//==- BuiltinsAMDGPU.def - AMDGPU Builtin function database ------*- C++ -*-==//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the AMDGPU-specific builtin function database. Users of
// this file must define the BUILTIN macro to make use of this information.
//
// Note: (unsigned) long int type should be avoided in builtin definitions
// since it has different size on Linux (64 bit) and Windows (32 bit).
// (unsigned) long long int type should also be avoided, which is 64 bit for
// C/C++/HIP but is 128 bit for OpenCL. Use `W` as width modifier in builtin
// definitions since it is fixed for 64 bit.
//===----------------------------------------------------------------------===//

// The format of this database matches clang/Basic/Builtins.def.

#if defined(BUILTIN) && !defined(TARGET_BUILTIN)
#   define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE) BUILTIN(ID, TYPE, ATTRS)
#endif
//===----------------------------------------------------------------------===//
// SI+ only builtins.
//===----------------------------------------------------------------------===//

BUILTIN(__builtin_amdgcn_dispatch_ptr, "v*4", "nc")
BUILTIN(__builtin_amdgcn_kernarg_segment_ptr, "v*4", "nc")
BUILTIN(__builtin_amdgcn_implicitarg_ptr, "v*4", "nc")
BUILTIN(__builtin_amdgcn_queue_ptr, "v*4", "nc")

BUILTIN(__builtin_amdgcn_workgroup_id_x, "Ui", "nc")
BUILTIN(__builtin_amdgcn_workgroup_id_y, "Ui", "nc")
BUILTIN(__builtin_amdgcn_workgroup_id_z, "Ui", "nc")

BUILTIN(__builtin_amdgcn_workitem_id_x, "Ui", "nc")
BUILTIN(__builtin_amdgcn_workitem_id_y, "Ui", "nc")
BUILTIN(__builtin_amdgcn_workitem_id_z, "Ui", "nc")

BUILTIN(__builtin_amdgcn_workgroup_size_x, "Us", "nc")
BUILTIN(__builtin_amdgcn_workgroup_size_y, "Us", "nc")
BUILTIN(__builtin_amdgcn_workgroup_size_z, "Us", "nc")

BUILTIN(__builtin_amdgcn_grid_size_x, "Ui", "nc")
BUILTIN(__builtin_amdgcn_grid_size_y, "Ui", "nc")
BUILTIN(__builtin_amdgcn_grid_size_z, "Ui", "nc")

BUILTIN(__builtin_amdgcn_mbcnt_hi, "UiUiUi", "nc")
BUILTIN(__builtin_amdgcn_mbcnt_lo, "UiUiUi", "nc")

TARGET_BUILTIN(__builtin_amdgcn_s_memtime, "WUi", "n", "s-memtime-inst")

//===----------------------------------------------------------------------===//
// Instruction builtins.
//===----------------------------------------------------------------------===//
BUILTIN(__builtin_amdgcn_s_getreg, "UiIi", "n")
BUILTIN(__builtin_amdgcn_s_setreg, "vIiUi", "n")
BUILTIN(__builtin_amdgcn_s_getpc, "WUi", "n")
BUILTIN(__builtin_amdgcn_s_waitcnt, "vIi", "n")
BUILTIN(__builtin_amdgcn_s_sendmsg, "vIiUi", "n")
BUILTIN(__builtin_amdgcn_s_sendmsghalt, "vIiUi", "n")
BUILTIN(__builtin_amdgcn_s_barrier, "v", "n")
BUILTIN(__builtin_amdgcn_wave_barrier, "v", "n")
BUILTIN(__builtin_amdgcn_s_dcache_inv, "v", "n")
BUILTIN(__builtin_amdgcn_buffer_wbinvl1, "v", "n")
BUILTIN(__builtin_amdgcn_ds_gws_init, "vUiUi", "n")
BUILTIN(__builtin_amdgcn_ds_gws_barrier, "vUiUi", "n")
BUILTIN(__builtin_amdgcn_ds_gws_sema_v, "vUi", "n")
BUILTIN(__builtin_amdgcn_ds_gws_sema_br, "vUiUi", "n")
BUILTIN(__builtin_amdgcn_ds_gws_sema_p, "vUi", "n")
BUILTIN(__builtin_amdgcn_fence, "vUicC*", "n")
BUILTIN(__builtin_amdgcn_groupstaticsize, "Ui", "n")

BUILTIN(__builtin_amdgcn_atomic_inc32, "UZiUZiD*UZiUicC*", "n")
BUILTIN(__builtin_amdgcn_atomic_inc64, "UWiUWiD*UWiUicC*", "n")

BUILTIN(__builtin_amdgcn_atomic_dec32, "UZiUZiD*UZiUicC*", "n")
BUILTIN(__builtin_amdgcn_atomic_dec64, "UWiUWiD*UWiUicC*", "n")

// FIXME: Need to disallow constant address space.
BUILTIN(__builtin_amdgcn_div_scale, "dddbb*", "n")
BUILTIN(__builtin_amdgcn_div_scalef, "fffbb*", "n")
BUILTIN(__builtin_amdgcn_div_fmas, "ddddb", "nc")
BUILTIN(__builtin_amdgcn_div_fmasf, "ffffb", "nc")
BUILTIN(__builtin_amdgcn_div_fixup, "dddd", "nc")
BUILTIN(__builtin_amdgcn_div_fixupf, "ffff", "nc")
BUILTIN(__builtin_amdgcn_trig_preop, "ddi", "nc")
BUILTIN(__builtin_amdgcn_trig_preopf, "ffi", "nc")
BUILTIN(__builtin_amdgcn_rcp, "dd", "nc")
BUILTIN(__builtin_amdgcn_rcpf, "ff", "nc")
BUILTIN(__builtin_amdgcn_sqrt, "dd", "nc")
BUILTIN(__builtin_amdgcn_sqrtf, "ff", "nc")
BUILTIN(__builtin_amdgcn_rsq, "dd", "nc")
BUILTIN(__builtin_amdgcn_rsqf, "ff", "nc")
BUILTIN(__builtin_amdgcn_rsq_clamp, "dd", "nc")
BUILTIN(__builtin_amdgcn_rsq_clampf, "ff", "nc")
BUILTIN(__builtin_amdgcn_sinf, "ff", "nc")
BUILTIN(__builtin_amdgcn_cosf, "ff", "nc")
BUILTIN(__builtin_amdgcn_log_clampf, "ff", "nc")
BUILTIN(__builtin_amdgcn_ldexp, "ddi", "nc")
BUILTIN(__builtin_amdgcn_ldexpf, "ffi", "nc")
BUILTIN(__builtin_amdgcn_frexp_mant, "dd", "nc")
BUILTIN(__builtin_amdgcn_frexp_mantf, "ff", "nc")
BUILTIN(__builtin_amdgcn_frexp_exp, "id", "nc")
BUILTIN(__builtin_amdgcn_frexp_expf, "if", "nc")
BUILTIN(__builtin_amdgcn_fract, "dd", "nc")
BUILTIN(__builtin_amdgcn_fractf, "ff", "nc")
BUILTIN(__builtin_amdgcn_lerp, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_class, "bdi", "nc")
BUILTIN(__builtin_amdgcn_classf, "bfi", "nc")
BUILTIN(__builtin_amdgcn_cubeid, "ffff", "nc")
BUILTIN(__builtin_amdgcn_cubesc, "ffff", "nc")
BUILTIN(__builtin_amdgcn_cubetc, "ffff", "nc")
BUILTIN(__builtin_amdgcn_cubema, "ffff", "nc")
BUILTIN(__builtin_amdgcn_s_sleep, "vIi", "n")
BUILTIN(__builtin_amdgcn_s_incperflevel, "vIi", "n")
BUILTIN(__builtin_amdgcn_s_decperflevel, "vIi", "n")
BUILTIN(__builtin_amdgcn_uicmp, "WUiUiUiIi", "nc")
BUILTIN(__builtin_amdgcn_uicmpl, "WUiWUiWUiIi", "nc")
BUILTIN(__builtin_amdgcn_sicmp, "WUiiiIi", "nc")
BUILTIN(__builtin_amdgcn_sicmpl, "WUiWiWiIi", "nc")
BUILTIN(__builtin_amdgcn_fcmp, "WUiddIi", "nc")
BUILTIN(__builtin_amdgcn_fcmpf, "WUiffIi", "nc")
BUILTIN(__builtin_amdgcn_ds_swizzle, "iiIi", "nc")
BUILTIN(__builtin_amdgcn_ds_permute, "iii", "nc")
BUILTIN(__builtin_amdgcn_ds_bpermute, "iii", "nc")
BUILTIN(__builtin_amdgcn_readfirstlane, "ii", "nc")
BUILTIN(__builtin_amdgcn_readlane, "iii", "nc")
BUILTIN(__builtin_amdgcn_fmed3f, "ffff", "nc")
BUILTIN(__builtin_amdgcn_ds_faddf, "ff*3fIiIiIb", "n")
BUILTIN(__builtin_amdgcn_ds_fminf, "ff*3fIiIiIb", "n")
BUILTIN(__builtin_amdgcn_ds_fmaxf, "ff*3fIiIiIb", "n")
BUILTIN(__builtin_amdgcn_ds_append, "ii*3", "n")
BUILTIN(__builtin_amdgcn_ds_consume, "ii*3", "n")
BUILTIN(__builtin_amdgcn_alignbit, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_alignbyte, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_ubfe, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_sbfe, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_cvt_pkrtz, "E2hff", "nc")
BUILTIN(__builtin_amdgcn_cvt_pknorm_i16, "E2sff", "nc")
BUILTIN(__builtin_amdgcn_cvt_pknorm_u16, "E2Usff", "nc")
BUILTIN(__builtin_amdgcn_cvt_pk_i16, "E2sii", "nc")
BUILTIN(__builtin_amdgcn_cvt_pk_u16, "E2UsUiUi", "nc")
BUILTIN(__builtin_amdgcn_cvt_pk_u8_f32, "UifUiUi", "nc")
BUILTIN(__builtin_amdgcn_sad_u8, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_msad_u8, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_sad_hi_u8, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_sad_u16, "UiUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_qsad_pk_u16_u8, "WUiWUiUiWUi", "nc")
BUILTIN(__builtin_amdgcn_mqsad_pk_u16_u8, "WUiWUiUiWUi", "nc")
BUILTIN(__builtin_amdgcn_mqsad_u32_u8, "V4UiWUiUiV4Ui", "nc")

//===----------------------------------------------------------------------===//
// CI+ only builtins.
//===----------------------------------------------------------------------===//
TARGET_BUILTIN(__builtin_amdgcn_s_dcache_inv_vol, "v", "n", "ci-insts")
TARGET_BUILTIN(__builtin_amdgcn_buffer_wbinvl1_vol, "v", "n", "ci-insts")
TARGET_BUILTIN(__builtin_amdgcn_ds_gws_sema_release_all, "vUi", "n", "ci-insts")
TARGET_BUILTIN(__builtin_amdgcn_is_shared, "bvC*0", "nc", "flat-address-space")
TARGET_BUILTIN(__builtin_amdgcn_is_private, "bvC*0", "nc", "flat-address-space")

//===----------------------------------------------------------------------===//
// Interpolation builtins.
//===----------------------------------------------------------------------===//
BUILTIN(__builtin_amdgcn_interp_p1_f16, "ffUiUibUi", "nc")
BUILTIN(__builtin_amdgcn_interp_p2_f16, "hffUiUibUi", "nc")
BUILTIN(__builtin_amdgcn_interp_p1, "ffUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_interp_p2, "fffUiUiUi", "nc")
BUILTIN(__builtin_amdgcn_interp_mov, "fUiUiUiUi", "nc")

//===----------------------------------------------------------------------===//
// VI+ only builtins.
//===----------------------------------------------------------------------===//

TARGET_BUILTIN(__builtin_amdgcn_div_fixuph, "hhhh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_rcph, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_sqrth, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_rsqh, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_sinh, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_cosh, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_ldexph, "hhi", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_frexp_manth, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_frexp_exph, "sh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_fracth, "hh", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_classh, "bhi", "nc", "16-bit-insts")
TARGET_BUILTIN(__builtin_amdgcn_s_memrealtime, "WUi", "n", "s-memrealtime")
TARGET_BUILTIN(__builtin_amdgcn_mov_dpp, "iiIiIiIiIb", "nc", "dpp")
TARGET_BUILTIN(__builtin_amdgcn_update_dpp, "iiiIiIiIiIb", "nc", "dpp")
TARGET_BUILTIN(__builtin_amdgcn_s_dcache_wb, "v", "n", "gfx8-insts")
TARGET_BUILTIN(__builtin_amdgcn_perm, "UiUiUiUi", "nc", "gfx8-insts")

//===----------------------------------------------------------------------===//
// GFX9+ only builtins.
//===----------------------------------------------------------------------===//

TARGET_BUILTIN(__builtin_amdgcn_fmed3h, "hhhh", "nc", "gfx9-insts")

TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fadd_f64, "dd*1d", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fadd_f32, "ff*1f", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fadd_v2f16, "V2hV2h*1V2h", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fmin_f64, "dd*1d", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fmax_f64, "dd*1d", "t", "gfx90a-insts")

TARGET_BUILTIN(__builtin_amdgcn_flat_atomic_fadd_f64, "dd*0d", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_flat_atomic_fmin_f64, "dd*0d", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_flat_atomic_fmax_f64, "dd*0d", "t", "gfx90a-insts")

TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_f64, "dd*3d", "t", "gfx90a-insts")
TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_f32, "ff*3f", "t", "gfx8-insts")

//===----------------------------------------------------------------------===//
// Deep learning builtins.
//===----------------------------------------------------------------------===//

TARGET_BUILTIN(__builtin_amdgcn_fdot2, "fV2hV2hfIb", "nc", "dot7-insts")
TARGET_BUILTIN(__builtin_amdgcn_sdot2, "SiV2SsV2SsSiIb", "nc", "dot2-insts")
TARGET_BUILTIN(__builtin_amdgcn_udot2, "UiV2UsV2UsUiIb", "nc", "dot2-insts")
TARGET_BUILTIN(__builtin_amdgcn_sdot4, "SiSiSiSiIb", "nc", "dot1-insts")
TARGET_BUILTIN(__builtin_amdgcn_udot4, "UiUiUiUiIb", "nc", "dot7-insts")
TARGET_BUILTIN(__builtin_amdgcn_sdot8, "SiSiSiSiIb", "nc", "dot1-insts")
TARGET_BUILTIN(__builtin_amdgcn_udot8, "UiUiUiUiIb", "nc", "dot7-insts")

//===----------------------------------------------------------------------===//
// GFX10+ only builtins.
//===----------------------------------------------------------------------===//
TARGET_BUILTIN(__builtin_amdgcn_permlane16, "UiUiUiUiUiIbIb", "nc", "gfx10-insts")
TARGET_BUILTIN(__builtin_amdgcn_permlanex16, "UiUiUiUiUiIbIb", "nc", "gfx10-insts")
TARGET_BUILTIN(__builtin_amdgcn_mov_dpp8, "UiUiIUi", "nc", "gfx10-insts")

//===----------------------------------------------------------------------===//
// Raytracing builtins.
// By default the 1st argument is i32 and the 4/5-th arguments are float4.
// Postfix l indicates the 1st argument is i64.
// Postfix h indicates the 4/5-th arguments are half4.
//===----------------------------------------------------------------------===//
TARGET_BUILTIN(__builtin_amdgcn_image_bvh_intersect_ray, "V4UiUifV4fV4fV4fV4Ui", "nc", "gfx10-insts")
TARGET_BUILTIN(__builtin_amdgcn_image_bvh_intersect_ray_h, "V4UiUifV4fV4hV4hV4Ui", "nc", "gfx10-insts")
TARGET_BUILTIN(__builtin_amdgcn_image_bvh_intersect_ray_l, "V4UiWUifV4fV4fV4fV4Ui", "nc", "gfx10-insts")
TARGET_BUILTIN(__builtin_amdgcn_image_bvh_intersect_ray_lh, "V4UiWUifV4fV4hV4hV4Ui", "nc", "gfx10-insts")

//===----------------------------------------------------------------------===//
// Special builtins.
//===----------------------------------------------------------------------===//
BUILTIN(__builtin_amdgcn_read_exec, "WUi", "nc")
BUILTIN(__builtin_amdgcn_read_exec_lo, "Ui", "nc")
BUILTIN(__builtin_amdgcn_read_exec_hi, "Ui", "nc")

BUILTIN(__builtin_amdgcn_endpgm, "v", "nr")

//===----------------------------------------------------------------------===//
// R600-NI only builtins.
//===----------------------------------------------------------------------===//

BUILTIN(__builtin_r600_implicitarg_ptr, "Uc*7", "nc")

BUILTIN(__builtin_r600_read_tgid_x, "Ui", "nc")
BUILTIN(__builtin_r600_read_tgid_y, "Ui", "nc")
BUILTIN(__builtin_r600_read_tgid_z, "Ui", "nc")

BUILTIN(__builtin_r600_read_tidig_x, "Ui", "nc")
BUILTIN(__builtin_r600_read_tidig_y, "Ui", "nc")
BUILTIN(__builtin_r600_read_tidig_z, "Ui", "nc")

BUILTIN(__builtin_r600_recipsqrt_ieee, "dd", "nc")
BUILTIN(__builtin_r600_recipsqrt_ieeef, "ff", "nc")

//===----------------------------------------------------------------------===//
// MFMA builtins.
//===----------------------------------------------------------------------===//

TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x1f32, "V32fffV32fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x1f32, "V16fffV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_4x4x1f32, "V4fffV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x2f32, "V16fffV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x4f32, "V4fffV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x4f16, "V32fV4hV4hV32fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x4f16, "V16fV4hV4hV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_4x4x4f16, "V4fV4hV4hV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x8f16, "V16fV4hV4hV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x16f16, "V4fV4hV4hV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_i32_32x32x4i8, "V32iiiV32iIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_i32_16x16x4i8, "V16iiiV16iIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_i32_4x4x4i8, "V4iiiV4iIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_i32_32x32x8i8, "V16iiiV16iIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_i32_16x16x16i8, "V4iiiV4iIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x2bf16, "V32fV2sV2sV32fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x2bf16, "V16fV2sV2sV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_4x4x2bf16, "V4fV2sV2sV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x4bf16, "V16fV2sV2sV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x8bf16, "V4fV2sV2sV4fIiIiIi", "nc", "mai-insts")

TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x4bf16_1k, "V32fV4sV4sV32fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x4bf16_1k, "V16fV4sV4sV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_4x4x4bf16_1k, "V4fV4sV4sV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x8bf16_1k, "V16fV4sV4sV16fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x16bf16_1k, "V4fV4sV4sV4fIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f64_16x16x4f64, "V4dddV4dIiIiIi", "nc", "mai-insts")
TARGET_BUILTIN(__builtin_amdgcn_mfma_f64_4x4x4f64, "ddddIiIiIi", "nc", "mai-insts")

#undef BUILTIN
#undef TARGET_BUILTIN