createPostMachineScheduler(MachineSchedContext *C) const override {
ScheduleDAGMI *DAG = createGenericSchedPostRA(C);
const GCNSubtarget &ST = C->MF->getSubtarget<GCNSubtarget>();
- DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
DAG->addMutation(ST.createFillMFMAShadowMutation(DAG->TII));
return DAG;
}
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_u32_e32 v3, vcc, 16, v0
; GFX8-NEXT: v_addc_u32_e32 v4, vcc, 0, v1, vcc
-; GFX8-NEXT: flat_load_dwordx4 v[4:7], v[3:4]
; GFX8-NEXT: flat_load_dwordx4 v[8:11], v[0:1]
+; GFX8-NEXT: flat_load_dwordx4 v[4:7], v[3:4]
; GFX8-NEXT: v_lshlrev_b32_e32 v16, 1, v2
; GFX8-NEXT: v_add_u32_e32 v17, vcc, 1, v16
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 1, v17
; GFX8-NEXT: v_cmp_eq_u32_e64 s[4:5], 1, v16
; GFX8-NEXT: v_cmp_eq_u32_e64 s[6:7], 6, v16
; GFX8-NEXT: v_cmp_eq_u32_e64 s[8:9], 7, v16
-; GFX8-NEXT: s_waitcnt vmcnt(0)
+; GFX8-NEXT: s_waitcnt vmcnt(1)
; GFX8-NEXT: v_cndmask_b32_e64 v2, v8, v10, s[4:5]
; GFX8-NEXT: v_cndmask_b32_e64 v3, v9, v11, s[4:5]
; GFX8-NEXT: v_cndmask_b32_e32 v8, v8, v10, vcc
; GFX8-NEXT: v_cndmask_b32_e32 v9, v9, v11, vcc
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 2, v16
+; GFX8-NEXT: s_waitcnt vmcnt(0)
; GFX8-NEXT: v_cndmask_b32_e32 v2, v2, v4, vcc
; GFX8-NEXT: v_cndmask_b32_e32 v3, v3, v5, vcc
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 2, v17
; GFX9-LABEL: udivrem_v4i32:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x20
-; GFX9-NEXT: s_load_dwordx4 s[8:11], s[4:5], 0x10
; GFX9-NEXT: v_mov_b32_e32 v2, 0x4f7ffffe
+; GFX9-NEXT: s_load_dwordx4 s[8:11], s[4:5], 0x10
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_cvt_f32_u32_e32 v0, s0
; GFX9-NEXT: v_cvt_f32_u32_e32 v1, s1
;
; GFX10-LABEL: udivrem_v4i32:
; GFX10: ; %bb.0:
-; GFX10-NEXT: s_clause 0x1
; GFX10-NEXT: s_load_dwordx4 s[8:11], s[4:5], 0x20
-; GFX10-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x10
; GFX10-NEXT: v_mov_b32_e32 v4, 0x4f7ffffe
+; GFX10-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x10
; GFX10-NEXT: v_mov_b32_e32 v8, 0
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-NEXT: v_cvt_f32_u32_e32 v0, s8
; GFX6-LABEL: sdiv_i64_pow2_shl_denom:
; GFX6: ; %bb.0:
; GFX6-NEXT: s_load_dword s4, s[0:1], 0xd
-; GFX6-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GFX6-NEXT: s_mov_b64 s[2:3], 0x1000
+; GFX6-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GFX6-NEXT: s_mov_b32 s7, 0xf000
; GFX6-NEXT: s_mov_b32 s6, -1
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-LABEL: srem_i64_pow2_shl_denom:
; GFX6: ; %bb.0:
; GFX6-NEXT: s_load_dword s4, s[0:1], 0xd
-; GFX6-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GFX6-NEXT: s_mov_b64 s[2:3], 0x1000
+; GFX6-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GFX6-NEXT: s_mov_b32 s7, 0xf000
; GFX6-NEXT: s_mov_b32 s6, -1
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-LABEL: urem16_invariant_denom:
; GFX9: ; %bb.0: ; %bb
; GFX9-NEXT: s_load_dword s2, s[0:1], 0x2c
-; GFX9-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
; GFX9-NEXT: s_mov_b32 s6, 0xffff
+; GFX9-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
; GFX9-NEXT: v_mov_b32_e32 v1, 0
; GFX9-NEXT: s_movk_i32 s8, 0x400
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX900: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
;
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
-; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
-; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
-; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
+; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
+; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
+; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off{{$}}
; GFX10: global_load_dwordx2 v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}], off offset:-2048
; GCN-LABEL: s_test_sdiv:
; GCN: ; %bb.0:
; GCN-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xd
-; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: v_mov_b32_e32 v7, 0
+; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: s_mov_b32 s7, 0xf000
; GCN-NEXT: s_mov_b32 s6, -1
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-LABEL: s_test_srem:
; GCN: ; %bb.0:
; GCN-NEXT: s_load_dwordx2 s[12:13], s[0:1], 0xd
-; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: v_mov_b32_e32 v2, 0
+; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: s_mov_b32 s7, 0xf000
; GCN-NEXT: s_mov_b32 s6, -1
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-LABEL: s_test_udiv_i64:
; GCN: ; %bb.0:
; GCN-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0xd
-; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: v_mov_b32_e32 v2, 0
+; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: s_mov_b32 s7, 0xf000
; GCN-NEXT: s_mov_b32 s6, -1
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-LABEL: s_test_urem_i64:
; GCN: ; %bb.0:
; GCN-NEXT: s_load_dwordx2 s[12:13], s[0:1], 0xd
-; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: v_mov_b32_e32 v2, 0
+; GCN-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
; GCN-NEXT: s_mov_b32 s7, 0xf000
; GCN-NEXT: s_mov_b32 s6, -1
; GCN-NEXT: s_waitcnt lgkmcnt(0)