[CUDA] Bump default GPU architecture to sm_35.

[tra]

Summary

It's the oldest GPU architecture currently supported by all CUDA versions clang
can use.

See the comments in D77670 for more details.

[tra]

cuda-options-freebsd.cu has been removed as it does not test anything useful -- it's a somewhat out of date copy of cuda-options.cu with replaced host triple, which does not matter for processing GPU options.

[Hahnfeld]

LGTM

[Hahnfeld]

(might be good to have an entry in the release notes?)

[tra]

In D108235#2952714, @Hahnfeld wrote:

(might be good to have an entry in the release notes?)

I've updated release notes in D108248.

clang/lib/Driver/Driver.cpp

class OffloadingActionBuilder final {
 
   /// \brief CUDA action builder. It injects device code in the host backend
   /// action.
   class CudaActionBuilder final : public CudaActionBuilderBase {
   public:
     CudaActionBuilder(Compilation &C, DerivedArgList &Args,
                       const Driver::InputList &Inputs)
         : CudaActionBuilderBase(C, Args, Inputs, Action::OFK_Cuda) {
-      DefaultCudaArch = CudaArch::SM_20;
+      DefaultCudaArch = CudaArch::SM_35;
     }
 
     StringRef getCanonicalOffloadArch(StringRef ArchStr) override {
       CudaArch Arch = StringToCudaArch(ArchStr);
       if (Arch == CudaArch::UNKNOWN || !IsNVIDIAGpuArch(Arch)) {
         C.getDriver().Diag(clang::diag::err_drv_cuda_bad_gpu_arch) << ArchStr;
         return StringRef();
       }

clang/test/Driver/cuda-external-tools.cu

 // Tests that ptxas and fatbinary are invoked correctly during CUDA
 // compilation.
 //
 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: nvptx-registered-target
 
 // Regular compiles with -O{0,1,2,3,4,fast}.  -O4 and -Ofast map to ptxas O3.
 // RUN: %clang -### -target x86_64-linux-gnu -O0 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT0 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT0 %s
 // RUN: %clang -### -target x86_64-linux-gnu -O1 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT1 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT1 %s
 // RUN: %clang -### -target x86_64-linux-gnu -O2 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT2 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT2 %s
 // RUN: %clang -### -target x86_64-linux-gnu -O3 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT3 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT3 %s
 // RUN: %clang -### -target x86_64-linux-gnu -O4 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT3 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT3 %s
 // RUN: %clang -### -target x86_64-linux-gnu -Ofast -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT3 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT3 %s
 // Generating relocatable device code
 // RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,RDC %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,RDC %s
 
 // With debugging enabled, ptxas should be run with with no ptxas optimizations.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-device-debug -O2 -g -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,DBG %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,DBG %s
 
 // --no-cuda-noopt-device-debug overrides --cuda-noopt-device-debug.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-device-debug \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN:   --no-cuda-noopt-device-debug -O2 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT2 %s
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT2 %s
 
 // Regular compile without -O.  This should result in us passing -O0 to ptxas.
 // RUN: %clang -### -target x86_64-linux-gnu -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT0 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT0 %s
 
 // Regular compiles with -Os and -Oz.  For lack of a better option, we map
 // these to ptxas -O3.
 // RUN: %clang -### -target x86_64-linux-gnu -Os -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT2 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT2 %s
 // RUN: %clang -### -target x86_64-linux-gnu -Oz -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT2 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT2 %s
 
 // Regular compile targeting sm_35.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_35 -c %s 2>&1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35 %s
 // Separate compilation targeting sm_35.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_35 -fgpu-rdc -c %s 2>&1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,RDC %s
 
 // 32-bit compile.
 // RUN: %clang -### -target i386-linux-gnu -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM20 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM35 %s
 // 32-bit compile when generating relocatable device code.
 // RUN: %clang -### -target i386-linux-gnu -fgpu-rdc -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM20,RDC %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM35,RDC %s
 
 // Compile with -fintegrated-as.  This should still cause us to invoke ptxas.
 // RUN: %clang -### -target x86_64-linux-gnu -fintegrated-as -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT0 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT0 %s
 // Check that we still pass -c when generating relocatable device code.
 // RUN: %clang -### -target x86_64-linux-gnu -fintegrated-as -fgpu-rdc -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,RDC %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,RDC %s
 
 // Check -Xcuda-ptxas and -Xcuda-fatbinary
 // RUN: %clang -### -target x86_64-linux-gnu -c -Xcuda-ptxas -foo1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN:   -Xcuda-fatbinary -bar1 -Xcuda-ptxas -foo2 -Xcuda-fatbinary -bar2 %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,SM20,PTXAS-EXTRA,FATBINARY-EXTRA %s
+// RUN: | FileCheck -check-prefixes=CHECK,SM35,PTXAS-EXTRA,FATBINARY-EXTRA %s
 
 // MacOS spot-checks
 // RUN: %clang -### -target x86_64-apple-macosx -O0 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,OPT0 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,OPT0 %s
 // RUN: %clang -### -target x86_64-apple-macosx --cuda-gpu-arch=sm_35 -c %s 2>&1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35 %s
 // RUN: %clang -### -target i386-apple-macosx -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM20 %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM35 %s
 
 // Check relocatable device code generation on MacOS.
 // RUN: %clang -### -target x86_64-apple-macosx -O0 -fgpu-rdc -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,RDC %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,RDC %s
 // RUN: %clang -### -target x86_64-apple-macosx --cuda-gpu-arch=sm_35 -fgpu-rdc -c %s 2>&1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
 // RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM35,RDC %s
 // RUN: %clang -### -target i386-apple-macosx -fgpu-rdc -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM20,RDC %s
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefixes=CHECK,ARCH32,SM35,RDC %s
 
 // Check that CLANG forwards the -v flag to PTXAS.
-// RUN:   %clang -### -save-temps -no-canonical-prefixes -v %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-PTXAS-VERBOSE %s
+// RUN: %clang -### -save-temps -no-canonical-prefixes -v %s 2>&1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-VERBOSE %s
 
 // Match clang job that produces PTX assembly.
 // CHECK: "-cc1"
 // ARCH64-SAME: "-triple" "nvptx64-nvidia-cuda"
 // ARCH32-SAME: "-triple" "nvptx-nvidia-cuda"
-// SM20-SAME: "-target-cpu" "sm_20"
 // SM35-SAME: "-target-cpu" "sm_35"
 // RDC-SAME: "-fgpu-rdc"
 // CHECK-NOT: "-fgpu-rdc"
-// SM20-SAME: "-o" "[[PTXFILE:[^"]*]]"
 // SM35-SAME: "-o" "[[PTXFILE:[^"]*]]"
 
 // Match the call to ptxas (which assembles PTX to SASS).
 // CHECK: ptxas
 // ARCH64-SAME: "-m64"
 // ARCH32-SAME: "-m32"
 // OPT0-SAME: "-O0"
 // OPT0-NOT: "-g"
 // OPT1-SAME: "-O1"
 // OPT1-NOT: "-g"
 // OPT2-SAME: "-O2"
 // OPT2-NOT: "-g"
 // OPT3-SAME: "-O3"
 // OPT3-NOT: "-g"
 // DBG-SAME: "-g" "--dont-merge-basicblocks" "--return-at-end"
-// SM20-SAME: "--gpu-name" "sm_20"
 // SM35-SAME: "--gpu-name" "sm_35"
-// SM20-SAME: "--output-file" "[[CUBINFILE:[^"]*]]"
 // SM35-SAME: "--output-file" "[[CUBINFILE:[^"]*]]"
 // CHECK-SAME: "[[PTXFILE]]"
 // PTXAS-EXTRA-SAME: "-foo1"
 // PTXAS-EXTRA-SAME: "-foo2"
 // RDC-SAME: "-c"
 // CHECK-NOT: "-c"
 
 // Match the call to fatbinary (which combines all our PTX and SASS into one
 // blob).
 // CHECK: fatbinary
 // CHECK-SAME-DAG: "--cuda"
 // ARCH64-SAME-DAG: "-64"
 // ARCH32-SAME-DAG: "-32"
 // CHECK-DAG: "--create" "[[FATBINARY:[^"]*]]"
-// SM20-SAME-DAG: "--image=profile=compute_20,file=[[PTXFILE]]"
 // SM35-SAME-DAG: "--image=profile=compute_35,file=[[PTXFILE]]"
-// SM20-SAME-DAG: "--image=profile=sm_20,file=[[CUBINFILE]]"
 // SM35-SAME-DAG: "--image=profile=sm_35,file=[[CUBINFILE]]"
 // FATBINARY-EXTRA-SAME: "-bar1"
 // FATBINARY-EXTRA-SAME: "-bar2"
 
 // Match the clang job for host compilation.
 // CHECK: "-cc1"
 // ARCH64-SAME: "-triple" "x86_64-
 // ARCH32-SAME: "-triple" "i386-
 // CHECK-SAME: "-fcuda-include-gpubinary" "[[FATBINARY]]"
 // RDC-SAME: "-fgpu-rdc"
 // CHECK-NOT: "-fgpu-rdc"
 
 // CHK-PTXAS-VERBOSE: ptxas{{.*}}" "-v"

clang/test/Driver/cuda-march.cu

 // Checks that cuda compilation does the right thing when passed -march.
 // (Specifically, we want to pass it to host compilation, but not to device
 // compilation or ptxas!)
 //
 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c \
 // RUN: -march=haswell %s 2>&1 | FileCheck %s
 // RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c \
-// RUN: -march=haswell --cuda-gpu-arch=sm_20 %s 2>&1 | FileCheck %s
+// RUN: -march=haswell --cuda-gpu-arch=sm_35 %s 2>&1 | FileCheck %s
 
 // CHECK: {{.*}}clang{{.*}}" "-cc1"
 // CHECK-SAME: "-triple" "nvptx
-// CHECK-SAME: "-target-cpu" "sm_20"
+// CHECK-SAME: "-target-cpu" "sm_35"
 
 // CHECK: ptxas
-// CHECK-SAME: "--gpu-name" "sm_20"
+// CHECK-SAME: "--gpu-name" "sm_35"
 
 // CHECK: {{.*}}clang{{.*}}" "-cc1"
 // CHECK-SAME: "-target-cpu" "haswell"

clang/test/Driver/cuda-options-freebsd.cu

-// Tests CUDA compilation pipeline construction in Driver.
-// REQUIRES: clang-driver
-// REQUIRES: x86-registered-target
-// REQUIRES: nvptx-registered-target
-
-// Simple compilation case. Compile device-side to PTX assembly and make sure
-// we use it on the host side.
-// RUN: %clang -### -target x86_64-unknown-freebsd -c %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-unknown-freebsd %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-unknown-freebsd --cuda-host-only %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-unknown-freebsd --cuda-device-only %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-unknown-freebsd --cuda-device-only \
-// RUN:    --cuda-host-only %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-unknown-freebsd --cuda-compile-host-device \
-// RUN:    --cuda-host-only %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-unknown-freebsd --cuda-host-only \
-// RUN:    --cuda-device-only %s 2>&1 \
-// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
-// RUN:    -check-prefix NOHOST -check-prefix NOLINK %s
-
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-compile-host-device \
-// RUN:    --cuda-device-only %s 2>&1 \
-// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
-// RUN:    -check-prefix NOHOST -check-prefix NOLINK %s
-
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-host-only \
-// RUN:   --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: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --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: %clang -### -target x86_64-unknown-freebsd --cuda-gpu-arch=sm_30 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
-// RUN:    -check-prefix DEVICE-SM30 -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: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes DEVICE,DEVICE-NOSAVE,DEVICE2 \
-// RUN:             -check-prefixes DEVICE-SM30,DEVICE2-SM35 \
-// 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: %clang -### -target x86_64-unknown-freebsd -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: %clang -### -target x86_64-unknown-freebsd -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: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-gpu-arch=sm_35 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,NOARCH-SM35 %s
-
-// b) --no-cuda-gpu-arch=X negates more than one preceding --cuda-gpu-arch=X
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-gpu-arch=sm_35 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,NOARCH-SM35 %s
-
-// c) if --no-cuda-gpu-arch=X negates all preceding --cuda-gpu-arch=X
-//    we default to sm_20 -- same as if no --cuda-gpu-arch were passed.
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-gpu-arch=sm_35 --no-cuda-gpu-arch=sm_30 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM20,NOARCH-SM30,NOARCH-SM35 %s
-
-// d) --no-cuda-gpu-arch=X is a no-op if there's no preceding --cuda-gpu-arch=X
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30\
-// RUN:   --no-cuda-gpu-arch=sm_50 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,ARCH-SM35 %s
-
-// e) --no-cuda-gpu-arch=X does not affect following --cuda-gpu-arch=X
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --no-cuda-gpu-arch=sm_35 --no-cuda-gpu-arch=sm_30 \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,ARCH-SM35 %s
-
-// f) --no-cuda-gpu-arch=all negates all preceding --cuda-gpu-arch=X
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --cuda-gpu-arch=sm_20 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-gpu-arch=all \
-// RUN:   --cuda-gpu-arch=sm_35 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,NOARCH-SM30,ARCH-SM35 %s
-
-// g) There's no --cuda-gpu-arch=all
-// RUN: %clang -### -target x86_64-unknown-freebsd --cuda-device-only \
-// RUN:   --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: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
-
-// b) --no-cuda-include-ptx=all disables PTX inclusion for all GPUs
-// RUN: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-include-ptx=all \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,NOPTX-SM30 %s
-
-// c) --no-cuda-include-ptx=sm_XX disables PTX inclusion for that GPU only.
-// RUN: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-include-ptx=sm_35 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,PTX-SM30 %s
-// RUN: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-include-ptx=sm_30 \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,NOPTX-SM30 %s
-
-// d) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=all
-// RUN: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// 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
-
-// e) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=sm_XX
-// RUN: %clang -### -target x86_64-unknown-freebsd \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-include-ptx=sm_30 --cuda-include-ptx=all \
-// RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
-
-
-// ARCH-SM20: "-cc1"{{.*}}"-target-cpu" "sm_20"
-// NOARCH-SM20-NOT: "-cc1"{{.*}}"-target-cpu" "sm_20"
-// 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"
-// ARCHALLERROR: error: unsupported CUDA gpu architecture: all
-
-// Match device-side preprocessor and compiler phases with -save-temps.
-// DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
-// DEVICE-SAVE-SAME: "-aux-triple" "x86_64-unknown-freebsd"
-// DEVICE-SAVE-SAME: "-fcuda-is-device"
-// DEVICE-SAVE-SAME: "-x" "cuda"
-
-// DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
-// DEVICE-SAVE-SAME: "-aux-triple" "x86_64-unknown-freebsd"
-// DEVICE-SAVE-SAME: "-fcuda-is-device"
-// DEVICE-SAVE-SAME: "-x" "cuda-cpp-output"
-
-// Match the job that produces PTX assembly.
-// DEVICE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
-// DEVICE-NOSAVE-SAME: "-aux-triple" "x86_64-unknown-freebsd"
-// DEVICE-SAME: "-fcuda-is-device"
-// DEVICE-SM30-SAME: "-target-cpu" "sm_30"
-// DEVICE-SAME: "-o" "[[PTXFILE:[^"]*]]"
-// DEVICE-NOSAVE-SAME: "-x" "cuda"
-// DEVICE-SAVE-SAME: "-x" "ir"
-
-// Match the call to ptxas (which assembles PTX to SASS).
-// DEVICE:ptxas
-// DEVICE-SM30-DAG: "--gpu-name" "sm_30"
-// DEVICE-DAG: "--output-file" "[[CUBINFILE:[^"]*]]"
-// DEVICE-DAG: "[[PTXFILE]]"
-
-// Match another device-side compilation.
-// DEVICE2: "-cc1" "-triple" "nvptx64-nvidia-cuda"
-// DEVICE2-SAME: "-aux-triple" "x86_64-unknown-freebsd"
-// DEVICE2-SAME: "-fcuda-is-device"
-// DEVICE2-SM35-SAME: "-target-cpu" "sm_35"
-// DEVICE2-SAME: "-o" "[[PTXFILE2:[^"]*]]"
-// DEVICE2-SAME: "-x" "cuda"
-
-// Match another call to ptxas.
-// DEVICE2: ptxas
-// DEVICE2-SM35-DAG: "--gpu-name" "sm_35"
-// DEVICE2-DAG: "--output-file" "[[CUBINFILE2:[^"]*]]"
-// DEVICE2-DAG: "[[PTXFILE2]]"
-
-// Match no device-side compilation.
-// NODEVICE-NOT: "-cc1" "-triple" "nvptx64-nvidia-cuda"
-// NODEVICE-NOT: "-fcuda-is-device"
-
-// INCLUDES-DEVICE:fatbinary
-// INCLUDES-DEVICE-DAG: "--create" "[[FATBINARY:[^"]*]]"
-// INCLUDES-DEVICE-DAG: "--image=profile=sm_{{[0-9]+}},file=[[CUBINFILE]]"
-// INCLUDES-DEVICE-DAG: "--image=profile=compute_{{[0-9]+}},file=[[PTXFILE]]"
-// INCLUDES-DEVICE2-DAG: "--image=profile=sm_{{[0-9]+}},file=[[CUBINFILE2]]"
-// INCLUDES-DEVICE2-DAG: "--image=profile=compute_{{[0-9]+}},file=[[PTXFILE2]]"
-
-// Match host-side preprocessor job with -save-temps.
-// HOST-SAVE: "-cc1" "-triple" "x86_64-unknown-freebsd"
-// HOST-SAVE-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
-// HOST-SAVE-NOT: "-fcuda-is-device"
-// HOST-SAVE-SAME: "-x" "cuda"
-
-// Match host-side compilation.
-// HOST: "-cc1" "-triple" "x86_64-unknown-freebsd"
-// HOST-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
-// HOST-NOT: "-fcuda-is-device"
-// There is only one GPU binary after combining it with fatbinary!
-// INCLUDES-DEVICE2-NOT: "-fcuda-include-gpubinary"
-// INCLUDES-DEVICE-SAME: "-fcuda-include-gpubinary" "[[FATBINARY]]"
-// There is only one GPU binary after combining it with fatbinary.
-// INCLUDES-DEVICE2-NOT: "-fcuda-include-gpubinary"
-// HOST-SAME: "-o" "[[HOSTOUTPUT:[^"]*]]"
-// HOST-NOSAVE-SAME: "-x" "cuda"
-// HOST-SAVE-SAME: "-x" "cuda-cpp-output"
-
-// Match external assembler that uses compilation output.
-// HOST-AS: "-o" "{{.*}}.o" "[[HOSTOUTPUT]]"
-
-// Match no GPU code inclusion.
-// NOINCLUDES-DEVICE-NOT: "-fcuda-include-gpubinary"
-
-// Match no host compilation.
-// NOHOST-NOT: "-cc1" "-triple"
-// NOHOST-NOT: "-x" "cuda"
-
-// Match linker.
-// LINK: "{{.*}}{{ld|link}}{{(.exe)?}}"
-// LINK-SAME: "[[HOSTOUTPUT]]"
-
-// Match no linker.
-// NOLINK-NOT: "{{.*}}{{ld|link}}{{(.exe)?}}"
-
-// 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=

clang/test/Driver/cuda-options.cu

 // RUN: %clang -### -target x86_64-linux-gnu -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: %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_35 \
+// RUN:   --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
+// RUN:   --no-cuda-gpu-arch=sm_50 \
 // RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,NOARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
 
 // b) --no-cuda-gpu-arch=X negates more than one 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_35 --cuda-gpu-arch=sm_30 \
-// RUN:   --no-cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
+// RUN:   --no-cuda-gpu-arch=sm_50 \
 // RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,NOARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
 
 // c) if --no-cuda-gpu-arch=X negates all preceding --cuda-gpu-arch=X
-//    we default to sm_20 -- same as if no --cuda-gpu-arch were passed.
+//    we default to sm_35 -- same as if no --cuda-gpu-arch were passed.
 // RUN: %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_35 --no-cuda-gpu-arch=sm_30 \
+// RUN:   --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
+// RUN:   --no-cuda-gpu-arch=sm_50 --no-cuda-gpu-arch=sm_30 \
 // RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes ARCH-SM20,NOARCH-SM30,NOARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes NOARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
 
 // d) --no-cuda-gpu-arch=X is a no-op if there's no 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:   --no-cuda-gpu-arch=sm_50 \
 // RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,ARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
 
 // e) --no-cuda-gpu-arch=X does not affect following --cuda-gpu-arch=X
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
-// RUN:   --no-cuda-gpu-arch=sm_35 --no-cuda-gpu-arch=sm_30 \
-// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
+// 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:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,ARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,ARCH-SM50 %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_20 --cuda-gpu-arch=sm_30 \
+// RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
 // RUN:   --no-cuda-gpu-arch=all \
-// RUN:   --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-gpu-arch=sm_50 \
 // RUN:   -c %s 2>&1 \
-// RUN: | FileCheck -check-prefixes NOARCH-SM20,NOARCH-SM30,ARCH-SM35 %s
+// RUN: | FileCheck -check-prefixes NOARCH-SM30,NOARCH-SM35,ARCH-SM50 %s
 
 // g) There's no --cuda-gpu-arch=all
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
 // RUN:   --cuda-gpu-arch=all \
 // RUN:   -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix ARCHALLERROR %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: %clang -### -target x86_64-linux-gnu -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-SM20: "-cc1"{{.*}}"-target-cpu" "sm_20"
-// NOARCH-SM20-NOT: "-cc1"{{.*}}"-target-cpu" "sm_20"
 // 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"
 // ARCHALLERROR: error: unsupported CUDA gpu architecture: all
 
 // Match device-side preprocessor and compiler phases with -save-temps.
 // DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
 // DEVICE-SAVE-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // DEVICE-SAVE-SAME: "-fcuda-is-device"
 // DEVICE-SAVE-SAME: "-x" "cuda"
 

clang/test/Driver/cuda-ptxas-path.cu

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang -### --target=i386-unknown-linux \
 // RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda \
 // RUN:   --ptxas-path=/some/path/to/ptxas %s 2>&1 \
 // RUN: | FileCheck %s
 
 // CHECK-NOT: "ptxas"
 // CHECK: "/some/path/to/ptxas"
-// CHECK-SAME: "--gpu-name" "sm_20"
+// CHECK-SAME: "--gpu-name" "sm_35"

clang/test/Driver/lto.cu

 // CHECK-COMPILE-ACTIONS: 12: backend, {11}, lto-bc, (host-cuda)
 
 // RUN: %clangxx -nocudainc -nocudalib -ccc-print-phases %s -flto 2> %t
 // RUN: FileCheck -check-prefix=CHECK-COMPILELINK-ACTIONS < %t %s
 //
 // CHECK-COMPILELINK-ACTIONS: 0: input, "{{.*}}lto.cu", cuda, (host-cuda)
 // CHECK-COMPILELINK-ACTIONS: 1: preprocessor, {0}, cuda-cpp-output
 // CHECK-COMPILELINK-ACTIONS: 2: compiler, {1}, ir, (host-cuda)
-// CHECK-COMPILELINK-ACTIONS: 3: input, "{{.*}}lto.cu", cuda, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 5: compiler, {4}, ir, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 6: backend, {5}, assembler, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 7: assembler, {6}, object, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 8: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_20)" {7}, object
-// CHECK-COMPILELINK-ACTIONS: 9: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_20)" {6}, assembler
+// CHECK-COMPILELINK-ACTIONS: 3: input, "{{.*}}lto.cu", cuda, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 5: compiler, {4}, ir, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 6: backend, {5}, assembler, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 7: assembler, {6}, object, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 8: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_{{.*}})" {7}, object
+// CHECK-COMPILELINK-ACTIONS: 9: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_{{.*}})" {6}, assembler
 // CHECK-COMPILELINK-ACTIONS: 10: linker, {8, 9}, cuda-fatbin, (device-cuda)
 // CHECK-COMPILELINK-ACTIONS: 11: offload, "host-cuda {{.*}}" {2}, "device-cuda{{.*}}" {10}, ir
 // CHECK-COMPILELINK-ACTIONS: 12: backend, {11}, lto-bc, (host-cuda)
 // CHECK-COMPILELINK-ACTIONS: 13: linker, {12}, image, (host-cuda)
 
 // llvm-bc and llvm-ll outputs need to match regular suffixes
 // (unfortunately).
 // RUN: %clangxx %s -nocudainc -nocudalib -flto -save-temps -### 2> %t

clang/test/Driver/openmp-offload.c

 
 /// Check the phases graph when using a single GPU target, and check the OpenMP
 /// and CUDA phases are articulated correctly.
 // RUN:   %clang -ccc-print-phases -fopenmp=libomp -target powerpc64le-ibm-linux-gnu -fopenmp-targets=nvptx64-nvidia-cuda -x cuda %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PHASES-WITH-CUDA %s
 // CHK-PHASES-WITH-CUDA: 0: input, "[[INPUT:.+\.c]]", cuda, (host-cuda-openmp)
 // CHK-PHASES-WITH-CUDA: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda-openmp)
 // CHK-PHASES-WITH-CUDA: 2: compiler, {1}, ir, (host-cuda-openmp)
-// CHK-PHASES-WITH-CUDA: 3: input, "[[INPUT]]", cuda, (device-cuda, sm_20)
-// CHK-PHASES-WITH-CUDA: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_20)
-// CHK-PHASES-WITH-CUDA: 5: compiler, {4}, ir, (device-cuda, sm_20)
-// CHK-PHASES-WITH-CUDA: 6: backend, {5}, assembler, (device-cuda, sm_20)
-// CHK-PHASES-WITH-CUDA: 7: assembler, {6}, object, (device-cuda, sm_20)
-// CHK-PHASES-WITH-CUDA: 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_20)" {7}, object
-// CHK-PHASES-WITH-CUDA: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_20)" {6}, assembler
+// CHK-PHASES-WITH-CUDA: 3: input, "[[INPUT]]", cuda, (device-cuda, sm_{{.*}})
+// CHK-PHASES-WITH-CUDA: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_{{.*}})
+// CHK-PHASES-WITH-CUDA: 5: compiler, {4}, ir, (device-cuda, sm_{{.*}})
+// CHK-PHASES-WITH-CUDA: 6: backend, {5}, assembler, (device-cuda, sm_{{.*}})
+// CHK-PHASES-WITH-CUDA: 7: assembler, {6}, object, (device-cuda, sm_{{.*}})
+// CHK-PHASES-WITH-CUDA: 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_{{.*}})" {7}, object
+// CHK-PHASES-WITH-CUDA: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_{{.*}})" {6}, assembler
 // CHK-PHASES-WITH-CUDA: 10: linker, {8, 9}, cuda-fatbin, (device-cuda)
 // CHK-PHASES-WITH-CUDA: 11: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-cuda (nvptx64-nvidia-cuda)" {10}, ir
 // CHK-PHASES-WITH-CUDA: 12: backend, {11}, assembler, (host-cuda-openmp)
 // CHK-PHASES-WITH-CUDA: 13: assembler, {12}, object, (host-cuda-openmp)
 // CHK-PHASES-WITH-CUDA: 14: input, "[[INPUT]]", cuda, (device-openmp)
 // CHK-PHASES-WITH-CUDA: 15: preprocessor, {14}, cuda-cpp-output, (device-openmp)
 // CHK-PHASES-WITH-CUDA: 16: compiler, {15}, ir, (device-openmp)
 // CHK-PHASES-WITH-CUDA: 17: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-openmp (nvptx64-nvidia-cuda)" {16}, ir

clang/test/Driver/opt-record.c

 // RUN: %clang -### -S -o FOO -fsave-optimization-record=some-format %s 2>&1 | FileCheck %s -check-prefix=CHECK-EQ-FORMAT
 // RUN: %clang -### -S -o FOO -fsave-optimization-record=some-format -fno-save-optimization-record %s 2>&1 | FileCheck %s --check-prefix=CHECK-FOPT-DISABLE-FORMAT
 //
 // CHECK: "-cc1"
 // CHECK: "-opt-record-file" "FOO.opt.yaml"
 
 // CHECK-NO-O: "-cc1"
 // CHECK-NO-O-DAG: "-opt-record-file" "opt-record.opt.yaml"
-// CHECK-CUDA-DEV-DAG: "-opt-record-file" "opt-record-cuda-{{nvptx64|nvptx}}-nvidia-cuda-sm_20.opt.yaml"
+// CHECK-CUDA-DEV-DAG: "-opt-record-file" "opt-record-cuda-{{nvptx64|nvptx}}-nvidia-cuda-sm_{{.*}}.opt.yaml"
 
 // CHECK-EQ: "-cc1"
 // CHECK-EQ: "-opt-record-file" "BAR.txt"
 
 // CHECK-FOPT-DISABLE-NOT: "-fno-save-optimization-record"
 
 // CHECK-EQ-PASSES: "-cc1"
 // CHECK-EQ-PASSES: "-opt-record-passes" "inline"

clang/test/Driver/thinlto.cu

 // CHECK-COMPILE-ACTIONS: 12: backend, {11}, lto-bc, (host-cuda)
 
 // RUN: %clangxx -ccc-print-phases -nocudainc -nocudalib %s -flto=thin 2> %t
 // RUN: FileCheck -check-prefix=CHECK-COMPILELINK-ACTIONS < %t %s
 //
 // CHECK-COMPILELINK-ACTIONS: 0: input, "{{.*}}thinlto.cu", cuda, (host-cuda)
 // CHECK-COMPILELINK-ACTIONS: 1: preprocessor, {0}, cuda-cpp-output
 // CHECK-COMPILELINK-ACTIONS: 2: compiler, {1}, ir, (host-cuda)
-// CHECK-COMPILELINK-ACTIONS: 3: input, "{{.*}}thinlto.cu", cuda, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 5: compiler, {4}, ir, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 6: backend, {5}, assembler, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 7: assembler, {6}, object, (device-cuda, sm_20)
-// CHECK-COMPILELINK-ACTIONS: 8: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_20)" {7}, object
-// CHECK-COMPILELINK-ACTIONS: 9: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_20)" {6}, assembler
+// CHECK-COMPILELINK-ACTIONS: 3: input, "{{.*}}thinlto.cu", cuda, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 5: compiler, {4}, ir, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 6: backend, {5}, assembler, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 7: assembler, {6}, object, (device-cuda, sm_{{.*}})
+// CHECK-COMPILELINK-ACTIONS: 8: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_{{.*}})" {7}, object
+// CHECK-COMPILELINK-ACTIONS: 9: offload, "device-cuda (nvptx{{.*}}-nvidia-cuda:sm_{{.*}})" {6}, assembler
 // CHECK-COMPILELINK-ACTIONS: 10: linker, {8, 9}, cuda-fatbin, (device-cuda)
 // CHECK-COMPILELINK-ACTIONS: 11: offload, "host-cuda {{.*}}" {2}, "device-cuda{{.*}}" {10}, ir
 // CHECK-COMPILELINK-ACTIONS: 12: backend, {11}, lto-bc, (host-cuda)
 // CHECK-COMPILELINK-ACTIONS: 13: linker, {12}, image, (host-cuda)