diff --git a/llvm/lib/Target/NVPTX/NVPTX.td b/llvm/lib/Target/NVPTX/NVPTX.td
--- a/llvm/lib/Target/NVPTX/NVPTX.td
+++ b/llvm/lib/Target/NVPTX/NVPTX.td
@@ -115,11 +115,11 @@
 class Proc<string Name, list<SubtargetFeature> Features>
  : Processor<Name, NoItineraries, Features>;
 
-def : Proc<"sm_20", [SM20]>;
-def : Proc<"sm_21", [SM21]>;
+def : Proc<"sm_20", [SM20, PTX32]>;
+def : Proc<"sm_21", [SM21, PTX32]>;
 def : Proc<"sm_30", [SM30]>;
 def : Proc<"sm_32", [SM32, PTX40]>;
-def : Proc<"sm_35", [SM35]>;
+def : Proc<"sm_35", [SM35, PTX32]>;
 def : Proc<"sm_37", [SM37, PTX41]>;
 def : Proc<"sm_50", [SM50, PTX40]>;
 def : Proc<"sm_52", [SM52, PTX41]>;
diff --git a/llvm/lib/Target/NVPTX/NVPTXSubtarget.cpp b/llvm/lib/Target/NVPTX/NVPTXSubtarget.cpp
--- a/llvm/lib/Target/NVPTX/NVPTXSubtarget.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXSubtarget.cpp
@@ -33,13 +33,13 @@
 NVPTXSubtarget &NVPTXSubtarget::initializeSubtargetDependencies(StringRef CPU,
                                                                 StringRef FS) {
     // Provide the default CPU if we don't have one.
-    TargetName = std::string(CPU.empty() ? "sm_20" : CPU);
+    TargetName = std::string(CPU.empty() ? "sm_30" : CPU);
 
     ParseSubtargetFeatures(TargetName, /*TuneCPU*/ TargetName, FS);
 
-    // Set default to PTX 3.2 (CUDA 5.5)
+    // Set default to PTX 6.0 (CUDA 9.0)
     if (PTXVersion == 0) {
-      PTXVersion = 32;
+      PTXVersion = 60;
   }
 
   return *this;
diff --git a/llvm/test/CodeGen/NVPTX/nvvm-reflect-arch.ll b/llvm/test/CodeGen/NVPTX/nvvm-reflect-arch.ll
--- a/llvm/test/CodeGen/NVPTX/nvvm-reflect-arch.ll
+++ b/llvm/test/CodeGen/NVPTX/nvvm-reflect-arch.ll
@@ -1,7 +1,7 @@
 ; Libdevice in recent CUDA versions relies on __CUDA_ARCH reflecting GPU type.
 ; Verify that __nvvm_reflect() is replaced with an appropriate value.
 ;
-; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 \
+; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 -mcpu=sm_20 \
 ; RUN:   | FileCheck %s --check-prefixes=COMMON,SM20
 ; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 -mcpu=sm_35 \
 ; RUN:   | FileCheck %s --check-prefixes=COMMON,SM35
diff --git a/llvm/test/CodeGen/NVPTX/nvvm-reflect-ocl.ll b/llvm/test/CodeGen/NVPTX/nvvm-reflect-ocl.ll
--- a/llvm/test/CodeGen/NVPTX/nvvm-reflect-ocl.ll
+++ b/llvm/test/CodeGen/NVPTX/nvvm-reflect-ocl.ll
@@ -1,6 +1,6 @@
 ; Verify that __nvvm_reflect_ocl() is replaced with an appropriate value
 ;
-; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 \
+; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 -mcpu=sm_20 \
 ; RUN:   | FileCheck %s --check-prefixes=COMMON,SM20
 ; RUN: opt %s -S -passes='default<O2>' -mtriple=nvptx64 -mcpu=sm_35 \
 ; RUN:   | FileCheck %s --check-prefixes=COMMON,SM35
diff --git a/llvm/test/CodeGen/NVPTX/sm-version.ll b/llvm/test/CodeGen/NVPTX/sm-version.ll
--- a/llvm/test/CodeGen/NVPTX/sm-version.ll
+++ b/llvm/test/CodeGen/NVPTX/sm-version.ll
@@ -32,7 +32,9 @@
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_80 | FileCheck %s --check-prefix=SM80
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_86 | FileCheck %s --check-prefix=SM86
 
-; SM30: .version 3.2
+; SM20: .version 3.2
+; SM21: .version 3.2
+; SM30: .version 6.0
 ; SM32: .version 4.0
 ; SM35: .version 3.2
 ; SM37: .version 4.1
diff --git a/llvm/test/CodeGen/NVPTX/surf-tex.py b/llvm/test/CodeGen/NVPTX/surf-tex.py
--- a/llvm/test/CodeGen/NVPTX/surf-tex.py
+++ b/llvm/test/CodeGen/NVPTX/surf-tex.py
@@ -1,6 +1,6 @@
 # RUN: %python %s --target=cuda --tests=suld,sust,tex,tld4 --gen-list=%t.list > %t-cuda.ll
-# RUN: llc %t-cuda.ll -verify-machineinstrs -o - | FileCheck %t-cuda.ll
-# RUN: %if ptxas %{ llc %t-cuda.ll -verify-machineinstrs -o - | %ptxas-verify %}
+# RUN: llc -mcpu=sm_20 %t-cuda.ll -verify-machineinstrs -o - | FileCheck %t-cuda.ll
+# RUN: %if ptxas %{ llc -mcpu=sm_20 %t-cuda.ll -verify-machineinstrs -o - | %ptxas-verify %}
 
 # We only need to run this second time for texture tests, because
 # there is a difference between unified and non-unified intrinsics.
diff --git a/llvm/test/DebugInfo/NVPTX/dbg-declare-alloca.ll b/llvm/test/DebugInfo/NVPTX/dbg-declare-alloca.ll
--- a/llvm/test/DebugInfo/NVPTX/dbg-declare-alloca.ll
+++ b/llvm/test/DebugInfo/NVPTX/dbg-declare-alloca.ll
@@ -1,7 +1,7 @@
 ; RUN: llc < %s -mtriple=nvptx64-nvidia-cuda | FileCheck %s
 ; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64-nvidia-cuda | %ptxas-verify %}
 
-; CHECK: .target sm_20, debug
+; CHECK: .target sm_30, debug
 
 ; CHECK: .visible .func use_dbg_declare()
 ; CHECK: .local .align 8 .b8 __local_depot0[8];