forked from OSchip/llvm-project
509 lines
24 KiB
TableGen
509 lines
24 KiB
TableGen
//===- X86InstrVecCompiler.td - Vector Compiler Patterns ---*- tablegen -*-===//
|
|
//
|
|
// 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 describes the various vector pseudo instructions used by the
|
|
// compiler, as well as Pat patterns used during instruction selection.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Non-instruction patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Predicates = [NoAVX512] in {
|
|
// A vector extract of the first f32/f64 position is a subregister copy
|
|
def : Pat<(f32 (extractelt (v4f32 VR128:$src), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (v4f32 VR128:$src), FR32)>;
|
|
def : Pat<(f64 (extractelt (v2f64 VR128:$src), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (v2f64 VR128:$src), FR64)>;
|
|
}
|
|
|
|
let Predicates = [HasAVX512] in {
|
|
// A vector extract of the first f32/f64 position is a subregister copy
|
|
def : Pat<(f32 (extractelt (v4f32 VR128X:$src), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (v4f32 VR128X:$src), FR32X)>;
|
|
def : Pat<(f64 (extractelt (v2f64 VR128X:$src), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (v2f64 VR128X:$src), FR64X)>;
|
|
}
|
|
|
|
let Predicates = [NoVLX] in {
|
|
// Implicitly promote a 32-bit scalar to a vector.
|
|
def : Pat<(v4f32 (scalar_to_vector FR32:$src)),
|
|
(COPY_TO_REGCLASS FR32:$src, VR128)>;
|
|
// Implicitly promote a 64-bit scalar to a vector.
|
|
def : Pat<(v2f64 (scalar_to_vector FR64:$src)),
|
|
(COPY_TO_REGCLASS FR64:$src, VR128)>;
|
|
}
|
|
|
|
let Predicates = [HasVLX] in {
|
|
// Implicitly promote a 32-bit scalar to a vector.
|
|
def : Pat<(v4f32 (scalar_to_vector FR32X:$src)),
|
|
(COPY_TO_REGCLASS FR32X:$src, VR128X)>;
|
|
// Implicitly promote a 64-bit scalar to a vector.
|
|
def : Pat<(v2f64 (scalar_to_vector FR64X:$src)),
|
|
(COPY_TO_REGCLASS FR64X:$src, VR128X)>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Subvector tricks
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Patterns for insert_subvector/extract_subvector to/from index=0
|
|
multiclass subvector_subreg_lowering<RegisterClass subRC, ValueType subVT,
|
|
RegisterClass RC, ValueType VT,
|
|
SubRegIndex subIdx> {
|
|
def : Pat<(subVT (extract_subvector (VT RC:$src), (iPTR 0))),
|
|
(subVT (EXTRACT_SUBREG RC:$src, subIdx))>;
|
|
|
|
def : Pat<(VT (insert_subvector undef, subRC:$src, (iPTR 0))),
|
|
(VT (INSERT_SUBREG (IMPLICIT_DEF), subRC:$src, subIdx))>;
|
|
}
|
|
|
|
// A 128-bit subvector extract from the first 256-bit vector position is a
|
|
// subregister copy that needs no instruction. Likewise, a 128-bit subvector
|
|
// insert to the first 256-bit vector position is a subregister copy that needs
|
|
// no instruction.
|
|
defm : subvector_subreg_lowering<VR128, v4i32, VR256, v8i32, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v4f32, VR256, v8f32, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v2i64, VR256, v4i64, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v2f64, VR256, v4f64, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v8i16, VR256, v16i16, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v16i8, VR256, v32i8, sub_xmm>;
|
|
|
|
// A 128-bit subvector extract from the first 512-bit vector position is a
|
|
// subregister copy that needs no instruction. Likewise, a 128-bit subvector
|
|
// insert to the first 512-bit vector position is a subregister copy that needs
|
|
// no instruction.
|
|
defm : subvector_subreg_lowering<VR128, v4i32, VR512, v16i32, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v4f32, VR512, v16f32, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v2i64, VR512, v8i64, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v2f64, VR512, v8f64, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v8i16, VR512, v32i16, sub_xmm>;
|
|
defm : subvector_subreg_lowering<VR128, v16i8, VR512, v64i8, sub_xmm>;
|
|
|
|
// A 128-bit subvector extract from the first 512-bit vector position is a
|
|
// subregister copy that needs no instruction. Likewise, a 128-bit subvector
|
|
// insert to the first 512-bit vector position is a subregister copy that needs
|
|
// no instruction.
|
|
defm : subvector_subreg_lowering<VR256, v8i32, VR512, v16i32, sub_ymm>;
|
|
defm : subvector_subreg_lowering<VR256, v8f32, VR512, v16f32, sub_ymm>;
|
|
defm : subvector_subreg_lowering<VR256, v4i64, VR512, v8i64, sub_ymm>;
|
|
defm : subvector_subreg_lowering<VR256, v4f64, VR512, v8f64, sub_ymm>;
|
|
defm : subvector_subreg_lowering<VR256, v16i16, VR512, v32i16, sub_ymm>;
|
|
defm : subvector_subreg_lowering<VR256, v32i8, VR512, v64i8, sub_ymm>;
|
|
|
|
|
|
multiclass subvector_store_lowering<string AlignedStr, string UnalignedStr,
|
|
RegisterClass RC, ValueType DstTy,
|
|
ValueType SrcTy, SubRegIndex SubIdx> {
|
|
def : Pat<(alignedstore (DstTy (extract_subvector
|
|
(SrcTy RC:$src), (iPTR 0))), addr:$dst),
|
|
(!cast<Instruction>("VMOV"#AlignedStr#"mr") addr:$dst,
|
|
(DstTy (EXTRACT_SUBREG RC:$src, SubIdx)))>;
|
|
|
|
def : Pat<(store (DstTy (extract_subvector
|
|
(SrcTy RC:$src), (iPTR 0))), addr:$dst),
|
|
(!cast<Instruction>("VMOV"#UnalignedStr#"mr") addr:$dst,
|
|
(DstTy (EXTRACT_SUBREG RC:$src, SubIdx)))>;
|
|
}
|
|
|
|
let Predicates = [HasAVX, NoVLX] in {
|
|
defm : subvector_store_lowering<"APD", "UPD", VR256X, v2f64, v4f64, sub_xmm>;
|
|
defm : subvector_store_lowering<"APS", "UPS", VR256X, v4f32, v8f32, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA", "DQU", VR256X, v2i64, v4i64, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA", "DQU", VR256X, v4i32, v8i32, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA", "DQU", VR256X, v8i16, v16i16, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA", "DQU", VR256X, v16i8, v32i8, sub_xmm>;
|
|
}
|
|
|
|
let Predicates = [HasVLX] in {
|
|
// Special patterns for storing subvector extracts of lower 128-bits
|
|
// Its cheaper to just use VMOVAPS/VMOVUPS instead of VEXTRACTF128mr
|
|
defm : subvector_store_lowering<"APDZ128", "UPDZ128", VR256X, v2f64, v4f64,
|
|
sub_xmm>;
|
|
defm : subvector_store_lowering<"APSZ128", "UPSZ128", VR256X, v4f32, v8f32,
|
|
sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR256X, v2i64,
|
|
v4i64, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR256X, v4i32,
|
|
v8i32, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR256X, v8i16,
|
|
v16i16, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR256X, v16i8,
|
|
v32i8, sub_xmm>;
|
|
|
|
// Special patterns for storing subvector extracts of lower 128-bits of 512.
|
|
// Its cheaper to just use VMOVAPS/VMOVUPS instead of VEXTRACTF128mr
|
|
defm : subvector_store_lowering<"APDZ128", "UPDZ128", VR512, v2f64, v8f64,
|
|
sub_xmm>;
|
|
defm : subvector_store_lowering<"APSZ128", "UPSZ128", VR512, v4f32, v16f32,
|
|
sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR512, v2i64,
|
|
v8i64, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR512, v4i32,
|
|
v16i32, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR512, v8i16,
|
|
v32i16, sub_xmm>;
|
|
defm : subvector_store_lowering<"DQA64Z128", "DQU64Z128", VR512, v16i8,
|
|
v64i8, sub_xmm>;
|
|
|
|
// Special patterns for storing subvector extracts of lower 256-bits of 512.
|
|
// Its cheaper to just use VMOVAPS/VMOVUPS instead of VEXTRACTF128mr
|
|
defm : subvector_store_lowering<"APDZ256", "UPDZ256", VR512, v4f64, v8f64,
|
|
sub_ymm>;
|
|
defm : subvector_store_lowering<"APSZ256", "UPSZ256", VR512, v8f32, v16f32,
|
|
sub_ymm>;
|
|
defm : subvector_store_lowering<"DQA64Z256", "DQU64Z256", VR512, v4i64,
|
|
v8i64, sub_ymm>;
|
|
defm : subvector_store_lowering<"DQA64Z256", "DQU64Z256", VR512, v8i32,
|
|
v16i32, sub_ymm>;
|
|
defm : subvector_store_lowering<"DQA64Z256", "DQU64Z256", VR512, v16i16,
|
|
v32i16, sub_ymm>;
|
|
defm : subvector_store_lowering<"DQA64Z256", "DQU64Z256", VR512, v32i8,
|
|
v64i8, sub_ymm>;
|
|
}
|
|
|
|
// If we're inserting into an all zeros vector, just use a plain move which
|
|
// will zero the upper bits. A post-isel hook will take care of removing
|
|
// any moves that we can prove are unnecessary.
|
|
multiclass subvec_zero_lowering<string MoveStr,
|
|
RegisterClass RC, ValueType DstTy,
|
|
ValueType SrcTy, ValueType ZeroTy,
|
|
SubRegIndex SubIdx> {
|
|
def : Pat<(DstTy (insert_subvector (bitconvert (ZeroTy immAllZerosV)),
|
|
(SrcTy RC:$src), (iPTR 0))),
|
|
(SUBREG_TO_REG (i64 0),
|
|
(SrcTy (!cast<Instruction>("VMOV"#MoveStr#"rr") RC:$src)), SubIdx)>;
|
|
}
|
|
|
|
let Predicates = [HasAVX, NoVLX] in {
|
|
defm : subvec_zero_lowering<"APD", VR128, v4f64, v2f64, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"APS", VR128, v8f32, v4f32, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v4i64, v2i64, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v8i32, v4i32, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v16i16, v8i16, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v32i8, v16i8, v8i32, sub_xmm>;
|
|
}
|
|
|
|
let Predicates = [HasVLX] in {
|
|
defm : subvec_zero_lowering<"APDZ128", VR128X, v4f64, v2f64, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"APSZ128", VR128X, v8f32, v4f32, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v4i64, v2i64, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v8i32, v4i32, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v16i16, v8i16, v8i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v32i8, v16i8, v8i32, sub_xmm>;
|
|
|
|
defm : subvec_zero_lowering<"APDZ128", VR128X, v8f64, v2f64, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"APSZ128", VR128X, v16f32, v4f32, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v8i64, v2i64, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v16i32, v4i32, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v32i16, v8i16, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA64Z128", VR128X, v64i8, v16i8, v16i32, sub_xmm>;
|
|
|
|
defm : subvec_zero_lowering<"APDZ256", VR256X, v8f64, v4f64, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"APSZ256", VR256X, v16f32, v8f32, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQA64Z256", VR256X, v8i64, v4i64, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQA64Z256", VR256X, v16i32, v8i32, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQA64Z256", VR256X, v32i16, v16i16, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQA64Z256", VR256X, v64i8, v32i8, v16i32, sub_ymm>;
|
|
}
|
|
|
|
let Predicates = [HasAVX512, NoVLX] in {
|
|
defm : subvec_zero_lowering<"APD", VR128, v8f64, v2f64, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"APS", VR128, v16f32, v4f32, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v8i64, v2i64, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v16i32, v4i32, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v32i16, v8i16, v16i32, sub_xmm>;
|
|
defm : subvec_zero_lowering<"DQA", VR128, v64i8, v16i8, v16i32, sub_xmm>;
|
|
|
|
defm : subvec_zero_lowering<"APDY", VR256, v8f64, v4f64, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"APSY", VR256, v16f32, v8f32, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQAY", VR256, v8i64, v4i64, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQAY", VR256, v16i32, v8i32, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQAY", VR256, v32i16, v16i16, v16i32, sub_ymm>;
|
|
defm : subvec_zero_lowering<"DQAY", VR256, v64i8, v32i8, v16i32, sub_ymm>;
|
|
}
|
|
|
|
class maskzeroupper<ValueType vt, RegisterClass RC> :
|
|
PatLeaf<(vt RC:$src), [{
|
|
return isMaskZeroExtended(N);
|
|
}]>;
|
|
|
|
def maskzeroupperv1i1 : maskzeroupper<v1i1, VK1>;
|
|
def maskzeroupperv2i1 : maskzeroupper<v2i1, VK2>;
|
|
def maskzeroupperv4i1 : maskzeroupper<v4i1, VK4>;
|
|
def maskzeroupperv8i1 : maskzeroupper<v8i1, VK8>;
|
|
def maskzeroupperv16i1 : maskzeroupper<v16i1, VK16>;
|
|
def maskzeroupperv32i1 : maskzeroupper<v32i1, VK32>;
|
|
|
|
// The patterns determine if we can depend on the upper bits of a mask register
|
|
// being zeroed by the previous operation so that we can skip explicit
|
|
// zeroing.
|
|
let Predicates = [HasBWI] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
maskzeroupperv1i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK1:$src, VK32)>;
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
maskzeroupperv8i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK8:$src, VK32)>;
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
maskzeroupperv16i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK16:$src, VK32)>;
|
|
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv1i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK1:$src, VK64)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv8i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK8:$src, VK64)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv16i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK16:$src, VK64)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv32i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK32:$src, VK64)>;
|
|
}
|
|
|
|
let Predicates = [HasAVX512] in {
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
maskzeroupperv1i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK1:$src, VK16)>;
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
maskzeroupperv8i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK8:$src, VK16)>;
|
|
}
|
|
|
|
let Predicates = [HasDQI] in {
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
maskzeroupperv1i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK1:$src, VK8)>;
|
|
}
|
|
|
|
let Predicates = [HasVLX, HasDQI] in {
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
maskzeroupperv2i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK2:$src, VK8)>;
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
maskzeroupperv4i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK4:$src, VK8)>;
|
|
}
|
|
|
|
let Predicates = [HasVLX] in {
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
maskzeroupperv2i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK2:$src, VK16)>;
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
maskzeroupperv4i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK4:$src, VK16)>;
|
|
}
|
|
|
|
let Predicates = [HasBWI, HasVLX] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
maskzeroupperv2i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK2:$src, VK32)>;
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
maskzeroupperv4i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK4:$src, VK32)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv2i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK2:$src, VK64)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
maskzeroupperv4i1:$src, (iPTR 0))),
|
|
(COPY_TO_REGCLASS VK4:$src, VK64)>;
|
|
}
|
|
|
|
// If the bits are not zero we have to fall back to explicitly zeroing by
|
|
// using shifts.
|
|
let Predicates = [HasAVX512] in {
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
(v1i1 VK1:$mask), (iPTR 0))),
|
|
(KSHIFTRWri (KSHIFTLWri (COPY_TO_REGCLASS VK1:$mask, VK16),
|
|
(i8 15)), (i8 15))>;
|
|
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
(v2i1 VK2:$mask), (iPTR 0))),
|
|
(KSHIFTRWri (KSHIFTLWri (COPY_TO_REGCLASS VK2:$mask, VK16),
|
|
(i8 14)), (i8 14))>;
|
|
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
(v4i1 VK4:$mask), (iPTR 0))),
|
|
(KSHIFTRWri (KSHIFTLWri (COPY_TO_REGCLASS VK4:$mask, VK16),
|
|
(i8 12)), (i8 12))>;
|
|
}
|
|
|
|
let Predicates = [HasAVX512, NoDQI] in {
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(KSHIFTRWri (KSHIFTLWri (COPY_TO_REGCLASS VK8:$mask, VK16),
|
|
(i8 8)), (i8 8))>;
|
|
}
|
|
|
|
let Predicates = [HasDQI] in {
|
|
def : Pat<(v16i1 (insert_subvector (v16i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVBkk VK8:$mask), VK16)>;
|
|
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
(v1i1 VK1:$mask), (iPTR 0))),
|
|
(KSHIFTRBri (KSHIFTLBri (COPY_TO_REGCLASS VK1:$mask, VK8),
|
|
(i8 7)), (i8 7))>;
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
(v2i1 VK2:$mask), (iPTR 0))),
|
|
(KSHIFTRBri (KSHIFTLBri (COPY_TO_REGCLASS VK2:$mask, VK8),
|
|
(i8 6)), (i8 6))>;
|
|
def : Pat<(v8i1 (insert_subvector (v8i1 immAllZerosV),
|
|
(v4i1 VK4:$mask), (iPTR 0))),
|
|
(KSHIFTRBri (KSHIFTLBri (COPY_TO_REGCLASS VK4:$mask, VK8),
|
|
(i8 4)), (i8 4))>;
|
|
}
|
|
|
|
let Predicates = [HasBWI] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v16i1 VK16:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVWkk VK16:$mask), VK32)>;
|
|
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v16i1 VK16:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVWkk VK16:$mask), VK64)>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v32i1 VK32:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVDkk VK32:$mask), VK64)>;
|
|
}
|
|
|
|
let Predicates = [HasBWI, NoDQI] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(KSHIFTRDri (KSHIFTLDri (COPY_TO_REGCLASS VK8:$mask, VK32),
|
|
(i8 24)), (i8 24))>;
|
|
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(KSHIFTRQri (KSHIFTLQri (COPY_TO_REGCLASS VK8:$mask, VK64),
|
|
(i8 56)), (i8 56))>;
|
|
}
|
|
|
|
let Predicates = [HasBWI, HasDQI] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVBkk VK8:$mask), VK32)>;
|
|
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v8i1 VK8:$mask), (iPTR 0))),
|
|
(COPY_TO_REGCLASS (KMOVBkk VK8:$mask), VK64)>;
|
|
}
|
|
|
|
let Predicates = [HasBWI] in {
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v1i1 VK1:$mask), (iPTR 0))),
|
|
(KSHIFTRDri (KSHIFTLDri (COPY_TO_REGCLASS VK1:$mask, VK32),
|
|
(i8 31)), (i8 31))>;
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v2i1 VK2:$mask), (iPTR 0))),
|
|
(KSHIFTRDri (KSHIFTLDri (COPY_TO_REGCLASS VK2:$mask, VK32),
|
|
(i8 30)), (i8 30))>;
|
|
def : Pat<(v32i1 (insert_subvector (v32i1 immAllZerosV),
|
|
(v4i1 VK4:$mask), (iPTR 0))),
|
|
(KSHIFTRDri (KSHIFTLDri (COPY_TO_REGCLASS VK4:$mask, VK32),
|
|
(i8 28)), (i8 28))>;
|
|
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v1i1 VK1:$mask), (iPTR 0))),
|
|
(KSHIFTRQri (KSHIFTLQri (COPY_TO_REGCLASS VK1:$mask, VK64),
|
|
(i8 63)), (i8 63))>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v2i1 VK2:$mask), (iPTR 0))),
|
|
(KSHIFTRQri (KSHIFTLQri (COPY_TO_REGCLASS VK2:$mask, VK64),
|
|
(i8 62)), (i8 62))>;
|
|
def : Pat<(v64i1 (insert_subvector (v64i1 immAllZerosV),
|
|
(v4i1 VK4:$mask), (iPTR 0))),
|
|
(KSHIFTRQri (KSHIFTLQri (COPY_TO_REGCLASS VK4:$mask, VK64),
|
|
(i8 60)), (i8 60))>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Extra selection patterns for f128, f128mem
|
|
|
|
// movaps is shorter than movdqa. movaps is in SSE and movdqa is in SSE2.
|
|
let Predicates = [NoAVX] in {
|
|
def : Pat<(alignedstore (f128 VR128:$src), addr:$dst),
|
|
(MOVAPSmr addr:$dst, VR128:$src)>;
|
|
def : Pat<(store (f128 VR128:$src), addr:$dst),
|
|
(MOVUPSmr addr:$dst, VR128:$src)>;
|
|
|
|
def : Pat<(alignedloadf128 addr:$src),
|
|
(MOVAPSrm addr:$src)>;
|
|
def : Pat<(loadf128 addr:$src),
|
|
(MOVUPSrm addr:$src)>;
|
|
}
|
|
|
|
let Predicates = [HasAVX, NoVLX] in {
|
|
def : Pat<(alignedstore (f128 VR128:$src), addr:$dst),
|
|
(VMOVAPSmr addr:$dst, VR128:$src)>;
|
|
def : Pat<(store (f128 VR128:$src), addr:$dst),
|
|
(VMOVUPSmr addr:$dst, VR128:$src)>;
|
|
|
|
def : Pat<(alignedloadf128 addr:$src),
|
|
(VMOVAPSrm addr:$src)>;
|
|
def : Pat<(loadf128 addr:$src),
|
|
(VMOVUPSrm addr:$src)>;
|
|
}
|
|
|
|
let Predicates = [HasVLX] in {
|
|
def : Pat<(alignedstore (f128 VR128X:$src), addr:$dst),
|
|
(VMOVAPSZ128mr addr:$dst, VR128X:$src)>;
|
|
def : Pat<(store (f128 VR128X:$src), addr:$dst),
|
|
(VMOVUPSZ128mr addr:$dst, VR128X:$src)>;
|
|
|
|
def : Pat<(alignedloadf128 addr:$src),
|
|
(VMOVAPSZ128rm addr:$src)>;
|
|
def : Pat<(loadf128 addr:$src),
|
|
(VMOVUPSZ128rm addr:$src)>;
|
|
}
|
|
|
|
let Predicates = [UseSSE1] in {
|
|
// andps is shorter than andpd or pand. andps is SSE and andpd/pand are in SSE2
|
|
def : Pat<(f128 (X86fand VR128:$src1, (memopf128 addr:$src2))),
|
|
(ANDPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fand VR128:$src1, VR128:$src2)),
|
|
(ANDPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
def : Pat<(f128 (X86for VR128:$src1, (memopf128 addr:$src2))),
|
|
(ORPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86for VR128:$src1, VR128:$src2)),
|
|
(ORPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fxor VR128:$src1, (memopf128 addr:$src2))),
|
|
(XORPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fxor VR128:$src1, VR128:$src2)),
|
|
(XORPSrr VR128:$src1, VR128:$src2)>;
|
|
}
|
|
|
|
let Predicates = [HasAVX] in {
|
|
// andps is shorter than andpd or pand. andps is SSE and andpd/pand are in SSE2
|
|
def : Pat<(f128 (X86fand VR128:$src1, (loadf128 addr:$src2))),
|
|
(VANDPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fand VR128:$src1, VR128:$src2)),
|
|
(VANDPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
def : Pat<(f128 (X86for VR128:$src1, (loadf128 addr:$src2))),
|
|
(VORPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86for VR128:$src1, VR128:$src2)),
|
|
(VORPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fxor VR128:$src1, (loadf128 addr:$src2))),
|
|
(VXORPSrm VR128:$src1, f128mem:$src2)>;
|
|
|
|
def : Pat<(f128 (X86fxor VR128:$src1, VR128:$src2)),
|
|
(VXORPSrr VR128:$src1, VR128:$src2)>;
|
|
}
|