llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgpu_vs.ll

103 lines
4.8 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -stop-after=irtranslator %s -o - | FileCheck %s
define amdgpu_vs void @test_f32_inreg(float inreg %arg0) {
; CHECK-LABEL: name: test_f32_inreg
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
ret void
}
define amdgpu_vs void @test_f32(float %arg0) {
; CHECK-LABEL: name: test_f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
ret void
}
define amdgpu_vs void @test_ptr2_inreg(i32 addrspace(4)* inreg %arg0) {
; CHECK-LABEL: name: test_ptr2_inreg
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
; CHECK: [[MV:%[0-9]+]]:_(p4) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p4) :: (volatile load 4 from %ir.arg0, addrspace 4)
; CHECK: S_ENDPGM 0
%tmp0 = load volatile i32, i32 addrspace(4)* %arg0
ret void
}
define amdgpu_vs void @test_sgpr_alignment0(float inreg %arg0, i32 addrspace(4)* inreg %arg1) {
; CHECK-LABEL: name: test_sgpr_alignment0
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
; CHECK: [[MV:%[0-9]+]]:_(p4) = G_MERGE_VALUES [[COPY1]](s32), [[COPY2]](s32)
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p4) :: (volatile load 4 from %ir.arg1, addrspace 4)
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
; CHECK: S_ENDPGM 0
%tmp0 = load volatile i32, i32 addrspace(4)* %arg1
call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
ret void
}
define amdgpu_vs void @test_order(float inreg %arg0, float inreg %arg1, float %arg2, float %arg3) {
; CHECK-LABEL: name: test_order
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $vgpr0, $vgpr1
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY2]](s32), [[COPY]](s32), [[COPY3]](s32), [[COPY1]](s32), 0, 0
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg2, float %arg0, float %arg3, float %arg1, i1 false, i1 false) #0
ret void
}
define amdgpu_vs <{ i32, i32 }> @ret_struct(i32 inreg %arg0, i32 inreg %arg1) {
; CHECK-LABEL: name: ret_struct
; CHECK: bb.1.main_body:
; CHECK: liveins: $sgpr2, $sgpr3
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[COPY]](s32)
; CHECK: $sgpr0 = COPY [[INT]](s32)
; CHECK: [[INT1:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[COPY1]](s32)
; CHECK: $sgpr1 = COPY [[INT1]](s32)
; CHECK: SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
main_body:
%tmp0 = insertvalue <{ i32, i32 }> undef, i32 %arg0, 0
%tmp1 = insertvalue <{ i32, i32 }> %tmp0, i32 %arg1, 1
ret <{ i32, i32 }> %tmp1
}
define amdgpu_vs i32 @non_void_ret() {
; CHECK-LABEL: name: non_void_ret
; CHECK: bb.1 (%ir-block.0):
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[C]](s32)
; CHECK: $sgpr0 = COPY [[INT]](s32)
; CHECK: SI_RETURN_TO_EPILOG implicit $sgpr0
ret i32 0
}
declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
attributes #0 = { nounwind }