Index: llvm/lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- llvm/lib/Target/AMDGPU/SIInstructions.td
+++ llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -418,6 +418,7 @@
   let Size = 12;
   let hasSideEffects = 1;
   let IsNeverUniform = 1;
+  let isConvergent = 1;
 }
 
 def SI_ELSE : CFPseudoInstSI <
@@ -426,6 +427,7 @@
   let Size = 12;
   let hasSideEffects = 1;
   let IsNeverUniform = 1;
+  let isConvergent = 1;
 }
 
 def SI_WATERFALL_LOOP : CFPseudoInstSI <
@@ -434,6 +436,7 @@
   let Size = 8;
   let isBranch = 1;
   let Defs = [];
+  let isConvergent = 1;
 }
 
 def SI_LOOP : CFPseudoInstSI <
@@ -443,6 +446,7 @@
   let isBranch = 1;
   let hasSideEffects = 1;
   let IsNeverUniform = 1;
+  let isConvergent = 1;
 }
 
 } // End isTerminator = 1
@@ -453,6 +457,7 @@
   let isAsCheapAsAMove = 1;
   let isReMaterializable = 1;
   let hasSideEffects = 1;
+  let isConvergent = 1;
   let isNotDuplicable = 1; // Not a hard requirement, see long comments above for details.
   let mayLoad = 1; // FIXME: Should not need memory flags
   let mayStore = 1;
@@ -464,6 +469,7 @@
   let isNotDuplicable = 1; // Not a hard requirement, see long comments above for details.
   let isAsCheapAsAMove = 1;
   let isReMaterializable = 1;
+  let isConvergent = 1;
 }
 
 // Branch to the early termination block of the shader if SCC is 0.
Index: llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
+++ llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
@@ -18,12 +18,12 @@
 ; GFX10-NEXT:    ; in Loop: Header=BB0_2 Depth=1
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_or_b32 exec_lo, exec_lo, s3
-; GFX10-NEXT:    s_and_b32 s0, exec_lo, vcc_lo
-; GFX10-NEXT:    s_or_b32 s2, s0, s2
 ; GFX10-NEXT:    s_andn2_b32 exec_lo, exec_lo, s2
 ; GFX10-NEXT:    s_cbranch_execz .LBB0_5
 ; GFX10-NEXT:  .LBB0_2: ; %bb4
 ; GFX10-NEXT:    ; =>This Inner Loop Header: Depth=1
+; GFX10-NEXT:    s_and_b32 s0, exec_lo, vcc_lo
+; GFX10-NEXT:    s_or_b32 s2, s0, s2
 ; GFX10-NEXT:    s_and_saveexec_b32 s3, s1
 ; GFX10-NEXT:    s_cbranch_execz .LBB0_1
 ; GFX10-NEXT:  ; %bb.3: ; in Loop: Header=BB0_2 Depth=1
Index: llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
+++ llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
@@ -1010,8 +1010,8 @@
 ; GCN-NEXT:    v_cmp_gt_i32_e32 vcc, s4, v0
 ; GCN-NEXT:    s_mov_b32 s8, 0
 ; GCN-NEXT:    v_cmp_eq_u32_e64 s[4:5], 0, v0
-; GCN-NEXT:    s_mov_b64 s[12:13], 0
 ; GCN-NEXT:    s_mov_b64 s[6:7], 0
+; GCN-NEXT:    s_mov_b64 s[10:11], 0
 ; GCN-NEXT:    s_branch .LBB5_3
 ; GCN-NEXT:  .LBB5_1: ; %Flow
 ; GCN-NEXT:    ; in Loop: Header=BB5_3 Depth=1
@@ -1019,20 +1019,21 @@
 ; GCN-NEXT:  .LBB5_2: ; %bb10
 ; GCN-NEXT:    ; in Loop: Header=BB5_3 Depth=1
 ; GCN-NEXT:    s_or_b64 exec, exec, s[14:15]
-; GCN-NEXT:    s_and_b64 s[6:7], exec, s[4:5]
-; GCN-NEXT:    s_or_b64 s[12:13], s[6:7], s[12:13]
-; GCN-NEXT:    s_mov_b64 s[6:7], 0
+; GCN-NEXT:    s_mov_b64 s[6:7], s[12:13]
+; GCN-NEXT:    s_mov_b64 s[10:11], 0
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[12:13]
 ; GCN-NEXT:    s_cbranch_execz .LBB5_7
 ; GCN-NEXT:  .LBB5_3: ; %bb1
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GCN-NEXT:    s_and_b64 s[10:11], exec, vcc
-; GCN-NEXT:    s_or_b64 s[6:7], s[10:11], s[6:7]
-; GCN-NEXT:    s_andn2_b64 exec, exec, s[6:7]
+; GCN-NEXT:    s_and_b64 s[12:13], exec, s[4:5]
+; GCN-NEXT:    s_or_b64 s[12:13], s[12:13], s[6:7]
+; GCN-NEXT:    s_and_b64 s[14:15], exec, vcc
+; GCN-NEXT:    s_or_b64 s[10:11], s[14:15], s[10:11]
+; GCN-NEXT:    s_andn2_b64 exec, exec, s[10:11]
 ; GCN-NEXT:    s_cbranch_execnz .LBB5_3
 ; GCN-NEXT:  ; %bb.4: ; %bb2
 ; GCN-NEXT:    ; in Loop: Header=BB5_3 Depth=1
-; GCN-NEXT:    s_or_b64 exec, exec, s[6:7]
+; GCN-NEXT:    s_or_b64 exec, exec, s[10:11]
 ; GCN-NEXT:    s_mov_b32 s9, s8
 ; GCN-NEXT:    s_mov_b32 s10, s8
 ; GCN-NEXT:    s_mov_b32 s11, s8
Index: llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
+++ llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
@@ -10,26 +10,25 @@
 ; GCN-LABEL: needs_and:
 ; GCN:       ; %bb.0: ; %entry
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT:    s_mov_b32 s10, 1
+; GCN-NEXT:    s_mov_b32 s8, 1
 ; GCN-NEXT:    s_mov_b64 s[6:7], 0
 ; GCN-NEXT:    s_branch .LBB0_2
 ; GCN-NEXT:  .LBB0_1: ; %endif
 ; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
-; GCN-NEXT:    s_or_b64 exec, exec, s[8:9]
-; GCN-NEXT:    s_and_b64 s[4:5], exec, vcc
-; GCN-NEXT:    s_or_b64 s[6:7], s[4:5], s[6:7]
-; GCN-NEXT:    s_add_i32 s10, s10, 1
+; GCN-NEXT:    s_or_b64 exec, exec, s[4:5]
+; GCN-NEXT:    s_add_i32 s8, s8, 1
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[6:7]
 ; GCN-NEXT:    s_cbranch_execz .LBB0_4
 ; GCN-NEXT:  .LBB0_2: ; %loop
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GCN-NEXT:    v_cmp_gt_u32_e64 s[4:5], s10, v0
-; GCN-NEXT:    v_cmp_le_u32_e32 vcc, s10, v0
-; GCN-NEXT:    s_and_saveexec_b64 s[8:9], s[4:5]
+; GCN-NEXT:    v_cmp_le_u32_e64 s[4:5], s8, v0
+; GCN-NEXT:    v_cmp_gt_u32_e32 vcc, s8, v0
+; GCN-NEXT:    s_or_b64 s[6:7], s[4:5], s[6:7]
+; GCN-NEXT:    s_and_saveexec_b64 s[4:5], vcc
 ; GCN-NEXT:    s_cbranch_execz .LBB0_1
 ; GCN-NEXT:  ; %bb.3: ; %then
 ; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
-; GCN-NEXT:    s_nop 1
+; GCN-NEXT:    s_nop 0
 ; GCN-NEXT:    buffer_store_dword v0, off, s[4:7], s4
 ; GCN-NEXT:    s_branch .LBB0_1
 ; GCN-NEXT:  .LBB0_4: ; %loopexit
@@ -108,13 +107,13 @@
 ; GCN-NEXT:  .LBB2_1: ; %endif
 ; GCN-NEXT:    ; in Loop: Header=BB2_2 Depth=1
 ; GCN-NEXT:    s_or_b64 exec, exec, s[8:9]
-; GCN-NEXT:    s_and_b64 s[8:9], exec, s[4:5]
-; GCN-NEXT:    s_or_b64 s[6:7], s[8:9], s[6:7]
 ; GCN-NEXT:    s_add_i32 s10, s10, 1
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[6:7]
 ; GCN-NEXT:    s_cbranch_execz .LBB2_4
 ; GCN-NEXT:  .LBB2_2: ; %loop
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
+; GCN-NEXT:    s_and_b64 s[8:9], exec, s[4:5]
+; GCN-NEXT:    s_or_b64 s[6:7], s[8:9], s[6:7]
 ; GCN-NEXT:    v_cmp_gt_u32_e32 vcc, s10, v0
 ; GCN-NEXT:    s_and_saveexec_b64 s[8:9], vcc
 ; GCN-NEXT:    s_cbranch_execz .LBB2_1
Index: llvm/test/CodeGen/AMDGPU/multilevel-break.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/multilevel-break.ll
+++ llvm/test/CodeGen/AMDGPU/multilevel-break.ll
@@ -49,37 +49,38 @@
 ; GCN-NEXT:    s_branch .LBB0_2
 ; GCN-NEXT:  .LBB0_1: ; %loop.exit.guard
 ; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
-; GCN-NEXT:    s_or_b64 exec, exec, s[4:5]
-; GCN-NEXT:    s_and_b64 s[2:3], exec, s[2:3]
-; GCN-NEXT:    s_or_b64 s[0:1], s[2:3], s[0:1]
-; GCN-NEXT:    s_andn2_b64 exec, exec, s[0:1]
+; GCN-NEXT:    s_or_b64 exec, exec, s[2:3]
+; GCN-NEXT:    s_mov_b64 s[0:1], s[8:9]
+; GCN-NEXT:    s_andn2_b64 exec, exec, s[8:9]
 ; GCN-NEXT:    s_cbranch_execz .LBB0_6
 ; GCN-NEXT:  .LBB0_2: ; %LOOP.outer
 ; GCN-NEXT:    ; =>This Loop Header: Depth=1
 ; GCN-NEXT:    ; Child Loop BB0_4 Depth 2
 ; GCN-NEXT:    ; implicit-def: $sgpr6_sgpr7
-; GCN-NEXT:    ; implicit-def: $sgpr2_sgpr3
-; GCN-NEXT:    s_mov_b64 s[4:5], 0
+; GCN-NEXT:    ; implicit-def: $sgpr4_sgpr5
+; GCN-NEXT:    s_mov_b64 s[2:3], 0
 ; GCN-NEXT:    s_branch .LBB0_4
 ; GCN-NEXT:  .LBB0_3: ; %Flow
 ; GCN-NEXT:    ; in Loop: Header=BB0_4 Depth=2
 ; GCN-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GCN-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
-; GCN-NEXT:    s_or_b64 s[4:5], s[8:9], s[4:5]
-; GCN-NEXT:    s_andn2_b64 exec, exec, s[4:5]
+; GCN-NEXT:    s_or_b64 s[2:3], s[8:9], s[2:3]
+; GCN-NEXT:    s_and_b64 s[8:9], exec, s[4:5]
+; GCN-NEXT:    s_or_b64 s[8:9], s[8:9], s[0:1]
+; GCN-NEXT:    s_andn2_b64 exec, exec, s[2:3]
 ; GCN-NEXT:    s_cbranch_execz .LBB0_1
 ; GCN-NEXT:  .LBB0_4: ; %LOOP
 ; GCN-NEXT:    ; Parent Loop BB0_2 Depth=1
 ; GCN-NEXT:    ; => This Inner Loop Header: Depth=2
 ; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, v0, v4
-; GCN-NEXT:    s_or_b64 s[2:3], s[2:3], exec
+; GCN-NEXT:    s_or_b64 s[4:5], s[4:5], exec
 ; GCN-NEXT:    s_or_b64 s[6:7], s[6:7], exec
 ; GCN-NEXT:    s_and_saveexec_b64 s[8:9], vcc
 ; GCN-NEXT:    s_cbranch_execz .LBB0_3
 ; GCN-NEXT:  ; %bb.5: ; %ENDIF
 ; GCN-NEXT:    ; in Loop: Header=BB0_4 Depth=2
 ; GCN-NEXT:    v_add_i32_e32 v0, vcc, 1, v0
-; GCN-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
+; GCN-NEXT:    s_andn2_b64 s[4:5], s[4:5], exec
 ; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, v5, v0
 ; GCN-NEXT:    s_andn2_b64 s[6:7], s[6:7], exec
 ; GCN-NEXT:    s_and_b64 s[10:11], vcc, exec
Index: llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
+++ llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
@@ -13,12 +13,12 @@
 ; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
 ; GCN-NEXT:    s_waitcnt_depctr 0xffe3
 ; GCN-NEXT:    s_or_b32 exec_lo, exec_lo, s8
-; GCN-NEXT:    s_and_b32 s8, exec_lo, s6
-; GCN-NEXT:    s_or_b32 s7, s8, s7
 ; GCN-NEXT:    s_andn2_b32 exec_lo, exec_lo, s7
 ; GCN-NEXT:    s_cbranch_execz .LBB0_5
 ; GCN-NEXT:  .LBB0_2: ; %bb
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
+; GCN-NEXT:    s_and_b32 s8, exec_lo, s6
+; GCN-NEXT:    s_or_b32 s7, s8, s7
 ; GCN-NEXT:    s_and_saveexec_b32 s8, vcc_lo
 ; GCN-NEXT:    s_cbranch_execz .LBB0_1
 ; GCN-NEXT:  ; %bb.3: ; %bb1