shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[LinkerWrapper] Always pass -flto if the linker supports it (#102972)

Browse Source 
Summary;
Now that we use the linker to do LTO / device linking, we need to inform
the `clang` invocation to use `-flto` so it forwards arguments like
`-On` correctly.
This commit is contained in:
Joseph Huber 2024-08-13 11:23:55 -05:00 committed by GitHub
parent afd42fb303
commit dcc27ea41e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 21 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
clang/test/Driver/linker-wrapper.c
View File

@ -21,7 +21,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=NVPTX-LINK // RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=NVPTX-LINK
// NVPTX-LINK: clang{{.*}} -o {{.*}}.img --target=nvptx64-nvidia-cuda -march=sm_70 -O2 {{.*}}.o {{.*}}.o // NVPTX-LINK: clang{{.*}} -o {{.*}}.img --target=nvptx64-nvidia-cuda -march=sm_70 -O2 -flto {{.*}}.o {{.*}}.o
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70 \ // RUN: --image=file=%t.elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70 \
@ -30,7 +30,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --device-debug -O0 \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --device-debug -O0 \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=NVPTX-LINK-DEBUG // RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=NVPTX-LINK-DEBUG
// NVPTX-LINK-DEBUG: clang{{.*}} -o {{.*}}.img --target=nvptx64-nvidia-cuda -march=sm_70 -O2 {{.*}}.o {{.*}}.o -g // NVPTX-LINK-DEBUG: clang{{.*}} -o {{.*}}.img --target=nvptx64-nvidia-cuda -march=sm_70 -O2 -flto {{.*}}.o {{.*}}.o -g
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908 \ // RUN: --image=file=%t.elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908 \
@ -39,7 +39,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=AMDGPU-LINK // RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=AMDGPU-LINK
// AMDGPU-LINK: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o // AMDGPU-LINK: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.amdgpu.bc,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx1030 \ // RUN: --image=file=%t.amdgpu.bc,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx1030 \
@ -48,7 +48,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --save-temps -O2 \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --save-temps -O2 \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=AMDGPU-LTO-TEMPS // RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=AMDGPU-LTO-TEMPS
// AMDGPU-LTO-TEMPS: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx1030 -O2 -Wl,--no-undefined {{.*}}.o -save-temps // AMDGPU-LTO-TEMPS: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx1030 -O2 -flto -Wl,--no-undefined {{.*}}.o -save-temps
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu \ // RUN: --image=file=%t.elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu \
@ -59,7 +59,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: --linker-path=/usr/bin/ld.lld --whole-archive %t.a --no-whole-archive \ // RUN: --linker-path=/usr/bin/ld.lld --whole-archive %t.a --no-whole-archive \
// RUN: %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CPU-LINK // RUN: %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CPU-LINK
// CPU-LINK: clang{{.*}} -o {{.*}}.img --target=x86_64-unknown-linux-gnu -march=native -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o -Wl,-Bsymbolic -shared -Wl,--whole-archive {{.*}}.a -Wl,--no-whole-archive // CPU-LINK: clang{{.*}} -o {{.*}}.img --target=x86_64-unknown-linux-gnu -march=native -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o -Wl,-Bsymbolic -shared -Wl,--whole-archive {{.*}}.a -Wl,--no-whole-archive
// RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o
// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu -mllvm -openmp-opt-disable \ // RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu -mllvm -openmp-opt-disable \
@ -148,7 +148,7 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --clang-backend \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run --clang-backend \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CLANG-BACKEND // RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CLANG-BACKEND
// CLANG-BACKEND: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -Wl,--no-undefined {{.*}}.o // CLANG-BACKEND: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -flto -Wl,--no-undefined {{.*}}.o
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70 // RUN: --image=file=%t.elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70
@ -171,8 +171,8 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \
// RUN: --linker-path=/usr/bin/ld %t-on.o %t-off.o %t.a -o a.out 2>&1 | FileCheck %s --check-prefix=AMD-TARGET-ID // RUN: --linker-path=/usr/bin/ld %t-on.o %t-off.o %t.a -o a.out 2>&1 | FileCheck %s --check-prefix=AMD-TARGET-ID
// AMD-TARGET-ID: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack+ -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o // AMD-TARGET-ID: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack+ -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o
// AMD-TARGET-ID: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack- -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o // AMD-TARGET-ID: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack- -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o
// RUN: clang-offload-packager -o %t-lib.out \ // RUN: clang-offload-packager -o %t-lib.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=generic // RUN: --image=file=%t.elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=generic
@ -187,8 +187,8 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \ // RUN: clang-linker-wrapper --host-triple=x86_64-unknown-linux-gnu --dry-run \
// RUN: --linker-path=/usr/bin/ld %t1.o %t2.o %t.a -o a.out 2>&1 | FileCheck %s --check-prefix=ARCH-ALL // RUN: --linker-path=/usr/bin/ld %t1.o %t2.o %t.a -o a.out 2>&1 | FileCheck %s --check-prefix=ARCH-ALL
// ARCH-ALL: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o // ARCH-ALL: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx90a -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o
// ARCH-ALL: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -Wl,--no-undefined {{.*}}.o {{.*}}.o // ARCH-ALL: clang{{.*}} -o {{.*}}.img --target=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -flto -Wl,--no-undefined {{.*}}.o {{.*}}.o
// RUN: clang-offload-packager -o %t.out \ // RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu \ // RUN: --image=file=%t.elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu \

1
clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
View File

@ -527,6 +527,7 @@ Expected<StringRef> clang(ArrayRef<StringRef> InputFiles, const ArgList &Args) {
// Forward all of the `--offload-opt` and similar options to the device. // Forward all of the `--offload-opt` and similar options to the device.
if (linkerSupportsLTO(Args)) { if (linkerSupportsLTO(Args)) {
CmdArgs.push_back("-flto");
for (auto &Arg : Args.filtered(OPT_offload_opt_eq_minus, OPT_mllvm)) for (auto &Arg : Args.filtered(OPT_offload_opt_eq_minus, OPT_mllvm))
CmdArgs.append( CmdArgs.append(
{"-Xlinker", {"-Xlinker",

3
offload/test/api/omp_dynamic_shared_memory_amdgpu.c
View File

@ -1,4 +1,5 @@
// RUN: %libomptarget-compile-amdgcn-amd-amdhsa -O1 -mllvm -openmp-opt-inline-device // RUN: %libomptarget-compile-amdgcn-amd-amdhsa -O2 -mllvm \
// RUN: -openmp-opt-inline-device
// RUN: env LIBOMPTARGET_SHARED_MEMORY_SIZE=256 \ // RUN: env LIBOMPTARGET_SHARED_MEMORY_SIZE=256 \
// RUN: %libomptarget-run-amdgcn-amd-amdhsa | %fcheck-amdgcn-amd-amdhsa // RUN: %libomptarget-run-amdgcn-amd-amdhsa | %fcheck-amdgcn-amd-amdhsa
// REQUIRES: amdgcn-amd-amdhsa // REQUIRES: amdgcn-amd-amdhsa

3
offload/test/api/omp_dynamic_shared_memory_mixed_amdgpu.c
View File

@ -1,4 +1,5 @@
// RUN: %libomptarget-compile-amdgcn-amd-amdhsa -O1 -mllvm -openmp-opt-inline-device -I %S // RUN: %libomptarget-compile-amdgcn-amd-amdhsa -O2 -mllvm \
// RUN: -openmp-opt-inline-device -I %S
// RUN: env LIBOMPTARGET_NEXTGEN_PLUGINS=1 \ // RUN: env LIBOMPTARGET_NEXTGEN_PLUGINS=1 \
// RUN: %libomptarget-run-amdgcn-amd-amdhsa | %fcheck-amdgcn-amd-amdhsa // RUN: %libomptarget-run-amdgcn-amd-amdhsa | %fcheck-amdgcn-amd-amdhsa
// REQUIRES: amdgcn-amd-amdhsa // REQUIRES: amdgcn-amd-amdhsa

6
offload/test/offloading/bug51781.c
View File

@ -5,7 +5,7 @@
// SPMDize. There is no main thread, so there's no issue. // SPMDize. There is no main thread, so there's no issue.
// //
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt > %t.spmd 2>&1 // RUN: %libomptarget-compile-generic -O2 -Rpass=openmp-opt > %t.spmd 2>&1
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=SPMD -input-file=%t.spmd // RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=SPMD -input-file=%t.spmd
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=SPMD -input-file=%t.spmd // RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=SPMD -input-file=%t.spmd
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic // RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
@ -15,7 +15,7 @@
// Use the custom state machine, which must avoid the same barrier problem as // Use the custom state machine, which must avoid the same barrier problem as
// the generic state machine. // the generic state machine.
// //
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt \ // RUN: %libomptarget-compile-generic -O2 -Rpass=openmp-opt \
// RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1 // RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom // RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom // RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom
@ -24,7 +24,7 @@
// Repeat with reduction clause, which has managed to break the custom state // Repeat with reduction clause, which has managed to break the custom state
// machine in the past. // machine in the past.
// //
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt -DADD_REDUCTION \ // RUN: %libomptarget-compile-generic -O2 -Rpass=openmp-opt -DADD_REDUCTION \
// RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1 // RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom // RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom // RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom

6
offload/test/offloading/bug51982.c
View File

@ -1,6 +1,6 @@
// RUN: %libomptarget-compile-generic -O1 && %libomptarget-run-generic // RUN: %libomptarget-compile-generic -O2 && %libomptarget-run-generic
// -O1 to run openmp-opt // -O2 to run openmp-opt
// RUN: %libomptarget-compileopt-generic -O1 && %libomptarget-run-generic // RUN: %libomptarget-compileopt-generic -O2 && %libomptarget-run-generic
int main(void) { int main(void) {
long int aa = 0; long int aa = 0;