Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -6286,6 +6286,13 @@
   // fold (ctlz c1) -> c2
   if (DAG.isConstantIntBuildVectorOrConstantInt(N0))
     return DAG.getNode(ISD::CTLZ, SDLoc(N), VT, N0);
+
+  // If the value is known never to be zero, switch to the undef version.
+  if (!LegalOperations || TLI.isOperationLegal(ISD::CTLZ_ZERO_UNDEF, VT)) {
+    if (DAG.isKnownNeverZero(N0))
+      return DAG.getNode(ISD::CTLZ_ZERO_UNDEF, SDLoc(N), VT, N0);
+  }
+
   return SDValue();
 }
 
@@ -6306,6 +6313,13 @@
   // fold (cttz c1) -> c2
   if (DAG.isConstantIntBuildVectorOrConstantInt(N0))
     return DAG.getNode(ISD::CTTZ, SDLoc(N), VT, N0);
+
+  // If the value is known never to be zero, switch to the undef version.
+  if (!LegalOperations || TLI.isOperationLegal(ISD::CTTZ_ZERO_UNDEF, VT)) {
+    if (DAG.isKnownNeverZero(N0))
+      return DAG.getNode(ISD::CTTZ_ZERO_UNDEF, SDLoc(N), VT, N0);
+  }
+
   return SDValue();
 }
 
Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -32066,17 +32066,6 @@
   X86::CondCode CC = (X86::CondCode)N->getConstantOperandVal(2);
   SDValue Cond = N->getOperand(3);
 
-  if (CC == X86::COND_E || CC == X86::COND_NE) {
-    switch (Cond.getOpcode()) {
-    default: break;
-    case X86ISD::BSR:
-    case X86ISD::BSF:
-      // If operand of BSR / BSF are proven never zero, then ZF cannot be set.
-      if (DAG.isKnownNeverZero(Cond.getOperand(0)))
-        return (CC == X86::COND_E) ? FalseOp : TrueOp;
-    }
-  }
-
   // Try to simplify the EFLAGS and condition code operands.
   // We can't always do this as FCMOV only supports a subset of X86 cond.
   if (SDValue Flags = combineSetCCEFLAGS(Cond, CC, DAG, Subtarget)) {
Index: test/CodeGen/AMDGPU/cttz_zero_undef.ll
===================================================================
--- test/CodeGen/AMDGPU/cttz_zero_undef.ll
+++ test/CodeGen/AMDGPU/cttz_zero_undef.ll
@@ -239,7 +239,8 @@
 
 ; FUNC-LABEL: {{^}}v_cttz_i8_sel_eq_neg1:
 ; SI: {{buffer|flat}}_load_ubyte
-; SI: v_ffbl_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}
+; SI-NOSDWA: v_ffbl_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}
+; SI-SDWA: v_ffbl_b32_sdwa
 ; EG: MEM_RAT MSKOR
 ; EG: FFBL_INT
  define amdgpu_kernel void @v_cttz_i8_sel_eq_neg1(i8 addrspace(1)* noalias %out, i8 addrspace(1)* nocapture readonly %arrayidx) nounwind {