Index: lib/Target/NVPTX/NVPTXTargetMachine.cpp
===================================================================
--- lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -167,9 +167,10 @@
   disablePass(&TailDuplicateID);
 
   addPass(createNVPTXImageOptimizerPass());
-  TargetPassConfig::addIRPasses();
   addPass(createNVPTXAssignValidGlobalNamesPass());
   addPass(createGenericToNVVMPass());
+
+  // === Propagate special address spaces ===
   addPass(createNVPTXLowerKernelArgsPass(&getNVPTXTargetMachine()));
   // NVPTXLowerKernelArgs emits alloca for byval parameters which can often
   // be eliminated by SROA.
@@ -180,6 +181,8 @@
   // them unused. We could remove dead code in an ad-hoc manner, but that
   // requires manual work and might be error-prone.
   addPass(createDeadCodeEliminationPass());
+
+  // === Straight-line scalar optimizations ===
   addPass(createSeparateConstOffsetFromGEPPass());
   addPass(createSpeculativeExecutionPass());
   // ReassociateGEPs exposes more opportunites for SLSR. See
@@ -197,6 +200,22 @@
   // NaryReassociate on GEPs creates redundant common expressions, so run
   // EarlyCSE after it.
   addPass(createEarlyCSEPass());
+
+  // === LSR and other generic IR passes ===
+  TargetPassConfig::addIRPasses();
+  // EarlyCSE is not strong enough to clean up what LSR produces. For example,
+  // GVN can combine
+  //
+  //   %0 = add %a, %b
+  //   %1 = add %b, %a
+  //
+  // and
+  //
+  //   %0 = shl nsw %a, 2
+  //   %1 = shl %a, 2
+  //
+  // but EarlyCSE can do neither of them.
+  addPass(llvm::createGVNPass());
 }
 
 bool NVPTXPassConfig::addInstSelector() {