forked from OSchip/llvm-project
[X86] Add versions of the avx512 gather intrinsics that take the mask as a vXi1 vector instead of a scalar
In keeping with our general direction of having the vXi1 type present in IR, this patch converts the mask argument for avx512 gather to vXi1. This can avoid k-register to GPR to k-register transitions late in codegen. I left the existing intrinsics behind because they have many out of tree users such as ISPC. They generate their own code and don't go through the autoupgrade path which only works for bitcode and ll parsing. Ideally we will get them to migrate to target independent intrinsics, but it might be easier for them to migrate to these new intrinsics. I'll work on scatter and gatherpf/scatterpf next. Differential Revision: https://reviews.llvm.org/D56527 llvm-svn: 351234
This commit is contained in:
Craig Topper
parent
c9e9e28487
commit
82015b633b
|
|
@ -3569,133 +3569,121 @@ let TargetPrefix = "x86" in {
|
|||
|
||||
// Gather and Scatter ops
|
||||
let TargetPrefix = "x86" in {
|
||||
def int_x86_avx512_gather_dpd_512 : GCCBuiltin<"__builtin_ia32_gathersiv8df">,
|
||||
// These are gather intrinsics that use a scalar integer for the mask. They
|
||||
// have been superceded by new versions that use a vXi1 mask. Leaving these
|
||||
// for now as they have multiple out of tree users that need to migrate.
|
||||
// TODO: Remove when we can confirm out of tree migration.
|
||||
def int_x86_avx512_gather_dpd_512 :
|
||||
Intrinsic<[llvm_v8f64_ty], [llvm_v8f64_ty, llvm_ptr_ty,
|
||||
llvm_v8i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_dps_512 : GCCBuiltin<"__builtin_ia32_gathersiv16sf">,
|
||||
def int_x86_avx512_gather_dps_512 :
|
||||
Intrinsic<[llvm_v16f32_ty], [llvm_v16f32_ty, llvm_ptr_ty,
|
||||
llvm_v16i32_ty, llvm_i16_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_qpd_512 : GCCBuiltin<"__builtin_ia32_gatherdiv8df">,
|
||||
def int_x86_avx512_gather_qpd_512 :
|
||||
Intrinsic<[llvm_v8f64_ty], [llvm_v8f64_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_qps_512 : GCCBuiltin<"__builtin_ia32_gatherdiv16sf">,
|
||||
def int_x86_avx512_gather_qps_512 :
|
||||
Intrinsic<[llvm_v8f32_ty], [llvm_v8f32_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
|
||||
def int_x86_avx512_gather_dpq_512 : GCCBuiltin<"__builtin_ia32_gathersiv8di">,
|
||||
def int_x86_avx512_gather_dpq_512 :
|
||||
Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty, llvm_ptr_ty,
|
||||
llvm_v8i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_dpi_512 : GCCBuiltin<"__builtin_ia32_gathersiv16si">,
|
||||
def int_x86_avx512_gather_dpi_512 :
|
||||
Intrinsic<[llvm_v16i32_ty], [llvm_v16i32_ty, llvm_ptr_ty,
|
||||
llvm_v16i32_ty, llvm_i16_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_qpq_512 : GCCBuiltin<"__builtin_ia32_gatherdiv8di">,
|
||||
def int_x86_avx512_gather_qpq_512 :
|
||||
Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_gather_qpi_512 : GCCBuiltin<"__builtin_ia32_gatherdiv16si">,
|
||||
def int_x86_avx512_gather_qpi_512 :
|
||||
Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div2_df :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div2df">,
|
||||
Intrinsic<[llvm_v2f64_ty],
|
||||
[llvm_v2f64_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div2_di :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div2di">,
|
||||
Intrinsic<[llvm_v2i64_ty],
|
||||
[llvm_v2i64_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div4_df :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div4df">,
|
||||
Intrinsic<[llvm_v4f64_ty],
|
||||
[llvm_v4f64_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div4_di :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div4di">,
|
||||
Intrinsic<[llvm_v4i64_ty],
|
||||
[llvm_v4i64_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div4_sf :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div4sf">,
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div4_si :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div4si">,
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div8_sf :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div8sf">,
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3div8_si :
|
||||
GCCBuiltin<"__builtin_ia32_gather3div8si">,
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv2_df :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv2df">,
|
||||
Intrinsic<[llvm_v2f64_ty],
|
||||
[llvm_v2f64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv2_di :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv2di">,
|
||||
Intrinsic<[llvm_v2i64_ty],
|
||||
[llvm_v2i64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv4_df :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv4df">,
|
||||
Intrinsic<[llvm_v4f64_ty],
|
||||
[llvm_v4f64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv4_di :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv4di">,
|
||||
Intrinsic<[llvm_v4i64_ty],
|
||||
[llvm_v4i64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv4_sf :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv4sf">,
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv4_si :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv4si">,
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv8_sf :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv8sf">,
|
||||
Intrinsic<[llvm_v8f32_ty],
|
||||
[llvm_v8f32_ty, llvm_ptr_ty, llvm_v8i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_gather3siv8_si :
|
||||
GCCBuiltin<"__builtin_ia32_gather3siv8si">,
|
||||
Intrinsic<[llvm_v8i32_ty],
|
||||
[llvm_v8i32_ty, llvm_ptr_ty, llvm_v8i32_ty, llvm_i8_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
|
@ -3861,6 +3849,124 @@ let TargetPrefix = "x86" in {
|
|||
llvm_i32_ty, llvm_i32_ty], [IntrArgMemOnly]>;
|
||||
}
|
||||
|
||||
// AVX512 gather intrinsics that use vXi1 masks.
|
||||
let TargetPrefix = "x86" in {
|
||||
def int_x86_avx512_mask_gather_dpd_512 :
|
||||
Intrinsic<[llvm_v8f64_ty], [llvm_v8f64_ty, llvm_ptr_ty,
|
||||
llvm_v8i32_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_dps_512 :
|
||||
Intrinsic<[llvm_v16f32_ty], [llvm_v16f32_ty, llvm_ptr_ty,
|
||||
llvm_v16i32_ty, llvm_v16i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_qpd_512 :
|
||||
Intrinsic<[llvm_v8f64_ty], [llvm_v8f64_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_qps_512 :
|
||||
Intrinsic<[llvm_v8f32_ty], [llvm_v8f32_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
|
||||
def int_x86_avx512_mask_gather_dpq_512 :
|
||||
Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty, llvm_ptr_ty,
|
||||
llvm_v8i32_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_dpi_512 :
|
||||
Intrinsic<[llvm_v16i32_ty], [llvm_v16i32_ty, llvm_ptr_ty,
|
||||
llvm_v16i32_ty, llvm_v16i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_qpq_512 :
|
||||
Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
def int_x86_avx512_mask_gather_qpi_512 :
|
||||
Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty, llvm_ptr_ty,
|
||||
llvm_v8i64_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div2_df :
|
||||
Intrinsic<[llvm_v2f64_ty],
|
||||
[llvm_v2f64_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div2_di :
|
||||
Intrinsic<[llvm_v2i64_ty],
|
||||
[llvm_v2i64_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div4_df :
|
||||
Intrinsic<[llvm_v4f64_ty],
|
||||
[llvm_v4f64_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div4_di :
|
||||
Intrinsic<[llvm_v4i64_ty],
|
||||
[llvm_v4i64_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div4_sf :
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div4_si :
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v2i64_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div8_sf :
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3div8_si :
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v4i64_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv2_df :
|
||||
Intrinsic<[llvm_v2f64_ty],
|
||||
[llvm_v2f64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv2_di :
|
||||
Intrinsic<[llvm_v2i64_ty],
|
||||
[llvm_v2i64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v2i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv4_df :
|
||||
Intrinsic<[llvm_v4f64_ty],
|
||||
[llvm_v4f64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv4_di :
|
||||
Intrinsic<[llvm_v4i64_ty],
|
||||
[llvm_v4i64_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv4_sf :
|
||||
Intrinsic<[llvm_v4f32_ty],
|
||||
[llvm_v4f32_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv4_si :
|
||||
Intrinsic<[llvm_v4i32_ty],
|
||||
[llvm_v4i32_ty, llvm_ptr_ty, llvm_v4i32_ty, llvm_v4i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv8_sf :
|
||||
Intrinsic<[llvm_v8f32_ty],
|
||||
[llvm_v8f32_ty, llvm_ptr_ty, llvm_v8i32_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
|
||||
def int_x86_avx512_mask_gather3siv8_si :
|
||||
Intrinsic<[llvm_v8i32_ty],
|
||||
[llvm_v8i32_ty, llvm_ptr_ty, llvm_v8i32_ty, llvm_v8i1_ty, llvm_i32_ty],
|
||||
[IntrReadMem, IntrArgMemOnly]>;
|
||||
}
|
||||
|
||||
// AVX-512 conflict detection instruction
|
||||
// Instructions that count the number of leading zero bits
|
||||
let TargetPrefix = "x86" in {
|
||||
|
|
|
|||
|
|
@ -22326,16 +22326,20 @@ static SDValue getGatherNode(unsigned Opc, SDValue Op, SelectionDAG &DAG,
|
|||
VT.getVectorNumElements());
|
||||
MVT MaskVT = MVT::getVectorVT(MVT::i1, MinElts);
|
||||
|
||||
SDValue VMask = getMaskNode(Mask, MaskVT, Subtarget, DAG, dl);
|
||||
// We support two versions of the gather intrinsics. One with scalar mask and
|
||||
// one with vXi1 mask. Convert scalar to vXi1 if necessary.
|
||||
if (Mask.getValueType() != MaskVT)
|
||||
Mask = getMaskNode(Mask, MaskVT, Subtarget, DAG, dl);
|
||||
|
||||
SDVTList VTs = DAG.getVTList(Op.getValueType(), MaskVT, MVT::Other);
|
||||
SDValue Disp = DAG.getTargetConstant(0, dl, MVT::i32);
|
||||
SDValue Segment = DAG.getRegister(0, MVT::i32);
|
||||
// If source is undef or we know it won't be used, use a zero vector
|
||||
// to break register dependency.
|
||||
// TODO: use undef instead and let BreakFalseDeps deal with it?
|
||||
if (Src.isUndef() || ISD::isBuildVectorAllOnes(VMask.getNode()))
|
||||
if (Src.isUndef() || ISD::isBuildVectorAllOnes(Mask.getNode()))
|
||||
Src = getZeroVector(Op.getSimpleValueType(), Subtarget, DAG, dl);
|
||||
SDValue Ops[] = {Src, VMask, Base, Scale, Index, Disp, Segment, Chain};
|
||||
SDValue Ops[] = {Src, Mask, Base, Scale, Index, Disp, Segment, Chain};
|
||||
SDNode *Res = DAG.getMachineNode(Opc, dl, VTs, Ops);
|
||||
SDValue RetOps[] = { SDValue(Res, 0), SDValue(Res, 2) };
|
||||
return DAG.getMergeValues(RetOps, dl);
|
||||
|
|
|
|||
|
|
@ -115,6 +115,31 @@ static const IntrinsicData IntrinsicsWithChain[] = {
|
|||
X86_INTRINSIC_DATA(avx512_gatherpf_qps_512, PREFETCH,
|
||||
X86::VGATHERPF0QPSm, X86::VGATHERPF1QPSm),
|
||||
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_dpd_512, GATHER, X86::VGATHERDPDZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_dpi_512, GATHER, X86::VPGATHERDDZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_dpq_512, GATHER, X86::VPGATHERDQZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_dps_512, GATHER, X86::VGATHERDPSZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_qpd_512, GATHER, X86::VGATHERQPDZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_qpi_512, GATHER, X86::VPGATHERQDZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_qpq_512, GATHER, X86::VPGATHERQQZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather_qps_512, GATHER, X86::VGATHERQPSZrm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div2_df, GATHER, X86::VGATHERQPDZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div2_di, GATHER, X86::VPGATHERQQZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div4_df, GATHER, X86::VGATHERQPDZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div4_di, GATHER, X86::VPGATHERQQZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div4_sf, GATHER, X86::VGATHERQPSZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div4_si, GATHER, X86::VPGATHERQDZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div8_sf, GATHER, X86::VGATHERQPSZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3div8_si, GATHER, X86::VPGATHERQDZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv2_df, GATHER, X86::VGATHERDPDZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv2_di, GATHER, X86::VPGATHERDQZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv4_df, GATHER, X86::VGATHERDPDZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv4_di, GATHER, X86::VPGATHERDQZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv4_sf, GATHER, X86::VGATHERDPSZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv4_si, GATHER, X86::VPGATHERDDZ128rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv8_sf, GATHER, X86::VGATHERDPSZ256rm, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_gather3siv8_si, GATHER, X86::VPGATHERDDZ256rm, 0),
|
||||
|
||||
X86_INTRINSIC_DATA(avx512_mask_pmov_db_mem_128, TRUNCATE_TO_MEM_VI8,
|
||||
X86ISD::VTRUNC, 0),
|
||||
X86_INTRINSIC_DATA(avx512_mask_pmov_db_mem_256, TRUNCATE_TO_MEM_VI8,
|
||||
|
|
|
|||
|
|
@ -0,0 +1,875 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f,+avx512bw,+avx512vl,+avx512dq | FileCheck %s
|
||||
|
||||
declare <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float>, i8*, <16 x i32>, i16, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dps.512 (i8*, i16, <16 x i32>, <16 x float>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double>, i8*, <8 x i32>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpd.512 (i8*, i8, <8 x i32>, <8 x double>, i32)
|
||||
|
||||
declare <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qps.512 (i8*, i8, <8 x i64>, <8 x float>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpd.512 (i8*, i8, <8 x i64>, <8 x double>, i32)
|
||||
|
||||
define void @gather_mask_dps(<16 x i32> %ind, <16 x float> %src, i16 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_dps:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vgatherdps (%rsi,%zmm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddd {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vscatterdps %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
%ind2 = add <16 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dps.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind2, <16 x float> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_dpd(<8 x i32> %ind, <8 x double> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_dpd:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vgatherdpd (%rsi,%ymm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; CHECK-NEXT: vscatterdpd %zmm1, (%rdx,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpd.512 (i8* %stbuf, i8 %mask, <8 x i32>%ind2, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_qps(<8 x i64> %ind, <8 x float> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_qps:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vgatherqps (%rsi,%zmm0,4), %ymm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vscatterqps %ymm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qps.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x float> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_qpd(<8 x i64> %ind, <8 x double> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_qpd:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vgatherqpd (%rsi,%zmm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vscatterqpd %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpd.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
;;
|
||||
;; Integer Gather/Scatter
|
||||
;;
|
||||
declare <16 x i32> @llvm.x86.avx512.gather.dpi.512 (<16 x i32>, i8*, <16 x i32>, i16, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpi.512 (i8*, i16, <16 x i32>, <16 x i32>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.gather.dpq.512 (<8 x i64>, i8*, <8 x i32>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpq.512 (i8*, i8, <8 x i32>, <8 x i64>, i32)
|
||||
|
||||
declare <8 x i32> @llvm.x86.avx512.gather.qpi.512 (<8 x i32>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpi.512 (i8*, i8, <8 x i64>, <8 x i32>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.gather.qpq.512 (<8 x i64>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpq.512 (i8*, i8, <8 x i64>, <8 x i64>, i32)
|
||||
|
||||
define void @gather_mask_dd(<16 x i32> %ind, <16 x i32> %src, i16 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_dd:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherdd (%rsi,%zmm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddd {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vpscatterdd %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <16 x i32> @llvm.x86.avx512.gather.dpi.512 (<16 x i32> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
%ind2 = add <16 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpi.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind2, <16 x i32> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_qd(<8 x i64> %ind, <8 x i32> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_qd:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherqd (%rsi,%zmm0,4), %ymm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vpscatterqd %ymm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i32> @llvm.x86.avx512.gather.qpi.512 (<8 x i32> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpi.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x i32> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_qq(<8 x i64> %ind, <8 x i64> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_qq:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherqq (%rsi,%zmm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vpscatterqq %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i64> @llvm.x86.avx512.gather.qpq.512 (<8 x i64> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpq.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x i64> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_dq(<8 x i32> %ind, <8 x i64> %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_dq:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherdq (%rsi,%ymm0,4), %zmm1 {%k2}
|
||||
; CHECK-NEXT: vpaddd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; CHECK-NEXT: vpscatterdq %zmm1, (%rdx,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i64> @llvm.x86.avx512.gather.dpq.512 (<8 x i64> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
%ind2 = add <8 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpq.512 (i8* %stbuf, i8 %mask, <8 x i32>%ind2, <8 x i64> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_dpd_execdomain(<8 x i32> %ind, <8 x double> %src, i8 %mask, i8* %base, <8 x double>* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_dpd_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: vgatherdpd (%rsi,%ymm0,4), %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovapd %zmm1, (%rdx)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
store <8 x double> %x, <8 x double>* %stbuf
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_mask_qpd_execdomain(<8 x i64> %ind, <8 x double> %src, i8 %mask, i8* %base, <8 x double>* %stbuf) {
|
||||
; CHECK-LABEL: gather_mask_qpd_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: vgatherqpd (%rsi,%zmm0,4), %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovapd %zmm1, (%rdx)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
store <8 x double> %x, <8 x double>* %stbuf
|
||||
ret void
|
||||
}
|
||||
|
||||
define <16 x float> @gather_mask_dps_execdomain(<16 x i32> %ind, <16 x float> %src, i16 %mask, i8* %base) {
|
||||
; CHECK-LABEL: gather_mask_dps_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rsi,%zmm0,4), %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
ret <16 x float> %res;
|
||||
}
|
||||
|
||||
define <8 x float> @gather_mask_qps_execdomain(<8 x i64> %ind, <8 x float> %src, i8 %mask, i8* %base) {
|
||||
; CHECK-LABEL: gather_mask_qps_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %edi, %k1
|
||||
; CHECK-NEXT: vgatherqps (%rsi,%zmm0,4), %ymm1 {%k1}
|
||||
; CHECK-NEXT: vmovaps %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
ret <8 x float> %res;
|
||||
}
|
||||
|
||||
define void @scatter_mask_dpd_execdomain(<8 x i32> %ind, <8 x double>* %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: scatter_mask_dpd_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovapd (%rdi), %zmm1
|
||||
; CHECK-NEXT: vscatterdpd %zmm1, (%rcx,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = load <8 x double>, <8 x double>* %src, align 64
|
||||
call void @llvm.x86.avx512.scatter.dpd.512 (i8* %stbuf, i8 %mask, <8 x i32>%ind, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @scatter_mask_qpd_execdomain(<8 x i64> %ind, <8 x double>* %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: scatter_mask_qpd_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovapd (%rdi), %zmm1
|
||||
; CHECK-NEXT: vscatterqpd %zmm1, (%rcx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = load <8 x double>, <8 x double>* %src, align 64
|
||||
call void @llvm.x86.avx512.scatter.qpd.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @scatter_mask_dps_execdomain(<16 x i32> %ind, <16 x float>* %src, i16 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: scatter_mask_dps_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovaps (%rdi), %zmm1
|
||||
; CHECK-NEXT: vscatterdps %zmm1, (%rcx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = load <16 x float>, <16 x float>* %src, align 64
|
||||
call void @llvm.x86.avx512.scatter.dps.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind, <16 x float> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @scatter_mask_qps_execdomain(<8 x i64> %ind, <8 x float>* %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: scatter_mask_qps_execdomain:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovaps (%rdi), %ymm1
|
||||
; CHECK-NEXT: vscatterqps %ymm1, (%rcx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = load <8 x float>, <8 x float>* %src, align 32
|
||||
call void @llvm.x86.avx512.scatter.qps.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind, <8 x float> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @gather_qps(<8 x i64> %ind, <8 x float> %src, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_qps:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%zmm0,4), %ymm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vscatterqps %ymm1, (%rsi,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 -1, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qps.512 (i8* %stbuf, i8 -1, <8 x i64>%ind2, <8 x float> %x, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.gatherpf.qps.512(i8, <8 x i64>, i8* , i32, i32);
|
||||
declare void @llvm.x86.avx512.scatterpf.qps.512(i8, <8 x i64>, i8* , i32, i32);
|
||||
define void @prefetch(<8 x i64> %ind, i8* %base) {
|
||||
; CHECK-LABEL: prefetch:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vgatherpf0qps (%rdi,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: kxorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vgatherpf1qps (%rdi,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: movb $1, %al
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vscatterpf0qps (%rdi,%zmm0,2) {%k1}
|
||||
; CHECK-NEXT: movb $120, %al
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vscatterpf1qps (%rdi,%zmm0,2) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.gatherpf.qps.512(i8 -1, <8 x i64> %ind, i8* %base, i32 4, i32 3)
|
||||
call void @llvm.x86.avx512.gatherpf.qps.512(i8 0, <8 x i64> %ind, i8* %base, i32 4, i32 2)
|
||||
call void @llvm.x86.avx512.scatterpf.qps.512(i8 1, <8 x i64> %ind, i8* %base, i32 2, i32 3)
|
||||
call void @llvm.x86.avx512.scatterpf.qps.512(i8 120, <8 x i64> %ind, i8* %base, i32 2, i32 2)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <2 x double>@test_int_x86_avx512_gather3div2_df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <2 x double> %res, %res1
|
||||
ret <2 x double> %res2
|
||||
}
|
||||
|
||||
declare <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <2 x i64>@test_int_x86_avx512_gather3div2_di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherqq (%rdi,%xmm1,8), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 8)
|
||||
%res2 = add <2 x i64> %res, %res1
|
||||
ret <2 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x double>@test_int_x86_avx512_gather3div4_df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%ymm1,4), %ymm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%ymm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <4 x double> %res, %res1
|
||||
ret <4 x double> %res2
|
||||
}
|
||||
|
||||
declare <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x i64>@test_int_x86_avx512_gather3div4_di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherqq (%rdi,%ymm1,8), %ymm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpgatherqq (%rdi,%ymm1,8), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vpaddq %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 8)
|
||||
%res2 = add <4 x i64> %res, %res1
|
||||
ret <4 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3div4_sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3div4_si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%xmm1,4), %xmm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3div8_sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%ymm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%ymm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3div8_si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovdqa %xmm0, %xmm2
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%ymm1,4), %xmm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%ymm1,2), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 2)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <2 x double>@test_int_x86_avx512_gather3siv2_df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <2 x double> %res, %res1
|
||||
ret <2 x double> %res2
|
||||
}
|
||||
|
||||
declare <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <2 x i64>@test_int_x86_avx512_gather3siv2_di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherdq (%rdi,%xmm1,8), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res2 = add <2 x i64> %res, %res1
|
||||
ret <2 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x double>@test_int_x86_avx512_gather3siv4_df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,4), %ymm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <4 x double> %res, %res1
|
||||
ret <4 x double> %res2
|
||||
}
|
||||
|
||||
declare <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x i64>@test_int_x86_avx512_gather3siv4_di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherdq (%rdi,%xmm1,8), %ymm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %ymm0, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res2 = add <4 x i64> %res, %res1
|
||||
ret <4 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3siv4_sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3siv4_si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%xmm1,4), %xmm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%xmm1,2), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 2)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float>, i8*, <8 x i32>, i8, i32)
|
||||
|
||||
define <8 x float>@test_int_x86_avx512_gather3siv8_sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%ymm1,4), %ymm0 {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%ymm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 -1, i32 2)
|
||||
%res2 = fadd <8 x float> %res, %res1
|
||||
ret <8 x float> %res2
|
||||
}
|
||||
|
||||
declare <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32>, i8*, <8 x i32>, i8, i32)
|
||||
|
||||
define <8 x i32>@test_int_x86_avx512_gather3siv8_si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovdqa %ymm0, %ymm2
|
||||
; CHECK-NEXT: kmovq %k1, %k2
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%ymm1,4), %ymm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%ymm1,2), %ymm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %ymm0, %ymm2, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 2)
|
||||
%res2 = add <8 x i32> %res, %res1
|
||||
ret <8 x i32> %res2
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv2.df(i8*, i8, <2 x i64>, <2 x double>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv2_df(i8* %x0, i8 %x1, <2 x i64> %x2, <2 x double> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vscatterqpd %xmm1, (%rdi,%xmm0,2) {%k2}
|
||||
; CHECK-NEXT: vscatterqpd %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv2.df(i8* %x0, i8 -1, <2 x i64> %x2, <2 x double> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv2.df(i8* %x0, i8 %x1, <2 x i64> %x2, <2 x double> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv2.di(i8*, i8, <2 x i64>, <2 x i64>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv2_di(i8* %x0, i8 %x1, <2 x i64> %x2, <2 x i64> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpscatterqq %xmm1, (%rdi,%xmm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterqq %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv2.di(i8* %x0, i8 %x1, <2 x i64> %x2, <2 x i64> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv2.di(i8* %x0, i8 -1, <2 x i64> %x2, <2 x i64> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv4.df(i8*, i8, <4 x i64>, <4 x double>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv4_df(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x double> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterqpd %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterqpd %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv4.df(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x double> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv4.df(i8* %x0, i8 -1, <4 x i64> %x2, <4 x double> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv4.di(i8*, i8, <4 x i64>, <4 x i64>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv4_di(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x i64> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpscatterqq %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterqq %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv4.di(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x i64> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv4.di(i8* %x0, i8 -1, <4 x i64> %x2, <4 x i64> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv4.sf(i8*, i8, <2 x i64>, <4 x float>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv4_sf(i8* %x0, i8 %x1, <2 x i64> %x2, <4 x float> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterqps %xmm1, (%rdi,%xmm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterqps %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv4.sf(i8* %x0, i8 %x1, <2 x i64> %x2, <4 x float> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv4.sf(i8* %x0, i8 -1, <2 x i64> %x2, <4 x float> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv4.si(i8*, i8, <2 x i64>, <4 x i32>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv4_si(i8* %x0, i8 %x1, <2 x i64> %x2, <4 x i32> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vpscatterqd %xmm1, (%rdi,%xmm0,2) {%k2}
|
||||
; CHECK-NEXT: vpscatterqd %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv4.si(i8* %x0, i8 -1, <2 x i64> %x2, <4 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv4.si(i8* %x0, i8 %x1, <2 x i64> %x2, <4 x i32> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv8.sf(i8*, i8, <4 x i64>, <4 x float>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv8_sf(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x float> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterqps %xmm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterqps %xmm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv8.sf(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x float> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv8.sf(i8* %x0, i8 -1, <4 x i64> %x2, <4 x float> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scatterdiv8.si(i8*, i8, <4 x i64>, <4 x i32>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scatterdiv8_si(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x i32> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scatterdiv8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpscatterqd %xmm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterqd %xmm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scatterdiv8.si(i8* %x0, i8 %x1, <4 x i64> %x2, <4 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scatterdiv8.si(i8* %x0, i8 -1, <4 x i64> %x2, <4 x i32> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv2.df(i8*, i8, <4 x i32>, <2 x double>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv2_df(i8* %x0, i8 %x1, <4 x i32> %x2, <2 x double> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vscatterdpd %xmm1, (%rdi,%xmm0,2) {%k2}
|
||||
; CHECK-NEXT: vscatterdpd %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv2.df(i8* %x0, i8 -1, <4 x i32> %x2, <2 x double> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv2.df(i8* %x0, i8 %x1, <4 x i32> %x2, <2 x double> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv2.di(i8*, i8, <4 x i32>, <2 x i64>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv2_di(i8* %x0, i8 %x1, <4 x i32> %x2, <2 x i64> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vpscatterdq %xmm1, (%rdi,%xmm0,2) {%k2}
|
||||
; CHECK-NEXT: vpscatterdq %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv2.di(i8* %x0, i8 -1, <4 x i32> %x2, <2 x i64> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv2.di(i8* %x0, i8 %x1, <4 x i32> %x2, <2 x i64> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv4.df(i8*, i8, <4 x i32>, <4 x double>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv4_df(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x double> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterdpd %ymm1, (%rdi,%xmm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterdpd %ymm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv4.df(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x double> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv4.df(i8* %x0, i8 -1, <4 x i32> %x2, <4 x double> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv4.di(i8*, i8, <4 x i32>, <4 x i64>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv4_di(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x i64> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vpscatterdq %ymm1, (%rdi,%xmm0,2) {%k2}
|
||||
; CHECK-NEXT: vpscatterdq %ymm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv4.di(i8* %x0, i8 -1, <4 x i32> %x2, <4 x i64> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv4.di(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x i64> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv4.sf(i8*, i8, <4 x i32>, <4 x float>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv4_sf(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x float> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterdps %xmm1, (%rdi,%xmm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterdps %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv4.sf(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x float> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv4.sf(i8* %x0, i8 -1, <4 x i32> %x2, <4 x float> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv4.si(i8*, i8, <4 x i32>, <4 x i32>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv4_si(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x i32> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpscatterdd %xmm1, (%rdi,%xmm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterdd %xmm1, (%rdi,%xmm0,4) {%k1}
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv4.si(i8* %x0, i8 %x1, <4 x i32> %x2, <4 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv4.si(i8* %x0, i8 -1, <4 x i32> %x2, <4 x i32> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv8.sf(i8*, i8, <8 x i32>, <8 x float>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv8_sf(i8* %x0, i8 %x1, <8 x i32> %x2, <8 x float> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vscatterdps %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vscatterdps %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv8.sf(i8* %x0, i8 %x1, <8 x i32> %x2, <8 x float> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv8.sf(i8* %x0, i8 -1, <8 x i32> %x2, <8 x float> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.x86.avx512.scattersiv8.si(i8*, i8, <8 x i32>, <8 x i32>, i32)
|
||||
|
||||
define void@test_int_x86_avx512_scattersiv8_si(i8* %x0, i8 %x1, <8 x i32> %x2, <8 x i32> %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_scattersiv8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 %x1, <8 x i32> %x2, <8 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 -1, <8 x i32> %x2, <8 x i32> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @scatter_mask_test(i8* %x0, <8 x i32> %x2, <8 x i32> %x3) {
|
||||
; CHECK-LABEL: scatter_mask_test:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: kxorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: movb $1, %al
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,2) {%k1}
|
||||
; CHECK-NEXT: movb $96, %al
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vpscatterdd %ymm1, (%rdi,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 -1, <8 x i32> %x2, <8 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 0, <8 x i32> %x2, <8 x i32> %x3, i32 4)
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 1, <8 x i32> %x2, <8 x i32> %x3, i32 2)
|
||||
call void @llvm.x86.avx512.scattersiv8.si(i8* %x0, i8 96, <8 x i32> %x2, <8 x i32> %x3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
define <16 x float> @gather_mask_test(<16 x i32> %ind, <16 x float> %src, i8* %base) {
|
||||
; CHECK-LABEL: gather_mask_test:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%zmm0,4), %zmm2 {%k1}
|
||||
; CHECK-NEXT: kxorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vmovaps %zmm1, %zmm3
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%zmm0,4), %zmm3 {%k1}
|
||||
; CHECK-NEXT: vaddps %zmm3, %zmm2, %zmm2
|
||||
; CHECK-NEXT: movw $1, %ax
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vmovaps %zmm1, %zmm3
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%zmm0,4), %zmm3 {%k1}
|
||||
; CHECK-NEXT: movw $220, %ax
|
||||
; CHECK-NEXT: kmovd %eax, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
|
||||
; CHECK-NEXT: vaddps %zmm3, %zmm1, %zmm0
|
||||
; CHECK-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 -1, i32 4)
|
||||
%res1 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 0, i32 4)
|
||||
%res2 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 1, i32 4)
|
||||
%res3 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 220, i32 4)
|
||||
|
||||
%res4 = fadd <16 x float> %res, %res1
|
||||
%res5 = fadd <16 x float> %res3, %res2
|
||||
%res6 = fadd <16 x float> %res5, %res4
|
||||
ret <16 x float> %res6
|
||||
}
|
||||
|
|
@ -1,14 +1,10 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f,+avx512bw,+avx512vl,+avx512dq | FileCheck %s
|
||||
|
||||
declare <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float>, i8*, <16 x i32>, i16, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dps.512 (i8*, i16, <16 x i32>, <16 x float>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double>, i8*, <8 x i32>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpd.512 (i8*, i8, <8 x i32>, <8 x double>, i32)
|
||||
|
||||
declare <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qps.512 (i8*, i8, <8 x i64>, <8 x float>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpd.512 (i8*, i8, <8 x i64>, <8 x double>, i32)
|
||||
|
||||
define void @gather_mask_dps(<16 x i32> %ind, <16 x float> %src, i16 %mask, i8* %base, i8* %stbuf) {
|
||||
|
|
@ -21,7 +17,8 @@ define void @gather_mask_dps(<16 x i32> %ind, <16 x float> %src, i16 %mask, i8*
|
|||
; CHECK-NEXT: vscatterdps %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%x = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> %1, i32 4)
|
||||
%ind2 = add <16 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dps.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind2, <16 x float> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -37,7 +34,8 @@ define void @gather_mask_dpd(<8 x i32> %ind, <8 x double> %src, i8 %mask, i8* %b
|
|||
; CHECK-NEXT: vscatterdpd %zmm1, (%rdx,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x double> @llvm.x86.avx512.mask.gather.dpd.512(<8 x double> %src, i8* %base, <8 x i32> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpd.512 (i8* %stbuf, i8 %mask, <8 x i32>%ind2, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -53,7 +51,8 @@ define void @gather_mask_qps(<8 x i64> %ind, <8 x float> %src, i8 %mask, i8* %ba
|
|||
; CHECK-NEXT: vscatterqps %ymm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x float> @llvm.x86.avx512.mask.gather.qps.512(<8 x float> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qps.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x float> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -69,7 +68,8 @@ define void @gather_mask_qpd(<8 x i64> %ind, <8 x double> %src, i8 %mask, i8* %b
|
|||
; CHECK-NEXT: vscatterqpd %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x double> @llvm.x86.avx512.mask.gather.qpd.512(<8 x double> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpd.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x double> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -77,14 +77,10 @@ define void @gather_mask_qpd(<8 x i64> %ind, <8 x double> %src, i8 %mask, i8* %b
|
|||
;;
|
||||
;; Integer Gather/Scatter
|
||||
;;
|
||||
declare <16 x i32> @llvm.x86.avx512.gather.dpi.512 (<16 x i32>, i8*, <16 x i32>, i16, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpi.512 (i8*, i16, <16 x i32>, <16 x i32>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.gather.dpq.512 (<8 x i64>, i8*, <8 x i32>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.dpq.512 (i8*, i8, <8 x i32>, <8 x i64>, i32)
|
||||
|
||||
declare <8 x i32> @llvm.x86.avx512.gather.qpi.512 (<8 x i32>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpi.512 (i8*, i8, <8 x i64>, <8 x i32>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.gather.qpq.512 (<8 x i64>, i8*, <8 x i64>, i8, i32)
|
||||
declare void @llvm.x86.avx512.scatter.qpq.512 (i8*, i8, <8 x i64>, <8 x i64>, i32)
|
||||
|
||||
define void @gather_mask_dd(<16 x i32> %ind, <16 x i32> %src, i16 %mask, i8* %base, i8* %stbuf) {
|
||||
|
|
@ -97,7 +93,8 @@ define void @gather_mask_dd(<16 x i32> %ind, <16 x i32> %src, i16 %mask, i8* %ba
|
|||
; CHECK-NEXT: vpscatterdd %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <16 x i32> @llvm.x86.avx512.gather.dpi.512 (<16 x i32> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%x = call <16 x i32> @llvm.x86.avx512.mask.gather.dpi.512(<16 x i32> %src, i8* %base, <16 x i32> %ind, <16 x i1> %1, i32 4)
|
||||
%ind2 = add <16 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpi.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind2, <16 x i32> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -113,7 +110,8 @@ define void @gather_mask_qd(<8 x i64> %ind, <8 x i32> %src, i8 %mask, i8* %base,
|
|||
; CHECK-NEXT: vpscatterqd %ymm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i32> @llvm.x86.avx512.gather.qpi.512 (<8 x i32> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x i32> @llvm.x86.avx512.mask.gather.qpi.512(<8 x i32> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpi.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x i32> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -129,7 +127,8 @@ define void @gather_mask_qq(<8 x i64> %ind, <8 x i64> %src, i8 %mask, i8* %base,
|
|||
; CHECK-NEXT: vpscatterqq %zmm1, (%rdx,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i64> @llvm.x86.avx512.gather.qpq.512 (<8 x i64> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x i64> @llvm.x86.avx512.mask.gather.qpq.512(<8 x i64> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qpq.512 (i8* %stbuf, i8 %mask, <8 x i64>%ind2, <8 x i64> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -145,7 +144,8 @@ define void @gather_mask_dq(<8 x i32> %ind, <8 x i64> %src, i8 %mask, i8* %base,
|
|||
; CHECK-NEXT: vpscatterdq %zmm1, (%rdx,%ymm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x i64> @llvm.x86.avx512.gather.dpq.512 (<8 x i64> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x i64> @llvm.x86.avx512.mask.gather.dpq.512(<8 x i64> %src, i8* %base, <8 x i32> %ind, <8 x i1> %1, i32 4)
|
||||
%ind2 = add <8 x i32> %ind, <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
||||
call void @llvm.x86.avx512.scatter.dpq.512 (i8* %stbuf, i8 %mask, <8 x i32>%ind2, <8 x i64> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -159,7 +159,8 @@ define void @gather_mask_dpd_execdomain(<8 x i32> %ind, <8 x double> %src, i8 %m
|
|||
; CHECK-NEXT: vmovapd %zmm1, (%rdx)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double> %src, i8* %base, <8 x i32>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x double> @llvm.x86.avx512.mask.gather.dpd.512(<8 x double> %src, i8* %base, <8 x i32> %ind, <8 x i1> %1, i32 4)
|
||||
store <8 x double> %x, <8 x double>* %stbuf
|
||||
ret void
|
||||
}
|
||||
|
|
@ -172,7 +173,8 @@ define void @gather_mask_qpd_execdomain(<8 x i64> %ind, <8 x double> %src, i8 %m
|
|||
; CHECK-NEXT: vmovapd %zmm1, (%rdx)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%x = call <8 x double> @llvm.x86.avx512.mask.gather.qpd.512(<8 x double> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
store <8 x double> %x, <8 x double>* %stbuf
|
||||
ret void
|
||||
}
|
||||
|
|
@ -184,8 +186,9 @@ define <16 x float> @gather_mask_dps_execdomain(<16 x i32> %ind, <16 x float> %s
|
|||
; CHECK-NEXT: vgatherdps (%rsi,%zmm0,4), %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 %mask, i32 4)
|
||||
ret <16 x float> %res;
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%res = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> %1, i32 4)
|
||||
ret <16 x float> %res
|
||||
}
|
||||
|
||||
define <8 x float> @gather_mask_qps_execdomain(<8 x i64> %ind, <8 x float> %src, i8 %mask, i8* %base) {
|
||||
|
|
@ -195,8 +198,9 @@ define <8 x float> @gather_mask_qps_execdomain(<8 x i64> %ind, <8 x float> %src,
|
|||
; CHECK-NEXT: vgatherqps (%rsi,%zmm0,4), %ymm1 {%k1}
|
||||
; CHECK-NEXT: vmovaps %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 %mask, i32 4)
|
||||
ret <8 x float> %res;
|
||||
%1 = bitcast i8 %mask to <8 x i1>
|
||||
%res = call <8 x float> @llvm.x86.avx512.mask.gather.qps.512(<8 x float> %src, i8* %base, <8 x i64> %ind, <8 x i1> %1, i32 4)
|
||||
ret <8 x float> %res
|
||||
}
|
||||
|
||||
define void @scatter_mask_dpd_execdomain(<8 x i32> %ind, <8 x double>* %src, i8 %mask, i8* %base, i8* %stbuf) {
|
||||
|
|
@ -254,15 +258,15 @@ define void @scatter_mask_qps_execdomain(<8 x i64> %ind, <8 x float>* %src, i8 %
|
|||
define void @gather_qps(<8 x i64> %ind, <8 x float> %src, i8* %base, i8* %stbuf) {
|
||||
; CHECK-LABEL: gather_qps:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%zmm0,4), %ymm1 {%k2}
|
||||
; CHECK-NEXT: vpaddq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; CHECK-NEXT: vscatterqps %ymm1, (%rsi,%zmm0,4) {%k1}
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%x = call <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float> %src, i8* %base, <8 x i64>%ind, i8 -1, i32 4)
|
||||
%x = call <8 x float> @llvm.x86.avx512.mask.gather.qps.512(<8 x float> %src, i8* %base, <8 x i64> %ind, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 4)
|
||||
%ind2 = add <8 x i64> %ind, <i64 0, i64 1, i64 2, i64 3, i64 0, i64 1, i64 2, i64 3>
|
||||
call void @llvm.x86.avx512.scatter.qps.512 (i8* %stbuf, i8 -1, <8 x i64>%ind2, <8 x float> %x, i32 4)
|
||||
ret void
|
||||
|
|
@ -292,10 +296,8 @@ define void @prefetch(<8 x i64> %ind, i8* %base) {
|
|||
ret void
|
||||
}
|
||||
|
||||
declare <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <2 x double>@test_int_x86_avx512_gather3div2_df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div2_df:
|
||||
define <2 x double> @test_int_x86_avx512_mask_gather3div2_df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
|
|
@ -304,31 +306,33 @@ define <2 x double>@test_int_x86_avx512_gather3div2_df(<2 x double> %x0, i8* %x1
|
|||
; CHECK-NEXT: vgatherqpd (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res = call <2 x double> @llvm.x86.avx512.mask.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> %extract, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.mask.gather3div2.df(<2 x double> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> <i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <2 x double> %res, %res1
|
||||
ret <2 x double> %res2
|
||||
}
|
||||
|
||||
declare <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <2 x i64>@test_int_x86_avx512_gather3div2_di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div2_di:
|
||||
define <2 x i64> @test_int_x86_avx512_mask_gather3div2_di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherqq (%rdi,%xmm1,8), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 8)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract1 = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res = call <2 x i64> @llvm.x86.avx512.mask.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> %extract1, i32 8)
|
||||
%2 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.mask.gather3div2.di(<2 x i64> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> %extract, i32 8)
|
||||
%res2 = add <2 x i64> %res, %res1
|
||||
ret <2 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x double>@test_int_x86_avx512_gather3div4_df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_df:
|
||||
define <4 x double> @test_int_x86_avx512_mask_gather3div4_df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqpd (%rdi,%ymm1,4), %ymm0 {%k1}
|
||||
|
|
@ -337,16 +341,16 @@ define <4 x double>@test_int_x86_avx512_gather3div4_df(<4 x double> %x0, i8* %x1
|
|||
; CHECK-NEXT: vgatherqpd (%rdi,%ymm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x double> @llvm.x86.avx512.mask.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> %extract, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.mask.gather3div4.df(<4 x double> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <4 x double> %res, %res1
|
||||
ret <4 x double> %res2
|
||||
}
|
||||
|
||||
declare <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x i64>@test_int_x86_avx512_gather3div4_di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_di:
|
||||
define <4 x i64> @test_int_x86_avx512_mask_gather3div4_di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherqq (%rdi,%ymm1,8), %ymm0 {%k1}
|
||||
|
|
@ -355,16 +359,16 @@ define <4 x i64>@test_int_x86_avx512_gather3div4_di(<4 x i64> %x0, i8* %x1, <4 x
|
|||
; CHECK-NEXT: vpgatherqq (%rdi,%ymm1,8), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vpaddq %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 8)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x i64> @llvm.x86.avx512.mask.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> %extract, i32 8)
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.mask.gather3div4.di(<4 x i64> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 8)
|
||||
%res2 = add <4 x i64> %res, %res1
|
||||
ret <4 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3div4_sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_sf:
|
||||
define <4 x float> @test_int_x86_avx512_mask_gather3div4_sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
|
|
@ -373,34 +377,34 @@ define <4 x float>@test_int_x86_avx512_gather3div4_sf(<4 x float> %x0, i8* %x1,
|
|||
; CHECK-NEXT: vgatherqps (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res = call <4 x float> @llvm.x86.avx512.mask.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> %extract, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.mask.gather3div4.sf(<4 x float> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> <i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32>, i8*, <2 x i64>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3div4_si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div4_si:
|
||||
define <4 x i32> @test_int_x86_avx512_mask_gather3div4_si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%xmm1,4), %xmm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%xmm1,4), %xmm2 {%k1}
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherqd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 -1, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, i8 %x3, i32 4)
|
||||
%res = call <4 x i32> @llvm.x86.avx512.mask.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> <i1 true, i1 true>, i32 4)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.mask.gather3div4.si(<4 x i32> %x0, i8* %x1, <2 x i64> %x2, <2 x i1> %extract, i32 4)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3div8_sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div8_sf:
|
||||
define <4 x float> @test_int_x86_avx512_mask_gather3div8_sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherqps (%rdi,%ymm1,4), %xmm0 {%k1}
|
||||
|
|
@ -410,16 +414,16 @@ define <4 x float>@test_int_x86_avx512_gather3div8_sf(<4 x float> %x0, i8* %x1,
|
|||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x float> @llvm.x86.avx512.mask.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> %extract, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.mask.gather3div8.sf(<4 x float> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32>, i8*, <4 x i64>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3div8_si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3div8_si:
|
||||
define <4 x i32> @test_int_x86_avx512_mask_gather3div8_si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3div8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovdqa %xmm0, %xmm2
|
||||
|
|
@ -429,16 +433,18 @@ define <4 x i32>@test_int_x86_avx512_gather3div8_si(<4 x i32> %x0, i8* %x1, <4 x
|
|||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, i8 %x3, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract1 = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x i32> @llvm.x86.avx512.mask.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> %extract1, i32 4)
|
||||
%2 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.mask.gather3div8.si(<4 x i32> %x0, i8* %x1, <4 x i64> %x2, <4 x i1> %extract, i32 2)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <2 x double>@test_int_x86_avx512_gather3siv2_df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv2_df:
|
||||
define <2 x double> @test_int_x86_avx512_mask_gather3siv2_df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv2_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
|
|
@ -447,31 +453,33 @@ define <2 x double>@test_int_x86_avx512_gather3siv2_df(<2 x double> %x0, i8* %x1
|
|||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res = call <2 x double> @llvm.x86.avx512.mask.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, <2 x i1> %extract, i32 4)
|
||||
%res1 = call <2 x double> @llvm.x86.avx512.mask.gather3siv2.df(<2 x double> %x0, i8* %x1, <4 x i32> %x2, <2 x i1> <i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <2 x double> %res, %res1
|
||||
ret <2 x double> %res2
|
||||
}
|
||||
|
||||
declare <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <2 x i64>@test_int_x86_avx512_gather3siv2_di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv2_di:
|
||||
define <2 x i64> @test_int_x86_avx512_mask_gather3siv2_di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv2_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherdq (%rdi,%xmm1,8), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract1 = shufflevector <8 x i1> %1, <8 x i1> %1, <2 x i32> <i32 0, i32 1>
|
||||
%res = call <2 x i64> @llvm.x86.avx512.mask.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, <2 x i1> %extract1, i32 8)
|
||||
%2 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
|
||||
%res1 = call <2 x i64> @llvm.x86.avx512.mask.gather3siv2.di(<2 x i64> %x0, i8* %x1, <4 x i32> %x2, <2 x i1> %extract, i32 8)
|
||||
%res2 = add <2 x i64> %res, %res1
|
||||
ret <2 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x double>@test_int_x86_avx512_gather3siv4_df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_df:
|
||||
define <4 x double> @test_int_x86_avx512_mask_gather3siv4_df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv4_df:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,4), %ymm0 {%k1}
|
||||
|
|
@ -480,31 +488,33 @@ define <4 x double>@test_int_x86_avx512_gather3siv4_df(<4 x double> %x0, i8* %x1
|
|||
; CHECK-NEXT: vgatherdpd (%rdi,%xmm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x double> @llvm.x86.avx512.mask.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> %extract, i32 4)
|
||||
%res1 = call <4 x double> @llvm.x86.avx512.mask.gather3siv4.df(<4 x double> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <4 x double> %res, %res1
|
||||
ret <4 x double> %res2
|
||||
}
|
||||
|
||||
declare <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x i64>@test_int_x86_avx512_gather3siv4_di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_di:
|
||||
define <4 x i64> @test_int_x86_avx512_mask_gather3siv4_di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv4_di:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherdq (%rdi,%xmm1,8), %ymm0 {%k1}
|
||||
; CHECK-NEXT: vpaddq %ymm0, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 8)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract1 = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x i64> @llvm.x86.avx512.mask.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> %extract1, i32 8)
|
||||
%2 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res1 = call <4 x i64> @llvm.x86.avx512.mask.gather3siv4.di(<4 x i64> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> %extract, i32 8)
|
||||
%res2 = add <4 x i64> %res, %res1
|
||||
ret <4 x i64> %res2
|
||||
}
|
||||
|
||||
declare <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x float>@test_int_x86_avx512_gather3siv4_sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_sf:
|
||||
define <4 x float> @test_int_x86_avx512_mask_gather3siv4_sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv4_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%xmm1,4), %xmm0 {%k1}
|
||||
|
|
@ -513,34 +523,34 @@ define <4 x float>@test_int_x86_avx512_gather3siv4_sf(<4 x float> %x0, i8* %x1,
|
|||
; CHECK-NEXT: vgatherdps (%rdi,%xmm1,2), %xmm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res = call <4 x float> @llvm.x86.avx512.mask.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> %extract, i32 4)
|
||||
%res1 = call <4 x float> @llvm.x86.avx512.mask.gather3siv4.sf(<4 x float> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <4 x float> %res, %res1
|
||||
ret <4 x float> %res2
|
||||
}
|
||||
|
||||
declare <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32>, i8*, <4 x i32>, i8, i32)
|
||||
|
||||
define <4 x i32>@test_int_x86_avx512_gather3siv4_si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv4_si:
|
||||
define <4 x i32> @test_int_x86_avx512_mask_gather3siv4_si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv4_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k2
|
||||
; CHECK-NEXT: kxnorw %k0, %k0, %k1
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%xmm1,4), %xmm2 {%k2}
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%xmm1,4), %xmm2 {%k1}
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vpgatherdd (%rdi,%xmm1,2), %xmm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 -1, i32 4)
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, i8 %x3, i32 2)
|
||||
%res = call <4 x i32> @llvm.x86.avx512.mask.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 4)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%extract = shufflevector <8 x i1> %1, <8 x i1> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
%res1 = call <4 x i32> @llvm.x86.avx512.mask.gather3siv4.si(<4 x i32> %x0, i8* %x1, <4 x i32> %x2, <4 x i1> %extract, i32 2)
|
||||
%res2 = add <4 x i32> %res, %res1
|
||||
ret <4 x i32> %res2
|
||||
}
|
||||
|
||||
declare <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float>, i8*, <8 x i32>, i8, i32)
|
||||
|
||||
define <8 x float>@test_int_x86_avx512_gather3siv8_sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv8_sf:
|
||||
define <8 x float> @test_int_x86_avx512_mask_gather3siv8_sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv8_sf:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vgatherdps (%rdi,%ymm1,4), %ymm0 {%k1}
|
||||
|
|
@ -549,16 +559,15 @@ define <8 x float>@test_int_x86_avx512_gather3siv8_sf(<8 x float> %x0, i8* %x1,
|
|||
; CHECK-NEXT: vgatherdps (%rdi,%ymm1,2), %ymm2 {%k1}
|
||||
; CHECK-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <8 x float> @llvm.x86.avx512.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, i8 -1, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%res = call <8 x float> @llvm.x86.avx512.mask.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, <8 x i1> %1, i32 4)
|
||||
%res1 = call <8 x float> @llvm.x86.avx512.mask.gather3siv8.sf(<8 x float> %x0, i8* %x1, <8 x i32> %x2, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 2)
|
||||
%res2 = fadd <8 x float> %res, %res1
|
||||
ret <8 x float> %res2
|
||||
}
|
||||
|
||||
declare <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32>, i8*, <8 x i32>, i8, i32)
|
||||
|
||||
define <8 x i32>@test_int_x86_avx512_gather3siv8_si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_gather3siv8_si:
|
||||
define <8 x i32> @test_int_x86_avx512_mask_gather3siv8_si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3) {
|
||||
; CHECK-LABEL: test_int_x86_avx512_mask_gather3siv8_si:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: kmovd %esi, %k1
|
||||
; CHECK-NEXT: vmovdqa %ymm0, %ymm2
|
||||
|
|
@ -567,8 +576,10 @@ define <8 x i32>@test_int_x86_avx512_gather3siv8_si(<8 x i32> %x0, i8* %x1, <8 x
|
|||
; CHECK-NEXT: vpgatherdd (%rdi,%ymm1,2), %ymm0 {%k1}
|
||||
; CHECK-NEXT: vpaddd %ymm0, %ymm2, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 4)
|
||||
%res1 = call <8 x i32> @llvm.x86.avx512.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, i8 %x3, i32 2)
|
||||
%1 = bitcast i8 %x3 to <8 x i1>
|
||||
%res = call <8 x i32> @llvm.x86.avx512.mask.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, <8 x i1> %1, i32 4)
|
||||
%2 = bitcast i8 %x3 to <8 x i1>
|
||||
%res1 = call <8 x i32> @llvm.x86.avx512.mask.gather3siv8.si(<8 x i32> %x0, i8* %x1, <8 x i32> %x2, <8 x i1> %2, i32 2)
|
||||
%res2 = add <8 x i32> %res, %res1
|
||||
ret <8 x i32> %res2
|
||||
}
|
||||
|
|
@ -863,13 +874,37 @@ define <16 x float> @gather_mask_test(<16 x i32> %ind, <16 x float> %src, i8* %b
|
|||
; CHECK-NEXT: vaddps %zmm3, %zmm1, %zmm0
|
||||
; CHECK-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 -1, i32 4)
|
||||
%res1 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 0, i32 4)
|
||||
%res2 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 1, i32 4)
|
||||
%res3 = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%ind, i16 220, i32 4)
|
||||
|
||||
%res = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 4)
|
||||
%res1 = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> zeroinitializer, i32 4)
|
||||
%res2 = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> bitcast (<1 x i16> <i16 1> to <16 x i1>), i32 4)
|
||||
%res3 = call <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float> %src, i8* %base, <16 x i32> %ind, <16 x i1> bitcast (<1 x i16> <i16 220> to <16 x i1>), i32 4)
|
||||
%res4 = fadd <16 x float> %res, %res1
|
||||
%res5 = fadd <16 x float> %res3, %res2
|
||||
%res6 = fadd <16 x float> %res5, %res4
|
||||
ret <16 x float> %res6
|
||||
}
|
||||
|
||||
declare <16 x float> @llvm.x86.avx512.mask.gather.dps.512(<16 x float>, i8*, <16 x i32>, <16 x i1>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.mask.gather.dpd.512(<8 x double>, i8*, <8 x i32>, <8 x i1>, i32)
|
||||
declare <8 x float> @llvm.x86.avx512.mask.gather.qps.512(<8 x float>, i8*, <8 x i64>, <8 x i1>, i32)
|
||||
declare <8 x double> @llvm.x86.avx512.mask.gather.qpd.512(<8 x double>, i8*, <8 x i64>, <8 x i1>, i32)
|
||||
declare <16 x i32> @llvm.x86.avx512.mask.gather.dpi.512(<16 x i32>, i8*, <16 x i32>, <16 x i1>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.mask.gather.dpq.512(<8 x i64>, i8*, <8 x i32>, <8 x i1>, i32)
|
||||
declare <8 x i32> @llvm.x86.avx512.mask.gather.qpi.512(<8 x i32>, i8*, <8 x i64>, <8 x i1>, i32)
|
||||
declare <8 x i64> @llvm.x86.avx512.mask.gather.qpq.512(<8 x i64>, i8*, <8 x i64>, <8 x i1>, i32)
|
||||
declare <2 x double> @llvm.x86.avx512.mask.gather3div2.df(<2 x double>, i8*, <2 x i64>, <2 x i1>, i32)
|
||||
declare <2 x i64> @llvm.x86.avx512.mask.gather3div2.di(<2 x i64>, i8*, <2 x i64>, <2 x i1>, i32)
|
||||
declare <4 x double> @llvm.x86.avx512.mask.gather3div4.df(<4 x double>, i8*, <4 x i64>, <4 x i1>, i32)
|
||||
declare <4 x i64> @llvm.x86.avx512.mask.gather3div4.di(<4 x i64>, i8*, <4 x i64>, <4 x i1>, i32)
|
||||
declare <4 x float> @llvm.x86.avx512.mask.gather3div4.sf(<4 x float>, i8*, <2 x i64>, <2 x i1>, i32)
|
||||
declare <4 x i32> @llvm.x86.avx512.mask.gather3div4.si(<4 x i32>, i8*, <2 x i64>, <2 x i1>, i32)
|
||||
declare <4 x float> @llvm.x86.avx512.mask.gather3div8.sf(<4 x float>, i8*, <4 x i64>, <4 x i1>, i32)
|
||||
declare <4 x i32> @llvm.x86.avx512.mask.gather3div8.si(<4 x i32>, i8*, <4 x i64>, <4 x i1>, i32)
|
||||
declare <2 x double> @llvm.x86.avx512.mask.gather3siv2.df(<2 x double>, i8*, <4 x i32>, <2 x i1>, i32)
|
||||
declare <2 x i64> @llvm.x86.avx512.mask.gather3siv2.di(<2 x i64>, i8*, <4 x i32>, <2 x i1>, i32)
|
||||
declare <4 x double> @llvm.x86.avx512.mask.gather3siv4.df(<4 x double>, i8*, <4 x i32>, <4 x i1>, i32)
|
||||
declare <4 x i64> @llvm.x86.avx512.mask.gather3siv4.di(<4 x i64>, i8*, <4 x i32>, <4 x i1>, i32)
|
||||
declare <4 x float> @llvm.x86.avx512.mask.gather3siv4.sf(<4 x float>, i8*, <4 x i32>, <4 x i1>, i32)
|
||||
declare <4 x i32> @llvm.x86.avx512.mask.gather3siv4.si(<4 x i32>, i8*, <4 x i32>, <4 x i1>, i32)
|
||||
declare <8 x float> @llvm.x86.avx512.mask.gather3siv8.sf(<8 x float>, i8*, <8 x i32>, <8 x i1>, i32)
|
||||
declare <8 x i32> @llvm.x86.avx512.mask.gather3siv8.si(<8 x i32>, i8*, <8 x i32>, <8 x i1>, i32)
|
||||
|
|
|
|||
Loading…
Reference in New Issue