// There are 3 meta phases of the Dynamic Programming (DP) algorithm. The input is a CostGraph, and the goal
// is to compute the strategy for each operator in the CostGraph.
//
// Phase 1: Shrink the CostGraph using 6 operations, and record them in the order
//       Using for operations: Operator Elimination, Edge Elimination, Merge Elimination, and Contract Elimination,
//       each connected component in the CostGraph can be shrunk in to the final graph: u --> v. See the
//       interpretation of 6 operations in costmodel.h.
// Phase 2: Search the cost_list in the final graph, and determine the optimal one
//       Create the cost_list for the final graph, and choose the optimal one: one the minimum quantity
//       COST_MODEL_ALPHA * memory_cost + COST_MODEL_BETA * communication_cost
// Phase 3: Recover the original CostGraph, the determine strategy for each operator
//       After determining the optimal cost for the final graph, the algorithm recovers the original graph by applying
//       the 4 operations in the reverse order in the Phase 1. Because each operation decision contains the strategy,
//       the operators' strategies can be all determined.

%fused_computation.3461.clone (param_0.15226: f32[3,35,1024], param_1.21991: f32[3,35,1024], param_2.18880: s32[], param_3.11384: s32[], param_4.4941: f32[3,35], param_5.2397: f32[3,35], param_6.2244: s32[], param_7.2283: f32[3,35,1024], param_8.2008: f32[3,35,1024], param_9.1351: f32[3,35,1024], param_10.643: s32[], param_11.421: s32[], param_12.202: s32[], param_13.379: f32[3,35], param_14.480: f32[3,35]) -> f32[3,35,1024] {
  %param_9.1351 = f32[3,35,1024]{2,1,0} parameter(9)
  %param_14.480 = f32[3,35]{1,0} parameter(14)
  %negate.1964 = f32[3,35]{1,0} negate(f32[3,35]{1,0} %param_14.480), metadata={op_type="Neg" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/SquaredDifference_grad/Neg"}
  %param_13.379 = f32[3,35]{1,0} parameter(13)
  %negate.1965 = f32[3,35]{1,0} negate(f32[3,35]{1,0} %param_13.379), metadata={op_type="Neg" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/sub_grad/Neg"}
  %add.9068 = f32[3,35]{1,0} add(f32[3,35]{1,0} %negate.1964, f32[3,35]{1,0} %negate.1965), metadata={op_type="AddN" op_name="training/gradients/AddN_4"}
  %constant.8355 = pred[] constant(false), metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_prepostprocess/layer_norm/Mean_1_grad/floordiv_1"}
  %constant.8354 = s32[] constant(840), metadata={op_type="Size" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_prepostprocess/layer_norm/Mean_1_grad/Prod_1"}
  %param_12.202 = s32[] parameter(12)
  %maximum.1386 = s32[] maximum(s32[] %constant.8354, s32[] %param_12.202), metadata={op_type="Maximum" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/Maximum_1"}
  %constant.8353 = s32[] constant(0), metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/encoder/layer_0/self_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %compare.2227 = pred[] compare(s32[] %maximum.1386, s32[] %constant.8353), direction=LT, metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %compare.2228 = pred[] compare(pred[] %constant.8355, pred[] %compare.2227), direction=NE, metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %param_10.643 = s32[] parameter(10)
  %param_11.421 = s32[] parameter(11)
  %select.606 = s32[] select(pred[] %compare.2228, s32[] %param_10.643, s32[] %param_11.421), metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %convert.2718 = f32[] convert(s32[] %select.606), metadata={op_type="Cast" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/Cast"}
  %broadcast.18365 = f32[3,35]{1,0} broadcast(f32[] %convert.2718), dimensions={}
  %divide.3442 = f32[3,35]{1,0} divide(f32[3,35]{1,0} %add.9068, f32[3,35]{1,0} %broadcast.18365), metadata={op_type="RealDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/encdec_attention/layer_prepostprocess/layer_norm/Mean_grad/truediv"}
  %broadcast.18367 = f32[3,35,1024]{2,1,0} broadcast(f32[3,35]{1,0} %divide.3442), dimensions={0,1}
  %add.9069 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %param_9.1351, f32[3,35,1024]{2,1,0} %broadcast.18367), metadata={op_type="AddN" op_name="training/gradients/AddN_5"}
  %param_8.2008 = f32[3,35,1024]{2,1,0} parameter(8)
  %add.9070 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %add.9069, f32[3,35,1024]{2,1,0} %param_8.2008), metadata={op_type="AddN" op_name="training/gradients/AddN_5"}
  %param_7.2283 = f32[3,35,1024]{2,1,0} parameter(7)
  %add.9071 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %add.9070, f32[3,35,1024]{2,1,0} %param_7.2283), metadata={op_type="AddN" op_name="training/gradients/AddN_5"}
  %param_5.2397 = f32[3,35]{1,0} parameter(5)
  %negate.1966 = f32[3,35]{1,0} negate(f32[3,35]{1,0} %param_5.2397), metadata={op_type="Neg" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/SquaredDifference_grad/Neg"}
  %param_4.4941 = f32[3,35]{1,0} parameter(4)
  %negate.1967 = f32[3,35]{1,0} negate(f32[3,35]{1,0} %param_4.4941), metadata={op_type="Neg" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/sub_grad/Neg"}
  %add.9072 = f32[3,35]{1,0} add(f32[3,35]{1,0} %negate.1966, f32[3,35]{1,0} %negate.1967), metadata={op_type="AddN" op_name="training/gradients/AddN_7"}
  %param_6.2244 = s32[] parameter(6)
  %maximum.1385 = s32[] maximum(s32[] %constant.8354, s32[] %param_6.2244), metadata={op_type="Maximum" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/Maximum_1"}
  %compare.2225 = pred[] compare(s32[] %maximum.1385, s32[] %constant.8353), direction=LT, metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %compare.2226 = pred[] compare(pred[] %constant.8355, pred[] %compare.2225), direction=NE, metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %param_2.18880 = s32[] parameter(2)
  %param_3.11384 = s32[] parameter(3)
  %select.605 = s32[] select(pred[] %compare.2226, s32[] %param_2.18880, s32[] %param_3.11384), metadata={op_type="FloorDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/floordiv_1"}
  %convert.2717 = f32[] convert(s32[] %select.605), metadata={op_type="Cast" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/Cast"}
  %broadcast.18368 = f32[3,35]{1,0} broadcast(f32[] %convert.2717), dimensions={}
  %divide.3443 = f32[3,35]{1,0} divide(f32[3,35]{1,0} %add.9072, f32[3,35]{1,0} %broadcast.18368), metadata={op_type="RealDiv" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23/self_attention/layer_prepostprocess/layer_norm/Mean_grad/truediv"}
  %broadcast.18369 = f32[3,35,1024]{2,1,0} broadcast(f32[3,35]{1,0} %divide.3443), dimensions={0,1}
  %add.9073 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %add.9071, f32[3,35,1024]{2,1,0} %broadcast.18369), metadata={op_type="AddN" op_name="training/gradients/AddN_8"}
  %param_1.21991 = f32[3,35,1024]{2,1,0} parameter(1)
  %add.9074 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %add.9073, f32[3,35,1024]{2,1,0} %param_1.21991), metadata={op_type="AddN" op_name="training/gradients/AddN_8"}
  %param_0.15226 = f32[3,35,1024]{2,1,0} parameter(0)
  ROOT %add.9075 = f32[3,35,1024]{2,1,0} add(f32[3,35,1024]{2,1,0} %add.9074, f32[3,35,1024]{2,1,0} %param_0.15226), metadata={op_type="AddN" op_name="training/gradients/AddN_8"}
}

%fusion.8228 = f32[4,32,48,32]{3,2,1,0} fusion(f32[192,1024]{1,0} %dot.2067, f32[] %arg217.0), kind=kLoop, calls=%fused_computation.4684.clone, metadata={op_type="Mul" op_name="transformer/parallel_0_5/transformer/transformer/body/encoder/layer_11/self_attention/multihead_attention/mul"}

class block:
    def __init__(self):
        self.name = “”
        self.firstline = “”
        self.params = []
        self.body = []
        self.calls = []

class node:
    def __init__(self):
        self.id = “”
        self.label = “”
class edge:
    def __init__(self):
        self.source = “”
        self.target = “”
class graph:
    def __init__(self):
        self.nodes = []
        self.edges = []

result = []

def process_body_line(s):
    # into calls
    ret = []
    call_fn = ["calls=", "to_apply="]
    for w in call_fn:
        while w in s:
            start = s.find(w) + len(w)
            end = s.find(",", start)
            ret.append(s[start:end])
            s = s.replace(w, ''.join(reversed(w)))
    return ret

def process_first_line_into_args(s):
    # into params
    ret = []
    param_end = s.find(“->”)
    if param_end != -1:
        s = s[0 : param_end - 2]
    param_start = s.find(“(“) + 1
    s = s[param_start : param_end + 1]
    params = s.split(", ")
    for x in params:
        ret.append(x[0:x.find(":")])
    # param_end = s.find(")", param_end) - 1
    return ret

def process_first_line_into_name(s):
    name_end = s.find(" (")
    name = s[0:name_end]
    name = name.replace("ENTRY ", "")
    return name

l = 0
while l < len(lines):
    # print(l)
    line = lines[l]
    if len(line) < 2:
        l = l + 1
        continue
    if line[:2] == “  “:
        print(“Unhandled Situation, printing surround lines…”)
        print(lines[l - 1], lines[l + 1])
        exit
    if line[0] != " ":
        f = block()
        f.firstline = line.replace("\n", "")
        f.params = process_first_line_into_args(f.firstline)
        f.name = process_first_line_into_name(f.firstline)
        # print(process_first_line_into_name(f.firstline))
        l = l + 1
        line = lines[l]
        while line[0] != “}”:
            f.calls = f.calls + process_body_line(line)
            f.body.append(line.replace(“\n”, “”))
            l = l + 1
            line = lines[l]
        result.append(f)
    l = l + 1
    # if l % 10 == 0:
    #     print("Currently l = ", l)

def parse_fn_line(s):
    i = 0
    ret = []
    while i < len(s):
        if s[i] == '%':
            new_var = "%"
            i = i + 1
            while s[i] != ' ' and s[i] != ')' and s[i] != ',':
                new_var += s[i]
                i = i + 1
            ret.append(new_var)
        i = i + 1
    return ret

def parse_fn_dfg(blk):
    # print("parsing fn", blk.name)
    variables = []
    for x in blk.body:
        variables.append(parse_fn_line(x))
    # print(variables)
    g = graph()
    created = set()
    for l in variables:
        for x in l:
            if x in created:
                continue
            n = node()
            n.id = x
            n.label = x#shorten_name(x)
            g.nodes.append(n)
            created.add(x)
    for l in variables:
        if len(l) <= 1:
            continue
        for x in l[1:]:
            e = edge()
            e.source = x
            e.target = l[0]
            g.edges.append(e)
    def dumper(obj):
        try:
            return obj.toJSON()
        except:
            return obj.__dict__
    return json.dumps(g, default=dumper, indent=2)

var HLOLexer = lexer.Must(ebnf.New(`
Comment = ("#" | "//") { "\u0000"…"\uffff"-"\n" } .
Ident = (alpha | "_") { "." | "_" | "-" | alpha | digit } .
String = "\"" {Ident | "/"} "\"" .
VarName = "%" Ident .
Number = { "-" } ("." | digit | "inf") {"." | digit} .
Whitespace = " " | "\t" | "\n" | "\r" .
Rightarrow = "->" .
Assign = "=" .
Punct = "!"…"/" | ":"…"@" | "["…"_" | "{"…"~" .
alpha = "a"…"z" | "A"…"Z" .
digit = "0"…"9" .
`))

type HLO struct {
    Functions []*HLOFunction `@@*`
}

type HLOFunction struct {
    Name        string         `("ENTRY")? @VarName`
    Params      []*Param       `"(" [ @@ { "," @@ } ] ")"`
    ReturnTypes []*Type        `"->" ( "(" [ @@ { "," @@ } ] ")" | @@)`
    Body        []*Instruction `"{" @@ {@@} "}"`
}

type Instruction struct {
    VarName string        `("ROOT")? @VarName "="`
    Fn      *FunctionCall `@@`
    Meta    []*Meta       `{ "," @@ }`
}

type FunctionCall struct {
    ReturnTypes []*RichType  `(@@ | "(" @@ { "," @@ } ")" )`
    Name        string       `@Ident`
    Params      []*RichParam `"(" [ @@ { "," @@ } ] ")"`
}

type Meta struct {
    Key        string  `@Ident "="`
    Value      string  `(@Ident|@VarName|@Number)?`
    DictValue  []*Dict `("{" { @@ } "}")?`
    ListNums   []int   `("{" @Number {"," @Number } "}")?`
    ListSlices []Slice `("{" @@ {"," @@ } "}")?`
}

type Dict struct {
    Key   string `@Ident "="`
    Value string `@String | @Ident`
}

type Slice struct {
    Start int `"[" @Number ":"`
    End   int `@Number "]"`
}

type Param struct {
    Name string `@Ident ":"`
    Type *Type  `@@`
}

type Type struct {
    DataType   string `@Ident`
    Dimensions []int  `"[" [ @Number { "," @Number } ] "]"`
}

type RichParam struct {
    Type *RichType `(@@)?`
    Name string    `@VarName | @Number | @Ident`
}

type RichType struct {
    VarType string `@Ident`
    VarDim  []int  `"[" [ @Number { "," @Number } ] "]" ("{" [ @Number { "," @Number } ] "}")?`
}

%fused_computation.19.clone (param_0.16672: f32[4,49,1024], param_1.23221: f32[196,1024]) -> f32[1024] {
  %param_1.23221 = f32[196,1024]{1,0} parameter(1)
  %reshape.13330 = f32[4,49,1024]{2,1,0} reshape(f32[196,1024]{1,0} %param_1.23221), metadata={op_type="Reshape" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/conv1/Tensordot/Reshape_grad/Reshape"}
  %param_0.16672 = f32[4,49,1024]{2,1,0} parameter(0)
  %multiply.14985 = f32[4,49,1024]{2,1,0} multiply(f32[4,49,1024]{2,1,0} %reshape.13330, f32[4,49,1024]{2,1,0} %param_0.16672), metadata={op_type="Mul" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Mul_1"}
  %constant.11228 = f32[] constant(0), metadata={op_type="RandomUniform" op_name="transformer/parallel_0_5/transformer/transformer/body/dropout/random_uniform/RandomUniform"}
  ROOT %reduce.1954 = f32[1024]{0} reduce(f32[4,49,1024]{2,1,0} %multiply.14985, f32[] %constant.11228), dimensions={0,1}, to_apply=%training_gradients_transformer_parallel_0_5_transformer_transformer_body_decoder_layer_23_1_ffn_layer_prepostprocess_layer_norm_mul_1_grad_Sum_1-reduction.48850, metadata={op_type="Sum" op_name="training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Sum_1"}
}

[%fused_computation.19.clone   ( param_0.16672 :   f32 [ 4 , 49 , 1024 ] ,   param_1.23221 :   f32 [ 196 , 1024 ] )   ->   f32 [ 1024 ]   {
     %param_1.23221   =   f32 [ 196 , 1024 ] { 1 , 0 }   parameter ( 1 )
     %reshape.13330   =   f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   reshape ( f32 [ 196 , 1024 ] { 1 , 0 }   %param_1.23221 ) ,   metadata = { op_type = "Reshape"   op_name = "training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/conv1/Tensordot/Reshape_grad/Reshape" }
     %param_0.16672   =   f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   parameter ( 0 )
     %multiply.14985   =   f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   multiply ( f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   %reshape.13330 ,   f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   %param_0.16672 ) ,   metadata = { op_type = "Mul"   op_name = "training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Mul_1" }
     %constant.11228   =   f32 [ ]   constant ( 0 ) ,   metadata = { op_type = "RandomUniform"   op_name = "transformer/parallel_0_5/transformer/transformer/body/dropout/random_uniform/RandomUniform" }
     ROOT   %reduce.1954   =   f32 [ 1024 ] { 0 }   reduce ( f32 [ 4 , 49 , 1024 ] { 2 , 1 , 0 }   %multiply.14985 ,   f32 [ ]   %constant.11228 ) ,   dimensions = { 0 , 1 } ,   to_apply = %training_gradients_transformer_parallel_0_5_transformer_transformer_body_decoder_layer_23_1_ffn_layer_prepostprocess_layer_norm_mul_1_grad_Sum_1-reduction.48850 ,   metadata = { op_type = "Sum"   op_name = "training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Sum_1" }
 } <EOF>]
&main.HLO{
  Functions: []*main.HLOFunction{
    &main.HLOFunction{
      Name: "%fused_computation.19.clone",
      Params: []*main.Param{
        &main.Param{
          Name: "param_0.16672",
          Type: &main.Type{
            DataType: "f32",
            Dimensions: []int{
              4,
              49,
              1024,
            },
          },
        },
        &main.Param{
          Name: "param_1.23221",
          Type: &main.Type{
            DataType: "f32",
            Dimensions: []int{
              196,
              1024,
            },
          },
        },
      },
      ReturnTypes: []*main.Type{
        &main.Type{
          DataType: "f32",
          Dimensions: []int{
            1024,
          },
        },
      },
      Body: []*main.Instruction{
        &main.Instruction{
          VarName: "%param_1.23221",
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
                VarDim: []int{
                  196,
                  1024,
                  1,
                  0,
                },
              },
            },
            Name: "parameter",
            Params: []*main.RichParam{
              &main.RichParam{
                Name: "1",
              },
            },
          },
        },
        &main.Instruction{
          VarName: "%reshape.13330",
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
                VarDim: []int{
                  4,
                  49,
                  1024,
                  2,
                  1,
                  0,
                },
              },
            },
            Name: "reshape",
            Params: []*main.RichParam{
              &main.RichParam{
                Type: &main.RichType{
                  VarType: "f32",
                  VarDim: []int{
                    196,
                    1024,
                    1,
                    0,
                  },
                },
                Name: "%param_1.23221",
              },
            },
          },
          Meta: []*main.Meta{
            &main.Meta{
              Key: "metadata",
              DictValue: []*main.Dict{
                &main.Dict{
                  Key: “op_type”,
                  Value: “\”Reshape\””,
                },
                &main.Dict{
                  Key: "op_name”,
                  Value: “\”training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/conv1/Tensordot/Reshape_grad/Reshape\””,
                },
              },
            },
          },
        },
        &main.Instruction{
          VarName: “%param_0.16672”,
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
                VarDim: []int{
                  4,
                  49,
                  1024,
                  2,
                  1,
                  0,
                },
              },
            },
            Name: "parameter",
            Params: []*main.RichParam{
              &main.RichParam{
                Name: "0",
              },
            },
          },
        },
        &main.Instruction{
          VarName: "%multiply.14985",
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
                VarDim: []int{
                  4,
                  49,
                  1024,
                  2,
                  1,
                  0,
                },
              },
            },
            Name: "multiply",
            Params: []*main.RichParam{
              &main.RichParam{
                Type: &main.RichType{
                  VarType: "f32",
                  VarDim: []int{
                    4,
                    49,
                    1024,
                    2,
                    1,
                    0,
                  },
                },
                Name: "%reshape.13330",
              },
              &main.RichParam{
                Type: &main.RichType{
                  VarType: "f32",
                  VarDim: []int{
                    4,
                    49,
                    1024,
                    2,
                    1,
                    0,
                  },
                },
                Name: "%param_0.16672",
              },
            },
          },
          Meta: []*main.Meta{
            &main.Meta{
              Key: "metadata",
              DictValue: []*main.Dict{
                &main.Dict{
                  Key: "op_type",
                  Value: "\"Mul\"",
                },
                &main.Dict{
                  Key: “op_name”,
                  Value: "\"training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Mul_1\"",
                },
              },
            },
          },
        },
        &main.Instruction{
          VarName: "%constant.11228",
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
              },
            },
            Name: "constant",
            Params: []*main.RichParam{
              &main.RichParam{
                Name: "0",
              },
            },
          },
          Meta: []*main.Meta{
            &main.Meta{
              Key: "metadata",
              DictValue: []*main.Dict{
                &main.Dict{
                  Key: "op_type",
                  Value: "\"RandomUniform\"",
                },
                &main.Dict{
                  Key: "op_name",
                  Value: "\"transformer/parallel_0_5/transformer/transformer/body/dropout/random_uniform/RandomUniform\"",
                },
              },
            },
          },
        },
        &main.Instruction{
          VarName: “%reduce.1954”,
          Fn: &main.FunctionCall{
            ReturnTypes: []*main.RichType{
              &main.RichType{
                VarType: "f32",
                VarDim: []int{
                  1024,
                  0,
                },
              },
            },
            Name: "reduce",
            Params: []*main.RichParam{
              &main.RichParam{
                Type: &main.RichType{
                  VarType: “f32”,
                  VarDim: []int{
                    4,
                    49,
                    1024,
                    2,
                    1,
                    0,
                  },
                },
                Name: “%multiply.14985”,
              },
              &main.RichParam{
                Type: &main.RichType{
                  VarType: "f32",
                },
                Name: "%constant.11228",
              },
            },
          },
          Meta: []*main.Meta{
            &main.Meta{
              Key: "dimensions",
              ListNums: []int{
                0,
                1,
              },
            },
            &main.Meta{
              Key: "to_apply",
              Value: "%training_gradients_transformer_parallel_0_5_transformer_transformer_body_decoder_layer_23_1_ffn_layer_prepostprocess_layer_norm_mul_1_grad_Sum_1-reduction.48850",
            },
            &main.Meta{
              Key: "metadata",
              DictValue: []*main.Dict{
                &main.Dict{
                  Key: "op_type",
                  Value: "\"Sum\"",
                },
                &main.Dict{
                  Key: "op_name",
                  Value: "\"training/gradients/transformer/parallel_0_5/transformer/transformer/body/decoder/layer_23_1/ffn/layer_prepostprocess/layer_norm/mul_1_grad/Sum_1\"",
                },
              },
            },
          },
        },
      },
    },
  },
}
{Functions:[0xc0000f03c0]}