forked from OSchip/llvm-project
[CUDA] Bump default GPU architecture to sm_35.
It's the oldest GPU architecture currently supported by all CUDA versions clang can use. Differential Revision: https://reviews.llvm.org/D108235
This commit is contained in:
Artem Belevich
parent
10c982e0b3
commit
0060fffc82
|
|
@ -2765,7 +2765,7 @@ class OffloadingActionBuilder final {
|
|||
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 {
|
||||
|
|
|
|||
|
|
@ -7,96 +7,120 @@
|
|||
|
||||
// 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).
|
||||
|
|
@ -112,9 +136,7 @@
|
|||
// 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"
|
||||
|
|
@ -129,9 +151,7 @@
|
|||
// 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"
|
||||
|
|
|
|||
|
|
@ -9,14 +9,14 @@
|
|||
// 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"
|
||||
|
|
|
|||
|
|
@ -1,289 +0,0 @@
|
|||
// 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=
|
||||
|
|
@ -94,47 +94,47 @@
|
|||
// 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 \
|
||||
|
|
@ -190,12 +190,12 @@
|
|||
// 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.
|
||||
|
|
|
|||
|
|
@ -9,4 +9,4 @@
|
|||
|
||||
// CHECK-NOT: "ptxas"
|
||||
// CHECK: "/some/path/to/ptxas"
|
||||
// CHECK-SAME: "--gpu-name" "sm_20"
|
||||
// CHECK-SAME: "--gpu-name" "sm_35"
|
||||
|
|
|
|||
|
|
@ -16,13 +16,13 @@
|
|||
// 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)
|
||||
|
|
|
|||
|
|
@ -215,13 +215,13 @@
|
|||
// 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)
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@
|
|||
|
||||
// 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"
|
||||
|
|
|
|||
|
|
@ -16,13 +16,13 @@
|
|||
// 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)
|
||||
|
|
|
|||
Loading…
Reference in New Issue