llvm/test/CodeGen/RISCV/mem.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN:   | FileCheck %s -check-prefix=RV32I

; Check indexed and unindexed, sext, zext and anyext loads

define dso_local i32 @lb(ptr %a) nounwind {
; RV32I-LABEL: lb:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lb a1, 1(a0)
; RV32I-NEXT:    lbu zero, 0(a0)
; RV32I-NEXT:    mv a0, a1
; RV32I-NEXT:    ret
  %1 = getelementptr i8, ptr %a, i32 1
  %2 = load i8, ptr %1
  %3 = sext i8 %2 to i32
  ; the unused load will produce an anyext for selection
  %4 = load volatile i8, ptr %a
  ret i32 %3
}

define dso_local i32 @lh(ptr %a) nounwind {
; RV32I-LABEL: lh:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lh a1, 4(a0)
; RV32I-NEXT:    lh zero, 0(a0)
; RV32I-NEXT:    mv a0, a1
; RV32I-NEXT:    ret
  %1 = getelementptr i16, ptr %a, i32 2
  %2 = load i16, ptr %1
  %3 = sext i16 %2 to i32
  ; the unused load will produce an anyext for selection
  %4 = load volatile i16, ptr %a
  ret i32 %3
}

define dso_local i32 @lw(ptr %a) nounwind {
; RV32I-LABEL: lw:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lw a1, 12(a0)
; RV32I-NEXT:    lw zero, 0(a0)
; RV32I-NEXT:    mv a0, a1
; RV32I-NEXT:    ret
  %1 = getelementptr i32, ptr %a, i32 3
  %2 = load i32, ptr %1
  %3 = load volatile i32, ptr %a
  ret i32 %2
}

define dso_local i32 @lbu(ptr %a) nounwind {
; RV32I-LABEL: lbu:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lbu a1, 4(a0)
; RV32I-NEXT:    lbu a0, 0(a0)
; RV32I-NEXT:    add a0, a1, a0
; RV32I-NEXT:    ret
  %1 = getelementptr i8, ptr %a, i32 4
  %2 = load i8, ptr %1
  %3 = zext i8 %2 to i32
  %4 = load volatile i8, ptr %a
  %5 = zext i8 %4 to i32
  %6 = add i32 %3, %5
  ret i32 %6
}

define dso_local i32 @lhu(ptr %a) nounwind {
; RV32I-LABEL: lhu:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lhu a1, 10(a0)
; RV32I-NEXT:    lhu a0, 0(a0)
; RV32I-NEXT:    add a0, a1, a0
; RV32I-NEXT:    ret
  %1 = getelementptr i16, ptr %a, i32 5
  %2 = load i16, ptr %1
  %3 = zext i16 %2 to i32
  %4 = load volatile i16, ptr %a
  %5 = zext i16 %4 to i32
  %6 = add i32 %3, %5
  ret i32 %6
}

; Check indexed and unindexed stores

define dso_local void @sb(ptr %a, i8 %b) nounwind {
; RV32I-LABEL: sb:
; RV32I:       # %bb.0:
; RV32I-NEXT:    sb a1, 0(a0)
; RV32I-NEXT:    sb a1, 6(a0)
; RV32I-NEXT:    ret
  store i8 %b, ptr %a
  %1 = getelementptr i8, ptr %a, i32 6
  store i8 %b, ptr %1
  ret void
}

define dso_local void @sh(ptr %a, i16 %b) nounwind {
; RV32I-LABEL: sh:
; RV32I:       # %bb.0:
; RV32I-NEXT:    sh a1, 0(a0)
; RV32I-NEXT:    sh a1, 14(a0)
; RV32I-NEXT:    ret
  store i16 %b, ptr %a
  %1 = getelementptr i16, ptr %a, i32 7
  store i16 %b, ptr %1
  ret void
}

define dso_local void @sw(ptr %a, i32 %b) nounwind {
; RV32I-LABEL: sw:
; RV32I:       # %bb.0:
; RV32I-NEXT:    sw a1, 0(a0)
; RV32I-NEXT:    sw a1, 32(a0)
; RV32I-NEXT:    ret
  store i32 %b, ptr %a
  %1 = getelementptr i32, ptr %a, i32 8
  store i32 %b, ptr %1
  ret void
}

; Check load and store to an i1 location
define dso_local i32 @load_sext_zext_anyext_i1(ptr %a) nounwind {
; RV32I-LABEL: load_sext_zext_anyext_i1:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lbu a1, 1(a0)
; RV32I-NEXT:    lbu a2, 2(a0)
; RV32I-NEXT:    lbu zero, 0(a0)
; RV32I-NEXT:    sub a0, a2, a1
; RV32I-NEXT:    ret
  ; sextload i1
  %1 = getelementptr i1, ptr %a, i32 1
  %2 = load i1, ptr %1
  %3 = sext i1 %2 to i32
  ; zextload i1
  %4 = getelementptr i1, ptr %a, i32 2
  %5 = load i1, ptr %4
  %6 = zext i1 %5 to i32
  %7 = add i32 %3, %6
  ; extload i1 (anyext). Produced as the load is unused.
  %8 = load volatile i1, ptr %a
  ret i32 %7
}

define dso_local i16 @load_sext_zext_anyext_i1_i16(ptr %a) nounwind {
; RV32I-LABEL: load_sext_zext_anyext_i1_i16:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lbu a1, 1(a0)
; RV32I-NEXT:    lbu a2, 2(a0)
; RV32I-NEXT:    lbu zero, 0(a0)
; RV32I-NEXT:    sub a0, a2, a1
; RV32I-NEXT:    ret
  ; sextload i1
  %1 = getelementptr i1, ptr %a, i32 1
  %2 = load i1, ptr %1
  %3 = sext i1 %2 to i16
  ; zextload i1
  %4 = getelementptr i1, ptr %a, i32 2
  %5 = load i1, ptr %4
  %6 = zext i1 %5 to i16
  %7 = add i16 %3, %6
  ; extload i1 (anyext). Produced as the load is unused.
  %8 = load volatile i1, ptr %a
  ret i16 %7
}

; Check load and store to a global
@G = dso_local global i32 0

define dso_local i32 @lw_sw_global(i32 %a) nounwind {
; RV32I-LABEL: lw_sw_global:
; RV32I:       # %bb.0:
; RV32I-NEXT:    mv a1, a0
; RV32I-NEXT:    lui a2, %hi(G)
; RV32I-NEXT:    addi a2, a2, %lo(G)
; RV32I-NEXT:    lw a0, 0(a2)
; RV32I-NEXT:    sw a1, 0(a2)
; RV32I-NEXT:    lw zero, 36(a2)
; RV32I-NEXT:    sw a1, 36(a2)
; RV32I-NEXT:    ret
  %1 = load volatile i32, ptr @G
  store i32 %a, ptr @G
  %2 = getelementptr i32, ptr @G, i32 9
  %3 = load volatile i32, ptr %2
  store i32 %a, ptr %2
  ret i32 %1
}

; Ensure that 1 is added to the high 20 bits if bit 11 of the low part is 1
define dso_local i32 @lw_sw_constant(i32 %a) nounwind {
; RV32I-LABEL: lw_sw_constant:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a3, 912092
; RV32I-NEXT:    lw a1, -273(a3)
; RV32I-NEXT:    mv a2, a0
; RV32I-NEXT:    mv a0, a1
; RV32I-NEXT:    sw a2, -273(a3)
; RV32I-NEXT:    ret
  %1 = inttoptr i32 3735928559 to ptr
  %2 = load volatile i32, ptr %1
  store i32 %a, ptr %1
  ret i32 %2
}

define i32 @lw_near_local(ptr %a)  {
; RV32I-LABEL: lw_near_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    addi a0, a0, 2047
; RV32I-NEXT:    lw a0, 5(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 513
  %2 = load volatile i32, ptr %1
  ret i32 %2
}

define void @st_near_local(ptr %a, i32 %b)  {
; RV32I-LABEL: st_near_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    addi a0, a0, 2047
; RV32I-NEXT:    sw a1, 5(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 513
  store i32 %b, ptr %1
  ret void
}

define i32 @lw_sw_near_local(ptr %a, i32 %b)  {
; RV32I-LABEL: lw_sw_near_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    addi a2, a0, 2047
; RV32I-NEXT:    lw a0, 5(a2)
; RV32I-NEXT:    sw a1, 5(a2)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 513
  %2 = load volatile i32, ptr %1
  store i32 %b, ptr %1
  ret i32 %2
}

define i32 @lw_far_local(ptr %a)  {
; RV32I-LABEL: lw_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a1, 4
; RV32I-NEXT:    add a0, a0, a1
; RV32I-NEXT:    lw a0, -4(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 4095
  %2 = load volatile i32, ptr %1
  ret i32 %2
}

define void @st_far_local(ptr %a, i32 %b)  {
; RV32I-LABEL: st_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a2, 4
; RV32I-NEXT:    add a0, a0, a2
; RV32I-NEXT:    sw a1, -4(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 4095
  store i32 %b, ptr %1
  ret void
}

define i32 @lw_sw_far_local(ptr %a, i32 %b)  {
; RV32I-LABEL: lw_sw_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a2, 4
; RV32I-NEXT:    add a2, a0, a2
; RV32I-NEXT:    lw a0, -4(a2)
; RV32I-NEXT:    sw a1, -4(a2)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i64 4095
  %2 = load volatile i32, ptr %1
  store i32 %b, ptr %1
  ret i32 %2
}

define i32 @lw_really_far_local(ptr %a)  {
; RV32I-LABEL: lw_really_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a1, 524288
; RV32I-NEXT:    add a0, a0, a1
; RV32I-NEXT:    lw a0, -2048(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i32 536870400
  %2 = load volatile i32, ptr %1
  ret i32 %2
}

define void @st_really_far_local(ptr %a, i32 %b)  {
; RV32I-LABEL: st_really_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a2, 524288
; RV32I-NEXT:    add a0, a0, a2
; RV32I-NEXT:    sw a1, -2048(a0)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i32 536870400
  store i32 %b, ptr %1
  ret void
}

define i32 @lw_sw_really_far_local(ptr %a, i32 %b)  {
; RV32I-LABEL: lw_sw_really_far_local:
; RV32I:       # %bb.0:
; RV32I-NEXT:    lui a2, 524288
; RV32I-NEXT:    add a2, a0, a2
; RV32I-NEXT:    lw a0, -2048(a2)
; RV32I-NEXT:    sw a1, -2048(a2)
; RV32I-NEXT:    ret
  %1 = getelementptr inbounds i32, ptr %a, i32 536870400
  %2 = load volatile i32, ptr %1
  store i32 %b, ptr %1
  ret i32 %2
}

%struct.quux = type { i32, [0 x i8] }

; Make sure we don't remove the addi and fold the C from
; (add (addi FrameIndex, C), X) into the store address.
; FrameIndex cannot be the operand of an ADD. We must keep the ADDI.
define void @addi_fold_crash(i32 %arg) nounwind {
; RV32I-LABEL: addi_fold_crash:
; RV32I:       # %bb.0: # %bb
; RV32I-NEXT:    addi sp, sp, -16
; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT:    addi a1, sp, 12
; RV32I-NEXT:    add a0, a1, a0
; RV32I-NEXT:    sb zero, 0(a0)
; RV32I-NEXT:    mv a0, a1
; RV32I-NEXT:    call snork
; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT:    addi sp, sp, 16
; RV32I-NEXT:    ret
bb:
  %tmp = alloca %struct.quux, align 4
  %tmp1 = getelementptr inbounds %struct.quux, ptr %tmp, i32 0, i32 1
  %tmp2 = getelementptr inbounds %struct.quux, ptr %tmp, i32 0, i32 1, i32 %arg
  store i8 0, ptr %tmp2, align 1
  call void @snork(ptr %tmp1)
  ret void
}

declare void @snork(ptr)

define i8 @disjoint_or_lb(ptr %a, i32 %off) nounwind {
; RV32I-LABEL: disjoint_or_lb:
; RV32I:       # %bb.0:
; RV32I-NEXT:    add a0, a0, a1
; RV32I-NEXT:    lbu a0, 3(a0)
; RV32I-NEXT:    ret
  %b = or disjoint i32 %off, 3
  %1 = getelementptr i8, ptr %a, i32 %b
  %2 = load i8, ptr %1
  ret i8 %2
}

define i32 @disjoint_or_lw(ptr %a, i32 %off) nounwind {
; RV32I-LABEL: disjoint_or_lw:
; RV32I:       # %bb.0:
; RV32I-NEXT:    slli a1, a1, 2
; RV32I-NEXT:    add a0, a0, a1
; RV32I-NEXT:    lw a0, 12(a0)
; RV32I-NEXT:    ret
  %b = or disjoint i32 %off, 3
  %1 = getelementptr i32, ptr %a, i32 %b
  %2 = load i32, ptr %1
  ret i32 %2
}