Benjamin Kramer
1a20252978
Revert "Reland "Reland "Reland "[X86][RFC] Enable _Float16 type support on X86 following the psABI""""
...
This reverts commit 04a3d5f3a1193fb87576425a385aa0a6115b1e7c.
I see two more issues:
- uitofp/sitofp from i32/i64 to half now generates
__floatsihf/__floatdihf, which exists in neither compiler-rt nor
libgcc
- This crashes when legalizing the bitcast:
```
; RUN: llc < %s -mcpu=skx
define void @main.45(ptr nocapture readnone %retval, ptr noalias nocapture readnone %run_options, ptr noalias nocapture readnone %params, ptr noalias nocapture readonly %buffer_table, ptr noalias nocapture readnone %status, ptr noalias nocapture readnone %prof_counters) local_unnamed_addr {
entry:
%fusion = load ptr, ptr %buffer_table, align 8
%0 = getelementptr inbounds ptr, ptr %buffer_table, i64 1
%Arg_1.2 = load ptr, ptr %0, align 8
%1 = getelementptr inbounds ptr, ptr %buffer_table, i64 2
%Arg_0.1 = load ptr, ptr %1, align 8
%2 = load half, ptr %Arg_0.1, align 8
%3 = bitcast half %2 to i16
%4 = and i16 %3, 32767
%5 = icmp eq i16 %4, 0
%6 = and i16 %3, -32768
%broadcast.splatinsert = insertelement <4 x half> poison, half %2, i64 0
%broadcast.splat = shufflevector <4 x half> %broadcast.splatinsert, <4 x half> poison, <4 x i32> zeroinitializer
%broadcast.splatinsert9 = insertelement <4 x i16> poison, i16 %4, i64 0
%broadcast.splat10 = shufflevector <4 x i16> %broadcast.splatinsert9, <4 x i16> poison, <4 x i32> zeroinitializer
%broadcast.splatinsert11 = insertelement <4 x i16> poison, i16 %6, i64 0
%broadcast.splat12 = shufflevector <4 x i16> %broadcast.splatinsert11, <4 x i16> poison, <4 x i32> zeroinitializer
%broadcast.splatinsert13 = insertelement <4 x i16> poison, i16 %3, i64 0
%broadcast.splat14 = shufflevector <4 x i16> %broadcast.splatinsert13, <4 x i16> poison, <4 x i32> zeroinitializer
%wide.load = load <4 x half>, ptr %Arg_1.2, align 8
%7 = fcmp uno <4 x half> %broadcast.splat, %wide.load
%8 = fcmp oeq <4 x half> %broadcast.splat, %wide.load
%9 = bitcast <4 x half> %wide.load to <4 x i16>
%10 = and <4 x i16> %9, <i16 32767, i16 32767, i16 32767, i16 32767>
%11 = icmp eq <4 x i16> %10, zeroinitializer
%12 = and <4 x i16> %9, <i16 -32768, i16 -32768, i16 -32768, i16 -32768>
%13 = or <4 x i16> %12, <i16 1, i16 1, i16 1, i16 1>
%14 = select <4 x i1> %11, <4 x i16> %9, <4 x i16> %13
%15 = icmp ugt <4 x i16> %broadcast.splat10, %10
%16 = icmp ne <4 x i16> %broadcast.splat12, %12
%17 = or <4 x i1> %15, %16
%18 = select <4 x i1> %17, <4 x i16> <i16 -1, i16 -1, i16 -1, i16 -1>, <4 x i16> <i16 1, i16 1, i16 1, i16 1>
%19 = add <4 x i16> %18, %broadcast.splat14
%20 = select i1 %5, <4 x i16> %14, <4 x i16> %19
%21 = select <4 x i1> %8, <4 x i16> %9, <4 x i16> %20
%22 = bitcast <4 x i16> %21 to <4 x half>
%23 = select <4 x i1> %7, <4 x half> <half 0xH7E00, half 0xH7E00, half 0xH7E00, half 0xH7E00>, <4 x half> %22
store <4 x half> %23, ptr %fusion, align 16
ret void
}
```
llc: llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp:977: void (anonymous namespace)::SelectionDAGLegalize::LegalizeOp(llvm::SDNode *): Assertion `(TLI.getTypeAction(*DAG.getContext(), Op.getValueType()) == TargetLowering::TypeLegal || Op.getOpcode() == ISD::TargetConstant || Op.getOpcode() == ISD::Register) && "Unexpected illegal type!"' failed.
2022-06-17 09:43:07 +02:00
Frederik Gossen
3cd5696a33
Revert "Reland "Reland "[X86][RFC] Enable _Float16 type support on X86 following the psABI"""
...
This reverts commit e1c5afa47d37012499467b5061fc42e50884d129.
This introduces crashes in the JAX backend on CPU. A reproducer in LLVM is
below. Let me know if you have trouble reproducing this.
; ModuleID = '__compute_module'
source_filename = "__compute_module"
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-grtev4-linux-gnu"
@0 = private unnamed_addr constant [4 x i8] c"\00\00\00?"
@1 = private unnamed_addr constant [4 x i8] c"\1C}\908"
@2 = private unnamed_addr constant [4 x i8] c"?\00\\4"
@3 = private unnamed_addr constant [4 x i8] c"%ci1"
@4 = private unnamed_addr constant [4 x i8] zeroinitializer
@5 = private unnamed_addr constant [4 x i8] c"\00\00\00\C0"
@6 = private unnamed_addr constant [4 x i8] c"\00\00\00B"
@7 = private unnamed_addr constant [4 x i8] c"\94\B4\C22"
@8 = private unnamed_addr constant [4 x i8] c"^\09B6"
@9 = private unnamed_addr constant [4 x i8] c"\15\F3M?"
@10 = private unnamed_addr constant [4 x i8] c"e\CC\\;"
@11 = private unnamed_addr constant [4 x i8] c"d\BD/>"
@12 = private unnamed_addr constant [4 x i8] c"V\F4I="
@13 = private unnamed_addr constant [4 x i8] c"\10\CB,<"
@14 = private unnamed_addr constant [4 x i8] c"\AC\E3\D6:"
@15 = private unnamed_addr constant [4 x i8] c"\DC\A8E9"
@16 = private unnamed_addr constant [4 x i8] c"\C6\FA\897"
@17 = private unnamed_addr constant [4 x i8] c"%\F9\955"
@18 = private unnamed_addr constant [4 x i8] c"\B5\DB\813"
@19 = private unnamed_addr constant [4 x i8] c"\B4W_\B2"
@20 = private unnamed_addr constant [4 x i8] c"\1Cc\8F\B4"
@21 = private unnamed_addr constant [4 x i8] c"~3\94\B6"
@22 = private unnamed_addr constant [4 x i8] c"3Yq\B8"
@23 = private unnamed_addr constant [4 x i8] c"\E9\17\17\BA"
@24 = private unnamed_addr constant [4 x i8] c"\F1\B2\8D\BB"
@25 = private unnamed_addr constant [4 x i8] c"\F8t\C2\BC"
@26 = private unnamed_addr constant [4 x i8] c"\82[\C2\BD"
@27 = private unnamed_addr constant [4 x i8] c"uB-?"
@28 = private unnamed_addr constant [4 x i8] c"^\FF\9B\BE"
@29 = private unnamed_addr constant [4 x i8] c"\00\00\00A"
; Function Attrs: uwtable
define void @main.158(ptr %retval, ptr noalias %run_options, ptr noalias %params, ptr noalias %buffer_table, ptr noalias %status, ptr noalias %prof_counters) #0 {
entry:
%fusion.invar_address.dim.1 = alloca i64, align 8
%fusion.invar_address.dim.0 = alloca i64, align 8
%0 = getelementptr inbounds ptr, ptr %buffer_table, i64 1
%Arg_0.1 = load ptr, ptr %0, align 8, !invariant.load !0 , !dereferenceable !1 , !align !2
%1 = getelementptr inbounds ptr, ptr %buffer_table, i64 0
%fusion = load ptr, ptr %1, align 8, !invariant.load !0 , !dereferenceable !1 , !align !2
store i64 0, ptr %fusion.invar_address.dim.0, align 8
br label %fusion.loop_header.dim.0
return: ; preds = %fusion.loop_exit.dim.0
ret void
fusion.loop_header.dim.0: ; preds = %fusion.loop_exit.dim.1, %entry
%fusion.indvar.dim.0 = load i64, ptr %fusion.invar_address.dim.0, align 8
%2 = icmp uge i64 %fusion.indvar.dim.0, 3
br i1 %2, label %fusion.loop_exit.dim.0, label %fusion.loop_body.dim.0
fusion.loop_body.dim.0: ; preds = %fusion.loop_header.dim.0
store i64 0, ptr %fusion.invar_address.dim.1, align 8
br label %fusion.loop_header.dim.1
fusion.loop_header.dim.1: ; preds = %fusion.loop_body.dim.1, %fusion.loop_body.dim.0
%fusion.indvar.dim.1 = load i64, ptr %fusion.invar_address.dim.1, align 8
%3 = icmp uge i64 %fusion.indvar.dim.1, 1
br i1 %3, label %fusion.loop_exit.dim.1, label %fusion.loop_body.dim.1
fusion.loop_body.dim.1: ; preds = %fusion.loop_header.dim.1
%4 = getelementptr inbounds [3 x [1 x half]], ptr %Arg_0.1, i64 0, i64 %fusion.indvar.dim.0, i64 0
%5 = load half, ptr %4, align 2, !invariant.load !0 , !noalias !3
%6 = fpext half %5 to float
%7 = call float @llvm.fabs.f32(float %6)
%constant.121 = load float, ptr @29, align 4
%compare.2 = fcmp ole float %7, %constant.121
%8 = zext i1 %compare.2 to i8
%constant.120 = load float, ptr @0, align 4
%multiply.95 = fmul float %7, %constant.120
%constant.119 = load float, ptr @5, align 4
%add.82 = fadd float %multiply.95, %constant.119
%constant.118 = load float, ptr @4, align 4
%multiply.94 = fmul float %add.82, %constant.118
%constant.117 = load float, ptr @19, align 4
%add.81 = fadd float %multiply.94, %constant.117
%multiply.92 = fmul float %add.82, %add.81
%constant.116 = load float, ptr @18, align 4
%add.79 = fadd float %multiply.92, %constant.116
%multiply.91 = fmul float %add.82, %add.79
%subtract.87 = fsub float %multiply.91, %add.81
%constant.115 = load float, ptr @20, align 4
%add.78 = fadd float %subtract.87, %constant.115
%multiply.89 = fmul float %add.82, %add.78
%subtract.86 = fsub float %multiply.89, %add.79
%constant.114 = load float, ptr @17, align 4
%add.76 = fadd float %subtract.86, %constant.114
%multiply.88 = fmul float %add.82, %add.76
%subtract.84 = fsub float %multiply.88, %add.78
%constant.113 = load float, ptr @21, align 4
%add.75 = fadd float %subtract.84, %constant.113
%multiply.86 = fmul float %add.82, %add.75
%subtract.83 = fsub float %multiply.86, %add.76
%constant.112 = load float, ptr @16, align 4
%add.73 = fadd float %subtract.83, %constant.112
%multiply.85 = fmul float %add.82, %add.73
%subtract.81 = fsub float %multiply.85, %add.75
%constant.111 = load float, ptr @22, align 4
%add.72 = fadd float %subtract.81, %constant.111
%multiply.83 = fmul float %add.82, %add.72
%subtract.80 = fsub float %multiply.83, %add.73
%constant.110 = load float, ptr @15, align 4
%add.70 = fadd float %subtract.80, %constant.110
%multiply.82 = fmul float %add.82, %add.70
%subtract.78 = fsub float %multiply.82, %add.72
%constant.109 = load float, ptr @23, align 4
%add.69 = fadd float %subtract.78, %constant.109
%multiply.80 = fmul float %add.82, %add.69
%subtract.77 = fsub float %multiply.80, %add.70
%constant.108 = load float, ptr @14, align 4
%add.68 = fadd float %subtract.77, %constant.108
%multiply.79 = fmul float %add.82, %add.68
%subtract.75 = fsub float %multiply.79, %add.69
%constant.107 = load float, ptr @24, align 4
%add.67 = fadd float %subtract.75, %constant.107
%multiply.77 = fmul float %add.82, %add.67
%subtract.74 = fsub float %multiply.77, %add.68
%constant.106 = load float, ptr @13, align 4
%add.66 = fadd float %subtract.74, %constant.106
%multiply.76 = fmul float %add.82, %add.66
%subtract.72 = fsub float %multiply.76, %add.67
%constant.105 = load float, ptr @25, align 4
%add.65 = fadd float %subtract.72, %constant.105
%multiply.74 = fmul float %add.82, %add.65
%subtract.71 = fsub float %multiply.74, %add.66
%constant.104 = load float, ptr @12, align 4
%add.64 = fadd float %subtract.71, %constant.104
%multiply.73 = fmul float %add.82, %add.64
%subtract.69 = fsub float %multiply.73, %add.65
%constant.103 = load float, ptr @26, align 4
%add.63 = fadd float %subtract.69, %constant.103
%multiply.71 = fmul float %add.82, %add.63
%subtract.67 = fsub float %multiply.71, %add.64
%constant.102 = load float, ptr @11, align 4
%add.62 = fadd float %subtract.67, %constant.102
%multiply.70 = fmul float %add.82, %add.62
%subtract.66 = fsub float %multiply.70, %add.63
%constant.101 = load float, ptr @28, align 4
%add.61 = fadd float %subtract.66, %constant.101
%multiply.68 = fmul float %add.82, %add.61
%subtract.65 = fsub float %multiply.68, %add.62
%constant.100 = load float, ptr @27, align 4
%add.60 = fadd float %subtract.65, %constant.100
%subtract.64 = fsub float %add.60, %add.62
%multiply.66 = fmul float %subtract.64, %constant.120
%constant.99 = load float, ptr @6, align 4
%divide.4 = fdiv float %constant.99, %7
%add.59 = fadd float %divide.4, %constant.119
%multiply.65 = fmul float %add.59, %constant.118
%constant.98 = load float, ptr @3, align 4
%add.58 = fadd float %multiply.65, %constant.98
%multiply.64 = fmul float %add.59, %add.58
%constant.97 = load float, ptr @7, align 4
%add.57 = fadd float %multiply.64, %constant.97
%multiply.63 = fmul float %add.59, %add.57
%subtract.63 = fsub float %multiply.63, %add.58
%constant.96 = load float, ptr @2, align 4
%add.56 = fadd float %subtract.63, %constant.96
%multiply.62 = fmul float %add.59, %add.56
%subtract.62 = fsub float %multiply.62, %add.57
%constant.95 = load float, ptr @8, align 4
%add.55 = fadd float %subtract.62, %constant.95
%multiply.61 = fmul float %add.59, %add.55
%subtract.61 = fsub float %multiply.61, %add.56
%constant.94 = load float, ptr @1, align 4
%add.54 = fadd float %subtract.61, %constant.94
%multiply.60 = fmul float %add.59, %add.54
%subtract.60 = fsub float %multiply.60, %add.55
%constant.93 = load float, ptr @10, align 4
%add.53 = fadd float %subtract.60, %constant.93
%multiply.59 = fmul float %add.59, %add.53
%subtract.59 = fsub float %multiply.59, %add.54
%constant.92 = load float, ptr @9, align 4
%add.52 = fadd float %subtract.59, %constant.92
%subtract.58 = fsub float %add.52, %add.54
%multiply.58 = fmul float %subtract.58, %constant.120
%9 = call float @llvm.sqrt.f32(float %7)
%10 = fdiv float 1.000000e+00, %9
%multiply.57 = fmul float %multiply.58, %10
%11 = trunc i8 %8 to i1
%12 = select i1 %11, float %multiply.66, float %multiply.57
%13 = fptrunc float %12 to half
%14 = getelementptr inbounds [3 x [1 x half]], ptr %fusion, i64 0, i64 %fusion.indvar.dim.0, i64 0
store half %13, ptr %14, align 2, !alias.scope !3
%invar.inc1 = add nuw nsw i64 %fusion.indvar.dim.1, 1
store i64 %invar.inc1, ptr %fusion.invar_address.dim.1, align 8
br label %fusion.loop_header.dim.1
fusion.loop_exit.dim.1: ; preds = %fusion.loop_header.dim.1
%invar.inc = add nuw nsw i64 %fusion.indvar.dim.0, 1
store i64 %invar.inc, ptr %fusion.invar_address.dim.0, align 8
br label %fusion.loop_header.dim.0
fusion.loop_exit.dim.0: ; preds = %fusion.loop_header.dim.0
br label %return
}
; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn
declare float @llvm.fabs.f32(float %0) #1
; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn
declare float @llvm.sqrt.f32(float %0) #1
attributes #0 = { uwtable "denormal-fp-math"="preserve-sign" "no-frame-pointer-elim"="false" }
attributes #1 = { nocallback nofree nosync nounwind readnone speculatable willreturn }
!0 = !{}
!1 = !{i64 6}
!2 = !{i64 8}
!3 = !{!4}
!4 = !{!"buffer: {index:0, offset:0, size:6}", !5}
!5 = !{!"XLA global AA domain"}
2022-06-15 18:04:42 -04:00
Thomas Joerg
37455b1f71
Revert "Reland "[X86][RFC] Enable _Float16 type support on X86 following the psABI""
...
This reverts commit 6e02e27536b9de25a651cfc9c2966ce471169355.
This introduces a crash in the backend. Reproducer in MLIR's LLVM
dialect follows. Let me know if you have trouble reproducing this.
module {
llvm.func @malloc(i64) -> !llvm.ptr<i8>
llvm.func @_mlir_ciface_tf_report_error(!llvm.ptr<i8>, i32, !llvm.ptr<i8>)
llvm.mlir.global internal constant @error_message_2208944672953921889("failed to allocate memory at loc(\22-\22:3:8)\00")
llvm.func @_mlir_ciface_tf_alloc(!llvm.ptr<i8>, i64, i64, i32, i32, !llvm.ptr<i32>) -> !llvm.ptr<i8>
llvm.func @Rsqrt_CPU_DT_HALF_DT_HALF(%arg0: !llvm.ptr<i8>, %arg1: i64, %arg2: !llvm.ptr<i8>) -> !llvm.struct<(i64, ptr<i8>)> attributes {llvm.emit_c_interface, tf_entry} {
%0 = llvm.mlir.constant(8 : i32) : i32
%1 = llvm.mlir.constant(8 : index) : i64
%2 = llvm.mlir.constant(2 : index) : i64
%3 = llvm.mlir.constant(dense<0.000000e+00> : vector<4xf16>) : vector<4xf16>
%4 = llvm.mlir.constant(dense<[0, 1, 2, 3]> : vector<4xi32>) : vector<4xi32>
%5 = llvm.mlir.constant(dense<1.000000e+00> : vector<4xf16>) : vector<4xf16>
%6 = llvm.mlir.constant(false) : i1
%7 = llvm.mlir.constant(1 : i32) : i32
%8 = llvm.mlir.constant(0 : i32) : i32
%9 = llvm.mlir.constant(4 : index) : i64
%10 = llvm.mlir.constant(0 : index) : i64
%11 = llvm.mlir.constant(1 : index) : i64
%12 = llvm.mlir.constant(-1 : index) : i64
%13 = llvm.mlir.null : !llvm.ptr<f16>
%14 = llvm.getelementptr %13[%9] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%15 = llvm.ptrtoint %14 : !llvm.ptr<f16> to i64
%16 = llvm.alloca %15 x f16 {alignment = 32 : i64} : (i64) -> !llvm.ptr<f16>
%17 = llvm.alloca %15 x f16 {alignment = 32 : i64} : (i64) -> !llvm.ptr<f16>
%18 = llvm.mlir.null : !llvm.ptr<i64>
%19 = llvm.getelementptr %18[%arg1] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
%20 = llvm.ptrtoint %19 : !llvm.ptr<i64> to i64
%21 = llvm.alloca %20 x i64 : (i64) -> !llvm.ptr<i64>
llvm.br ^bb1(%10 : i64)
^bb1(%22: i64): // 2 preds: ^bb0, ^bb2
%23 = llvm.icmp "slt" %22, %arg1 : i64
llvm.cond_br %23, ^bb2, ^bb3
^bb2: // pred: ^bb1
%24 = llvm.bitcast %arg2 : !llvm.ptr<i8> to !llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64)>>
%25 = llvm.getelementptr %24[%10, 2] : (!llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64)>>, i64) -> !llvm.ptr<i64>
%26 = llvm.add %22, %11 : i64
%27 = llvm.getelementptr %25[%26] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
%28 = llvm.load %27 : !llvm.ptr<i64>
%29 = llvm.getelementptr %21[%22] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
llvm.store %28, %29 : !llvm.ptr<i64>
llvm.br ^bb1(%26 : i64)
^bb3: // pred: ^bb1
llvm.br ^bb4(%10, %11 : i64, i64)
^bb4(%30: i64, %31: i64): // 2 preds: ^bb3, ^bb5
%32 = llvm.icmp "slt" %30, %arg1 : i64
llvm.cond_br %32, ^bb5, ^bb6
^bb5: // pred: ^bb4
%33 = llvm.bitcast %arg2 : !llvm.ptr<i8> to !llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64)>>
%34 = llvm.getelementptr %33[%10, 2] : (!llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64)>>, i64) -> !llvm.ptr<i64>
%35 = llvm.add %30, %11 : i64
%36 = llvm.getelementptr %34[%35] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
%37 = llvm.load %36 : !llvm.ptr<i64>
%38 = llvm.mul %37, %31 : i64
llvm.br ^bb4(%35, %38 : i64, i64)
^bb6: // pred: ^bb4
%39 = llvm.bitcast %arg2 : !llvm.ptr<i8> to !llvm.ptr<ptr<f16>>
%40 = llvm.getelementptr %39[%11] : (!llvm.ptr<ptr<f16>>, i64) -> !llvm.ptr<ptr<f16>>
%41 = llvm.load %40 : !llvm.ptr<ptr<f16>>
%42 = llvm.getelementptr %13[%11] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%43 = llvm.ptrtoint %42 : !llvm.ptr<f16> to i64
%44 = llvm.alloca %7 x i32 : (i32) -> !llvm.ptr<i32>
llvm.store %8, %44 : !llvm.ptr<i32>
%45 = llvm.call @_mlir_ciface_tf_alloc(%arg0, %31, %43, %8, %7, %44) : (!llvm.ptr<i8>, i64, i64, i32, i32, !llvm.ptr<i32>) -> !llvm.ptr<i8>
%46 = llvm.bitcast %45 : !llvm.ptr<i8> to !llvm.ptr<f16>
%47 = llvm.icmp "eq" %31, %10 : i64
%48 = llvm.or %6, %47 : i1
%49 = llvm.mlir.null : !llvm.ptr<i8>
%50 = llvm.icmp "ne" %45, %49 : !llvm.ptr<i8>
%51 = llvm.or %50, %48 : i1
llvm.cond_br %51, ^bb7, ^bb13
^bb7: // pred: ^bb6
%52 = llvm.urem %31, %9 : i64
%53 = llvm.sub %31, %52 : i64
llvm.br ^bb8(%10 : i64)
^bb8(%54: i64): // 2 preds: ^bb7, ^bb9
%55 = llvm.icmp "slt" %54, %53 : i64
llvm.cond_br %55, ^bb9, ^bb10
^bb9: // pred: ^bb8
%56 = llvm.mul %54, %11 : i64
%57 = llvm.add %56, %10 : i64
%58 = llvm.add %57, %10 : i64
%59 = llvm.getelementptr %41[%58] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%60 = llvm.bitcast %59 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
%61 = llvm.load %60 {alignment = 2 : i64} : !llvm.ptr<vector<4xf16>>
%62 = "llvm.intr.sqrt"(%61) : (vector<4xf16>) -> vector<4xf16>
%63 = llvm.fdiv %5, %62 : vector<4xf16>
%64 = llvm.getelementptr %46[%58] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%65 = llvm.bitcast %64 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
llvm.store %63, %65 {alignment = 2 : i64} : !llvm.ptr<vector<4xf16>>
%66 = llvm.add %54, %9 : i64
llvm.br ^bb8(%66 : i64)
^bb10: // pred: ^bb8
%67 = llvm.icmp "ult" %53, %31 : i64
llvm.cond_br %67, ^bb11, ^bb12
^bb11: // pred: ^bb10
%68 = llvm.mul %53, %12 : i64
%69 = llvm.add %31, %68 : i64
%70 = llvm.mul %53, %11 : i64
%71 = llvm.add %70, %10 : i64
%72 = llvm.trunc %69 : i64 to i32
%73 = llvm.mlir.undef : vector<4xi32>
%74 = llvm.insertelement %72, %73[%8 : i32] : vector<4xi32>
%75 = llvm.shufflevector %74, %73 [0 : i32, 0 : i32, 0 : i32, 0 : i32] : vector<4xi32>, vector<4xi32>
%76 = llvm.icmp "slt" %4, %75 : vector<4xi32>
%77 = llvm.add %71, %10 : i64
%78 = llvm.getelementptr %41[%77] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%79 = llvm.bitcast %78 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
%80 = llvm.intr.masked.load %79, %76, %3 {alignment = 2 : i32} : (!llvm.ptr<vector<4xf16>>, vector<4xi1>, vector<4xf16>) -> vector<4xf16>
%81 = llvm.bitcast %16 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
llvm.store %80, %81 : !llvm.ptr<vector<4xf16>>
%82 = llvm.load %81 {alignment = 2 : i64} : !llvm.ptr<vector<4xf16>>
%83 = "llvm.intr.sqrt"(%82) : (vector<4xf16>) -> vector<4xf16>
%84 = llvm.fdiv %5, %83 : vector<4xf16>
%85 = llvm.bitcast %17 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
llvm.store %84, %85 {alignment = 2 : i64} : !llvm.ptr<vector<4xf16>>
%86 = llvm.load %85 : !llvm.ptr<vector<4xf16>>
%87 = llvm.getelementptr %46[%77] : (!llvm.ptr<f16>, i64) -> !llvm.ptr<f16>
%88 = llvm.bitcast %87 : !llvm.ptr<f16> to !llvm.ptr<vector<4xf16>>
llvm.intr.masked.store %86, %88, %76 {alignment = 2 : i32} : vector<4xf16>, vector<4xi1> into !llvm.ptr<vector<4xf16>>
llvm.br ^bb12
^bb12: // 2 preds: ^bb10, ^bb11
%89 = llvm.mul %2, %1 : i64
%90 = llvm.mul %arg1, %2 : i64
%91 = llvm.add %90, %11 : i64
%92 = llvm.mul %91, %1 : i64
%93 = llvm.add %89, %92 : i64
%94 = llvm.alloca %93 x i8 : (i64) -> !llvm.ptr<i8>
%95 = llvm.bitcast %94 : !llvm.ptr<i8> to !llvm.ptr<ptr<f16>>
llvm.store %46, %95 : !llvm.ptr<ptr<f16>>
%96 = llvm.getelementptr %95[%11] : (!llvm.ptr<ptr<f16>>, i64) -> !llvm.ptr<ptr<f16>>
llvm.store %46, %96 : !llvm.ptr<ptr<f16>>
%97 = llvm.getelementptr %95[%2] : (!llvm.ptr<ptr<f16>>, i64) -> !llvm.ptr<ptr<f16>>
%98 = llvm.bitcast %97 : !llvm.ptr<ptr<f16>> to !llvm.ptr<i64>
llvm.store %10, %98 : !llvm.ptr<i64>
%99 = llvm.bitcast %94 : !llvm.ptr<i8> to !llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64, i64)>>
%100 = llvm.getelementptr %99[%10, 3] : (!llvm.ptr<struct<(ptr<f16>, ptr<f16>, i64, i64)>>, i64) -> !llvm.ptr<i64>
%101 = llvm.getelementptr %100[%arg1] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
%102 = llvm.sub %arg1, %11 : i64
llvm.br ^bb14(%102, %11 : i64, i64)
^bb13: // pred: ^bb6
%103 = llvm.mlir.addressof @error_message_2208944672953921889 : !llvm.ptr<array<42 x i8>>
%104 = llvm.getelementptr %103[%10, %10] : (!llvm.ptr<array<42 x i8>>, i64, i64) -> !llvm.ptr<i8>
llvm.call @_mlir_ciface_tf_report_error(%arg0, %0, %104) : (!llvm.ptr<i8>, i32, !llvm.ptr<i8>) -> ()
%105 = llvm.mul %2, %1 : i64
%106 = llvm.mul %2, %10 : i64
%107 = llvm.add %106, %11 : i64
%108 = llvm.mul %107, %1 : i64
%109 = llvm.add %105, %108 : i64
%110 = llvm.alloca %109 x i8 : (i64) -> !llvm.ptr<i8>
%111 = llvm.bitcast %110 : !llvm.ptr<i8> to !llvm.ptr<ptr<f16>>
llvm.store %13, %111 : !llvm.ptr<ptr<f16>>
%112 = llvm.getelementptr %111[%11] : (!llvm.ptr<ptr<f16>>, i64) -> !llvm.ptr<ptr<f16>>
llvm.store %13, %112 : !llvm.ptr<ptr<f16>>
%113 = llvm.getelementptr %111[%2] : (!llvm.ptr<ptr<f16>>, i64) -> !llvm.ptr<ptr<f16>>
%114 = llvm.bitcast %113 : !llvm.ptr<ptr<f16>> to !llvm.ptr<i64>
llvm.store %10, %114 : !llvm.ptr<i64>
%115 = llvm.call @malloc(%109) : (i64) -> !llvm.ptr<i8>
"llvm.intr.memcpy"(%115, %110, %109, %6) : (!llvm.ptr<i8>, !llvm.ptr<i8>, i64, i1) -> ()
%116 = llvm.mlir.undef : !llvm.struct<(i64, ptr<i8>)>
%117 = llvm.insertvalue %10, %116[0] : !llvm.struct<(i64, ptr<i8>)>
%118 = llvm.insertvalue %115, %117[1] : !llvm.struct<(i64, ptr<i8>)>
llvm.return %118 : !llvm.struct<(i64, ptr<i8>)>
^bb14(%119: i64, %120: i64): // 2 preds: ^bb12, ^bb15
%121 = llvm.icmp "sge" %119, %10 : i64
llvm.cond_br %121, ^bb15, ^bb16
^bb15: // pred: ^bb14
%122 = llvm.getelementptr %21[%119] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
%123 = llvm.load %122 : !llvm.ptr<i64>
%124 = llvm.getelementptr %100[%119] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
llvm.store %123, %124 : !llvm.ptr<i64>
%125 = llvm.getelementptr %101[%119] : (!llvm.ptr<i64>, i64) -> !llvm.ptr<i64>
llvm.store %120, %125 : !llvm.ptr<i64>
%126 = llvm.mul %120, %123 : i64
%127 = llvm.sub %119, %11 : i64
llvm.br ^bb14(%127, %126 : i64, i64)
^bb16: // pred: ^bb14
%128 = llvm.call @malloc(%93) : (i64) -> !llvm.ptr<i8>
"llvm.intr.memcpy"(%128, %94, %93, %6) : (!llvm.ptr<i8>, !llvm.ptr<i8>, i64, i1) -> ()
%129 = llvm.mlir.undef : !llvm.struct<(i64, ptr<i8>)>
%130 = llvm.insertvalue %arg1, %129[0] : !llvm.struct<(i64, ptr<i8>)>
%131 = llvm.insertvalue %128, %130[1] : !llvm.struct<(i64, ptr<i8>)>
llvm.return %131 : !llvm.struct<(i64, ptr<i8>)>
}
llvm.func @_mlir_ciface_Rsqrt_CPU_DT_HALF_DT_HALF(%arg0: !llvm.ptr<struct<(i64, ptr<i8>)>>, %arg1: !llvm.ptr<i8>, %arg2: !llvm.ptr<struct<(i64, ptr<i8>)>>) attributes {llvm.emit_c_interface, tf_entry} {
%0 = llvm.load %arg2 : !llvm.ptr<struct<(i64, ptr<i8>)>>
%1 = llvm.extractvalue %0[0] : !llvm.struct<(i64, ptr<i8>)>
%2 = llvm.extractvalue %0[1] : !llvm.struct<(i64, ptr<i8>)>
%3 = llvm.call @Rsqrt_CPU_DT_HALF_DT_HALF(%arg1, %1, %2) : (!llvm.ptr<i8>, i64, !llvm.ptr<i8>) -> !llvm.struct<(i64, ptr<i8>)>
llvm.store %3, %arg0 : !llvm.ptr<struct<(i64, ptr<i8>)>>
llvm.return
}
}
2022-06-15 13:24:24 +02:00
Phoebe Wang