[AMDGPU] Extend pre-emit peephole to redundantly masked VCC

[critson]

Summary

Extend pre-emit peephole for S_CBRANCH_VCC[N]Z to eliminate
redundant S_AND operations against EXEC for V_CMP results in VCC.
These occur after after register allocation when VCC has been
selected as the comparison destination.

[rampitec]

LGTM, but misses new tests in the insert-skip-from-vcc.mir.

[arsenm]

Can you add some MIR tests, plus add a test for V_CMP_CLASS where this should also work

[critson]

• Add V_CMP_CLASS support
• Add MIR tests

[foad]

Extend pre-emit peephole for S_CBRANCH_VCC[N]Z to eliminate
redundant S_AND operations against EXEC for V_CMP results in VCC.

No particular objection to this patch, but it would be nice to do this more generally for comparison results that are not in vcc too.

[arsenm]

llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp

148

I think isCompare is always redundant with isVOPC

[rampitec]

LGTM

[critson]

llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp

148

Switched to using only isVOPC and documented why in a comment.

[arsenm]

llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp

149

isVOPC is redundant with isVALU

llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp

bool SIPreEmitPeephole::optimizeVccBranch(MachineInstr &MI) const {
   // sreg = -1 or 0
   // vcc = S_AND_B64 exec, sreg or S_ANDN2_B64 exec, sreg
   // S_CBRANCH_VCC[N]Z
   // =>
   // S_CBRANCH_EXEC[N]Z
   // We end up with this pattern sometimes after basic block placement.
   // It happens while combining a block which assigns -1 or 0 to a saved mask
   // and another block which consumes that saved mask and then a branch.
+  //
+  // While searching this also performs the following substitution:
+  // vcc = V_CMP
+  // vcc = S_AND exec, vcc
+  // S_CBRANCH_VCC[N]Z
+  // =>
+  // vcc = V_CMP
+  // S_CBRANCH_VCC[N]Z
+
   bool Changed = false;
   MachineBasicBlock &MBB = *MI.getParent();
   const GCNSubtarget &ST = MBB.getParent()->getSubtarget<GCNSubtarget>();
   const bool IsWave32 = ST.isWave32();
   const unsigned CondReg = TRI->getVCC();
   const unsigned ExecReg = IsWave32 ? AMDGPU::EXEC_LO : AMDGPU::EXEC;
   const unsigned And = IsWave32 ? AMDGPU::S_AND_B32 : AMDGPU::S_AND_B64;
   const unsigned AndN2 = IsWave32 ? AMDGPU::S_ANDN2_B32 : AMDGPU::S_ANDN2_B64;
if (Op2.isImm() && !(Op2.getImm() == -1 || Op2.getImm() == 0))
     return Changed;
 
   int64_t MaskValue = 0;
   Register SReg;
   if (Op2.isReg()) {
     SReg = Op2.getReg();
     auto M = std::next(A);
     bool ReadsSreg = false;
+    bool ModifiesExec = false;
     for (; M != E; ++M) {
       if (M->definesRegister(SReg, TRI))
         break;
       if (M->modifiesRegister(SReg, TRI))
         return Changed;
       ReadsSreg |= M->readsRegister(SReg, TRI);
+      ModifiesExec |= M->modifiesRegister(ExecReg, TRI);
+    }
+    if (M == E)
+      return Changed;
+    // If SReg is VCC and SReg definition is a VALU comparison.
+    // This means S_AND with EXEC is not required.
+    // Erase the S_AND and return.
+    // Note: isVOPC is used instead of isCompare to catch V_CMP_CLASS
+    if (A->getOpcode() == And && SReg == CondReg && !ModifiesExec &&
+        TII->isVOPC(*M) && TII->isVALU(*M)) {
+      A->eraseFromParent();
+      return true;
     }
-    if (M == E || !M->isMoveImmediate() || !M->getOperand(1).isImm() ||
+    if (!M->isMoveImmediate() || !M->getOperand(1).isImm() ||
         (M->getOperand(1).getImm() != -1 && M->getOperand(1).getImm() != 0))
       return Changed;
     MaskValue = M->getOperand(1).getImm();
     // First if sreg is only used in the AND instruction fold the immediate
     // into the AND.
     if (!ReadsSreg && Op2.isKill()) {
       A->getOperand(2).ChangeToImmediate(MaskValue);
       M->eraseFromParent();

llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll

 ; GFX908-NEXT:    s_branch .LBB3_5
 ; GFX908-NEXT:  .LBB3_4: ; %bb58
 ; GFX908-NEXT:    ; in Loop: Header=BB3_5 Depth=2
 ; GFX908-NEXT:    v_add_co_u32_e32 v12, vcc, v12, v30
 ; GFX908-NEXT:    v_addc_co_u32_e32 v13, vcc, 0, v13, vcc
 ; GFX908-NEXT:    v_cmp_gt_i64_e32 vcc, 0, v[12:13]
 ; GFX908-NEXT:    v_add_co_u32_e64 v14, s[2:3], v14, v6
 ; GFX908-NEXT:    v_addc_co_u32_e64 v15, s[2:3], v15, v7, s[2:3]
-; GFX908-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX908-NEXT:    s_cbranch_vccz .LBB3_1
 ; GFX908-NEXT:  .LBB3_5: ; %bb16
 ; GFX908-NEXT:    ; Parent Loop BB3_2 Depth=1
 ; GFX908-NEXT:    ; => This Inner Loop Header: Depth=2
 ; GFX908-NEXT:    v_add_co_u32_e32 v24, vcc, v14, v31
 ; GFX908-NEXT:    v_addc_co_u32_e32 v25, vcc, v15, v33, vcc
 ; GFX908-NEXT:    global_load_dword v35, v[24:25], off offset:-12 glc
 ; GFX908-NEXT:    s_waitcnt vmcnt(0)

 ; GFX90A-NEXT:    s_branch .LBB3_5
 ; GFX90A-NEXT:  .LBB3_4: ; %bb58
 ; GFX90A-NEXT:    ; in Loop: Header=BB3_5 Depth=2
 ; GFX90A-NEXT:    v_add_co_u32_e32 v14, vcc, v14, v30
 ; GFX90A-NEXT:    v_addc_co_u32_e32 v15, vcc, 0, v15, vcc
 ; GFX90A-NEXT:    v_add_co_u32_e32 v16, vcc, v16, v10
 ; GFX90A-NEXT:    v_addc_co_u32_e32 v17, vcc, v17, v11, vcc
 ; GFX90A-NEXT:    v_cmp_gt_i64_e32 vcc, 0, v[14:15]
-; GFX90A-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX90A-NEXT:    s_cbranch_vccz .LBB3_1
 ; GFX90A-NEXT:  .LBB3_5: ; %bb16
 ; GFX90A-NEXT:    ; Parent Loop BB3_2 Depth=1
 ; GFX90A-NEXT:    ; => This Inner Loop Header: Depth=2
 ; GFX90A-NEXT:    v_add_co_u32_e32 v26, vcc, v16, v31
 ; GFX90A-NEXT:    v_addc_co_u32_e32 v27, vcc, v17, v32, vcc
 ; GFX90A-NEXT:    global_load_dword v34, v[26:27], off offset:-12 glc
 ; GFX90A-NEXT:    s_waitcnt vmcnt(0)

llvm/test/CodeGen/AMDGPU/expand-scalar-carry-out-select-user.ll

 ; GFX7-NEXT:    s_add_i32 s0, s2, s2
 ; GFX7-NEXT:    s_cmp_lt_u32 s0, s2
 ; GFX7-NEXT:    s_cselect_b64 s[0:1], -1, 0
 ; GFX7-NEXT:    v_cndmask_b32_e64 v0, 0, 1, s[0:1]
 ; GFX7-NEXT:    s_or_b32 s0, s0, s1
 ; GFX7-NEXT:    s_cmp_lg_u32 s0, 0
 ; GFX7-NEXT:    s_addc_u32 s0, s2, 0
 ; GFX7-NEXT:    v_cmp_ge_u32_e32 vcc, s0, v0
-; GFX7-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX7-NEXT:    s_cbranch_vccnz .LBB1_2
 ; GFX7-NEXT:  ; %bb.1: ; %bb0
 ; GFX7-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX7-NEXT:    v_mov_b32_e32 v2, 9
 ; GFX7-NEXT:    flat_store_dword v[0:1], v2
 ; GFX7-NEXT:    s_waitcnt vmcnt(0)
 ; GFX7-NEXT:  .LBB1_2: ; %bb1

 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    s_add_i32 s0, s2, s2
 ; GFX9-NEXT:    s_cmp_lt_u32 s0, s2
 ; GFX9-NEXT:    s_cselect_b64 s[0:1], -1, 0
 ; GFX9-NEXT:    s_cmp_lg_u64 s[0:1], 0
 ; GFX9-NEXT:    v_cndmask_b32_e64 v0, 0, 1, s[0:1]
 ; GFX9-NEXT:    s_addc_u32 s0, s2, 0
 ; GFX9-NEXT:    v_cmp_ge_u32_e32 vcc, s0, v0
-; GFX9-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-NEXT:    s_cbranch_vccnz .LBB1_2
 ; GFX9-NEXT:  ; %bb.1: ; %bb0
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v2, 9
 ; GFX9-NEXT:    global_store_dword v[0:1], v2, off
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:  .LBB1_2: ; %bb1

 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_add_i32 s1, s0, s0
 ; GFX10-NEXT:    s_cmp_lt_u32 s1, s0
 ; GFX10-NEXT:    s_cselect_b32 s1, -1, 0
 ; GFX10-NEXT:    v_cndmask_b32_e64 v0, 0, 1, s1
 ; GFX10-NEXT:    s_cmpk_lg_u32 s1, 0x0
 ; GFX10-NEXT:    s_addc_u32 s0, s0, 0
 ; GFX10-NEXT:    v_cmp_ge_u32_e32 vcc_lo, s0, v0
-; GFX10-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-NEXT:    s_cbranch_vccnz .LBB1_2
 ; GFX10-NEXT:  ; %bb.1: ; %bb0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 9
 ; GFX10-NEXT:    global_store_dword v[0:1], v2, off
 ; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-NEXT:  .LBB1_2: ; %bb1

llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll

 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_lshlrev_b64 v[2:3], 1, v[0:1]
 ; GCN-NEXT:    v_mov_b32_e32 v0, s1
 ; GCN-NEXT:    v_add_co_u32_e32 v2, vcc, s0, v2
 ; GCN-NEXT:    v_addc_co_u32_e32 v3, vcc, v0, v3, vcc
 ; GCN-NEXT:    global_load_short_d16_hi v0, v[2:3], off glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, s2, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccz .LBB1_1
 ; GCN-NEXT:  ; %bb.2: ; %bb2
 ; GCN-NEXT:    s_endpgm
 bb:
   %i1 = getelementptr inbounds i16, i16 addrspace(1)* %arg, i64 0
   %load.pre = load volatile i16, i16 addrspace(1)* %i1, align 4
   %i2 = zext i16 %load.pre to i32
   br label %bb3

llvm/test/CodeGen/AMDGPU/idiv-licm.ll

 ; GFX9-NEXT:    v_mul_f32_e32 v0, v8, v3
 ; GFX9-NEXT:    v_trunc_f32_e32 v0, v0
 ; GFX9-NEXT:    v_addc_co_u32_e64 v6, s[0:1], v7, v6, s[0:1]
 ; GFX9-NEXT:    v_cvt_u32_f32_e32 v7, v0
 ; GFX9-NEXT:    v_add_u16_e32 v4, 1, v4
 ; GFX9-NEXT:    v_mad_f32 v0, -v0, v2, v8
 ; GFX9-NEXT:    v_cmp_eq_u16_e32 vcc, s5, v4
 ; GFX9-NEXT:    v_cmp_ge_f32_e64 s[0:1], |v0|, v2
-; GFX9-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-NEXT:    v_addc_co_u32_e64 v0, s[0:1], 0, v7, s[0:1]
 ; GFX9-NEXT:    global_store_short v[5:6], v0, off
 ; GFX9-NEXT:    s_cbranch_vccz .LBB4_1
 ; GFX9-NEXT:  ; %bb.2: ; %bb2
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: udiv16_invariant_denom:
 ; GFX10:       ; %bb.0: ; %bb

 ; GFX9-NEXT:    v_trunc_f32_e32 v9, v9
 ; GFX9-NEXT:    v_cvt_u32_f32_e32 v10, v9
 ; GFX9-NEXT:    v_mad_f32 v8, -v9, v2, v8
 ; GFX9-NEXT:    v_cmp_ge_f32_e64 s[2:3], |v8|, v2
 ; GFX9-NEXT:    v_cmp_eq_u16_e32 vcc, s8, v4
 ; GFX9-NEXT:    v_addc_co_u32_e64 v8, s[2:3], 0, v10, s[2:3]
 ; GFX9-NEXT:    v_mul_lo_u32 v8, v8, s7
 ; GFX9-NEXT:    v_add_co_u32_e64 v5, s[0:1], s4, v5
-; GFX9-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-NEXT:    v_addc_co_u32_e64 v6, s[0:1], v7, v6, s[0:1]
 ; GFX9-NEXT:    v_sub_u32_e32 v0, v0, v8
 ; GFX9-NEXT:    global_store_short v[5:6], v0, off
 ; GFX9-NEXT:    s_cbranch_vccz .LBB5_1
 ; GFX9-NEXT:  ; %bb.2: ; %bb2
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: urem16_invariant_denom:

 ; GFX10-NEXT:    v_add_co_ci_u32_e64 v6, s0, s3, v6, s0
 ; GFX10-NEXT:    v_trunc_f32_e32 v8, v8
 ; GFX10-NEXT:    v_mad_f32 v7, -v8, v2, v7
 ; GFX10-NEXT:    v_cvt_u32_f32_e32 v8, v8
 ; GFX10-NEXT:    v_cmp_ge_f32_e64 vcc_lo, |v7|, v2
 ; GFX10-NEXT:    v_add_co_ci_u32_e32 v7, vcc_lo, 0, v8, vcc_lo
 ; GFX10-NEXT:    v_cmp_eq_u16_e32 vcc_lo, 0x400, v4
 ; GFX10-NEXT:    v_mul_lo_u32 v7, v7, s4
-; GFX10-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-NEXT:    v_sub_nc_u32_e32 v0, v0, v7
 ; GFX10-NEXT:    global_store_short v[5:6], v0, off
 ; GFX10-NEXT:    s_cbranch_vccz .LBB5_1
 ; GFX10-NEXT:  ; %bb.2: ; %bb2
 ; GFX10-NEXT:    s_endpgm
 bb:
   br label %bb3
 

 ; GFX9-NEXT:    v_ashrrev_i32_e32 v0, 30, v8
 ; GFX9-NEXT:    v_cvt_i32_f32_e32 v8, v7
 ; GFX9-NEXT:    v_mad_f32 v7, -v7, v2, v9
 ; GFX9-NEXT:    v_add_u16_e32 v4, 1, v4
 ; GFX9-NEXT:    v_or_b32_e32 v0, 1, v0
 ; GFX9-NEXT:    v_cmp_ge_f32_e64 s[0:1], |v7|, |v2|
 ; GFX9-NEXT:    v_cmp_eq_u16_e32 vcc, s5, v4
 ; GFX9-NEXT:    v_cndmask_b32_e64 v0, 0, v0, s[0:1]
-; GFX9-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-NEXT:    v_add_u32_e32 v0, v8, v0
 ; GFX9-NEXT:    global_store_short v[5:6], v0, off
 ; GFX9-NEXT:    s_cbranch_vccz .LBB6_1
 ; GFX9-NEXT:  ; %bb.2: ; %bb2
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: sdiv16_invariant_denom:
 ; GFX10:       ; %bb.0: ; %bb

 ; GFX9-NEXT:    v_cmp_ge_f32_e64 s[2:3], |v9|, |v2|
 ; GFX9-NEXT:    v_cndmask_b32_e64 v0, 0, v0, s[2:3]
 ; GFX9-NEXT:    v_add_u32_e32 v0, v11, v0
 ; GFX9-NEXT:    v_mul_lo_u32 v0, v0, s6
 ; GFX9-NEXT:    v_add_u16_e32 v4, 1, v4
 ; GFX9-NEXT:    v_mov_b32_e32 v8, s5
 ; GFX9-NEXT:    v_cmp_eq_u16_e32 vcc, s7, v4
 ; GFX9-NEXT:    v_add_co_u32_e64 v5, s[0:1], s4, v5
-; GFX9-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-NEXT:    v_addc_co_u32_e64 v6, s[0:1], v8, v6, s[0:1]
 ; GFX9-NEXT:    v_sub_u32_e32 v0, v7, v0
 ; GFX9-NEXT:    global_store_short v[5:6], v0, off
 ; GFX9-NEXT:    s_cbranch_vccz .LBB7_1
 ; GFX9-NEXT:  ; %bb.2: ; %bb2
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: srem16_invariant_denom:

 ; GFX10-NEXT:    v_cmp_ge_f32_e64 vcc_lo, |v5|, |v2|
 ; GFX10-NEXT:    v_cndmask_b32_e32 v9, 0, v6, vcc_lo
 ; GFX10-NEXT:    v_lshlrev_b64 v[5:6], 1, v[0:1]
 ; GFX10-NEXT:    v_cmp_eq_u16_e32 vcc_lo, 0x400, v4
 ; GFX10-NEXT:    v_add_nc_u32_e32 v0, v8, v9
 ; GFX10-NEXT:    v_add_co_u32 v5, s0, s2, v5
 ; GFX10-NEXT:    v_add_co_ci_u32_e64 v6, s0, s3, v6, s0
 ; GFX10-NEXT:    v_mul_lo_u32 v0, v0, s1
-; GFX10-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-NEXT:    v_sub_nc_u32_e32 v0, v7, v0
 ; GFX10-NEXT:    global_store_short v[5:6], v0, off
 ; GFX10-NEXT:    s_cbranch_vccz .LBB7_1
 ; GFX10-NEXT:  ; %bb.2: ; %bb2
 ; GFX10-NEXT:    s_endpgm
 bb:
   br label %bb3
 

llvm/test/CodeGen/AMDGPU/insert-skip-from-vcc.mir

bb.1:
     S_NOP 0
 
   bb.2:
     $sgpr0_sgpr1 = S_MOV_B64 -1
     $vcc = S_ANDN2_B64 $exec, killed $sgpr0_sgpr1, implicit-def $scc
     S_CBRANCH_VCCZ %bb.1, implicit $vcc
     S_ENDPGM 0
 ...
+---
+# GCN-LABEL: name: and_cmp_vccz
+# GCN: V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+# GCN-NOT: S_AND_
+# GCN: S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+name:            and_cmp_vccz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+    $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...
+---
+# GCN-LABEL: name: and_cmp_vccnz
+# GCN: V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+# GCN-NOT: S_AND_
+# GCN: S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
+name:            and_cmp_vccnz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+    $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...
+---
+# GCN-LABEL: name: andn2_cmp_vccz
+# GCN: V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+# GCN: $vcc = S_ANDN2_B64 $exec, $vcc, implicit-def dead $scc
+# GCN: S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+name:            andn2_cmp_vccz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+    $vcc = S_ANDN2_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...
+---
+# GCN-LABEL: name: and_cmpclass_vccz
+# GCN: V_CMP_CLASS_F32_e32 killed $sgpr0, killed $vgpr0, implicit-def $vcc, implicit $exec
+# GCN-NOT: S_AND_
+# GCN: S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+name:            and_cmpclass_vccz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMP_CLASS_F32_e32 killed $sgpr0, killed $vgpr0, implicit-def $vcc, implicit $exec
+    $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...
+---
+# GCN-LABEL: name: and_cmpx_vccz
+# GCN: V_CMPX_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit-def $exec, implicit $exec
+# GCN-NOT: S_AND_
+# GCN: S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+name:            and_cmpx_vccz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMPX_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit-def $exec, implicit $exec
+    $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...
+---
+# GCN-LABEL: name: and_or_cmp_vccz
+# GCN: V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+# GCN: $exec = S_OR_B64 $exec, $sgpr0_sgpr1, implicit-def dead $scc
+# GCN: $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+# GCN: S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+name:            and_or_cmp_vccz
+body:             |
+  bb.0:
+    S_NOP 0
+
+  bb.1:
+    S_NOP 0
+
+  bb.2:
+    V_CMP_EQ_U32_e32 0, killed $vgpr0, implicit-def $vcc, implicit $exec
+    $exec = S_OR_B64 $exec, $sgpr0_sgpr1, implicit-def dead $scc
+    $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
+    S_CBRANCH_VCCZ %bb.1, implicit killed $vcc
+    S_ENDPGM 0
+...

llvm/test/CodeGen/AMDGPU/multilevel-break.ll

 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[0:1]
 ; GCN-NEXT:    s_cbranch_execz .LBB1_9
 ; GCN-NEXT:  .LBB1_2: ; %bb1
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_mov_b64 s[6:7], -1
 ; GCN-NEXT:    v_cmp_gt_i32_e32 vcc, 1, v1
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    ; implicit-def: $sgpr8_sgpr9
 ; GCN-NEXT:    s_mov_b64 s[10:11], -1
 ; GCN-NEXT:    s_cbranch_vccnz .LBB1_6
 ; GCN-NEXT:  ; %bb.3: ; %LeafBlock1
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    s_mov_b64 s[6:7], -1
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, 1, v1
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_mov_b64 s[8:9], -1
 ; GCN-NEXT:    s_cbranch_vccz .LBB1_5
 ; GCN-NEXT:  ; %bb.4: ; %case1
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    buffer_load_dword v2, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_ge_i32_e32 vcc, v0, v2
 ; GCN-NEXT:    s_mov_b64 s[8:9], 0
 ; GCN-NEXT:    s_orn2_b64 s[6:7], vcc, exec
 ; GCN-NEXT:  .LBB1_5: ; %Flow3
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    s_mov_b64 s[10:11], 0
 ; GCN-NEXT:  .LBB1_6: ; %Flow
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    s_and_b64 vcc, exec, s[10:11]
 ; GCN-NEXT:    s_cbranch_vccz .LBB1_1
 ; GCN-NEXT:  ; %bb.7: ; %LeafBlock
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v1
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_mov_b64 s[8:9], -1
 ; GCN-NEXT:    s_cbranch_vccz .LBB1_1
 ; GCN-NEXT:  ; %bb.8: ; %case0
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
 ; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_mov_b64 s[8:9], 0
 ; GCN-NEXT:    v_cmp_ge_i32_e32 vcc, v0, v1

llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll

 define amdgpu_kernel void @nested_loop_conditions(i64 addrspace(1)* nocapture %arg) #0 {
 ; GCN-LABEL: nested_loop_conditions:
 ; GCN:       ; %bb.0: ; %bb
 ; GCN-NEXT:    s_mov_b32 s3, 0xf000
 ; GCN-NEXT:    s_mov_b32 s2, -1
 ; GCN-NEXT:    buffer_load_dword v0, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, 8, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccnz .LBB1_6
 ; GCN-NEXT:  ; %bb.1: ; %bb14.lr.ph
 ; GCN-NEXT:    s_load_dword s4, s[0:1], 0x0
 ; GCN-NEXT:    s_branch .LBB1_3
 ; GCN-NEXT:  .LBB1_2: ; %Flow
 ; GCN-NEXT:    ; in Loop: Header=BB1_3 Depth=1
 ; GCN-NEXT:    s_and_b64 vcc, exec, s[0:1]
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    s_mov_b64 vcc, vcc
 ; GCN-NEXT:    s_cbranch_vccnz .LBB1_6
 ; GCN-NEXT:  .LBB1_3: ; %bb14
 ; GCN-NEXT:    ; =>This Loop Header: Depth=1
 ; GCN-NEXT:    ; Child Loop BB1_4 Depth 2
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    s_cmp_lg_u32 s4, 1
 ; GCN-NEXT:    s_mov_b64 s[0:1], -1
 ; GCN-NEXT:    ; implicit-def: $sgpr4
 ; GCN-NEXT:    s_cbranch_scc1 .LBB1_2
 ; GCN-NEXT:  .LBB1_4: ; %bb18
 ; GCN-NEXT:    ; Parent Loop BB1_3 Depth=1
 ; GCN-NEXT:    ; => This Inner Loop Header: Depth=2
 ; GCN-NEXT:    buffer_load_dword v0, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, 8, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccnz .LBB1_4
 ; GCN-NEXT:  ; %bb.5: ; %bb21
 ; GCN-NEXT:    ; in Loop: Header=BB1_3 Depth=1
 ; GCN-NEXT:    s_load_dword s4, s[0:1], 0x0
 ; GCN-NEXT:    buffer_load_dword v0, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_lt_i32_e64 s[0:1], 8, v0
 ; GCN-NEXT:    s_branch .LBB1_2

llvm/test/CodeGen/AMDGPU/salu-to-valu.ll

entry:
   ret void
 }
 
 ; Make sure we legalize vopc operands after moving an sopc to the value.
 
 ; {{^}}sopc_vopc_legalize_bug:
 ; GCN: s_load_dword [[SGPR:s[0-9]+]]
 ; GCN: v_cmp_le_u32_e32 vcc, [[SGPR]], v{{[0-9]+}}
-; GCN: s_and_b64 vcc, exec, vcc
 ; GCN: s_cbranch_vccnz [[EXIT:.L[A-Z0-9_]+]]
 ; GCN: v_mov_b32_e32 [[ONE:v[0-9]+]], 1
 ; GCN-NOHSA: buffer_store_dword [[ONE]]
 ; GCN-HSA: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[ONE]]
 ; GCN: {{^}}[[EXIT]]:
 ; GCN: s_endpgm
 define amdgpu_kernel void @sopc_vopc_legalize_bug(i32 %cond, i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
 bb3:                                              ; preds = %bb2

llvm/test/CodeGen/AMDGPU/sdiv64.ll

 ; GCN-IR-NEXT:    s_sub_u32 s18, s16, s18
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s10
 ; GCN-IR-NEXT:    s_subb_u32 s19, s17, s19
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s11
 ; GCN-IR-NEXT:    s_add_u32 s10, s10, 1
 ; GCN-IR-NEXT:    s_addc_u32 s11, s11, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[10:11], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[14:15], s[8:9]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB0_3
 ; GCN-IR-NEXT:  .LBB0_4: ; %Flow6
 ; GCN-IR-NEXT:    s_lshl_b64 s[6:7], s[12:13], 1
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[8:9], s[6:7]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_branch .LBB0_6
 ; GCN-IR-NEXT:  .LBB0_5:

 ; GCN-IR-NEXT:    s_sub_u32 s18, s16, s18
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s10
 ; GCN-IR-NEXT:    s_subb_u32 s19, s17, s19
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s11
 ; GCN-IR-NEXT:    s_add_u32 s10, s10, 1
 ; GCN-IR-NEXT:    s_addc_u32 s11, s11, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[10:11], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[14:15], s[8:9]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB9_3
 ; GCN-IR-NEXT:  .LBB9_4: ; %Flow3
 ; GCN-IR-NEXT:    s_lshl_b64 s[6:7], s[12:13], 1
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[8:9], s[6:7]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_branch .LBB9_6
 ; GCN-IR-NEXT:  .LBB9_5:

 ; GCN-IR-NEXT:    s_sub_u32 s14, s14, s18
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s8
 ; GCN-IR-NEXT:    s_subb_u32 s15, s15, s19
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s9
 ; GCN-IR-NEXT:    s_add_u32 s8, s8, 1
 ; GCN-IR-NEXT:    s_addc_u32 s9, s9, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[8:9], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[12:13], s[6:7]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB10_3
 ; GCN-IR-NEXT:  .LBB10_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[2:3], s[10:11], 1
 ; GCN-IR-NEXT:    s_or_b64 s[2:3], s[6:7], s[2:3]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_branch .LBB10_6
 ; GCN-IR-NEXT:  .LBB10_5:

llvm/test/CodeGen/AMDGPU/skip-if-dead.ll

 ; SI-NEXT:    s_andn2_b64 s[0:1], s[0:1], vcc
 ; SI-NEXT:    s_cbranch_scc0 .LBB10_5
 ; SI-NEXT:  ; %bb.3: ; %bb
 ; SI-NEXT:    ; in Loop: Header=BB10_2 Depth=1
 ; SI-NEXT:    s_andn2_b64 exec, exec, vcc
 ; SI-NEXT:    buffer_load_dword v0, off, s[0:3], 0 glc
 ; SI-NEXT:    s_waitcnt vmcnt(0)
 ; SI-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v0
-; SI-NEXT:    s_and_b64 vcc, exec, vcc
 ; SI-NEXT:    s_cbranch_vccnz .LBB10_2
 ; SI-NEXT:  .LBB10_4: ; %Flow1
 ; SI-NEXT:    s_or_b64 exec, exec, s[4:5]
 ; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v0, 8
 ; SI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; SI-NEXT:    s_waitcnt vmcnt(0)

 ; GFX10-WAVE64-NEXT:    s_andn2_b64 s[0:1], s[0:1], vcc
 ; GFX10-WAVE64-NEXT:    s_cbranch_scc0 .LBB10_4
 ; GFX10-WAVE64-NEXT:  ; %bb.2: ; %bb
 ; GFX10-WAVE64-NEXT:    ; in Loop: Header=BB10_1 Depth=1
 ; GFX10-WAVE64-NEXT:    s_andn2_b64 exec, exec, vcc
 ; GFX10-WAVE64-NEXT:    global_load_dword v0, v[0:1], off glc dlc
 ; GFX10-WAVE64-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-WAVE64-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v0
-; GFX10-WAVE64-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX10-WAVE64-NEXT:    s_cbranch_vccnz .LBB10_1
 ; GFX10-WAVE64-NEXT:  .LBB10_3: ; %Flow1
 ; GFX10-WAVE64-NEXT:    s_or_b64 exec, exec, s[2:3]
 ; GFX10-WAVE64-NEXT:    v_mov_b32_e32 v0, 8
 ; GFX10-WAVE64-NEXT:    global_store_dword v[0:1], v0, off
 ; GFX10-WAVE64-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE64-NEXT:    s_endpgm
 ; GFX10-WAVE64-NEXT:  .LBB10_4:

 ; GFX10-WAVE32-NEXT:    s_andn2_b32 s0, s0, vcc_lo
 ; GFX10-WAVE32-NEXT:    s_cbranch_scc0 .LBB10_4
 ; GFX10-WAVE32-NEXT:  ; %bb.2: ; %bb
 ; GFX10-WAVE32-NEXT:    ; in Loop: Header=BB10_1 Depth=1
 ; GFX10-WAVE32-NEXT:    s_andn2_b32 exec_lo, exec_lo, vcc_lo
 ; GFX10-WAVE32-NEXT:    global_load_dword v0, v[0:1], off glc dlc
 ; GFX10-WAVE32-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-WAVE32-NEXT:    v_cmp_eq_u32_e32 vcc_lo, 0, v0
-; GFX10-WAVE32-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-WAVE32-NEXT:    s_cbranch_vccnz .LBB10_1
 ; GFX10-WAVE32-NEXT:  .LBB10_3: ; %Flow1
 ; GFX10-WAVE32-NEXT:    s_or_b32 exec_lo, exec_lo, s1
 ; GFX10-WAVE32-NEXT:    v_mov_b32_e32 v0, 8
 ; GFX10-WAVE32-NEXT:    global_store_dword v[0:1], v0, off
 ; GFX10-WAVE32-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE32-NEXT:    s_endpgm
 ; GFX10-WAVE32-NEXT:  .LBB10_4:

 ; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v0, 8
 ; SI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; SI-NEXT:    s_waitcnt vmcnt(0) expcnt(0)
 ; SI-NEXT:    v_mov_b32_e32 v0, 4.0
 ; SI-NEXT:  .LBB11_3: ; %phibb
 ; SI-NEXT:    v_cmp_eq_f32_e32 vcc, 0, v0
-; SI-NEXT:    s_and_b64 vcc, exec, vcc
 ; SI-NEXT:    s_cbranch_vccz .LBB11_5
 ; SI-NEXT:  ; %bb.4: ; %bb10
 ; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v0, 9
 ; SI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; SI-NEXT:    s_waitcnt vmcnt(0)
 ; SI-NEXT:  .LBB11_5: ; %end

 ; GFX10-WAVE64-NEXT:    s_cbranch_scc0 .LBB11_3
 ; GFX10-WAVE64-NEXT:  ; %bb.2: ; %bb8
 ; GFX10-WAVE64-NEXT:    v_mov_b32_e32 v1, 8
 ; GFX10-WAVE64-NEXT:    v_mov_b32_e32 v0, 4.0
 ; GFX10-WAVE64-NEXT:    global_store_dword v[0:1], v1, off
 ; GFX10-WAVE64-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE64-NEXT:  .LBB11_3: ; %phibb
 ; GFX10-WAVE64-NEXT:    v_cmp_eq_f32_e32 vcc, 0, v0
-; GFX10-WAVE64-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX10-WAVE64-NEXT:    s_cbranch_vccz .LBB11_5
 ; GFX10-WAVE64-NEXT:  ; %bb.4: ; %bb10
 ; GFX10-WAVE64-NEXT:    v_mov_b32_e32 v0, 9
 ; GFX10-WAVE64-NEXT:    global_store_dword v[0:1], v0, off
 ; GFX10-WAVE64-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE64-NEXT:  .LBB11_5: ; %end
 ; GFX10-WAVE64-NEXT:    s_endpgm
 ; GFX10-WAVE64-NEXT:  .LBB11_6:

 ; GFX10-WAVE32-NEXT:    s_cbranch_scc0 .LBB11_3
 ; GFX10-WAVE32-NEXT:  ; %bb.2: ; %bb8
 ; GFX10-WAVE32-NEXT:    v_mov_b32_e32 v1, 8
 ; GFX10-WAVE32-NEXT:    v_mov_b32_e32 v0, 4.0
 ; GFX10-WAVE32-NEXT:    global_store_dword v[0:1], v1, off
 ; GFX10-WAVE32-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE32-NEXT:  .LBB11_3: ; %phibb
 ; GFX10-WAVE32-NEXT:    v_cmp_eq_f32_e32 vcc_lo, 0, v0
-; GFX10-WAVE32-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-WAVE32-NEXT:    s_cbranch_vccz .LBB11_5
 ; GFX10-WAVE32-NEXT:  ; %bb.4: ; %bb10
 ; GFX10-WAVE32-NEXT:    v_mov_b32_e32 v0, 9
 ; GFX10-WAVE32-NEXT:    global_store_dword v[0:1], v0, off
 ; GFX10-WAVE32-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-WAVE32-NEXT:  .LBB11_5: ; %end
 ; GFX10-WAVE32-NEXT:    s_endpgm
 ; GFX10-WAVE32-NEXT:  .LBB11_6:

llvm/test/CodeGen/AMDGPU/srem64.ll

 ; GCN-IR-NEXT:    s_sub_u32 s14, s14, s18
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s8
 ; GCN-IR-NEXT:    s_subb_u32 s15, s15, s19
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s9
 ; GCN-IR-NEXT:    s_add_u32 s8, s8, 1
 ; GCN-IR-NEXT:    s_addc_u32 s9, s9, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[8:9], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[12:13], s[6:7]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB0_3
 ; GCN-IR-NEXT:  .LBB0_4: ; %Flow6
 ; GCN-IR-NEXT:    s_lshl_b64 s[8:9], s[10:11], 1
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[6:7], s[8:9]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_branch .LBB0_6
 ; GCN-IR-NEXT:  .LBB0_5:

 ; GCN-IR-NEXT:    s_sub_u32 s16, s16, s20
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s10
 ; GCN-IR-NEXT:    s_subb_u32 s17, s17, s21
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s11
 ; GCN-IR-NEXT:    s_add_u32 s10, s10, 1
 ; GCN-IR-NEXT:    s_addc_u32 s11, s11, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[10:11], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[14:15], s[6:7]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB8_3
 ; GCN-IR-NEXT:  .LBB8_4: ; %Flow6
 ; GCN-IR-NEXT:    s_lshl_b64 s[10:11], s[12:13], 1
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[6:7], s[10:11]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_branch .LBB8_6
 ; GCN-IR-NEXT:  .LBB8_5:

 ; GCN-IR-NEXT:    s_sub_u32 s16, s16, s20
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s10
 ; GCN-IR-NEXT:    s_subb_u32 s17, s17, s21
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s11
 ; GCN-IR-NEXT:    s_add_u32 s10, s10, 1
 ; GCN-IR-NEXT:    s_addc_u32 s11, s11, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[10:11], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[14:15], s[8:9]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB9_3
 ; GCN-IR-NEXT:  .LBB9_4: ; %Flow3
 ; GCN-IR-NEXT:    s_lshl_b64 s[10:11], s[12:13], 1
 ; GCN-IR-NEXT:    s_or_b64 s[8:9], s[8:9], s[10:11]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s8
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s9
 ; GCN-IR-NEXT:    s_branch .LBB9_6
 ; GCN-IR-NEXT:  .LBB9_5:

 ; GCN-IR-NEXT:    s_sub_u32 s12, s12, s16
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    s_subb_u32 s13, s13, s17
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_add_u32 s6, s6, 1
 ; GCN-IR-NEXT:    s_addc_u32 s7, s7, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[6:7], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[2:3]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB10_3
 ; GCN-IR-NEXT:  .LBB10_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[6:7], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[2:3], s[2:3], s[6:7]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_branch .LBB10_6
 ; GCN-IR-NEXT:  .LBB10_5:

llvm/test/CodeGen/AMDGPU/trap-abis.ll

 ; NOHSA-TRAP-GFX900-V2-LABEL: non_entry_trap:
 ; NOHSA-TRAP-GFX900-V2:       ; %bb.0: ; %entry
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
 ; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_and_b64 vcc, exec, vcc
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
 ; NOHSA-TRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
 ; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
 ; NOHSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
 ; NOHSA-TRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
 ; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
 ;
 ; NOHSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
 ; NOHSA-TRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; NOHSA-TRAP-GFX900-V3-NEXT:    s_and_b64 vcc, exec, vcc
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_cbranch_vccz .LBB1_2
 ; NOHSA-TRAP-GFX900-V3-NEXT:  ; %bb.1: ; %ret
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 3
 ; NOHSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_endpgm
 ; NOHSA-TRAP-GFX900-V3-NEXT:  .LBB1_2: ; %trap
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_endpgm
 ;
 ; NOHSA-TRAP-GFX900-V4-LABEL: non_entry_trap:
 ; NOHSA-TRAP-GFX900-V4:       ; %bb.0: ; %entry
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; NOHSA-TRAP-GFX900-V4-NEXT:    s_and_b64 vcc, exec, vcc
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_cbranch_vccz .LBB1_2
 ; NOHSA-TRAP-GFX900-V4-NEXT:  ; %bb.1: ; %ret
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 3
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ; NOHSA-TRAP-GFX900-V4-NEXT:  .LBB1_2: ; %trap
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm

 ; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.0: ; %entry
 ; HSA-TRAP-GFX803-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V2-NEXT:    flat_load_dword v0, v[0:1] glc
 ; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v0
-; HSA-TRAP-GFX803-V2-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX803-V2-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v2, 3
 ; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V2-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V2-NEXT:    s_endpgm
 ; HSA-TRAP-GFX803-V2-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX803-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX803-V2-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX803-V3-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX803-V3:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX803-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V3-NEXT:    flat_load_dword v0, v[0:1] glc
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v0
-; HSA-TRAP-GFX803-V3-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX803-V3-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX803-V3-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v2, 3
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V3-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    s_endpgm
 ; HSA-TRAP-GFX803-V3-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX803-V3-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX803-V3-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX803-V4-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX803-V4:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX803-V4-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_load_dword v0, v[0:1] glc
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v0
-; HSA-TRAP-GFX803-V4-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX803-V4-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX803-V4-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v2, 3
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    s_endpgm

 ; HSA-TRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
 ; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.0: ; %entry
 ; HSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-TRAP-GFX900-V2-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V2-NEXT:    s_endpgm
 ; HSA-TRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX900-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX900-V2-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-TRAP-GFX900-V3-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX900-V3-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX900-V3-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    s_endpgm
 ; HSA-TRAP-GFX900-V3-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX900-V3-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX900-V3-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX900-V4-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX900-V4:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX900-V4-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-TRAP-GFX900-V4-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-TRAP-GFX900-V4-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-TRAP-GFX900-V4-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ; HSA-TRAP-GFX900-V4-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX900-V4-NEXT:    s_trap 2

 ; HSA-NOTRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
 ; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.0: ; %entry
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
 ; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-NOTRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
 ; HSA-NOTRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
 ; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
 ;
 ; HSA-NOTRAP-GFX900-V3-LABEL: non_entry_trap:
 ; HSA-NOTRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-NOTRAP-GFX900-V3-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-NOTRAP-GFX900-V3-NEXT:  ; %bb.1: ; %ret
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-NOTRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_endpgm
 ; HSA-NOTRAP-GFX900-V3-NEXT:  .LBB1_2: ; %trap
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_endpgm
 ;
 ; HSA-NOTRAP-GFX900-V4-LABEL: non_entry_trap:
 ; HSA-NOTRAP-GFX900-V4:       ; %bb.0: ; %entry
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-NOTRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V4-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V4-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-NOTRAP-GFX900-V4-NEXT:    s_and_b64 vcc, exec, vcc
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_cbranch_vccz .LBB1_2
 ; HSA-NOTRAP-GFX900-V4-NEXT:  ; %bb.1: ; %ret
 ; HSA-NOTRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-NOTRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_endpgm
 ; HSA-NOTRAP-GFX900-V4-NEXT:  .LBB1_2: ; %trap
 ; HSA-NOTRAP-GFX900-V4-NEXT:    s_endpgm

llvm/test/CodeGen/AMDGPU/udiv64.ll

 ; GCN-IR-NEXT:    s_sub_u32 s14, s12, s14
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    s_subb_u32 s15, s13, s15
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_add_u32 s2, s2, 1
 ; GCN-IR-NEXT:    s_addc_u32 s3, s3, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[2:3], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[6:7]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB0_3
 ; GCN-IR-NEXT:  .LBB0_4: ; %Flow6
 ; GCN-IR-NEXT:    s_lshl_b64 s[2:3], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[2:3], s[6:7], s[2:3]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_branch .LBB0_6
 ; GCN-IR-NEXT:  .LBB0_5:

 ; GCN-IR-NEXT:    s_sub_u32 s14, s12, s14
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    s_subb_u32 s15, s13, s15
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_add_u32 s6, s6, 1
 ; GCN-IR-NEXT:    s_addc_u32 s7, s7, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[6:7], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[0:1]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB7_3
 ; GCN-IR-NEXT:  .LBB7_4: ; %Flow3
 ; GCN-IR-NEXT:    s_lshl_b64 s[2:3], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[0:1], s[0:1], s[2:3]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s1
 ; GCN-IR-NEXT:    s_branch .LBB7_6
 ; GCN-IR-NEXT:  .LBB7_5:

 ; GCN-IR-NEXT:    s_sub_u32 s12, s12, s16
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    s_subb_u32 s13, s13, s17
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_add_u32 s6, s6, 1
 ; GCN-IR-NEXT:    s_addc_u32 s7, s7, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[6:7], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[4:5]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB8_3
 ; GCN-IR-NEXT:  .LBB8_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[2:3], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[2:3], s[4:5], s[2:3]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_branch .LBB8_6
 ; GCN-IR-NEXT:  .LBB8_5:

 ; GCN-IR-NEXT:    s_sub_u32 s10, s10, s8
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    s_subb_u32 s11, s11, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_add_u32 s2, s2, 1
 ; GCN-IR-NEXT:    s_addc_u32 s3, s3, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[2:3], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[8:9], s[4:5]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB11_3
 ; GCN-IR-NEXT:  .LBB11_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[2:3], s[6:7], 1
 ; GCN-IR-NEXT:    s_or_b64 s[2:3], s[4:5], s[2:3]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s2
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s3
 ; GCN-IR-NEXT:    s_branch .LBB11_6
 ; GCN-IR-NEXT:  .LBB11_5:

llvm/test/CodeGen/AMDGPU/uniform-cfg.ll

done:
   ret void
 }
 
 ; GCN-LABEL: {{^}}uniform_if_move_valu:
 ; GCN: v_add_f32_e32 [[CMP:v[0-9]+]]
 ; Using a floating-point value in an integer compare will cause the compare to
 ; be selected for the SALU and then later moved to the VALU.
 ; GCN: v_cmp_ne_u32_e32 [[COND:vcc|s\[[0-9]+:[0-9]+\]]], 5, [[CMP]]
-; GCN: s_and_b64 vcc, exec, [[COND]]
 ; GCN: s_cbranch_vccnz [[ENDIF_LABEL:.L[0-9_A-Za-z]+]]
 ; GCN: buffer_store_dword
 ; GCN: [[ENDIF_LABEL]]:
 ; GCN: s_endpgm
 define amdgpu_kernel void @uniform_if_move_valu(i32 addrspace(1)* %out, float %a) {
 entry:
   %a.0 = fadd float %a, 10.0
   %cond = bitcast float %a.0 to i32
   %cmp = icmp eq i32 %cond, 5
   br i1 %cmp, label %if, label %endif
 
 if:
   store i32 0, i32 addrspace(1)* %out
   br label %endif
 
 endif:
   ret void
 }
 
 ; GCN-LABEL: {{^}}uniform_if_move_valu_commute:
 ; GCN: v_add_f32_e32 [[CMP:v[0-9]+]]
 ; Using a floating-point value in an integer compare will cause the compare to
 ; be selected for the SALU and then later moved to the VALU.
 ; GCN: v_cmp_gt_u32_e32 [[COND:vcc|s\[[0-9]+:[0-9]+\]]], 6, [[CMP]]
-; GCN: s_and_b64 vcc, exec, [[COND]]
 ; GCN: s_cbranch_vccnz [[ENDIF_LABEL:.L[0-9_A-Za-z]+]]
 ; GCN: buffer_store_dword
 ; GCN: [[ENDIF_LABEL]]:
 ; GCN: s_endpgm
 define amdgpu_kernel void @uniform_if_move_valu_commute(i32 addrspace(1)* %out, float %a) {
 entry:
   %a.0 = fadd float %a, 10.0
   %cond = bitcast float %a.0 to i32

llvm/test/CodeGen/AMDGPU/unstructured-cfg-def-use-issue.ll

 ; GCN-NEXT:    s_addk_i32 s32, 0x400
 ; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    v_writelane_b32 v40, s31, 1
 ; GCN-NEXT:    v_mov_b32_e32 v0, 0
 ; GCN-NEXT:    v_mov_b32_e32 v1, 0
 ; GCN-NEXT:    flat_load_dword v0, v[0:1]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_gt_i32_e32 vcc, 21, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccz .LBB0_3
 ; GCN-NEXT:  ; %bb.1: ; %bb4
 ; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, 9, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccnz .LBB0_4
 ; GCN-NEXT:  ; %bb.2: ; %bb7
 ; GCN-NEXT:    s_getpc_b64 s[16:17]
 ; GCN-NEXT:    s_add_u32 s16, s16, wibble@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s17, s17, wibble@rel32@hi+12
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[16:17]
 ; GCN-NEXT:    s_branch .LBB0_7
 ; GCN-NEXT:  .LBB0_3: ; %bb2
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, 21, v0
-; GCN-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-NEXT:    s_cbranch_vccnz .LBB0_6
 ; GCN-NEXT:  .LBB0_4: ; %bb9
 ; GCN-NEXT:    s_getpc_b64 s[16:17]
 ; GCN-NEXT:    s_add_u32 s16, s16, wibble@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s17, s17, wibble@rel32@hi+12
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[16:17]
 ; GCN-NEXT:    v_cmp_lt_f32_e32 vcc, 0, v0
 ; GCN-NEXT:    s_and_saveexec_b64 s[4:5], vcc

llvm/test/CodeGen/AMDGPU/urem64.ll

 ; GCN-IR-NEXT:    s_sub_u32 s14, s14, s18
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s8
 ; GCN-IR-NEXT:    s_subb_u32 s15, s15, s19
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s9
 ; GCN-IR-NEXT:    s_add_u32 s8, s8, 1
 ; GCN-IR-NEXT:    s_addc_u32 s9, s9, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[8:9], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[12:13], s[6:7]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB0_3
 ; GCN-IR-NEXT:  .LBB0_4: ; %Flow6
 ; GCN-IR-NEXT:    s_lshl_b64 s[8:9], s[10:11], 1
 ; GCN-IR-NEXT:    s_or_b64 s[6:7], s[6:7], s[8:9]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_branch .LBB0_6
 ; GCN-IR-NEXT:  .LBB0_5:

 ; GCN-IR-NEXT:    s_sub_u32 s12, s12, s16
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    s_subb_u32 s13, s13, s17
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_add_u32 s6, s6, 1
 ; GCN-IR-NEXT:    s_addc_u32 s7, s7, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[6:7], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[4:5]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB6_3
 ; GCN-IR-NEXT:  .LBB6_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[6:7], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[4:5], s[4:5], s[6:7]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s4
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s5
 ; GCN-IR-NEXT:    s_branch .LBB6_6
 ; GCN-IR-NEXT:  .LBB6_5:

 ; GCN-IR-NEXT:    s_sub_u32 s12, s12, s10
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s6
 ; GCN-IR-NEXT:    s_subb_u32 s13, s13, 0
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s7
 ; GCN-IR-NEXT:    s_add_u32 s6, s6, 1
 ; GCN-IR-NEXT:    s_addc_u32 s7, s7, 0
 ; GCN-IR-NEXT:    v_cmp_lt_u64_e32 vcc, s[6:7], v[0:1]
 ; GCN-IR-NEXT:    s_mov_b64 s[10:11], s[4:5]
-; GCN-IR-NEXT:    s_and_b64 vcc, exec, vcc
 ; GCN-IR-NEXT:    s_cbranch_vccz .LBB7_3
 ; GCN-IR-NEXT:  .LBB7_4: ; %Flow5
 ; GCN-IR-NEXT:    s_lshl_b64 s[6:7], s[8:9], 1
 ; GCN-IR-NEXT:    s_or_b64 s[4:5], s[4:5], s[6:7]
 ; GCN-IR-NEXT:    v_mov_b32_e32 v0, s4
 ; GCN-IR-NEXT:    v_mov_b32_e32 v1, s5
 ; GCN-IR-NEXT:    s_branch .LBB7_6
 ; GCN-IR-NEXT:  .LBB7_5:

llvm/test/CodeGen/AMDGPU/wave32.ll

 entry:
   %fdiv = fdiv float %a, %b
   store float %fdiv, float addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_br_cc_f16:
 ; GFX1032:  v_cmp_nlt_f16_e32 vcc_lo,
-; GFX1032:  s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX1064:  v_cmp_nlt_f16_e32 vcc,
-; GFX1064:  s_and_b64 vcc, exec, vcc{{$}}
 ; GCN-NEXT: s_cbranch_vccnz
 define amdgpu_kernel void @test_br_cc_f16(
     half addrspace(1)* %r,
     half addrspace(1)* %a,
     half addrspace(1)* %b) {
 entry:
   %a.val = load half, half addrspace(1)* %a
   %b.val = load half, half addrspace(1)* %b

llvm/test/CodeGen/AMDGPU/wqm.ll

 ; GFX9-W64-NEXT:  .LBB31_2: ; %loop
 ; GFX9-W64-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GFX9-W64-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-W64-NEXT:    v_mov_b32_e32 v0, v4
 ; GFX9-W64-NEXT:    v_cmp_lt_f32_e32 vcc, s10, v8
 ; GFX9-W64-NEXT:    v_mov_b32_e32 v1, v5
 ; GFX9-W64-NEXT:    v_mov_b32_e32 v2, v6
 ; GFX9-W64-NEXT:    v_mov_b32_e32 v3, v7
-; GFX9-W64-NEXT:    s_and_b64 vcc, exec, vcc
 ; GFX9-W64-NEXT:    s_cbranch_vccz .LBB31_1
 ; GFX9-W64-NEXT:  ; %bb.3:
 ; GFX9-W64-NEXT:    s_mov_b64 s[2:3], -1
 ; GFX9-W64-NEXT:    ; implicit-def: $vgpr4_vgpr5_vgpr6_vgpr7
 ; GFX9-W64-NEXT:    ; implicit-def: $vgpr8
 ; GFX9-W64-NEXT:  .LBB31_4: ; %break
 ; GFX9-W64-NEXT:    s_and_b64 exec, exec, s[8:9]
 ; GFX9-W64-NEXT:    s_waitcnt vmcnt(0)

 ; GFX10-W32-NEXT:  .LBB31_2: ; %loop
 ; GFX10-W32-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GFX10-W32-NEXT:    v_cmp_lt_f32_e32 vcc_lo, 0x40e00000, v8
 ; GFX10-W32-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-W32-NEXT:    v_mov_b32_e32 v7, v3
 ; GFX10-W32-NEXT:    v_mov_b32_e32 v6, v2
 ; GFX10-W32-NEXT:    v_mov_b32_e32 v5, v1
 ; GFX10-W32-NEXT:    v_mov_b32_e32 v4, v0
-; GFX10-W32-NEXT:    s_and_b32 vcc_lo, exec_lo, vcc_lo
 ; GFX10-W32-NEXT:    s_cbranch_vccz .LBB31_1
 ; GFX10-W32-NEXT:  ; %bb.3:
 ; GFX10-W32-NEXT:    s_mov_b32 s1, -1
 ; GFX10-W32-NEXT:    ; implicit-def: $vgpr0_vgpr1_vgpr2_vgpr3
 ; GFX10-W32-NEXT:    ; implicit-def: $vgpr8
 ; GFX10-W32-NEXT:  .LBB31_4: ; %break
 ; GFX10-W32-NEXT:    s_and_b32 exec_lo, exec_lo, s8
 ; GFX10-W32-NEXT:    s_waitcnt vmcnt(0)