[clang] c99407e - [OpenMP] Make the new device runtime the default
Joseph Huber via cfe-commits
cfe-commits at lists.llvm.org
Thu Dec 2 08:12:05 PST 2021
Author: Joseph Huber
Date: 2021-12-02T11:11:45-05:00
New Revision: c99407e31c3977bf397531bf115a63b0fda68e4d
URL: https://github.com/llvm/llvm-project/commit/c99407e31c3977bf397531bf115a63b0fda68e4d
DIFF: https://github.com/llvm/llvm-project/commit/c99407e31c3977bf397531bf115a63b0fda68e4d.diff
LOG: [OpenMP] Make the new device runtime the default
This patch changes the `-fopenmp-target-new-runtime` option which controls if
the new or old device runtime is used to be true by default. Disabling this to
use the old runtime now requires using `-fno-openmp-target-new-runtime`.
Reviewed By: JonChesterfield, tianshilei1992, gregrodgers, ronlieb
Differential Revision: https://reviews.llvm.org/D114890
Added:
Modified:
clang/include/clang/Driver/Options.td
clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/lib/Driver/ToolChains/Cuda.cpp
clang/test/Driver/amdgpu-openmp-toolchain.c
clang/test/Driver/openmp-offload-gpu.c
Removed:
################################################################################
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 4e6dd20503446..6a1f557968a92 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2442,7 +2442,7 @@ def fno_openmp_assume_teams_oversubscription : Flag<["-"], "fno-openmp-assume-te
def fno_openmp_assume_threads_oversubscription : Flag<["-"], "fno-openmp-assume-threads-oversubscription">,
Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
defm openmp_target_new_runtime: BoolFOption<"openmp-target-new-runtime",
- LangOpts<"OpenMPTargetNewRuntime">, DefaultFalse,
+ LangOpts<"OpenMPTargetNewRuntime">, DefaultTrue,
PosFlag<SetTrue, [CC1Option], "Use the new bitcode library for OpenMP offloading">,
NegFlag<SetFalse>>;
defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
diff --git a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
index 863e2c597d53a..f282f04b79311 100644
--- a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
@@ -267,7 +267,7 @@ void AMDGPUOpenMPToolChain::addClangTargetOptions(
std::string BitcodeSuffix;
if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
- options::OPT_fno_openmp_target_new_runtime, false))
+ options::OPT_fno_openmp_target_new_runtime, true))
BitcodeSuffix = "new-amdgpu-" + GPUArch;
else
BitcodeSuffix = "amdgcn-" + GPUArch;
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index a7e41b24f2735..8d92c293d83a4 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5904,7 +5904,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
// runtime.
if (Args.hasFlag(options::OPT_fopenmp_target_new_runtime,
options::OPT_fno_openmp_target_new_runtime,
- /*Default=*/false))
+ /*Default=*/true))
CmdArgs.push_back("-fopenmp-target-new-runtime");
// When in OpenMP offloading mode, enable debugging on the device.
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 5397c7a9a0e66..ee573b89bed13 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -745,7 +745,7 @@ void CudaToolChain::addClangTargetOptions(
std::string BitcodeSuffix;
if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
- options::OPT_fno_openmp_target_new_runtime, false))
+ options::OPT_fno_openmp_target_new_runtime, true))
BitcodeSuffix = "new-nvptx-" + GpuArch.str();
else
BitcodeSuffix = "nvptx-" + GpuArch.str();
diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c
index 78fee12a5a98c..f6b22cd5973a8 100644
--- a/clang/test/Driver/amdgpu-openmp-toolchain.c
+++ b/clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -1,6 +1,6 @@
// REQUIRES: x86-registered-target
// REQUIRES: amdgpu-registered-target
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib %s 2>&1 \
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib %s 2>&1 \
// RUN: | FileCheck %s
// verify the tools invocations
@@ -14,7 +14,7 @@
// CHECK: clang{{.*}}"-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-o" "{{.*}}a-{{.*}}.o" "-x" "ir" "{{.*}}a-{{.*}}.bc"
// CHECK: ld{{.*}}"-o" "a.out"{{.*}}"{{.*}}amdgpu-openmp-toolchain-{{.*}}.o" "{{.*}}a-{{.*}}.o" "-lomp" "-lomptarget"
-// RUN: %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
+// RUN: %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-PHASES %s
// phases
// CHECK-PHASES: 0: input, "{{.*}}amdgpu-openmp-toolchain.c", c, (host-openmp)
@@ -36,13 +36,13 @@
// CHECK-PHASES: 16: linker, {4, 15}, image, (host-openmp)
// handling of --libomptarget-amdgcn-bc-path
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET
// CHECK-LIBOMPTARGET: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc"{{.*}}
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB
// CHECK-NOGPULIB-NOT: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx803.bc"{{.*}}
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-PRINT-BINDINGS
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-PRINT-BINDINGS
// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"],
// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang",{{.*}} output: "[[HOST_BC:.*]]"
// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]"], output: "[[HOST_S:.*]]"
@@ -56,13 +56,13 @@
// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[HOST_O]]", "[[OFFLOAD_O]]"], output:
// verify the llc is invoked for textual assembly output
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib -save-temps %s 2>&1 \
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib -save-temps %s 2>&1 \
// RUN: | FileCheck %s --check-prefix=CHECK-SAVE-ASM
// CHECK-SAVE-ASM: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=asm" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906.s"
// CHECK-SAVE-ASM: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=obj" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906.o"
// check the handling of -c
-// RUN: %clang -ccc-print-bindings -c --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib -save-temps %s 2>&1 \
+// RUN: %clang -ccc-print-bindings -c --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib -save-temps %s 2>&1 \
// RUN: | FileCheck %s --check-prefix=CHECK-C
// CHECK-C: "x86_64-unknown-linux-gnu" - "clang",
// CHECK-C: "x86_64-unknown-linux-gnu" - "clang",{{.*}}output: "[[HOST_BC:.*]]"
@@ -72,8 +72,8 @@
// CHECK-C: "x86_64-unknown-linux-gnu" - "clang::as"
// CHECK-C: "x86_64-unknown-linux-gnu" - "offload bundler"
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
// CHECK-EMIT-LLVM-IR: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-emit-llvm"
-// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -lm --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIB-DEVICE
+// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fno-openmp-target-new-runtime -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -lm --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIB-DEVICE
// CHECK-LIB-DEVICE: {{.*}}llvm-link{{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"
diff --git a/clang/test/Driver/openmp-offload-gpu.c b/clang/test/Driver/openmp-offload-gpu.c
index dd62b1e5a0760..525ee465d2469 100644
--- a/clang/test/Driver/openmp-offload-gpu.c
+++ b/clang/test/Driver/openmp-offload-gpu.c
@@ -162,8 +162,8 @@
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
-// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-BCLIB-DIR %s
+// RUN: -fopenmp-relocatable-target -fno-openmp-target-new-runtime -save-temps \
+// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB-DIR %s
/// Check with the new runtime enabled
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
@@ -185,8 +185,8 @@
/// Create a bogus bitcode library and find it with LIBRARY_PATH
// RUN: env LIBRARY_PATH=%S/Inputs/libomptarget/subdir %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
-// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-ENV-BCLIB %s
+// RUN: -fopenmp-relocatable-target -fno-openmp-target-new-runtime -save-temps \
+// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-ENV-BCLIB %s
// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-test.bc
// CHK-BCLIB-DIR: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget{{/|\\\\}}libomptarget-nvptx-sm_35.bc
@@ -204,7 +204,7 @@
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB-WARN %s
-// CHK-BCLIB-WARN: no library 'libomptarget-nvptx-sm_35.bc' found in the default clang lib directory or in LIBRARY_PATH; use '--libomptarget-nvptx-bc-path' to specify nvptx bitcode library
+// CHK-BCLIB-WARN: no library 'libomptarget-new-nvptx-sm_35.bc' found in the default clang lib directory or in LIBRARY_PATH; use '--libomptarget-nvptx-bc-path' to specify nvptx bitcode library
/// ###########################################################################
More information about the cfe-commits
mailing list