ef6fa9e26d
This release contains the following cherry-picked revisions from upstream trunk: 226124 226151 226164 226165 226166 226407 226408 226409 226652 226905 226983 227084 227087 227089 227208 227209 227210 227211 227212 227213 227214 227269 227430 227482 227503 227519 227574 227822 227986 227987 227988 227989 227990 228037 228038 228039 228040 228188 228189 228190 228273 228372 228373 228374 228403 228765 228848 228918 229223 229225 229226 229227 229228 229230 229234 229235 229236 229238 229239 229413 229507 229680 229750 229751 229752 229911 230146 230147 230235 230253 230255 230469 230500 230564 230603 230657 230742 230748 230956 231219 231237 231245 231259 231280 231451 231563 231601 231658 231659 231662 231984 231986 232046 232085 232142 232176 232179 232189 232382 232386 232389 232425 232438 232443 232675 232786 232797 232943 232957 233075 233080 233351 233353 233409 233410 233508 233584 233819 233904 234629 234636 234891 234975 234977 235524 235641 235662 235931 236099 236306 236307 Please note that from 3.5.0 onwards, clang and llvm require C++11 support to build; see UPDATING for more information.
91 lines
6.4 KiB
TableGen
91 lines
6.4 KiB
TableGen
//===-- AMDGPUIntrinsics.td - Common intrinsics -*- tablegen -*-----------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file defines intrinsics that are used by all hw codegen targets.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let TargetPrefix = "AMDGPU", isTarget = 1 in {
|
|
|
|
def int_AMDGPU_store_output : Intrinsic<[], [llvm_float_ty, llvm_i32_ty], []>;
|
|
def int_AMDGPU_swizzle : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_abs : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_arl : Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cndlt : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_div : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_fract : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
|
def int_AMDGPU_clamp : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
|
|
|
|
// This is named backwards (instead of rsq_legacy) so we don't have
|
|
// to define it with the public builtins intrinsics. This is a
|
|
// workaround for how intrinsic names are parsed. If the name is
|
|
// llvm.AMDGPU.rsq.legacy, the parser assumes that you meant
|
|
// llvm.AMDGPU.rsq.{f32 | f64} and incorrectly mangled the name.
|
|
def int_AMDGPU_legacy_rsq : Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
|
|
|
|
def int_AMDGPU_dp4 : Intrinsic<[llvm_float_ty], [llvm_v4f32_ty, llvm_v4f32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_kill : Intrinsic<[], [llvm_float_ty], []>;
|
|
def int_AMDGPU_kilp : Intrinsic<[], [], []>;
|
|
def int_AMDGPU_lrp : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_mul : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_pow : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_seq : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_sgt : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_sge : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_sle : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_sne : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_mullit : Intrinsic<[llvm_v4f32_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_tex : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_txb : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_txf : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_txq : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_txd : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_v4f32_ty, llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_txl : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_trunc : Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_ddx : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_ddy : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_imax : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_imin : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_umax : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_umin : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_umul24 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_imul24 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_imad24 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_umad24 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cvt_f32_ubyte0 : Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cvt_f32_ubyte1 : Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cvt_f32_ubyte2 : Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cvt_f32_ubyte3 : Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_cube : Intrinsic<[llvm_v4f32_ty], [llvm_v4f32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_bfi : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_bfe_i32 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_bfe_u32 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_bfm : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_brev : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_flbit_i32 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
|
|
def int_AMDGPU_barrier_local : Intrinsic<[], [], []>;
|
|
def int_AMDGPU_barrier_global : Intrinsic<[], [], []>;
|
|
}
|
|
|
|
// Legacy names for compatibility.
|
|
let TargetPrefix = "AMDIL", isTarget = 1 in {
|
|
def int_AMDIL_abs : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
|
def int_AMDIL_fraction : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
|
def int_AMDIL_clamp : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
|
|
def int_AMDIL_exp : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
|
def int_AMDIL_round_nearest : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
|
}
|
|
|
|
let TargetPrefix = "TGSI", isTarget = 1 in {
|
|
|
|
def int_TGSI_lit_z : Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],[IntrNoMem]>;
|
|
}
|
|
|
|
include "SIIntrinsics.td"
|