Index: include/llvm/IR/IntrinsicsAMDGPU.td
===================================================================
--- include/llvm/IR/IntrinsicsAMDGPU.td
+++ include/llvm/IR/IntrinsicsAMDGPU.td
@@ -747,6 +747,12 @@
   [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
 >;
 
+// Return true if at least one thread within the pixel quad passes true into
+// the function.
+def int_amdgcn_wqm_vote : Intrinsic<[llvm_i1_ty],
+  [llvm_i1_ty], [IntrNoMem, IntrSpeculatable, IntrConvergent]
+>;
+
 // Copies the active channels of the source value to the destination value,
 // with the guarantee that the source value is computed as if the entire
 // program were executed in Whole Wavefront Mode, i.e. with all channels
Index: lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- lib/Target/AMDGPU/SIInstructions.td
+++ lib/Target/AMDGPU/SIInstructions.td
@@ -1206,6 +1206,11 @@
 >;
 
 def : Pat <
+  (i1 (int_amdgcn_wqm_vote i1:$src0)),
+  (S_WQM_B64 $src0)
+>;
+
+def : Pat <
   (f32 (sint_to_fp i1:$src)),
   (V_CNDMASK_B32_e64 (i32 0), (i32 CONST.FP32_NEG_ONE), $src)
 >;
Index: lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -3532,6 +3532,14 @@
 
     break;
   }
+  case Intrinsic::amdgcn_wqm_vote: {
+    const ConstantInt *C = dyn_cast<ConstantInt>(II->getArgOperand(0));
+    if (!C)
+      break;
+
+    // wqm_vote is identity when the argument is constant.
+    return replaceInstUsesWith(*II, II->getArgOperand(0));
+  }
   case Intrinsic::stackrestore: {
     // If the save is right next to the restore, remove the restore.  This can
     // happen when variable allocas are DCE'd.
Index: test/CodeGen/AMDGPU/wqm.vote.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/wqm.vote.ll
@@ -0,0 +1,79 @@
+; RUN: opt -S -mtriple=amdgcn-- -instcombine < %s | llc -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefix=CHECK %s
+
+;CHECK-LABEL: {{^}}ret:
+;CHECK: v_cmp_eq_u32_e32 [[CMP:[^,]+]], v0, v1
+;CHECK: s_wqm_b64 [[WQM:[^,]+]], [[CMP]]
+;CHECK: v_cndmask_b32_e64 v0, 0, 1.0, [[WQM]]
+define amdgpu_ps float @ret(i32 %v0, i32 %v1) #1 {
+main_body:
+  %c = icmp eq i32 %v0, %v1
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 %c)
+  %r = select i1 %w, float 1.0, float 0.0
+  ret float %r
+}
+
+;CHECK-LABEL: {{^}}true:
+;CHECK-NOT: s_wqm_b64
+;CHECK: v_mov_b32_e32 v0, 1.0
+define amdgpu_ps float @true() #1 {
+main_body:
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 true)
+  %r = select i1 %w, float 1.0, float 0.0
+  ret float %r
+}
+
+;CHECK-LABEL: {{^}}false:
+;CHECK-NOT: s_wqm_b64
+;CHECK: v_mov_b32_e32 v0, 0
+define amdgpu_ps float @false() #1 {
+main_body:
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 false)
+  %r = select i1 %w, float 1.0, float 0.0
+  ret float %r
+}
+
+;CHECK-LABEL: {{^}}kill:
+;CHECK: v_cmp_eq_u32_e32 [[CMP:[^,]+]], v0, v1
+;CHECK: s_wqm_b64 [[WQM:[^,]+]], [[CMP]]
+;FIXME: This could just be: s_and_b64 exec, exec, [[WQM]]
+;CHECK: v_cndmask_b32_e64 [[KILL:[^,]+]], -1.0, 1.0, [[WQM]]
+;CHECK: v_cmpx_le_f32_e32 {{[^,]+}}, 0, [[KILL]]
+;CHECK: s_endpgm
+define amdgpu_ps void @kill(i32 %v0, i32 %v1) #1 {
+main_body:
+  %c = icmp eq i32 %v0, %v1
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 %c)
+  %r = select i1 %w, float 1.0, float -1.0
+  call void @llvm.AMDGPU.kill(float %r)
+  ret void
+}
+
+;CHECK-LABEL: {{^}}kill_true:
+;CHECK-NEXT: ; BB#
+;CHECK-NEXT: s_endpgm
+define amdgpu_ps void @kill_true(i32 %v0, i32 %v1) #1 {
+main_body:
+  %c = icmp eq i32 %v0, %v1
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 true)
+  %r = select i1 %w, float 1.0, float -1.0
+  call void @llvm.AMDGPU.kill(float %r)
+  ret void
+}
+
+;CHECK-LABEL: {{^}}kill_false:
+;CHECK: s_mov_b64 exec, 0
+;CHECK: s_endpgm
+define amdgpu_ps void @kill_false(i32 %v0, i32 %v1) #1 {
+main_body:
+  %c = icmp eq i32 %v0, %v1
+  %w = call i1 @llvm.amdgcn.wqm.vote(i1 false)
+  %r = select i1 %w, float 1.0, float -1.0
+  call void @llvm.AMDGPU.kill(float %r)
+  ret void
+}
+
+declare void @llvm.AMDGPU.kill(float) #1
+declare i1 @llvm.amdgcn.wqm.vote(i1) #0
+
+attributes #0 = { nounwind readnone speculatable convergent }
+attributes #1 = { nounwind }