for registering offloading entries on COFF targets #72697

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 21, 2023
Merged

[Offload] Initial support for registering offloading entries on COFF targets #72697

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 48 additions & 0 deletions clang/test/CodeGenCUDA/offloading-entries.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,12 @@
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-linux-gnu -fgpu-rdc \
// RUN: --offload-new-driver -emit-llvm -o - -x hip %s | FileCheck \
// RUN: --check-prefix=HIP %s
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-windows-gnu -fgpu-rdc \
// RUN: --offload-new-driver -emit-llvm -o - -x cuda %s | FileCheck \
// RUN: --check-prefix=CUDA-COFF %s
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-windows-gnu -fgpu-rdc \
// RUN: --offload-new-driver -emit-llvm -o - -x hip %s | FileCheck \
// RUN: --check-prefix=HIP-COFF %s

#include "Inputs/cuda.h"

Expand All @@ -23,6 +29,20 @@
// HIP: @.omp_offloading.entry_name.2 = internal unnamed_addr constant [2 x i8] c"x\00"
// HIP: @.omp_offloading.entry.x = weak constant %struct.__tgt_offload_entry { ptr @x, ptr @.omp_offloading.entry_name.2, i64 4, i32 0, i32 0 }, section "hip_offloading_entries", align 1
//.
// CUDA-COFF: @.omp_offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00"
// CUDA-COFF: @.omp_offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { ptr @_Z18__device_stub__foov, ptr @.omp_offloading.entry_name, i64 0, i32 0, i32 0 }, section "cuda_offloading_entries$OE", align 1
// CUDA-COFF: @.omp_offloading.entry_name.1 = internal unnamed_addr constant [8 x i8] c"_Z3barv\00"
// CUDA-COFF: @.omp_offloading.entry._Z3barv = weak constant %struct.__tgt_offload_entry { ptr @_Z18__device_stub__barv, ptr @.omp_offloading.entry_name.1, i64 0, i32 0, i32 0 }, section "cuda_offloading_entries$OE", align 1
// CUDA-COFF: @.omp_offloading.entry_name.2 = internal unnamed_addr constant [2 x i8] c"x\00"
// CUDA-COFF: @.omp_offloading.entry.x = weak constant %struct.__tgt_offload_entry { ptr @x, ptr @.omp_offloading.entry_name.2, i64 4, i32 0, i32 0 }, section "cuda_offloading_entries$OE", align 1
//.
// HIP-COFF: @.omp_offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00"
// HIP-COFF: @.omp_offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { ptr @_Z3foov, ptr @.omp_offloading.entry_name, i64 0, i32 0, i32 0 }, section "hip_offloading_entries$OE", align 1
// HIP-COFF: @.omp_offloading.entry_name.1 = internal unnamed_addr constant [8 x i8] c"_Z3barv\00"
// HIP-COFF: @.omp_offloading.entry._Z3barv = weak constant %struct.__tgt_offload_entry { ptr @_Z3barv, ptr @.omp_offloading.entry_name.1, i64 0, i32 0, i32 0 }, section "hip_offloading_entries$OE", align 1
// HIP-COFF: @.omp_offloading.entry_name.2 = internal unnamed_addr constant [2 x i8] c"x\00"
// HIP-COFF: @.omp_offloading.entry.x = weak constant %struct.__tgt_offload_entry { ptr @x, ptr @.omp_offloading.entry_name.2, i64 4, i32 0, i32 0 }, section "hip_offloading_entries$OE", align 1
//.
// CUDA-LABEL: @_Z18__device_stub__foov(
// CUDA-NEXT: entry:
// CUDA-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z18__device_stub__foov)
Expand All @@ -37,6 +57,20 @@
// HIP: setup.end:
// HIP-NEXT: ret void
//
// CUDA-COFF-LABEL: @_Z18__device_stub__foov(
// CUDA-COFF-NEXT: entry:
// CUDA-COFF-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z18__device_stub__foov)
// CUDA-COFF-NEXT: br label [[SETUP_END:%.*]]
// CUDA-COFF: setup.end:
// CUDA-COFF-NEXT: ret void
//
// HIP-COFF-LABEL: @_Z18__device_stub__foov(
// HIP-COFF-NEXT: entry:
// HIP-COFF-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z3foov)
// HIP-COFF-NEXT: br label [[SETUP_END:%.*]]
// HIP-COFF: setup.end:
// HIP-COFF-NEXT: ret void
//
__global__ void foo() {}

// CUDA-LABEL: @_Z18__device_stub__barv(
Expand All @@ -53,5 +87,19 @@ __global__ void foo() {}
// HIP: setup.end:
// HIP-NEXT: ret void
//
// CUDA-COFF-LABEL: @_Z18__device_stub__barv(
// CUDA-COFF-NEXT: entry:
// CUDA-COFF-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z18__device_stub__barv)
// CUDA-COFF-NEXT: br label [[SETUP_END:%.*]]
// CUDA-COFF: setup.end:
// CUDA-COFF-NEXT: ret void
//
// HIP-COFF-LABEL: @_Z18__device_stub__barv(
// HIP-COFF-NEXT: entry:
// HIP-COFF-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z3barv)
// HIP-COFF-NEXT: br label [[SETUP_END:%.*]]
// HIP-COFF: setup.end:
// HIP-COFF-NEXT: ret void
//
__global__ void bar() {}
__device__ int x = 1;
50 changes: 35 additions & 15 deletions clang/test/Driver/linker-wrapper-image.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,18 @@
// RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
// RUN: -fembed-offload-object=%t.out
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-linux-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=OPENMP
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=OPENMP,OPENMP-ELF
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=OPENMP,OPENMP-COFF

// OPENMP: @__start_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// OPENMP-NEXT: @__stop_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// OPENMP-NEXT: @__dummy.omp_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
// OPENMP-NEXT: @.omp_offloading.device_image = internal unnamed_addr constant [[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}"
// OPENMP-ELF: @__start_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// OPENMP-ELF-NEXT: @__stop_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// OPENMP-ELF-NEXT: @__dummy.omp_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"

// OPENMP-COFF: @__start_omp_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries$OA"
// OPENMP-COFF-NEXT: @__stop_omp_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries$OZ"

// OPENMP: @.omp_offloading.device_image = internal unnamed_addr constant [[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}"
// OPENMP-NEXT: @.omp_offloading.device_images = internal unnamed_addr constant [1 x %__tgt_device_image] [%__tgt_device_image { ptr @.omp_offloading.device_image, ptr getelementptr inbounds ([[[SIZE]] x i8], ptr @.omp_offloading.device_image, i64 1, i64 0), ptr @__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }]
// OPENMP-NEXT: @.omp_offloading.descriptor = internal constant %__tgt_bin_desc { i32 1, ptr @.omp_offloading.device_images, ptr @__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }
// OPENMP-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.omp_offloading.descriptor_reg, ptr null }]
Expand All @@ -35,15 +41,22 @@
// RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
// RUN: -fembed-offload-object=%t.out
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-linux-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CUDA
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=CUDA,CUDA-ELF
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=CUDA,CUDA-COFF

// CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".nv_fatbin"
// CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", align 8
// CUDA-NEXT: @.cuda.binary_handle = internal global ptr null
// CUDA-NEXT: @__start_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// CUDA-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// CUDA-NEXT: @__dummy.cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
// CUDA-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.cuda.fatbin_reg, ptr null }]

// CUDA-ELF: @__start_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// CUDA-ELF-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// CUDA-ELF-NEXT: @__dummy.cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"

// CUDA-COFF: @__start_cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OA"
// CUDA-COFF-NEXT: @__stop_cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OZ"

// CUDA: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.cuda.fatbin_reg, ptr null }]

// CUDA: define internal void @.cuda.fatbin_reg() section ".text.startup" {
// CUDA-NEXT: entry:
Expand Down Expand Up @@ -117,15 +130,22 @@
// RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
// RUN: -fembed-offload-object=%t.out
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-linux-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=HIP
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=HIP,HIP-ELF
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
// RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=HIP,HIP-COFF

// HIP: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".hip_fatbin"
// HIP-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1212764230, i32 1, ptr @.fatbin_image, ptr null }, section ".hipFatBinSegment", align 8
// HIP-NEXT: @.hip.binary_handle = internal global ptr null
// HIP-NEXT: @__start_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// HIP-NEXT: @__stop_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// HIP-NEXT: @__dummy.hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries"
// HIP-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.hip.fatbin_reg, ptr null }]

// HIP-ELF: @__start_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// HIP-ELF-NEXT: @__stop_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
// HIP-ELF-NEXT: @__dummy.hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries"

// HIP-COFF: @__start_hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OA"
// HIP-COFF-NEXT: @__stop_hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OZ"

// HIP: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.hip.fatbin_reg, ptr null }]

// HIP: define internal void @.hip.fatbin_reg() section ".text.startup" {
// HIP-NEXT: entry:
Expand Down
8 changes: 5 additions & 3 deletions clang/test/OpenMP/declare_target_link_codegen.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix HOST --check-prefix CHECK
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-windows-gnu -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix HOST-COFF --check-prefix CHECK
// RUN: %clang_cc1 -verify -fopenmp -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 -fopenmp -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 DEVICE --check-prefix CHECK
// RUN: %clang_cc1 -verify -fopenmp -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 -emit-pch -o %t
Expand Down Expand Up @@ -27,6 +28,7 @@
// HOST: [[MAPTYPES:@.+]] = private unnamed_addr constant [3 x i64] [i64 35, i64 531, i64 531]
// HOST: @.omp_offloading.entry_name{{.*}} = internal unnamed_addr constant [{{[0-9]+}} x i8] c"c_decl_tgt_ref_ptr\00"
// HOST: @.omp_offloading.entry.c_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { ptr @c_decl_tgt_ref_ptr, ptr @.omp_offloading.entry_name, i64 8, i32 1, i32 0 }, section "omp_offloading_entries", align 1
// HOST-COFF: @.omp_offloading.entry.{{.*}} = weak constant %struct.__tgt_offload_entry { ptr @.{{.*}}, ptr @.{{.*}}, i64 0, i32 0, i32 0 }, section "omp_offloading_entries$OE", align 1
// DEVICE-NOT: internal unnamed_addr constant [{{[0-9]+}} x i8] c"c_{{.*}}_decl_tgt_ref_ptr\00"
// HOST: @.omp_offloading.entry_name{{.*}} = internal unnamed_addr constant [{{[0-9]+}} x i8] c"_{{.*}}d_{{.*}}_decl_tgt_ref_ptr\00"
// HOST: @.omp_offloading.entry.[[D_PTR]] = weak constant %struct.__tgt_offload_entry { ptr @[[D_PTR]], ptr @.omp_offloading.entry_name{{.*}}
Expand All @@ -50,7 +52,7 @@ int maini1() {
return 0;
}

// DEVICE: define weak_odr protected void @__omp_offloading_{{.*}}_{{.*}}maini1{{.*}}_l42(ptr {{[^,]+}}, ptr noundef nonnull align {{[0-9]+}} dereferenceable{{[^,]*}}
// DEVICE: define weak_odr protected void @__omp_offloading_{{.*}}_{{.*}}maini1{{.*}}_l44(ptr {{[^,]+}}, ptr noundef nonnull align {{[0-9]+}} dereferenceable{{[^,]*}}
// DEVICE: [[C_REF:%.+]] = load ptr, ptr @c_decl_tgt_ref_ptr,
// DEVICE: [[C:%.+]] = load i32, ptr [[C_REF]],
// DEVICE: store i32 [[C]], ptr %
Expand All @@ -74,10 +76,10 @@ int maini1() {
// HOST: [[BP0:%.+]] = getelementptr inbounds [3 x ptr], ptr [[BASEPTRS]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// HOST: [[P0:%.+]] = getelementptr inbounds [3 x ptr], ptr [[PTRS]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// HOST: call i32 @__tgt_target_kernel(ptr @{{.+}}, i64 -1, i32 -1, i32 0, ptr @.{{.+}}.region_id, ptr %{{.+}})
// HOST: call void @__omp_offloading_{{.*}}_{{.*}}_{{.*}}maini1{{.*}}_l42(ptr %{{[^,]+}})
// HOST: call void @__omp_offloading_{{.*}}_{{.*}}_{{.*}}maini1{{.*}}_l44(ptr %{{[^,]+}})
// HOST: call i32 @__tgt_target_kernel(ptr @{{.+}}, i64 -1, i32 0, i32 0, ptr @.{{.+}}.region_id, ptr %{{.+}})

// HOST: define internal void @__omp_offloading_{{.*}}_{{.*}}maini1{{.*}}_l42(ptr noundef nonnull align {{[0-9]+}} dereferenceable{{.*}})
// HOST: define internal void @__omp_offloading_{{.*}}_{{.*}}maini1{{.*}}_l44(ptr noundef nonnull align {{[0-9]+}} dereferenceable{{.*}})
// HOST: [[C:%.*]] = load i32, ptr @c,
// HOST: store i32 [[C]], ptr %

Expand Down
1 change: 1 addition & 0 deletions llvm/lib/Frontend/Offloading/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,5 @@ add_llvm_component_library(LLVMFrontendOffloading
Core
Support
TransformUtils
TargetParser
)
Loading