# RUN: llc -mtriple=aarch64-none-linux-gnu -run-pass=prologepilog %s -o - | FileCheck %s
#
# Test allocation and deallocation of SVE objects on the stack,
# as well as using a combination of scalable and non-scalable
# offsets to access the SVE on the stack.
#
# SVE objects are allocated below the (scalar) callee saves,
# and above spills/locals and the alignment gap, e.g.
#
#     +-------------+
#     | stack arg   |
#     +-------------+ <- SP before call
#     | Callee Saves|
#     | Frame record|       (if available)
#     |-------------| <- FP (if available)
#     |  SVE area   |
#     +-------------+
#     |/////////////| alignment gap.
#     |     :       |
#     | Stack objs  |
#     |     :       |
#     +-------------+ <- SP after call and frame-setup
#
--- |

  define void @test_allocate_sve() nounwind { entry: unreachable }
  define void @test_allocate_sve_gpr_callee_saves() nounwind { entry: unreachable }
  define void @test_allocate_sve_gpr_realigned() nounwind { entry: unreachable }
  define void @test_address_sve() nounwind { entry: unreachable }
  define void @test_address_sve_fp() nounwind { entry: unreachable }
  define void @test_stack_arg_sve() nounwind { entry: unreachable }
  define void @test_address_sve_out_of_range() nounwind { entry: unreachable }

...
# +----------+
# |scratchreg|  // x29 is used as scratch reg.
# +----------+
# | %fixed-  |  // scalable SVE object of n * 18 bytes, aligned to 16 bytes,
# |  stack.0 |  // to be materialized with 2*ADDVL (<=> 2 * n * 16bytes)
# +----------+
# | %stack.0 |  // not scalable
# +----------+ <- SP

# CHECK-LABEL: name: test_allocate_sve
# CHECK:       stackSize: 32

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STRXpre killed $[[SCRATCH:[a-z0-9]+]], $sp, -16
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -2
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 16, 0

# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 2
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 16, 0
# CHECK-NEXT: $sp, $[[SCRATCH]] = frame-destroy LDRXpost $sp, 16
# CHECK-NEXT: RET_ReallyLR
name:            test_allocate_sve
fixedStack:
  - { id: 0, stack-id: sve-vec, size: 18, alignment: 2, offset: -18 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 8 }
body:             |
  bb.0.entry:
    RET_ReallyLR
---
...
# +----------+
# | x20, x21 |  // callee saves
# |scratchreg|  // x29 is used as scratch reg.
# +----------+
# | %fixed-  |  // scalable objects
# |  stack.0 |
# +----------+
# | %stack.0 |  // not scalable
# +----------+ <- SP

# CHECK-LABEL: name: test_allocate_sve_gpr_callee_saves
# CHECK:       stackSize: 48

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STRXpre killed $[[SCRATCH:[a-z0-9]+]], $sp, -32
# CHECK-NEXT: frame-setup STPXi killed $x21, killed $x20, $sp, 2
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -2
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 16, 0
# CHECK-NEXT: $x20 = IMPLICIT_DEF
# CHECK-NEXT: $x21 = IMPLICIT_DEF
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 2
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 16, 0
# CHECK-NEXT: $x21, $x20 = frame-destroy LDPXi $sp, 2
# CHECK-NEXT: $sp, $[[SCRATCH]] = frame-destroy LDRXpost $sp, 32
# CHECK-NEXT: RET_ReallyLR
name:            test_allocate_sve_gpr_callee_saves
fixedStack:
  - { id: 0, stack-id: sve-vec, size: 18, alignment: 2, offset: -18 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 8 }
body:             |
  bb.0.entry:
    $x20 = IMPLICIT_DEF
    $x21 = IMPLICIT_DEF
    RET_ReallyLR
---
...
# +----------+
# |  lr, fp  |  // frame record
# +----------+ <- FP
# | %fixed-  |  // scalable objects
# |  stack.0 |
# +----------+
# |//////////|  // alignment gap
# | %stack.0 |  // not scalable
# +----------+ <- SP
# CHECK-LABEL: name: test_allocate_sve_gpr_realigned
# CHECK:       stackSize: 32

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2
# CHECK-NEXT: $fp = frame-setup ADDXri $sp, 0, 0
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -2
# CHECK-NEXT: $[[TMP:x[0-9]+]] = frame-setup SUBXri $sp, 16, 0
# CHECK-NEXT: $sp = ANDXri killed $[[TMP]]
# CHECK-NEXT: $sp = frame-destroy ADDXri $fp, 0, 0
# CHECK-NEXT: $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2
# CHECK-NEXT: RET_ReallyLR
name:            test_allocate_sve_gpr_realigned
fixedStack:
  - { id: 0, stack-id: sve-vec, size: 18, alignment: 2, offset: -18 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 32 }
body:             |
  bb.0.entry:
    RET_ReallyLR
---
...
# +----------+
# | x20, x21 |  // callee saves
# +----------+
# | %stack.0 |  // scalable @ SP + 16b + 32 scalable bytes
# | %stack.1 |  // scalable @ SP + 16b + 16 scalable bytes
# | %stack.2 |  // scalable @ SP + 16b + 14 scalable bytes
# +----------+
# | %stack.0 |  // not scalable
# +----------+ <- SP

# CHECK-LABEL: name: test_address_sve
# CHECK:       stackSize: 32

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STRXpre killed $[[SCRATCH:[a-z0-9]+]], $sp, -16
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -3
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 16, 0

# CHECK-NEXT: $[[TMP:x[0-9]+]] = ADDXri $sp, 16
# CHECK-NEXT: STR_ZXI $z0, killed $[[TMP]], 2
# CHECK-NEXT: $[[TMP:x[0-9]+]] = ADDXri $sp, 16
# CHECK-NEXT: STR_ZXI $z1, killed $[[TMP]], 1
# CHECK-NEXT: $[[TMP:x[0-9]+]] = ADDXri $sp, 16
# CHECK-NEXT: STR_PXI $p0, killed $[[TMP]], 7

# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 3
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 16, 0
# CHECK-NEXT: $sp, $[[SCRATCH]] = frame-destroy LDRXpost $sp, 16
# CHECK-NEXT: RET_ReallyLR
name:            test_address_sve
frameInfo:
  maxAlignment:  16
fixedStack:
  - { id: 0, stack-id: sve-vec, size: 16, alignment: 8, offset: -16 }
  - { id: 1, stack-id: sve-vec, size: 16, alignment: 8, offset: -32 }
  - { id: 2, stack-id: sve-vec, size:  2, alignment: 2, offset: -34 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 8 }
body:             |
  bb.0.entry:
    liveins: $z0, $z1, $p0

    STR_ZXI $z0, %fixed-stack.0, 0
    STR_ZXI $z1, %fixed-stack.1, 0
    STR_PXI $p0, %fixed-stack.2, 0

    RET_ReallyLR
---
...
# +-----------+
# | x20, x21  |  // callee saves
# |  lr, fp   |  // frame record
# +-----------+ <- FP
# | %fstack.0 |  // scalable @ FP - 16 scalable bytes
# | %fstack.1 |  // scalable @ FP - 32 scalable bytes
# | %fstack.2 |  // scalable @ FP - 34 scalable bytes
# +-----------+
# | %stack.0  |  // not scalable
# +-----------+ <- SP

# CHECK-LABEL: name: test_address_sve_fp
# CHECK:       stackSize: 32

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2
# CHECK-NEXT: $fp = frame-setup ADDXri $sp, 0, 0
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -3
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 16, 0

# CHECK-NEXT: STR_ZXI $z0, $fp, -1
# CHECK-NEXT: STR_ZXI $z1, $fp, -2
# CHECK-NEXT: STR_PXI $p0, $fp, -17

# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 3
# CHECK:      $sp = frame-destroy ADDXri $sp, 16, 0
# CHECK-NEXT: $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2
# CHECK-NEXT: RET_ReallyLR
name:            test_address_sve_fp
frameInfo:
  maxAlignment:  16
  isFrameAddressTaken: true
fixedStack:
  - { id: 0, stack-id: sve-vec, size: 16, alignment: 8, offset: -16 }
  - { id: 1, stack-id: sve-vec, size: 16, alignment: 8, offset: -32 }
  - { id: 2, stack-id: sve-vec, size:  2, alignment: 2, offset: -34 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 8 }
body:             |
  bb.0.entry:
    liveins: $z0, $z1, $p0

    STR_ZXI $z0, %fixed-stack.0, 0
    STR_ZXI $z1, %fixed-stack.1, 0
    STR_PXI $p0, %fixed-stack.2, 0

    RET_ReallyLR
---
...
# +-----------+
# | %fstack.1 |  // stack arg @ SP + 16 scalable bytes + 32 bytes.
# +-----------+
# |callee save|  // register saved as scratch reg.
# +-----------+
# | %fstack.1 |  // vector of 16 scalable bytes
# +---------- +
# | %stack.0  |  // not scalable, 16 bytes
# +-----------+ <- SP
# CHECK-LABEL: name: test_stack_arg_sve
# CHECK:       stackSize: 32

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STRXpre killed $[[SCRATCH:[a-z0-9]+]], $sp, -16
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -1
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 16, 0

# CHECK:      $[[TMP:x[0-9]+]] = ADDVL_XXI $sp, 1
# CHECK-NEXT: $x0 = LDRXui killed $[[TMP]], 4

# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 1
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 16, 0
# CHECK-NEXT: $sp, $[[SCRATCH]] = frame-destroy LDRXpost $sp, 16
# CHECK-NEXT: RET_ReallyLR
name:             test_stack_arg_sve
fixedStack:
  - { id: 0, stack-id: default, size: 16, alignment: 16, offset: 0 }
  - { id: 1, stack-id: sve-vec, size: 16, alignment: 16, offset: -16 }
stack:
  - { id: 0, stack-id: default, size: 16, alignment: 16 }
body:             |
  bb.0.entry:
    liveins: $x0

    $x0 = LDRXui %fixed-stack.0, 0
    RET_ReallyLR
---
...
# Test that the address to access an SVE data vector at an offset that
# does not fit its immediate, is correctly materialized.
# +----------+
# |calleesave|  // register saved as scratch reg.
# +----------+
# | %stack.0 |  // one SVE data object @ SP + 256 scalable bytes.
# |::::::::::|
# |:        :|
# |:%stack.1:|  // Large object
# |:        :|
# |::::::::::|
# +----------+ <- SP
# CHECK-LABEL: name: test_address_sve_out_of_range
# CHECK:       stackSize: 16

# CHECK:      bb.0.entry:
# CHECK-NEXT: $sp = frame-setup STRXpre killed $[[SCRATCH:[a-z0-9]+]], $sp, -16
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -32
# CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -1

# CHECK-NEXT: $[[TMP2:x[0-9]+]] = ADDVL_XXI $sp, 1
# CHECK-NEXT: STR_ZXI $z0, killed $[[TMP2]], 255

# CHECK-NEXT: $[[TMP2:x[0-9]+]] = ADDPL_XXI $sp, 1
# CHECK-NEXT: STR_PXI $p0, killed $[[TMP2]], 255

# CHECK:      $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 31
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 9
# CHECK-NEXT: $sp, $[[SCRATCH]] = frame-destroy LDRXpost $sp, 16
# CHECK-NEXT: RET_ReallyLR
name:            test_address_sve_out_of_range
frameInfo:
  maxAlignment:  16
fixedStack:
  - { id: 0, stack-id: sve-vec, size:   16, alignment: 16, offset: -16 }
  - { id: 1, stack-id: sve-vec, size: 3584, alignment: 16, offset: -3600 }
  - { id: 2, stack-id: sve-vec, size:  512, alignment: 16, offset: -4112 }

body:             |
  bb.0.entry:
    liveins: $z0, $p0

    STR_ZXI $z0, %fixed-stack.0, 0
    STR_PXI $p0, %fixed-stack.1, 0

    RET_ReallyLR
---