; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX11-SDAG %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX11-GISEL %s

declare i32 @llvm.amdgcn.permlane64(i32)
declare i32 @llvm.amdgcn.workitem.id.x()

define amdgpu_kernel void @test_s(i32 addrspace(1)* %out, i32 %src0) {
; GFX11-LABEL: test_s:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    s_clause 0x1
; GFX11-NEXT:    s_load_b32 s2, s[0:1], 0x2c
; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x24
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v0, s2
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX11-NEXT:    v_permlane64_b32 v0, v0
; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-NEXT:    s_endpgm
  %v = call i32 @llvm.amdgcn.permlane64(i32 %src0)
  store i32 %v, i32 addrspace(1)* %out
  ret void
}

define amdgpu_kernel void @test_i(i32 addrspace(1)* %out) {
; GFX11-LABEL: test_i:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x24
; GFX11-NEXT:    v_dual_mov_b32 v0, 0x63 :: v_dual_mov_b32 v1, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX11-NEXT:    v_permlane64_b32 v0, v0
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-NEXT:    s_endpgm
  %v = call i32 @llvm.amdgcn.permlane64(i32 99)
  store i32 %v, i32 addrspace(1)* %out
  ret void
}

define amdgpu_kernel void @test_v(i32 addrspace(1)* %out, i32 %src0) #1 {
; GFX11-SDAG-LABEL: test_v:
; GFX11-SDAG:       ; %bb.0:
; GFX11-SDAG-NEXT:    s_load_b64 s[0:1], s[0:1], 0x24
; GFX11-SDAG-NEXT:    v_mov_b32_e32 v1, 0
; GFX11-SDAG-NEXT:    v_permlane64_b32 v0, v0
; GFX11-SDAG-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-SDAG-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-SDAG-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-SDAG-NEXT:    s_endpgm
;
; GFX11-GISEL-LABEL: test_v:
; GFX11-GISEL:       ; %bb.0:
; GFX11-GISEL-NEXT:    s_load_b64 s[0:1], s[0:1], 0x24
; GFX11-GISEL-NEXT:    v_permlane64_b32 v0, v0
; GFX11-GISEL-NEXT:    v_mov_b32_e32 v1, 0
; GFX11-GISEL-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-GISEL-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-GISEL-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-GISEL-NEXT:    s_endpgm
  %tidx = call i32 @llvm.amdgcn.workitem.id.x()
  %v = call i32 @llvm.amdgcn.permlane64(i32 %tidx)
  store i32 %v, i32 addrspace(1)* %out
  ret void
}