1 files changed, 72 insertions, 10 deletions
diff --git a/test/Driver/cuda-options.cu b/test/Driver/cuda-options.cu
index c4bfda903d9e1..4ffab317d16ac 100644
--- a/test/Driver/cuda-options.cu
+++ b/test/Driver/cuda-options.cu
@@ -62,7 +62,7 @@
 // RUN:    -check-prefix HOST -check-prefix INCLUDES-DEVICE \
 // RUN:    -check-prefix LINK %s
 
-// Verify that --cuda-gpu-arch option passes the correct GPU archtecture to
+// Verify that --cuda-gpu-arch option passes the correct GPU architecture to
 // device compilation.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_30 -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
@@ -73,11 +73,10 @@
 // and that all results are included on the host side.
 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 -c %s 2>&1 \
-// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
-// RUN:    -check-prefix DEVICE2 -check-prefix DEVICE-SM30 \
-// RUN:    -check-prefix DEVICE2-SM35 -check-prefix HOST \
-// RUN:    -check-prefix HOST-NOSAVE -check-prefix INCLUDES-DEVICE \
-// RUN:    -check-prefix NOLINK %s
+// 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.
@@ -93,21 +92,21 @@
 // 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 preceeding --cuda-gpu-arch=X
+// 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:   -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 preceeding --cuda-gpu-arch=X
+// 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:   -c %s 2>&1 \
 // RUN: | FileCheck -check-prefixes NOARCH-SM20,ARCH-SM30,NOARCH-SM35 %s
 
-// c) if --no-cuda-gpu-arch=X negates all preceeding --cuda-gpu-arch=X
+// 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-linux-gnu --cuda-device-only \
 // RUN:   --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
@@ -143,6 +142,48 @@
 // 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-linux-gnu \
+// 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-linux-gnu \
+// 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-linux-gnu \
+// 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-linux-gnu \
+// 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-linux-gnu \
+// 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-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:   -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"
@@ -182,9 +223,15 @@
 // DEVICE2-SAME: "-aux-triple" "x86_64--linux-gnu"
 // DEVICE2-SAME: "-fcuda-is-device"
 // DEVICE2-SM35-SAME: "-target-cpu" "sm_35"
-// DEVICE2-SAME: "-o" "[[GPUBINARY2:[^"]*]]"
+// 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"
@@ -193,6 +240,8 @@
 // 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--linux-gnu"
@@ -207,7 +256,11 @@
 // HOST-SAME: "-o" "[[HOSTOUTPUT:[^"]*]]"
 // HOST-NOSAVE-SAME: "-x" "cuda"
 // HOST-SAVE-SAME: "-x" "cuda-cpp-output"
+// 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"
 
 // Match external assembler that uses compilation output.
 // HOST-AS: "-o" "{{.*}}.o" "[[HOSTOUTPUT]]"
@@ -225,3 +278,12 @@
 
 // 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=