Index: llvm/include/llvm/Transforms/Scalar/GVN.h
===================================================================
--- llvm/include/llvm/Transforms/Scalar/GVN.h
+++ llvm/include/llvm/Transforms/Scalar/GVN.h
@@ -54,6 +54,12 @@
 class PHINode;
 class TargetLibraryInfo;
 class Value;
+
+template <typename _FunctionT> class GenericSSAContext;
+using SSAContext = GenericSSAContext<Function>;
+template <typename ContextT> class GenericUniformityInfo;
+using UniformityInfo = GenericUniformityInfo<SSAContext>;
+
 /// A private "module" namespace for types and utilities used by GVN. These
 /// are implementation details and should not be used by clients.
 namespace gvn LLVM_LIBRARY_VISIBILITY {
@@ -221,6 +227,7 @@
   MemoryDependenceResults *MD = nullptr;
   DominatorTree *DT = nullptr;
   const TargetLibraryInfo *TLI = nullptr;
+  const UniformityInfo *UI = nullptr;
   AssumptionCache *AC = nullptr;
   SetVector<BasicBlock *> DeadBlocks;
   OptimizationRemarkEmitter *ORE = nullptr;
@@ -260,8 +267,8 @@
   using UnavailBlkVect = SmallVector<BasicBlock *, 64>;
 
   bool runImpl(Function &F, AssumptionCache &RunAC, DominatorTree &RunDT,
-               const TargetLibraryInfo &RunTLI, AAResults &RunAA,
-               MemoryDependenceResults *RunMD, LoopInfo *LI,
+               const TargetLibraryInfo &RunTLI, const UniformityInfo &RunUI,
+               AAResults &RunAA, MemoryDependenceResults *RunMD, LoopInfo *LI,
                OptimizationRemarkEmitter *ORE, MemorySSA *MSSA = nullptr);
 
   /// Push a new Value to the LeaderTable onto the list for its value number.
Index: llvm/lib/Transforms/Scalar/GVN.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/GVN.cpp
+++ llvm/lib/Transforms/Scalar/GVN.cpp
@@ -41,6 +41,7 @@
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/PHITransAddr.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/UniformityAnalysis.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
@@ -747,19 +748,21 @@
   auto &AC = AM.getResult<AssumptionAnalysis>(F);
   auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
   auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
+  auto &UI = AM.getResult<UniformityInfoAnalysis>(F);
   auto &AA = AM.getResult<AAManager>(F);
   auto *MemDep =
       isMemDepEnabled() ? &AM.getResult<MemoryDependenceAnalysis>(F) : nullptr;
   auto *LI = AM.getCachedResult<LoopAnalysis>(F);
   auto *MSSA = AM.getCachedResult<MemorySSAAnalysis>(F);
   auto &ORE = AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
-  bool Changed = runImpl(F, AC, DT, TLI, AA, MemDep, LI, &ORE,
+  bool Changed = runImpl(F, AC, DT, TLI, UI, AA, MemDep, LI, &ORE,
                          MSSA ? &MSSA->getMSSA() : nullptr);
   if (!Changed)
     return PreservedAnalyses::all();
   PreservedAnalyses PA;
   PA.preserve<DominatorTreeAnalysis>();
   PA.preserve<TargetLibraryAnalysis>();
+  PA.preserve<UniformityInfoAnalysis>();
   if (MSSA)
     PA.preserve<MemorySSAAnalysis>();
   if (LI)
@@ -2304,12 +2307,15 @@
     uint32_t LVN = VN.lookupOrAdd(LHS);
     if ((isa<Argument>(LHS) && isa<Argument>(RHS)) ||
         (isa<Instruction>(LHS) && isa<Instruction>(RHS))) {
-      // Move the 'oldest' value to the right-hand side, using the value number
-      // as a proxy for age.
-      uint32_t RVN = VN.lookupOrAdd(RHS);
-      if (LVN < RVN) {
-        std::swap(LHS, RHS);
-        LVN = RVN;
+      // Avoid replacing uniform values with non-uniform values.
+      if (!UI->isUniform(RHS) || UI->isUniform(LHS)) {
+        // Move the 'oldest' value to the right-hand side, using the value
+        // number as a proxy for age.
+        uint32_t RVN = VN.lookupOrAdd(RHS);
+        if (LVN < RVN) {
+          std::swap(LHS, RHS);
+          LVN = RVN;
+        }
       }
     }
 
@@ -2562,13 +2568,15 @@
 
 /// runOnFunction - This is the main transformation entry point for a function.
 bool GVNPass::runImpl(Function &F, AssumptionCache &RunAC, DominatorTree &RunDT,
-                      const TargetLibraryInfo &RunTLI, AAResults &RunAA,
+                      const TargetLibraryInfo &RunTLI,
+                      const UniformityInfo &RunUI, AAResults &RunAA,
                       MemoryDependenceResults *RunMD, LoopInfo *LI,
                       OptimizationRemarkEmitter *RunORE, MemorySSA *MSSA) {
   AC = &RunAC;
   DT = &RunDT;
   VN.setDomTree(DT);
   TLI = &RunTLI;
+  UI = &RunUI;
   VN.setAliasAnalysis(&RunAA);
   MD = RunMD;
   ImplicitControlFlowTracking ImplicitCFT;
@@ -3168,6 +3176,7 @@
         F, getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F),
         getAnalysis<DominatorTreeWrapperPass>().getDomTree(),
         getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F),
+        getAnalysis<UniformityInfoWrapperPass>().getUniformityInfo(),
         getAnalysis<AAResultsWrapperPass>().getAAResults(),
         Impl.isMemDepEnabled()
             ? &getAnalysis<MemoryDependenceWrapperPass>().getMemDep()
@@ -3181,6 +3190,7 @@
     AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<DominatorTreeWrapperPass>();
     AU.addRequired<TargetLibraryInfoWrapperPass>();
+    AU.addRequired<UniformityInfoWrapperPass>();
     AU.addRequired<LoopInfoWrapperPass>();
     if (Impl.isMemDepEnabled())
       AU.addRequired<MemoryDependenceWrapperPass>();
@@ -3188,6 +3198,7 @@
     AU.addPreserved<DominatorTreeWrapperPass>();
     AU.addPreserved<GlobalsAAWrapperPass>();
     AU.addPreserved<TargetLibraryInfoWrapperPass>();
+    AU.addPreserved<UniformityInfoWrapperPass>();
     AU.addPreserved<LoopInfoWrapperPass>();
     AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
     AU.addPreserved<MemorySSAWrapperPass>();
@@ -3204,6 +3215,7 @@
 INITIALIZE_PASS_DEPENDENCY(MemoryDependenceWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(UniformityInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)
Index: llvm/test/Transforms/GVN/uniform-values.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/GVN/uniform-values.ll
@@ -0,0 +1,48 @@
+; REQUIRES: amdgpu-registered-target
+; RUN: opt < %s -mtriple=amdgcn -passes=gvn -S | FileCheck %s
+
+; CHECK-LABEL: @no_replace_uniform_with_non
+define void @no_replace_uniform_with_non(i32* %buf) {
+  %v1 = load i32, i32* %buf
+  %v2 = call i32 @llvm.amdgcn.readfirstlane(i32 %v1)
+  %cond = icmp eq i32 %v1, %v2
+  br i1 %cond, label %matches, label %end
+
+; Make sure we don't replace %v2 with %v1 when %v2 is known to be uniform
+; CHECK-LABEL: matches:
+; CHECK: call void @opaque(i32 %v2)
+matches:
+  call void @opaque(i32 %v2)
+  br label %end
+
+; CHECK-LABEL: end:
+; CHECK: call void @opaque(i32 %v1)
+end:
+  call void @opaque(i32 %v1)
+  ret void
+}
+
+; CHECK-LABEL: @replace_non_uniform_with_uniform
+define void @replace_non_uniform_with_uniform(i32* %buf, i32* %buf2) {
+  %v1 = load i32, i32* %buf
+  %v2 = call i32 @llvm.amdgcn.readfirstlane(i32 %v1)
+  %v3 = load i32, i32* %buf2
+  %cond = icmp eq i32 %v2, %v3
+  br i1 %cond, label %matches, label %end
+
+; CHECK-LABEL: matches:
+; CHECK: call void @opaque(i32 %v2)
+matches:
+  call void @opaque(i32 %v3)
+  br label %end
+
+; CHECK-LABEL: end:
+; CHECK: call void @opaque(i32 %v3)
+end:
+  call void @opaque(i32 %v3)
+  ret void
+}
+
+
+declare i32 @llvm.amdgcn.readfirstlane(i32) nounwind readnone
+declare void @opaque(i32)