Index: llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
===================================================================
--- llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
+++ llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
@@ -90,6 +90,11 @@
     return false;
   }
 
+  // If the numerator is a constant, bail if it doesn't fit into BypassType.
+  if (ConstantInt *ConstDividend = dyn_cast<ConstantInt>(Dividend))
+    if (ConstDividend->getValue().getActiveBits() > BypassType->getBitWidth())
+      return false;
+
   // Basic Block is split before divide
   BasicBlock *MainBB = &*I->getParent();
   BasicBlock *SuccessorBB = MainBB->splitBasicBlock(I);
@@ -151,7 +156,17 @@
   // Combine operands into a single value with OR for value testing below
   MainBB->getInstList().back().eraseFromParent();
   IRBuilder<> MainBuilder(MainBB, MainBB->end());
-  Value *OrV = MainBuilder.CreateOr(Dividend, Divisor);
+
+  // We should have bailed out above if the divisor is not a constant, but the
+  // dividend may still be a constant.  Set OrV to our non-constant operands
+  // OR'ed together.
+  assert(!isa<ConstantInt>(Divisor));
+
+  Value *OrV;
+  if (!isa<ConstantInt>(Dividend))
+    OrV = MainBuilder.CreateOr(Dividend, Divisor);
+  else
+    OrV = Divisor;
 
   // BitMask is inverted to check if the operands are
   // larger than the bypass type
Index: llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-constant-numerator.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-constant-numerator.ll
@@ -0,0 +1,35 @@
+; RUN: opt -S -codegenprepare < %s | FileCheck %s
+
+target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; When we bypass slow div with a constant numerator which fits into the bypass
+; width, we still emit the bypass code, but we don't 'or' the numerator with
+; the denominator.
+; CHECK-LABEL: @small_constant_numer
+define i64 @small_constant_numer(i64 %a) {
+  ; CHECK: [[AND:%[0-9]+]] = and i64 %a, -4294967296
+  ; CHECK: icmp eq i64 [[AND]], 0
+
+  ; CHECK: [[TRUNC:%[0-9]+]] = trunc i64 %a to i32
+  ; CHECK: udiv i32 -1, [[TRUNC]]
+  %d = sdiv i64 4294967295, %a  ; 0xffff'ffff
+  ret i64 %d
+}
+
+; When we try to bypass slow div with a constant numerator which *doesn't* fit
+; into the bypass width, leave it as a plain 64-bit div with no bypass.
+; CHECK-LABEL: @large_constant_numer
+define i64 @large_constant_numer(i64 %a) {
+  ; CHECK-NOT: udiv i32
+  %d = sdiv i64 4294967296, %a  ; 0x1'0000'0000
+  ret i64 %d
+}
+
+; For good measure, try a value larger than 2^32.
+; CHECK-LABEL: @larger_constant_numer
+define i64 @larger_constant_numer(i64 %a) {
+  ; CHECK-NOT: udiv i32
+  %d = sdiv i64 5000000000, %a
+  ret i64 %d
+}