; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -mtriple=riscv32 -mattr=+a -verify-machineinstrs < %s \
; RUN:   | FileCheck -check-prefixes=RV32 %s
; RUN: llc -O3 -mtriple=riscv64 -mattr=+a -verify-machineinstrs < %s \
; RUN:   | FileCheck -check-prefixes=RV64 %s

define void @amoswap_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amoswap_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amoswap.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amoswap_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoswap.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw xchg ptr %a, i32 %b seq_cst
  ret void
}

define void @amoswap_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amoswap_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT:    li a3, 5
; RV32-NEXT:    call __atomic_exchange_8
; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: amoswap_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoswap.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw xchg ptr %a, i64 %b seq_cst
  ret void
}

define void @amoadd_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amoadd_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amoadd.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amoadd_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoadd.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw add ptr %a, i32 %b seq_cst
  ret void
}

define void @amoadd_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amoadd_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT:    li a3, 5
; RV32-NEXT:    call __atomic_fetch_add_8
; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: amoadd_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoadd.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw add ptr %a, i64 %b seq_cst
  ret void
}

define void @amoand_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amoand_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amoand.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amoand_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoand.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw and ptr %a, i32 %b seq_cst
  ret void
}

define void @amoand_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amoand_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT:    li a3, 5
; RV32-NEXT:    call __atomic_fetch_and_8
; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: amoand_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoand.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw and ptr %a, i64 %b seq_cst
  ret void
}

define void @amoor_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amoor_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amoor.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amoor_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoor.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw or ptr %a, i32 %b seq_cst
  ret void
}

define void @amoor_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amoor_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT:    li a3, 5
; RV32-NEXT:    call __atomic_fetch_or_8
; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: amoor_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoor.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw or ptr %a, i64 %b seq_cst
  ret void
}

define void @amoxor_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amoxor_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amoor.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amoxor_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoor.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw or ptr %a, i32 %b seq_cst
  ret void
}

define void @amoxor_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amoxor_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT:    li a3, 5
; RV32-NEXT:    call __atomic_fetch_or_8
; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: amoxor_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amoor.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw or ptr %a, i64 %b seq_cst
  ret void
}

define void @amomax_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amomax_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amomax.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amomax_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomax.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw max ptr %a, i32 %b seq_cst
  ret void
}

define void @amomax_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amomax_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -32
; RV32-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s0, 24(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s1, 20(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s2, 16(sp) # 4-byte Folded Spill
; RV32-NEXT:    mv s0, a2
; RV32-NEXT:    mv s1, a0
; RV32-NEXT:    lw a4, 0(a0)
; RV32-NEXT:    lw a5, 4(a0)
; RV32-NEXT:    mv s2, a1
; RV32-NEXT:    j .LBB11_2
; RV32-NEXT:  .LBB11_1: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB11_2 Depth=1
; RV32-NEXT:    sw a4, 8(sp)
; RV32-NEXT:    sw a5, 12(sp)
; RV32-NEXT:    addi a1, sp, 8
; RV32-NEXT:    li a4, 5
; RV32-NEXT:    li a5, 5
; RV32-NEXT:    mv a0, s1
; RV32-NEXT:    call __atomic_compare_exchange_8
; RV32-NEXT:    lw a4, 8(sp)
; RV32-NEXT:    lw a5, 12(sp)
; RV32-NEXT:    bnez a0, .LBB11_6
; RV32-NEXT:  .LBB11_2: # %atomicrmw.start
; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
; RV32-NEXT:    beq a5, s0, .LBB11_4
; RV32-NEXT:  # %bb.3: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB11_2 Depth=1
; RV32-NEXT:    slt a0, s0, a5
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    bnez a0, .LBB11_1
; RV32-NEXT:    j .LBB11_5
; RV32-NEXT:  .LBB11_4: # in Loop: Header=BB11_2 Depth=1
; RV32-NEXT:    sltu a0, s2, a4
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    bnez a0, .LBB11_1
; RV32-NEXT:  .LBB11_5: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB11_2 Depth=1
; RV32-NEXT:    mv a2, s2
; RV32-NEXT:    mv a3, s0
; RV32-NEXT:    j .LBB11_1
; RV32-NEXT:  .LBB11_6: # %atomicrmw.end
; RV32-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s0, 24(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s1, 20(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s2, 16(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 32
; RV32-NEXT:    ret
;
; RV64-LABEL: amomax_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomax.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw max ptr %a, i64 %b seq_cst
  ret void
}

define void @amomaxu_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amomaxu_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amomaxu.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amomaxu_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomaxu.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw umax ptr %a, i32 %b seq_cst
  ret void
}

define void @amomaxu_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amomaxu_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -32
; RV32-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s0, 24(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s1, 20(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s2, 16(sp) # 4-byte Folded Spill
; RV32-NEXT:    mv s0, a2
; RV32-NEXT:    mv s1, a0
; RV32-NEXT:    lw a4, 0(a0)
; RV32-NEXT:    lw a5, 4(a0)
; RV32-NEXT:    mv s2, a1
; RV32-NEXT:    j .LBB13_2
; RV32-NEXT:  .LBB13_1: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB13_2 Depth=1
; RV32-NEXT:    sw a4, 8(sp)
; RV32-NEXT:    sw a5, 12(sp)
; RV32-NEXT:    addi a1, sp, 8
; RV32-NEXT:    li a4, 5
; RV32-NEXT:    li a5, 5
; RV32-NEXT:    mv a0, s1
; RV32-NEXT:    call __atomic_compare_exchange_8
; RV32-NEXT:    lw a4, 8(sp)
; RV32-NEXT:    lw a5, 12(sp)
; RV32-NEXT:    bnez a0, .LBB13_6
; RV32-NEXT:  .LBB13_2: # %atomicrmw.start
; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
; RV32-NEXT:    beq a5, s0, .LBB13_4
; RV32-NEXT:  # %bb.3: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB13_2 Depth=1
; RV32-NEXT:    sltu a0, s0, a5
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    bnez a0, .LBB13_1
; RV32-NEXT:    j .LBB13_5
; RV32-NEXT:  .LBB13_4: # in Loop: Header=BB13_2 Depth=1
; RV32-NEXT:    sltu a0, s2, a4
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    bnez a0, .LBB13_1
; RV32-NEXT:  .LBB13_5: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB13_2 Depth=1
; RV32-NEXT:    mv a2, s2
; RV32-NEXT:    mv a3, s0
; RV32-NEXT:    j .LBB13_1
; RV32-NEXT:  .LBB13_6: # %atomicrmw.end
; RV32-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s0, 24(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s1, 20(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s2, 16(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 32
; RV32-NEXT:    ret
;
; RV64-LABEL: amomaxu_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomaxu.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw umax ptr %a, i64 %b seq_cst
  ret void
}

define void @amomin_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amomin_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amomin.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amomin_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomin.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw min ptr %a, i32 %b seq_cst
  ret void
}

define void @amomin_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amomin_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -32
; RV32-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s0, 24(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s1, 20(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s2, 16(sp) # 4-byte Folded Spill
; RV32-NEXT:    mv s0, a2
; RV32-NEXT:    mv s1, a0
; RV32-NEXT:    lw a4, 0(a0)
; RV32-NEXT:    lw a5, 4(a0)
; RV32-NEXT:    mv s2, a1
; RV32-NEXT:    j .LBB15_2
; RV32-NEXT:  .LBB15_1: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB15_2 Depth=1
; RV32-NEXT:    sw a4, 8(sp)
; RV32-NEXT:    sw a5, 12(sp)
; RV32-NEXT:    addi a1, sp, 8
; RV32-NEXT:    li a4, 5
; RV32-NEXT:    li a5, 5
; RV32-NEXT:    mv a0, s1
; RV32-NEXT:    call __atomic_compare_exchange_8
; RV32-NEXT:    lw a4, 8(sp)
; RV32-NEXT:    lw a5, 12(sp)
; RV32-NEXT:    bnez a0, .LBB15_6
; RV32-NEXT:  .LBB15_2: # %atomicrmw.start
; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
; RV32-NEXT:    beq a5, s0, .LBB15_4
; RV32-NEXT:  # %bb.3: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB15_2 Depth=1
; RV32-NEXT:    slt a0, s0, a5
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    beqz a0, .LBB15_1
; RV32-NEXT:    j .LBB15_5
; RV32-NEXT:  .LBB15_4: # in Loop: Header=BB15_2 Depth=1
; RV32-NEXT:    sltu a0, s2, a4
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    beqz a0, .LBB15_1
; RV32-NEXT:  .LBB15_5: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB15_2 Depth=1
; RV32-NEXT:    mv a2, s2
; RV32-NEXT:    mv a3, s0
; RV32-NEXT:    j .LBB15_1
; RV32-NEXT:  .LBB15_6: # %atomicrmw.end
; RV32-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s0, 24(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s1, 20(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s2, 16(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 32
; RV32-NEXT:    ret
;
; RV64-LABEL: amomin_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amomin.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw min ptr %a, i64 %b seq_cst
  ret void
}

define void @amominu_w_discard(ptr %a, i32 %b) nounwind {
; RV32-LABEL: amominu_w_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    amominu.w.aqrl zero, a1, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: amominu_w_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amominu.w.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw umin ptr %a, i32 %b seq_cst
  ret void
}

define void @amominu_d_discard(ptr %a, i64 %b) nounwind {
; RV32-LABEL: amominu_d_discard:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -32
; RV32-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s0, 24(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s1, 20(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s2, 16(sp) # 4-byte Folded Spill
; RV32-NEXT:    mv s0, a2
; RV32-NEXT:    mv s1, a0
; RV32-NEXT:    lw a4, 0(a0)
; RV32-NEXT:    lw a5, 4(a0)
; RV32-NEXT:    mv s2, a1
; RV32-NEXT:    j .LBB17_2
; RV32-NEXT:  .LBB17_1: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB17_2 Depth=1
; RV32-NEXT:    sw a4, 8(sp)
; RV32-NEXT:    sw a5, 12(sp)
; RV32-NEXT:    addi a1, sp, 8
; RV32-NEXT:    li a4, 5
; RV32-NEXT:    li a5, 5
; RV32-NEXT:    mv a0, s1
; RV32-NEXT:    call __atomic_compare_exchange_8
; RV32-NEXT:    lw a4, 8(sp)
; RV32-NEXT:    lw a5, 12(sp)
; RV32-NEXT:    bnez a0, .LBB17_6
; RV32-NEXT:  .LBB17_2: # %atomicrmw.start
; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
; RV32-NEXT:    beq a5, s0, .LBB17_4
; RV32-NEXT:  # %bb.3: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB17_2 Depth=1
; RV32-NEXT:    sltu a0, s0, a5
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    beqz a0, .LBB17_1
; RV32-NEXT:    j .LBB17_5
; RV32-NEXT:  .LBB17_4: # in Loop: Header=BB17_2 Depth=1
; RV32-NEXT:    sltu a0, s2, a4
; RV32-NEXT:    mv a2, a4
; RV32-NEXT:    mv a3, a5
; RV32-NEXT:    beqz a0, .LBB17_1
; RV32-NEXT:  .LBB17_5: # %atomicrmw.start
; RV32-NEXT:    # in Loop: Header=BB17_2 Depth=1
; RV32-NEXT:    mv a2, s2
; RV32-NEXT:    mv a3, s0
; RV32-NEXT:    j .LBB17_1
; RV32-NEXT:  .LBB17_6: # %atomicrmw.end
; RV32-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s0, 24(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s1, 20(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s2, 16(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 32
; RV32-NEXT:    ret
;
; RV64-LABEL: amominu_d_discard:
; RV64:       # %bb.0:
; RV64-NEXT:    amominu.d.aqrl zero, a1, (a0)
; RV64-NEXT:    ret
  %1 = atomicrmw umin ptr %a, i64 %b seq_cst
  ret void
}