[clang] [CUDA] Correctly set CUDA default architecture (PR #84017)
Joseph Huber via cfe-commits
cfe-commits at lists.llvm.org
Tue Mar 5 16:10:51 PST 2024
https://github.com/jhuber6 updated https://github.com/llvm/llvm-project/pull/84017
>From d1bdd2af7e0c29f69315d8f7f87439538f10f5ca Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Tue, 5 Mar 2024 07:44:48 -0600
Subject: [PATCH] [CUDA] Correctly set CUDA default architecture
Summary:
We already had a special CUDA default that better tracked the state as
of modern CUDA installations. Recently this was bumped up to `sm_52`,
but there was a location that wasn't respecting this. Fix that.
Fix tests
---
clang/lib/Driver/Driver.cpp | 2 +-
clang/test/Driver/cuda-detect.cu | 5 +-
clang/test/Driver/cuda-march.cu | 12 +-
.../cuda-omp-unsupported-debug-options.cu | 48 ++---
clang/test/Driver/cuda-options.cu | 174 +++++++++---------
clang/test/Driver/cuda-ptxas-path.cu | 2 +-
.../test/Driver/dwarf-target-version-clamp.cu | 4 +-
7 files changed, 123 insertions(+), 124 deletions(-)
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index de8ceb2f0898bb..cecd34acbc92c0 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -3234,7 +3234,7 @@ class OffloadingActionBuilder final {
CudaActionBuilder(Compilation &C, DerivedArgList &Args,
const Driver::InputList &Inputs)
: CudaActionBuilderBase(C, Args, Inputs, Action::OFK_Cuda) {
- DefaultCudaArch = CudaArch::SM_35;
+ DefaultCudaArch = CudaArch::CudaDefault;
}
StringRef getCanonicalOffloadArch(StringRef ArchStr) override {
diff --git a/clang/test/Driver/cuda-detect.cu b/clang/test/Driver/cuda-detect.cu
index 077d555a3128f2..49e58004e672c3 100644
--- a/clang/test/Driver/cuda-detect.cu
+++ b/clang/test/Driver/cuda-detect.cu
@@ -11,7 +11,6 @@
// RUN: %clang -v --target=x86_64-apple-macosx \
// RUN: --sysroot=%S/no-cuda-there --cuda-path-ignore-env 2>&1 | FileCheck %s -check-prefix NOCUDA
-
// RUN: %clang -v --target=i386-unknown-linux \
// RUN: --sysroot=%S/Inputs/CUDA --cuda-path-ignore-env 2>&1 | FileCheck %s
// RUN: %clang -v --target=i386-apple-macosx \
@@ -146,9 +145,9 @@
// RUN: -check-prefix NOCUDAINC
// Verify that C++ include paths are passed for both host and device frontends.
-// RUN: not %clang -### --target=x86_64-linux-gnu %s \
+// RUN: %clang -### --target=x86_64-linux-gnu %s \
// RUN: --stdlib=libstdc++ --sysroot=%S/Inputs/ubuntu_14.04_multiarch_tree2 \
-// RUN: --gcc-toolchain="" 2>&1 \
+// RUN: -nogpulib -nogpuinc --gcc-toolchain="" 2>&1 \
// RUN: | FileCheck %s --check-prefix CHECK-CXXINCLUDE
// Verify that CUDA SDK version is propagated to the CC1 compilations.
diff --git a/clang/test/Driver/cuda-march.cu b/clang/test/Driver/cuda-march.cu
index 7003e9fd4198c6..25fd6f3a10f2a2 100644
--- a/clang/test/Driver/cuda-march.cu
+++ b/clang/test/Driver/cuda-march.cu
@@ -5,15 +5,15 @@
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
-// RUN: not %clang -### --target=x86_64-linux-gnu -c \
-// RUN: -march=haswell %s 2>&1 | FileCheck %s
-// RUN: not %clang -### --target=x86_64-linux-gnu -c \
-// RUN: -march=haswell --cuda-gpu-arch=sm_35 %s 2>&1 | FileCheck %s
+// RUN: %clang -### --target=x86_64-linux-gnu -c \
+// RUN: -nogpulib -nogpuinc -march=haswell %s 2>&1 | FileCheck %s
+// RUN: %clang -### --target=x86_64-linux-gnu -c \
+// RUN: -nogpulib -nogpuinc -march=haswell --cuda-gpu-arch=sm_52 %s 2>&1 | FileCheck %s
// CHECK: "-cc1"{{.*}} "-triple" "nvptx
-// CHECK-SAME: "-target-cpu" "sm_35"
+// CHECK-SAME: "-target-cpu" "sm_52"
// CHECK: ptxas
-// CHECK-SAME: "--gpu-name" "sm_35"
+// CHECK-SAME: "--gpu-name" "sm_52"
// CHECK: "-cc1"{{.*}} "-target-cpu" "haswell"
diff --git a/clang/test/Driver/cuda-omp-unsupported-debug-options.cu b/clang/test/Driver/cuda-omp-unsupported-debug-options.cu
index 77cfa6925e387f..8e1bb2e496c749 100644
--- a/clang/test/Driver/cuda-omp-unsupported-debug-options.cu
+++ b/clang/test/Driver/cuda-omp-unsupported-debug-options.cu
@@ -2,56 +2,56 @@
// REQUIRES: nvptx-registered-target
// REQUIRES: zlib
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -g -gz 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -g -gz 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf -fdebug-info-for-profiling 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf -fdebug-info-for-profiling 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-2 -gsplit-dwarf 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf-2 -gsplit-dwarf 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-3 -glldb 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf-3 -glldb 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-4 -gcodeview 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf-4 -gcodeview 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-5 -gmodules 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf-5 -gmodules 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -ggdb1 -fdebug-macro 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -ggdb1 -fdebug-macro 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -ggdb2 -ggnu-pubnames 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -ggdb2 -ggnu-pubnames 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -ggdb3 -gdwarf-aranges 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -ggdb3 -gdwarf-aranges 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -g -gcolumn-info -fdebug-types-section 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -g -gcolumn-info -fdebug-types-section 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN,COMMON
// Same tests for OpenMP
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -g -gz 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf -fdebug-info-for-profiling 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf-2 -gsplit-dwarf 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf-3 -glldb 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf-4 -gcodeview 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf-5 -gmodules 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -ggdb1 -fdebug-macro 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -ggdb2 -ggnu-pubnames 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -ggdb3 -gdwarf-aranges 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -g -gcolumn-info -fdebug-types-section 2>&1 | FileCheck %s --check-prefixes WARN,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-5 -gembed-source 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -gdwarf-5 -gembed-source 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN-GES,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -ggdb -gembed-source -gdwarf-5 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -c %s -ggdb -gembed-source -gdwarf-5 2>&1 \
// RUN: | FileCheck %s --check-prefixes WARN-GES,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -gdwarf-5 -gembed-source 2>&1 | FileCheck %s --check-prefixes WARN-GES,COMMON
-// RUN: not %clang -### --target=x86_64-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -c %s \
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-arch=sm_52 -nogpulib -nogpuinc -fopenmp=libomp -c %s \
// RUN: -fgpu-rdc -ggdb -gembed-source -gdwarf-5 2>&1 | FileCheck %s --check-prefixes WARN-GES,COMMON
// COMMON: warning: debug information option '{{-gz|-fdebug-info-for-profiling|-gsplit-dwarf|-glldb|-gcodeview|-gmodules|-gembed-source|-fdebug-macro|-ggnu-pubnames|-gdwarf-aranges|-fdebug-types-section}}' is not supported
diff --git a/clang/test/Driver/cuda-options.cu b/clang/test/Driver/cuda-options.cu
index ad892b7839b964..8999a6618fe1fa 100644
--- a/clang/test/Driver/cuda-options.cu
+++ b/clang/test/Driver/cuda-options.cu
@@ -4,197 +4,197 @@
// Simple compilation case. Compile device-side to PTX assembly and make sure
// we use it on the host side.
-// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu -c -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix NOLINK %s
// Typical compilation + link case.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
// Verify that --cuda-host-only disables device-side compilation, but doesn't
// disable host-side compilation/linking.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
// Verify that --cuda-device-only disables host-side compilation and linking.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
// Check that the last of --cuda-compile-host-device, --cuda-host-only, and
// --cuda-device-only wins.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-host-only --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: --cuda-host-only -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device \
-// RUN: --cuda-host-only --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-compile-host-device \
+// RUN: --cuda-host-only -nogpulib -nogpuinc %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-host-only \
-// RUN: --cuda-device-only %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-host-only \
+// RUN: -nogpulib -nogpuinc --cuda-device-only %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-compile-host-device \
-// RUN: --cuda-device-only %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-compile-host-device \
+// RUN: -nogpulib -nogpuinc --cuda-device-only %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-host-only \
-// RUN: --cuda-compile-host-device %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-host-only \
+// RUN: -nogpulib -nogpuinc --cuda-compile-host-device %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-compile-host-device %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --cuda-compile-host-device %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
// Verify that --cuda-gpu-arch option passes the correct GPU architecture to
// device compilation.
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-gpu-arch=sm_30 -c %s 2>&1 \
+// RUN: %clang -### -nogpulib -nogpuinc --target=x86_64-linux-gnu --cuda-gpu-arch=sm_52 -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
-// RUN: -check-prefix DEVICE-SM30 -check-prefix HOST \
+// RUN: -check-prefix DEVICE-SM52 -check-prefix HOST \
// RUN: -check-prefix INCLUDES-DEVICE -check-prefix NOLINK %s
// Verify that there is one device-side compilation per --cuda-gpu-arch args
// and that all results are included on the host side.
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 -c %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes DEVICE,DEVICE-NOSAVE,DEVICE2 \
-// RUN: -check-prefixes DEVICE-SM30,DEVICE2-SM35 \
+// RUN: -check-prefixes DEVICE-SM52,DEVICE2-SM60 \
// RUN: -check-prefixes INCLUDES-DEVICE,INCLUDES-DEVICE2 \
// RUN: -check-prefixes HOST,HOST-NOSAVE,NOLINK %s
// Verify that device-side results are passed to the correct tool when
// -save-temps is used.
-// RUN: not %clang -### --target=x86_64-linux-gnu -save-temps -c %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc -save-temps -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-SAVE \
// RUN: -check-prefix HOST -check-prefix HOST-SAVE -check-prefix NOLINK %s
// Verify that device-side results are passed to the correct tool when
// -fno-integrated-as is used.
-// RUN: not %clang -### --target=x86_64-linux-gnu -fno-integrated-as -c %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc -fno-integrated-as -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix HOST-NOSAVE \
// RUN: -check-prefix HOST-AS -check-prefix NOLINK %s
// Verify that --[no-]cuda-gpu-arch arguments are handled correctly.
// a) --no-cuda-gpu-arch=X negates preceding --cuda-gpu-arch=X
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-gpu-arch=sm_50 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_70 --cuda-gpu-arch=sm_52 \
+// RUN: --no-cuda-gpu-arch=sm_70 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM52,NOARCH-SM60,NOARCH-SM70 %s
// b) --no-cuda-gpu-arch=X negates more than one preceding --cuda-gpu-arch=X
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-gpu-arch=sm_50 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_70 --cuda-gpu-arch=sm_70 --cuda-gpu-arch=sm_52 \
+// RUN: --no-cuda-gpu-arch=sm_70 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM52,NOARCH-SM60,NOARCH-SM70 %s
// c) if --no-cuda-gpu-arch=X negates all preceding --cuda-gpu-arch=X
-// we default to sm_35 -- same as if no --cuda-gpu-arch were passed.
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-gpu-arch=sm_50 --no-cuda-gpu-arch=sm_30 \
+// we default to sm_52 -- same as if no --cuda-gpu-arch were passed.
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_70 --cuda-gpu-arch=sm_60 \
+// RUN: --no-cuda-gpu-arch=sm_70 --no-cuda-gpu-arch=sm_60 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM52,NOARCH-SM60,NOARCH-SM70 %s
// d) --no-cuda-gpu-arch=X is a no-op if there's no preceding --cuda-gpu-arch=X
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30\
-// RUN: --no-cuda-gpu-arch=sm_50 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52\
+// RUN: --no-cuda-gpu-arch=sm_70 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM52,ARCH-SM60,NOARCH-SM70 %s
// e) --no-cuda-gpu-arch=X does not affect following --cuda-gpu-arch=X
-// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --no-cuda-gpu-arch=sm_50 --no-cuda-gpu-arch=sm_30 \
-// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
+// RUN: %clang -### --target=x86_64-linux-gnu --cuda-device-only \
+// RUN: -nogpulib -nogpuinc --no-cuda-gpu-arch=sm_70 --no-cuda-gpu-arch=sm_52 \
+// RUN: --cuda-gpu-arch=sm_70 --cuda-gpu-arch=sm_52 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,ARCH-SM50 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM52,NOARCH-SM60,ARCH-SM70 %s
// f) --no-cuda-gpu-arch=all negates all preceding --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
// RUN: --no-cuda-gpu-arch=all \
-// RUN: --cuda-gpu-arch=sm_50 \
-// RUN: -c --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM30,NOARCH-SM35,ARCH-SM50 %s
+// RUN: --cuda-gpu-arch=sm_70 \
+// RUN: -c -nogpulib -nogpuinc %s 2>&1 \
+// RUN: | FileCheck -check-prefixes NOARCH-SM52,NOARCH-SM60,ARCH-SM70 %s
// g) There's no --cuda-gpu-arch=all
// RUN: not %clang -### --target=x86_64-linux-gnu --cuda-device-only \
-// RUN: --cuda-gpu-arch=all \
+// RUN: -nogpulib -nogpuinc --cuda-gpu-arch=all \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefix ARCHALLERROR %s
// Verify that --[no-]cuda-include-ptx arguments are handled correctly.
// a) by default we're including PTX for all GPUs.
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM60,PTX-SM52 %s
// b) --no-cuda-include-ptx=all disables PTX inclusion for all GPUs
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
// RUN: --no-cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,NOPTX-SM30 %s
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM60,NOPTX-SM52 %s
// c) --no-cuda-include-ptx=sm_XX disables PTX inclusion for that GPU only.
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-include-ptx=sm_35 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
+// RUN: --no-cuda-include-ptx=sm_60 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,PTX-SM30 %s
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-include-ptx=sm_30 \
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM60,PTX-SM52 %s
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
+// RUN: --no-cuda-include-ptx=sm_52 \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,NOPTX-SM30 %s
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM60,NOPTX-SM52 %s
// d) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=all
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
// RUN: --no-cuda-include-ptx=all --cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM60,PTX-SM52 %s
// e) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=sm_XX
-// RUN: not %clang -### --target=x86_64-linux-gnu \
-// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN: --no-cuda-include-ptx=sm_30 --cuda-include-ptx=all \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc \
+// RUN: --cuda-gpu-arch=sm_60 --cuda-gpu-arch=sm_52 \
+// RUN: --no-cuda-include-ptx=sm_52 --cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
+// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM60,PTX-SM52 %s
// Verify -flto=thin -fwhole-program-vtables handling. This should result in
// both options being passed to the host compilation, with neither passed to
// the device compilation.
-// RUN: not %clang -### --target=x86_64-linux-gnu -c -flto=thin -fwhole-program-vtables %s 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc -c -flto=thin -fwhole-program-vtables %s 2>&1 \
// RUN: | FileCheck -check-prefixes DEVICE,DEVICE-NOSAVE,HOST,INCLUDES-DEVICE,NOLINK,THINLTOWPD %s
// THINLTOWPD-NOT: error: invalid argument '-fwhole-program-vtables' only allowed with '-flto'
-// ARCH-SM30: "-cc1"{{.*}}"-target-cpu" "sm_30"
-// NOARCH-SM30-NOT: "-cc1"{{.*}}"-target-cpu" "sm_30"
-// ARCH-SM35: "-cc1"{{.*}}"-target-cpu" "sm_35"
-// NOARCH-SM35-NOT: "-cc1"{{.*}}"-target-cpu" "sm_35"
-// ARCH-SM50: "-cc1"{{.*}}"-target-cpu" "sm_50"
-// NOARCH-SM50-NOT: "-cc1"{{.*}}"-target-cpu" "sm_50"
+// ARCH-SM52: "-cc1"{{.*}}"-target-cpu" "sm_52"
+// NOARCH-SM52-NOT: "-cc1"{{.*}}"-target-cpu" "sm_52"
+// ARCH-SM60: "-cc1"{{.*}}"-target-cpu" "sm_60"
+// NOARCH-SM60-NOT: "-cc1"{{.*}}"-target-cpu" "sm_60"
+// ARCH-SM70: "-cc1"{{.*}}"-target-cpu" "sm_70"
+// NOARCH-SM70-NOT: "-cc1"{{.*}}"-target-cpu" "sm_70"
// ARCHALLERROR: error: unsupported CUDA gpu architecture: all
// Match device-side preprocessor and compiler phases with -save-temps.
@@ -213,7 +213,7 @@
// DEVICE-NOSAVE-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// THINLTOWPD-NOT: "-flto=thin"
// DEVICE-SAME: "-fcuda-is-device"
-// DEVICE-SM30-SAME: "-target-cpu" "sm_30"
+// DEVICE-SM52-SAME: "-target-cpu" "sm_52"
// THINLTOWPD-NOT: "-fwhole-program-vtables"
// DEVICE-SAME: "-o" "[[PTXFILE:[^"]*]]"
// DEVICE-NOSAVE-SAME: "-x" "cuda"
@@ -221,7 +221,7 @@
// Match the call to ptxas (which assembles PTX to SASS).
// DEVICE:ptxas
-// DEVICE-SM30-DAG: "--gpu-name" "sm_30"
+// DEVICE-SM52-DAG: "--gpu-name" "sm_52"
// DEVICE-DAG: "--output-file" "[[CUBINFILE:[^"]*]]"
// DEVICE-DAG: "[[PTXFILE]]"
@@ -229,13 +229,13 @@
// DEVICE2: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// DEVICE2-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// DEVICE2-SAME: "-fcuda-is-device"
-// DEVICE2-SM35-SAME: "-target-cpu" "sm_35"
+// DEVICE2-SM60-SAME: "-target-cpu" "sm_60"
// DEVICE2-SAME: "-o" "[[PTXFILE2:[^"]*]]"
// DEVICE2-SAME: "-x" "cuda"
// Match another call to ptxas.
// DEVICE2: ptxas
-// DEVICE2-SM35-DAG: "--gpu-name" "sm_35"
+// DEVICE2-SM60-DAG: "--gpu-name" "sm_60"
// DEVICE2-DAG: "--output-file" "[[CUBINFILE2:[^"]*]]"
// DEVICE2-DAG: "[[PTXFILE2]]"
@@ -290,9 +290,9 @@
// FATBIN-COMMON:fatbinary
// FATBIN-COMMON: "--create" "[[FATBINARY:[^"]*]]"
-// FATBIN-COMMON: "--image=profile=sm_30,file=
-// PTX-SM30: "--image=profile=compute_30,file=
-// NOPTX-SM30-NOT: "--image=profile=compute_30,file=
-// FATBIN-COMMON: "--image=profile=sm_35,file=
-// PTX-SM35: "--image=profile=compute_35,file=
-// NOPTX-SM35-NOT: "--image=profile=compute_35,file=
+// FATBIN-COMMON: "--image=profile=sm_52,file=
+// PTX-SM52: "--image=profile=compute_52,file=
+// NOPTX-SM52-NOT: "--image=profile=compute_52,file=
+// FATBIN-COMMON: "--image=profile=sm_60,file=
+// PTX-SM60: "--image=profile=compute_60,file=
+// NOPTX-SM60-NOT: "--image=profile=compute_60,file=
diff --git a/clang/test/Driver/cuda-ptxas-path.cu b/clang/test/Driver/cuda-ptxas-path.cu
index 09c6014a91a2ed..87b19d9d4d6163 100644
--- a/clang/test/Driver/cuda-ptxas-path.cu
+++ b/clang/test/Driver/cuda-ptxas-path.cu
@@ -8,4 +8,4 @@
// CHECK-NOT: "ptxas"
// CHECK: "/some/path/to/ptxas"
-// CHECK-SAME: "--gpu-name" "sm_35"
+// CHECK-SAME: "--gpu-name" "sm_52"
diff --git a/clang/test/Driver/dwarf-target-version-clamp.cu b/clang/test/Driver/dwarf-target-version-clamp.cu
index ec0386afbc57eb..d9dbbe62cfb2fb 100644
--- a/clang/test/Driver/dwarf-target-version-clamp.cu
+++ b/clang/test/Driver/dwarf-target-version-clamp.cu
@@ -2,9 +2,9 @@
// REQUIRES: nvptx-registered-target
// Verify that DWARF version is properly clamped for nvptx, but not for the host.
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -gdwarf-5 -gembed-source 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc -c %s -gdwarf-5 -gembed-source 2>&1 \
// RUN: | FileCheck %s --check-prefix=DWARF-CLAMP
-// RUN: not %clang -### --target=x86_64-linux-gnu -c %s -ggdb -gembed-source -gdwarf-5 2>&1 \
+// RUN: %clang -### --target=x86_64-linux-gnu -nogpulib -nogpuinc -c %s -ggdb -gembed-source -gdwarf-5 2>&1 \
// RUN: | FileCheck %s --check-prefix=DWARF-CLAMP
// DWARF-CLAMP: "-triple" "nvptx64-nvidia-cuda"
More information about the cfe-commits
mailing list