ret void
}
+define amdgpu_kernel void @add_i32_varying_nouse() {
+; GFX7LESS-LABEL: add_i32_varying_nouse:
+; GFX7LESS: ; %bb.0: ; %entry
+; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
+; GFX7LESS-NEXT: s_mov_b32 m0, -1
+; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
+; GFX7LESS-NEXT: ds_add_u32 v1, v0
+; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
+; GFX7LESS-NEXT: s_endpgm
+;
+; GFX8-LABEL: add_i32_varying_nouse:
+; GFX8: ; %bb.0: ; %entry
+; GFX8-NEXT: v_mov_b32_e32 v1, v0
+; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, exec_lo, 0
+; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, exec_hi, v0
+; GFX8-NEXT: s_not_b64 exec, exec
+; GFX8-NEXT: v_mov_b32_e32 v1, 0
+; GFX8-NEXT: s_not_b64 exec, exec
+; GFX8-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf
+; GFX8-NEXT: v_readlane_b32 s2, v1, 63
+; GFX8-NEXT: s_mov_b64 exec, s[0:1]
+; GFX8-NEXT: s_mov_b32 s0, s2
+; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX8-NEXT: s_cbranch_execz BB3_2
+; GFX8-NEXT: ; %bb.1:
+; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX8-NEXT: v_mov_b32_e32 v2, s0
+; GFX8-NEXT: s_mov_b32 m0, -1
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: ds_add_u32 v0, v2
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: BB3_2:
+; GFX8-NEXT: s_endpgm
+;
+; GFX9-LABEL: add_i32_varying_nouse:
+; GFX9: ; %bb.0: ; %entry
+; GFX9-NEXT: v_mov_b32_e32 v1, v0
+; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, exec_lo, 0
+; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, exec_hi, v0
+; GFX9-NEXT: s_not_b64 exec, exec
+; GFX9-NEXT: v_mov_b32_e32 v1, 0
+; GFX9-NEXT: s_not_b64 exec, exec
+; GFX9-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf
+; GFX9-NEXT: v_readlane_b32 s2, v1, 63
+; GFX9-NEXT: s_mov_b64 exec, s[0:1]
+; GFX9-NEXT: s_mov_b32 s0, s2
+; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX9-NEXT: s_cbranch_execz BB3_2
+; GFX9-NEXT: ; %bb.1:
+; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX9-NEXT: v_mov_b32_e32 v2, s0
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: ds_add_u32 v0, v2
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: BB3_2:
+; GFX9-NEXT: s_endpgm
+;
+; GFX1064-LABEL: add_i32_varying_nouse:
+; GFX1064: ; %bb.0: ; %entry
+; GFX1064-NEXT: v_mov_b32_e32 v1, v0
+; GFX1064-NEXT: s_not_b64 exec, exec
+; GFX1064-NEXT: v_mov_b32_e32 v1, 0
+; GFX1064-NEXT: s_not_b64 exec, exec
+; GFX1064-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_mov_b32_e32 v2, v1
+; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
+; GFX1064-NEXT: v_readlane_b32 s2, v1, 31
+; GFX1064-NEXT: v_mov_b32_e32 v2, s2
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
+; GFX1064-NEXT: s_mov_b64 exec, s[0:1]
+; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, exec_lo, 0
+; GFX1064-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX1064-NEXT: v_readlane_b32 s2, v1, 63
+; GFX1064-NEXT: s_mov_b64 exec, s[0:1]
+; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, exec_hi, v0
+; GFX1064-NEXT: s_mov_b32 s0, s2
+; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX1064-NEXT: s_cbranch_execz BB3_2
+; GFX1064-NEXT: ; %bb.1:
+; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX1064-NEXT: v_mov_b32_e32 v3, s0
+; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX1064-NEXT: ds_add_u32 v0, v3
+; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
+; GFX1064-NEXT: buffer_gl0_inv
+; GFX1064-NEXT: BB3_2:
+; GFX1064-NEXT: s_endpgm
+;
+; GFX1032-LABEL: add_i32_varying_nouse:
+; GFX1032: ; %bb.0: ; %entry
+; GFX1032-NEXT: v_mov_b32_e32 v1, v0
+; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
+; GFX1032-NEXT: v_mov_b32_e32 v1, 0
+; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
+; GFX1032-NEXT: s_or_saveexec_b32 s0, -1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_mov_b32_e32 v2, v1
+; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
+; GFX1032-NEXT: v_readlane_b32 s1, v1, 31
+; GFX1032-NEXT: s_mov_b32 exec_lo, s0
+; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, exec_lo, 0
+; GFX1032-NEXT: s_mov_b32 s0, s1
+; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
+; GFX1032-NEXT: s_and_saveexec_b32 s1, vcc_lo
+; GFX1032-NEXT: s_cbranch_execz BB3_2
+; GFX1032-NEXT: ; %bb.1:
+; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX1032-NEXT: v_mov_b32_e32 v3, s0
+; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX1032-NEXT: ds_add_u32 v0, v3
+; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
+; GFX1032-NEXT: buffer_gl0_inv
+; GFX1032-NEXT: BB3_2:
+; GFX1032-NEXT: s_endpgm
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+ ret void
+}
+
define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
;
;
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB3_2
+; GFX7LESS-NEXT: s_cbranch_execz BB4_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB3_2:
+; GFX7LESS-NEXT: BB4_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB3_2
+; GFX8-NEXT: s_cbranch_execz BB4_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX8-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB3_2:
+; GFX8-NEXT: BB4_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB3_2
+; GFX9-NEXT: s_cbranch_execz BB4_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX9-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB3_2:
+; GFX9-NEXT: BB4_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s5, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB3_2
+; GFX1064-NEXT: s_cbranch_execz BB4_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1064-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB3_2:
+; GFX1064-NEXT: BB4_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB3_2
+; GFX1032-NEXT: s_cbranch_execz BB4_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1032-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB3_2:
+; GFX1032-NEXT: BB4_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX7LESS-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB4_2
+; GFX7LESS-NEXT: s_cbranch_execz BB5_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB4_2:
+; GFX7LESS-NEXT: BB5_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
; GFX7LESS-NEXT: s_mov_b32 s6, -1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX8-NEXT: s_cbranch_execz BB4_2
+; GFX8-NEXT: s_cbranch_execz BB5_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX8-NEXT: v_mov_b32_e32 v1, s6
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB4_2:
+; GFX8-NEXT: BB5_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: s_mov_b32 s4, s0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX9-NEXT: s_cbranch_execz BB4_2
+; GFX9-NEXT: s_cbranch_execz BB5_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB4_2:
+; GFX9-NEXT: BB5_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_mul_lo_u32 v3, s3, v0
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s7, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB4_2
+; GFX1064-NEXT: s_cbranch_execz BB5_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1064-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB4_2:
+; GFX1064-NEXT: BB5_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s5, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB4_2
+; GFX1032-NEXT: s_cbranch_execz BB5_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s5, s5
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1032-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB4_2:
+; GFX1032-NEXT: BB5_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB6_2
+; GFX7LESS-NEXT: s_cbranch_execz BB7_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
; GFX7LESS-NEXT: s_mul_i32 s2, s2, 5
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB6_2:
+; GFX7LESS-NEXT: BB7_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX8-NEXT: s_cbranch_execz BB6_2
+; GFX8-NEXT: s_cbranch_execz BB7_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
; GFX8-NEXT: s_mul_i32 s2, s2, 5
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB6_2:
+; GFX8-NEXT: BB7_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX9-NEXT: s_cbranch_execz BB6_2
+; GFX9-NEXT: s_cbranch_execz BB7_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
; GFX9-NEXT: s_mul_i32 s2, s2, 5
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB6_2:
+; GFX9-NEXT: BB7_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB6_2
+; GFX1064-NEXT: s_cbranch_execz BB7_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
; GFX1064-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
; GFX1064-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB6_2:
+; GFX1064-NEXT: BB7_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB6_2
+; GFX1032-NEXT: s_cbranch_execz BB7_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
; GFX1032-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
; GFX1032-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB6_2:
+; GFX1032-NEXT: BB7_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[6:7], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB7_2
+; GFX7LESS-NEXT: s_cbranch_execz BB8_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s1, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB7_2:
+; GFX7LESS-NEXT: BB8_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[6:7]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s1, v1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[6:7], vcc
-; GFX8-NEXT: s_cbranch_execz BB7_2
+; GFX8-NEXT: s_cbranch_execz BB8_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s1, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB7_2:
+; GFX8-NEXT: BB8_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[6:7]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_mul_lo_u32 v0, s0, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[0:1], vcc
-; GFX9-NEXT: s_cbranch_execz BB7_2
+; GFX9-NEXT: s_cbranch_execz BB8_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s3, s[6:7]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB7_2:
+; GFX9-NEXT: BB8_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[0:1]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_mul_lo_u32 v0, s2, v0
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s7, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[0:1], vcc
-; GFX1064-NEXT: s_cbranch_execz BB7_2
+; GFX1064-NEXT: s_cbranch_execz BB8_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s3, s[6:7]
; GFX1064-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
; GFX1064-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB7_2:
+; GFX1064-NEXT: BB8_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[0:1]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s0, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB7_2
+; GFX1032-NEXT: s_cbranch_execz BB8_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s1, s3
; GFX1032-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
; GFX1032-NEXT: ds_sub_rtn_u32 v1, v1, v2
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB7_2:
+; GFX1032-NEXT: BB8_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s0
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB8_2
+; GFX8-NEXT: s_cbranch_execz BB9_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_sub_rtn_u32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB8_2:
+; GFX8-NEXT: BB9_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB8_2
+; GFX9-NEXT: s_cbranch_execz BB9_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_sub_rtn_u32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB8_2:
+; GFX9-NEXT: BB9_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB8_2
+; GFX1064-NEXT: s_cbranch_execz BB9_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_sub_rtn_u32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB8_2:
+; GFX1064-NEXT: BB9_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB8_2
+; GFX1032-NEXT: s_cbranch_execz BB9_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_sub_rtn_u32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB8_2:
+; GFX1032-NEXT: BB9_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
ret void
}
+define amdgpu_kernel void @sub_i32_varying_nouse() {
+; GFX7LESS-LABEL: sub_i32_varying_nouse:
+; GFX7LESS: ; %bb.0: ; %entry
+; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
+; GFX7LESS-NEXT: s_mov_b32 m0, -1
+; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
+; GFX7LESS-NEXT: ds_sub_u32 v1, v0
+; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
+; GFX7LESS-NEXT: s_endpgm
+;
+; GFX8-LABEL: sub_i32_varying_nouse:
+; GFX8: ; %bb.0: ; %entry
+; GFX8-NEXT: v_mov_b32_e32 v1, v0
+; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, exec_lo, 0
+; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, exec_hi, v0
+; GFX8-NEXT: s_not_b64 exec, exec
+; GFX8-NEXT: v_mov_b32_e32 v1, 0
+; GFX8-NEXT: s_not_b64 exec, exec
+; GFX8-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf
+; GFX8-NEXT: s_nop 1
+; GFX8-NEXT: v_add_u32_dpp v1, vcc, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf
+; GFX8-NEXT: v_readlane_b32 s2, v1, 63
+; GFX8-NEXT: s_mov_b64 exec, s[0:1]
+; GFX8-NEXT: s_mov_b32 s0, s2
+; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX8-NEXT: s_cbranch_execz BB10_2
+; GFX8-NEXT: ; %bb.1:
+; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX8-NEXT: v_mov_b32_e32 v2, s0
+; GFX8-NEXT: s_mov_b32 m0, -1
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: ds_sub_u32 v0, v2
+; GFX8-NEXT: s_waitcnt lgkmcnt(0)
+; GFX8-NEXT: BB10_2:
+; GFX8-NEXT: s_endpgm
+;
+; GFX9-LABEL: sub_i32_varying_nouse:
+; GFX9: ; %bb.0: ; %entry
+; GFX9-NEXT: v_mov_b32_e32 v1, v0
+; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, exec_lo, 0
+; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, exec_hi, v0
+; GFX9-NEXT: s_not_b64 exec, exec
+; GFX9-NEXT: v_mov_b32_e32 v1, 0
+; GFX9-NEXT: s_not_b64 exec, exec
+; GFX9-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf
+; GFX9-NEXT: s_nop 1
+; GFX9-NEXT: v_add_u32_dpp v1, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf
+; GFX9-NEXT: v_readlane_b32 s2, v1, 63
+; GFX9-NEXT: s_mov_b64 exec, s[0:1]
+; GFX9-NEXT: s_mov_b32 s0, s2
+; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX9-NEXT: s_cbranch_execz BB10_2
+; GFX9-NEXT: ; %bb.1:
+; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX9-NEXT: v_mov_b32_e32 v2, s0
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: ds_sub_u32 v0, v2
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: BB10_2:
+; GFX9-NEXT: s_endpgm
+;
+; GFX1064-LABEL: sub_i32_varying_nouse:
+; GFX1064: ; %bb.0: ; %entry
+; GFX1064-NEXT: v_mov_b32_e32 v1, v0
+; GFX1064-NEXT: s_not_b64 exec, exec
+; GFX1064-NEXT: v_mov_b32_e32 v1, 0
+; GFX1064-NEXT: s_not_b64 exec, exec
+; GFX1064-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1064-NEXT: v_mov_b32_e32 v2, v1
+; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
+; GFX1064-NEXT: v_readlane_b32 s2, v1, 31
+; GFX1064-NEXT: v_mov_b32_e32 v2, s2
+; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
+; GFX1064-NEXT: s_mov_b64 exec, s[0:1]
+; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, exec_lo, 0
+; GFX1064-NEXT: s_or_saveexec_b64 s[0:1], -1
+; GFX1064-NEXT: v_readlane_b32 s2, v1, 63
+; GFX1064-NEXT: s_mov_b64 exec, s[0:1]
+; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, exec_hi, v0
+; GFX1064-NEXT: s_mov_b32 s0, s2
+; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
+; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX1064-NEXT: s_cbranch_execz BB10_2
+; GFX1064-NEXT: ; %bb.1:
+; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX1064-NEXT: v_mov_b32_e32 v3, s0
+; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX1064-NEXT: ds_sub_u32 v0, v3
+; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
+; GFX1064-NEXT: buffer_gl0_inv
+; GFX1064-NEXT: BB10_2:
+; GFX1064-NEXT: s_endpgm
+;
+; GFX1032-LABEL: sub_i32_varying_nouse:
+; GFX1032: ; %bb.0: ; %entry
+; GFX1032-NEXT: v_mov_b32_e32 v1, v0
+; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
+; GFX1032-NEXT: v_mov_b32_e32 v1, 0
+; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
+; GFX1032-NEXT: s_or_saveexec_b32 s0, -1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1
+; GFX1032-NEXT: v_mov_b32_e32 v2, v1
+; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1
+; GFX1032-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
+; GFX1032-NEXT: v_readlane_b32 s1, v1, 31
+; GFX1032-NEXT: s_mov_b32 exec_lo, s0
+; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, exec_lo, 0
+; GFX1032-NEXT: s_mov_b32 s0, s1
+; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
+; GFX1032-NEXT: s_and_saveexec_b32 s1, vcc_lo
+; GFX1032-NEXT: s_cbranch_execz BB10_2
+; GFX1032-NEXT: ; %bb.1:
+; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
+; GFX1032-NEXT: v_mov_b32_e32 v3, s0
+; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX1032-NEXT: ds_sub_u32 v0, v3
+; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
+; GFX1032-NEXT: buffer_gl0_inv
+; GFX1032-NEXT: BB10_2:
+; GFX1032-NEXT: s_endpgm
+entry:
+ %lane = call i32 @llvm.amdgcn.workitem.id.x()
+ %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+ ret void
+}
+
define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
;
;
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB9_2
+; GFX7LESS-NEXT: s_cbranch_execz BB11_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB9_2:
+; GFX7LESS-NEXT: BB11_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB9_2
+; GFX8-NEXT: s_cbranch_execz BB11_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX8-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB9_2:
+; GFX8-NEXT: BB11_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s3, v2
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB9_2
+; GFX9-NEXT: s_cbranch_execz BB11_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX9-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB9_2:
+; GFX9-NEXT: BB11_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s3, v2
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s5, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB9_2
+; GFX1064-NEXT: s_cbranch_execz BB11_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1064-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB9_2:
+; GFX1064-NEXT: BB11_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB9_2
+; GFX1032-NEXT: s_cbranch_execz BB11_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1032-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB9_2:
+; GFX1032-NEXT: BB11_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX7LESS-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB10_2
+; GFX7LESS-NEXT: s_cbranch_execz BB12_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB10_2:
+; GFX7LESS-NEXT: BB12_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
; GFX7LESS-NEXT: s_mov_b32 s6, -1
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX8-NEXT: s_cbranch_execz BB10_2
+; GFX8-NEXT: s_cbranch_execz BB12_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX8-NEXT: v_mov_b32_e32 v1, s6
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB10_2:
+; GFX8-NEXT: BB12_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: s_mov_b32 s4, s0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX9-NEXT: s_cbranch_execz BB10_2
+; GFX9-NEXT: s_cbranch_execz BB12_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB10_2:
+; GFX9-NEXT: BB12_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_mul_lo_u32 v3, s3, v0
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s7, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB10_2
+; GFX1064-NEXT: s_cbranch_execz BB12_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1064-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB10_2:
+; GFX1064-NEXT: BB12_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s5, 0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB10_2
+; GFX1032-NEXT: s_cbranch_execz BB12_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: s_bcnt1_i32_b32 s5, s5
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
; GFX1032-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB10_2:
+; GFX1032-NEXT: BB12_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB12_2
+; GFX8-NEXT: s_cbranch_execz BB14_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_and_rtn_b32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB12_2:
+; GFX8-NEXT: BB14_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB12_2
+; GFX9-NEXT: s_cbranch_execz BB14_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_and_rtn_b32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB12_2:
+; GFX9-NEXT: BB14_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB12_2
+; GFX1064-NEXT: s_cbranch_execz BB14_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_and_rtn_b32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB12_2:
+; GFX1064-NEXT: BB14_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB12_2
+; GFX1032-NEXT: s_cbranch_execz BB14_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_and_rtn_b32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB12_2:
+; GFX1032-NEXT: BB14_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB13_2
+; GFX8-NEXT: s_cbranch_execz BB15_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_or_rtn_b32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB13_2:
+; GFX8-NEXT: BB15_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB13_2
+; GFX9-NEXT: s_cbranch_execz BB15_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_or_rtn_b32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB13_2:
+; GFX9-NEXT: BB15_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB13_2
+; GFX1064-NEXT: s_cbranch_execz BB15_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_or_rtn_b32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB13_2:
+; GFX1064-NEXT: BB15_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB13_2
+; GFX1032-NEXT: s_cbranch_execz BB15_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_or_rtn_b32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB13_2:
+; GFX1032-NEXT: BB15_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB14_2
+; GFX8-NEXT: s_cbranch_execz BB16_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_xor_rtn_b32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB14_2:
+; GFX8-NEXT: BB16_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB14_2
+; GFX9-NEXT: s_cbranch_execz BB16_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_xor_rtn_b32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB14_2:
+; GFX9-NEXT: BB16_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB14_2
+; GFX1064-NEXT: s_cbranch_execz BB16_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_xor_rtn_b32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB14_2:
+; GFX1064-NEXT: BB16_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB14_2
+; GFX1032-NEXT: s_cbranch_execz BB16_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_xor_rtn_b32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB14_2:
+; GFX1032-NEXT: BB16_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB15_2
+; GFX8-NEXT: s_cbranch_execz BB17_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_max_rtn_i32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB15_2:
+; GFX8-NEXT: BB17_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB15_2
+; GFX9-NEXT: s_cbranch_execz BB17_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_max_rtn_i32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB15_2:
+; GFX9-NEXT: BB17_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB15_2
+; GFX1064-NEXT: s_cbranch_execz BB17_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_max_rtn_i32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB15_2:
+; GFX1064-NEXT: BB17_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB15_2
+; GFX1032-NEXT: s_cbranch_execz BB17_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_max_rtn_i32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB15_2:
+; GFX1032-NEXT: BB17_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB16_2
+; GFX7LESS-NEXT: s_cbranch_execz BB18_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB16_2:
+; GFX7LESS-NEXT: BB18_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB16_2
+; GFX8-NEXT: s_cbranch_execz BB18_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, 5
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB16_2:
+; GFX8-NEXT: BB18_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB16_2
+; GFX9-NEXT: s_cbranch_execz BB18_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, 5
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB16_2:
+; GFX9-NEXT: BB18_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB16_2
+; GFX1064-NEXT: s_cbranch_execz BB18_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1064-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB16_2:
+; GFX1064-NEXT: BB18_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB16_2
+; GFX1032-NEXT: s_cbranch_execz BB18_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1032-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB16_2:
+; GFX1032-NEXT: BB18_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB17_2
+; GFX8-NEXT: s_cbranch_execz BB19_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_min_rtn_i32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB17_2:
+; GFX8-NEXT: BB19_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB17_2
+; GFX9-NEXT: s_cbranch_execz BB19_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_min_rtn_i32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB17_2:
+; GFX9-NEXT: BB19_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB17_2
+; GFX1064-NEXT: s_cbranch_execz BB19_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_min_rtn_i32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB17_2:
+; GFX1064-NEXT: BB19_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB17_2
+; GFX1032-NEXT: s_cbranch_execz BB19_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_min_rtn_i32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB17_2:
+; GFX1032-NEXT: BB19_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB18_2
+; GFX7LESS-NEXT: s_cbranch_execz BB20_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB18_2:
+; GFX7LESS-NEXT: BB20_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB18_2
+; GFX8-NEXT: s_cbranch_execz BB20_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, 5
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB18_2:
+; GFX8-NEXT: BB20_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s4, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB18_2
+; GFX9-NEXT: s_cbranch_execz BB20_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, 5
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB18_2:
+; GFX9-NEXT: BB20_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s4, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB18_2
+; GFX1064-NEXT: s_cbranch_execz BB20_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1064-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB18_2:
+; GFX1064-NEXT: BB20_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB18_2
+; GFX1032-NEXT: s_cbranch_execz BB20_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1032-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB18_2:
+; GFX1032-NEXT: BB20_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB19_2
+; GFX8-NEXT: s_cbranch_execz BB21_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_max_rtn_u32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB19_2:
+; GFX8-NEXT: BB21_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB19_2
+; GFX9-NEXT: s_cbranch_execz BB21_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_max_rtn_u32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB19_2:
+; GFX9-NEXT: BB21_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB19_2
+; GFX1064-NEXT: s_cbranch_execz BB21_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_max_rtn_u32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB19_2:
+; GFX1064-NEXT: BB21_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB19_2
+; GFX1032-NEXT: s_cbranch_execz BB21_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_max_rtn_u32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB19_2:
+; GFX1032-NEXT: BB21_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB20_2
+; GFX7LESS-NEXT: s_cbranch_execz BB22_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB20_2:
+; GFX7LESS-NEXT: BB22_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB20_2
+; GFX8-NEXT: s_cbranch_execz BB22_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, 5
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB20_2:
+; GFX8-NEXT: BB22_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB20_2
+; GFX9-NEXT: s_cbranch_execz BB22_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, 5
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB20_2:
+; GFX9-NEXT: BB22_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB20_2
+; GFX1064-NEXT: s_cbranch_execz BB22_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1064-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB20_2:
+; GFX1064-NEXT: BB22_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB20_2
+; GFX1032-NEXT: s_cbranch_execz BB22_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1032-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB20_2:
+; GFX1032-NEXT: BB22_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB21_2
+; GFX8-NEXT: s_cbranch_execz BB23_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX8-NEXT: v_mov_b32_e32 v3, s4
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_min_rtn_u32 v0, v0, v3
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB21_2:
+; GFX8-NEXT: BB23_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB21_2
+; GFX9-NEXT: s_cbranch_execz BB23_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
; GFX9-NEXT: v_mov_b32_e32 v3, s4
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_min_rtn_u32 v0, v0, v3
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB21_2:
+; GFX9-NEXT: BB23_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
; GFX1064-NEXT: s_mov_b32 s2, -1
; GFX1064-NEXT: ; implicit-def: $vgpr0
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
-; GFX1064-NEXT: s_cbranch_execz BB21_2
+; GFX1064-NEXT: s_cbranch_execz BB23_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1064-NEXT: v_mov_b32_e32 v4, s7
; GFX1064-NEXT: ds_min_rtn_u32 v0, v7, v4
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB21_2:
+; GFX1064-NEXT: BB23_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
; GFX1032-NEXT: s_mov_b32 s2, -1
; GFX1032-NEXT: ; implicit-def: $vgpr0
; GFX1032-NEXT: s_and_saveexec_b32 s3, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB21_2
+; GFX1032-NEXT: s_cbranch_execz BB23_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v7, local_var32@abs32@lo
; GFX1032-NEXT: v_mov_b32_e32 v4, s4
; GFX1032-NEXT: ds_min_rtn_u32 v0, v7, v4
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB21_2:
+; GFX1032-NEXT: BB23_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s3
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX7LESS-NEXT: s_cbranch_execz BB22_2
+; GFX7LESS-NEXT: s_cbranch_execz BB24_2
; GFX7LESS-NEXT: ; %bb.1:
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
-; GFX7LESS-NEXT: BB22_2:
+; GFX7LESS-NEXT: BB24_2:
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX8-NEXT: s_cbranch_execz BB22_2
+; GFX8-NEXT: s_cbranch_execz BB24_2
; GFX8-NEXT: ; %bb.1:
; GFX8-NEXT: v_mov_b32_e32 v0, 5
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
-; GFX8-NEXT: BB22_2:
+; GFX8-NEXT: BB24_2:
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
; GFX8-NEXT: v_readfirstlane_b32 s5, v1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX9-NEXT: s_cbranch_execz BB22_2
+; GFX9-NEXT: s_cbranch_execz BB24_2
; GFX9-NEXT: ; %bb.1:
; GFX9-NEXT: v_mov_b32_e32 v0, 5
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
-; GFX9-NEXT: BB22_2:
+; GFX9-NEXT: BB24_2:
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s5, v1
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
-; GFX1064-NEXT: s_cbranch_execz BB22_2
+; GFX1064-NEXT: s_cbranch_execz BB24_2
; GFX1064-NEXT: ; %bb.1:
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1064-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
; GFX1064-NEXT: buffer_gl0_inv
-; GFX1064-NEXT: BB22_2:
+; GFX1064-NEXT: BB24_2:
; GFX1064-NEXT: s_waitcnt_depctr 0xffe3
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX1064-NEXT: v_readfirstlane_b32 s2, v0
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
-; GFX1032-NEXT: s_cbranch_execz BB22_2
+; GFX1032-NEXT: s_cbranch_execz BB24_2
; GFX1032-NEXT: ; %bb.1:
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
; GFX1032-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
; GFX1032-NEXT: buffer_gl0_inv
-; GFX1032-NEXT: BB22_2:
+; GFX1032-NEXT: BB24_2:
; GFX1032-NEXT: s_waitcnt_depctr 0xffe3
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
; GFX1032-NEXT: v_readfirstlane_b32 s2, v0