ref_dict.txt

====== resnext50_32x4d_forward_0 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs.default', 'torch.ops.aten.abs.out', 'torch.ops.aten.acos.default', 'torch.ops.aten.acos.out', 'torch.ops.aten.acos.int', 'torch.ops.aten.acos.float', 'torch.ops.aten.acos.complex', 'torch.ops.aten.acos.Scalar', 'torch.ops.aten.acosh.default', 'torch.ops.aten.acosh.out', 'torch.ops.aten.acosh.int', 'torch.ops.aten.acosh.float', 'torch.ops.aten.acosh.complex', 'torch.ops.aten.acosh.Scalar', 'torch.ops.aten.asin.default', 'torch.ops.aten.asin.out', 'torch.ops.aten.asin.int', 'torch.ops.aten.asin.float', 'torch.ops.aten.asin.complex', 'torch.ops.aten.asin.Scalar', 'torch.ops.aten.atan.default', 'torch.ops.aten.atan.out', 'torch.ops.aten.atan.int', 'torch.ops.aten.atan.float', 'torch.ops.aten.atan.complex', 'torch.ops.aten.atan.Scalar', 'torch.ops.aten.bitwise_not.default', 'torch.ops.aten.bitwise_not.out', 'torch.ops.aten.ceil.default', 'torch.ops.aten.ceil.out', 'torch.ops.aten.ceil.int', 'torch.ops.aten.ceil.float', 'torch.ops.aten.ceil.Scalar', 'torch.ops.aten.cos.default', 'torch.ops.aten.cos.out', 'torch.ops.aten.cos.int', 'torch.ops.aten.cos.float', 'torch.ops.aten.cos.complex', 'torch.ops.aten.cos.Scalar', 'torch.ops.aten.cosh.default', 'torch.ops.aten.cosh.out', 'torch.ops.aten.cosh.int', 'torch.ops.aten.cosh.float', 'torch.ops.aten.cosh.complex', 'torch.ops.aten.cosh.Scalar', 'torch.ops.aten.digamma.default', 'torch.ops.aten.digamma.out', 'torch.ops.aten.erf.default', 'torch.ops.aten.erf.out', 'torch.ops.aten.erf.int', 'torch.ops.aten.erf.float', 'torch.ops.aten.erf.Scalar', 'torch.ops.aten.erfinv.default', 'torch.ops.aten.erfinv.out', 'torch.ops.aten.erfc.default', 'torch.ops.aten.erfc.out', 'torch.ops.aten.erfc.int', 'torch.ops.aten.erfc.float', 'torch.ops.aten.erfc.Scalar', 'torch.ops.aten.exp.default', 'torch.ops.aten.exp.out', 'torch.ops.aten.exp.int', 'torch.ops.aten.exp.float', 'torch.ops.aten.exp.complex', 'torch.ops.aten.exp.Scalar', 'torch.ops.aten.expm1.default', 'torch.ops.aten.expm1.out', 'torch.ops.aten.expm1.int', 'torch.ops.aten.expm1.float', 'torch.ops.aten.expm1.Scalar', 'torch.ops.aten.exp2.default', 'torch.ops.aten.exp2.out', 'torch.ops.aten.floor.default', 'torch.ops.aten.floor.out', 'torch.ops.aten.floor.int', 'torch.ops.aten.floor.float', 'torch.ops.aten.floor.Scalar', 'torch.ops.aten.frac.default', 'torch.ops.aten.frac.out', 'torch.ops.aten.isinf.default', 'torch.ops.aten.isinf.float', 'torch.ops.aten.isinf.complex', 'torch.ops.aten.isnan.default', 'torch.ops.aten.isnan.float', 'torch.ops.aten.isnan.complex', 'torch.ops.aten.special_i0.default', 'torch.ops.aten.special_i0.out', 'torch.ops.aten.lgamma.default', 'torch.ops.aten.lgamma.out', 'torch.ops.aten.lgamma.int', 'torch.ops.aten.lgamma.float', 'torch.ops.aten.lgamma.Scalar', 'torch.ops.aten.log.default', 'torch.ops.aten.log.out', 'torch.ops.aten.log.int', 'torch.ops.aten.log.float', 'torch.ops.aten.log.complex', 'torch.ops.aten.log.Scalar', 'torch.ops.aten.log.int_int', 'torch.ops.aten.log.float_float', 'torch.ops.aten.log.complex_complex', 'torch.ops.aten.log.int_float', 'torch.ops.aten.log.float_int', 'torch.ops.aten.log.int_complex', 'torch.ops.aten.log.complex_int', 'torch.ops.aten.log.float_complex', 'torch.ops.aten.log.complex_float', 'torch.ops.aten.log.Scalar_Scalar', 'torch.ops.aten.log1p.default', 'torch.ops.aten.log1p.out', 'torch.ops.aten.log1p.int', 'torch.ops.aten.log1p.float', 'torch.ops.aten.log1p.Scalar', 'torch.ops.aten.log2.default', 'torch.ops.aten.log2.out', 'torch.ops.aten.log10.default', 'torch.ops.aten.log10.out', 'torch.ops.aten.log10.int', 'torch.ops.aten.log10.float', 'torch.ops.aten.log10.complex', 'torch.ops.aten.log10.Scalar', 'torch.ops.aten.nan_to_num.out', 'torch.ops.aten.nan_to_num.default', 'torch.ops.aten.neg.default', 'torch.ops.aten.neg.out', 'torch.ops.aten.neg.int', 'torch.ops.aten.neg.float', 'torch.ops.aten.neg.complex', 'torch.ops.aten.neg.Scalar', 'torch.ops.aten.reciprocal.default', 'torch.ops.aten.reciprocal.out', 'torch.ops.aten.rsqrt.default', 'torch.ops.aten.rsqrt.out', 'torch.ops.aten.sigmoid.default', 'torch.ops.aten.sigmoid.out', 'torch.ops.aten.sign.default', 'torch.ops.aten.sign.out', 'torch.ops.aten.signbit.default', 'torch.ops.aten.signbit.out', 'torch.ops.aten.sin.default', 'torch.ops.aten.sin.out', 'torch.ops.aten.sin.int', 'torch.ops.aten.sin.float', 'torch.ops.aten.sin.complex', 'torch.ops.aten.sin.Scalar', 'torch.ops.aten.sinh.default', 'torch.ops.aten.sinh.out', 'torch.ops.aten.sinh.int', 'torch.ops.aten.sinh.float', 'torch.ops.aten.sinh.complex', 'torch.ops.aten.sinh.Scalar', 'torch.ops.aten.sqrt.default', 'torch.ops.aten.sqrt.out', 'torch.ops.aten.sqrt.int', 'torch.ops.aten.sqrt.float', 'torch.ops.aten.sqrt.complex', 'torch.ops.aten.sqrt.Scalar', 'torch.ops.aten.tan.default', 'torch.ops.aten.tan.out', 'torch.ops.aten.tan.int', 'torch.ops.aten.tan.float', 'torch.ops.aten.tan.complex', 'torch.ops.aten.tan.Scalar', 'torch.ops.aten.tanh.default', 'torch.ops.aten.tanh.out', 'torch.ops.aten.tanh.int', 'torch.ops.aten.tanh.float', 'torch.ops.aten.tanh.complex', 'torch.ops.aten.tanh.Scalar', 'torch.ops.aten.add.Tensor', 'torch.ops.aten.add.Scalar', 'torch.ops.aten.add.out', 'torch.ops.aten.add.Scalar_out', 'torch.ops.aten.add.t', 'torch.ops.aten.add.str', 'torch.ops.aten.add.int', 'torch.ops.aten.add.complex', 'torch.ops.aten.add.float', 'torch.ops.aten.add.int_complex', 'torch.ops.aten.add.complex_int', 'torch.ops.aten.add.float_complex', 'torch.ops.aten.add.complex_float', 'torch.ops.aten.add.int_float', 'torch.ops.aten.add.float_int', 'torch.ops.aten.add.default', 'torch.ops.aten.atan2.default', 'torch.ops.aten.atan2.out', 'torch.ops.aten.atan2.int', 'torch.ops.aten.atan2.float', 'torch.ops.aten.atan2.int_float', 'torch.ops.aten.atan2.float_int', 'torch.ops.aten.atan2.Scalar_Scalar', 'torch.ops.aten.bitwise_and.Tensor', 'torch.ops.aten.bitwise_and.Tensor_out', 'torch.ops.aten.bitwise_and.Scalar', 'torch.ops.aten.bitwise_and.Scalar_out', 'torch.ops.aten.bitwise_and.Scalar_Tensor', 'torch.ops.aten.bitwise_left_shift.Tensor', 'torch.ops.aten.bitwise_left_shift.Tensor_out', 'torch.ops.aten.bitwise_left_shift.Tensor_Scalar', 'torch.ops.aten.bitwise_left_shift.Tensor_Scalar_out', 'torch.ops.aten.bitwise_left_shift.Scalar_Tensor', 'torch.ops.aten.bitwise_or.Tensor', 'torch.ops.aten.bitwise_or.Tensor_out', 'torch.ops.aten.bitwise_or.Scalar_out', 'torch.ops.aten.bitwise_or.Scalar_Tensor', 'torch.ops.aten.bitwise_or.Scalar', 'torch.ops.aten.bitwise_right_shift.Tensor', 'torch.ops.aten.bitwise_right_shift.Tensor_out', 'torch.ops.aten.bitwise_right_shift.Tensor_Scalar', 'torch.ops.aten.bitwise_right_shift.Tensor_Scalar_out', 'torch.ops.aten.bitwise_right_shift.Scalar_Tensor', 'torch.ops.aten.bitwise_xor.Tensor', 'torch.ops.aten.bitwise_xor.Tensor_out', 'torch.ops.aten.bitwise_xor.Scalar_out', 'torch.ops.aten.bitwise_xor.Scalar_Tensor', 'torch.ops.aten.bitwise_xor.Scalar', 'torch.ops.aten.eq.Tensor', 'torch.ops.aten.eq.Scalar', 'torch.ops.aten.eq.Scalar_out', 'torch.ops.aten.eq.Tensor_out', 'torch.ops.aten.eq.int_list', 'torch.ops.aten.eq.device', 'torch.ops.aten.eq.bool', 'torch.ops.aten.eq.enum', 'torch.ops.aten.eq.int', 'torch.ops.aten.eq.complex', 'torch.ops.aten.eq.float', 'torch.ops.aten.eq.int_float', 'torch.ops.aten.eq.float_int', 'torch.ops.aten.eq.float_complex', 'torch.ops.aten.eq.complex_float', 'torch.ops.aten.eq.default', 'torch.ops.aten.eq.str', 'torch.ops.aten.eq.float_list', 'torch.ops.aten.eq.Tensor_list', 'torch.ops.aten.eq.bool_list', 'torch.ops.aten.eq.str_list', 'torch.ops.aten.fmax.default', 'torch.ops.aten.fmax.out', 'torch.ops.aten.fmin.default', 'torch.ops.aten.fmin.out', 'torch.ops.aten.fmod.Tensor', 'torch.ops.aten.fmod.Tensor_out', 'torch.ops.aten.fmod.Scalar', 'torch.ops.aten.fmod.Scalar_out', 'torch.ops.aten.fmod.int', 'torch.ops.aten.fmod.float', 'torch.ops.aten.fmod.int_float', 'torch.ops.aten.fmod.float_int', 'torch.ops.aten.fmod.default', 'torch.ops.aten.gcd.default', 'torch.ops.aten.gcd.out', 'torch.ops.aten.gcd.int', 'torch.ops.aten.ge.Tensor', 'torch.ops.aten.ge.Scalar', 'torch.ops.aten.ge.Scalar_out', 'torch.ops.aten.ge.Tensor_out', 'torch.ops.aten.ge.int', 'torch.ops.aten.ge.float', 'torch.ops.aten.ge.int_float', 'torch.ops.aten.ge.float_int', 'torch.ops.aten.ge.default', 'torch.ops.aten.ge.str', 'torch.ops.aten.gt.Tensor', 'torch.ops.aten.gt.Scalar', 'torch.ops.aten.gt.Scalar_out', 'torch.ops.aten.gt.Tensor_out', 'torch.ops.aten.gt.int', 'torch.ops.aten.gt.float', 'torch.ops.aten.gt.int_float', 'torch.ops.aten.gt.float_int', 'torch.ops.aten.gt.default', 'torch.ops.aten.gt.str', 'torch.ops.aten.igamma.default', 'torch.ops.aten.igamma.out', 'torch.ops.aten.igammac.default', 'torch.ops.aten.igammac.out', 'torch.ops.aten.lcm.default', 'torch.ops.aten.lcm.out', 'torch.ops.aten.le.Tensor', 'torch.ops.aten.le.Scalar', 'torch.ops.aten.le.Scalar_out', 'torch.ops.aten.le.Tensor_out', 'torch.ops.aten.le.int', 'torch.ops.aten.le.float', 'torch.ops.aten.le.int_float', 'torch.ops.aten.le.float_int', 'torch.ops.aten.le.default', 'torch.ops.aten.le.str', 'torch.ops.aten.logical_and.default', 'torch.ops.aten.logical_and.out', 'torch.ops.aten.logical_not.default', 'torch.ops.aten.logical_not.out', 'torch.ops.aten.logical_or.default', 'torch.ops.aten.logical_or.out', 'torch.ops.aten.logical_xor.default', 'torch.ops.aten.logical_xor.out', 'torch.ops.aten.lt.Tensor', 'torch.ops.aten.lt.Scalar', 'torch.ops.aten.lt.Scalar_out', 'torch.ops.aten.lt.Tensor_out', 'torch.ops.aten.lt.int', 'torch.ops.aten.lt.float', 'torch.ops.aten.lt.int_float', 'torch.ops.aten.lt.float_int', 'torch.ops.aten.lt.default', 'torch.ops.aten.lt.str', 'torch.ops.aten.maximum.default', 'torch.ops.aten.maximum.out', 'torch.ops.aten.minimum.default', 'torch.ops.aten.minimum.out', 'torch.ops.aten.mul.Tensor', 'torch.ops.aten.mul.Scalar', 'torch.ops.aten.mul.out', 'torch.ops.aten.mul.Scalar_out', 'torch.ops.aten.mul.left_t', 'torch.ops.aten.mul.right_', 'torch.ops.aten.mul.int', 'torch.ops.aten.mul.complex', 'torch.ops.aten.mul.float', 'torch.ops.aten.mul.int_complex', 'torch.ops.aten.mul.complex_int', 'torch.ops.aten.mul.float_complex', 'torch.ops.aten.mul.complex_float', 'torch.ops.aten.mul.int_float', 'torch.ops.aten.mul.float_int', 'torch.ops.aten.mul.default', 'torch.ops.aten.ne.Tensor', 'torch.ops.aten.ne.Scalar', 'torch.ops.aten.ne.Scalar_out', 'torch.ops.aten.ne.Tensor_out', 'torch.ops.aten.ne.int_list', 'torch.ops.aten.ne.device', 'torch.ops.aten.ne.bool', 'torch.ops.aten.ne.enum', 'torch.ops.aten.ne.int', 'torch.ops.aten.ne.complex', 'torch.ops.aten.ne.float', 'torch.ops.aten.ne.int_float', 'torch.ops.aten.ne.float_int', 'torch.ops.aten.ne.float_complex', 'torch.ops.aten.ne.complex_float', 'torch.ops.aten.ne.default', 'torch.ops.aten.ne.str', 'torch.ops.aten.ne.float_list', 'torch.ops.aten.ne.Tensor_list', 'torch.ops.aten.ne.bool_list', 'torch.ops.aten.ne.str_list', 'torch.ops.aten.nextafter.default', 'torch.ops.aten.nextafter.out', 'torch.ops.aten.pow.Tensor_Tensor', 'torch.ops.aten.pow.Tensor_Scalar', 'torch.ops.aten.pow.Scalar', 'torch.ops.aten.pow.Scalar_out', 'torch.ops.aten.pow.Tensor_Scalar_out', 'torch.ops.aten.pow.Tensor_Tensor_out', 'torch.ops.aten.pow.int', 'torch.ops.aten.pow.complex', 'torch.ops.aten.pow.float', 'torch.ops.aten.pow.int_float', 'torch.ops.aten.pow.float_int', 'torch.ops.aten.pow.float_complex', 'torch.ops.aten.pow.complex_float', 'torch.ops.aten.pow.Scalar_Scalar', 'torch.ops.aten.pow.int_to_int', 'torch.ops.aten.remainder.Tensor', 'torch.ops.aten.remainder.Tensor_out', 'torch.ops.aten.remainder.Scalar_Tensor', 'torch.ops.aten.remainder.Scalar', 'torch.ops.aten.remainder.Scalar_out', 'torch.ops.aten.remainder.int', 'torch.ops.aten.remainder.float', 'torch.ops.aten.remainder.int_float', 'torch.ops.aten.remainder.float_int', 'torch.ops.aten.remainder.default', 'torch.ops.aten.sub.Tensor', 'torch.ops.aten.sub.Scalar', 'torch.ops.aten.sub.out', 'torch.ops.aten.sub.Scalar_out', 'torch.ops.aten.sub.int', 'torch.ops.aten.sub.complex', 'torch.ops.aten.sub.float', 'torch.ops.aten.sub.int_complex', 'torch.ops.aten.sub.complex_int', 'torch.ops.aten.sub.float_complex', 'torch.ops.aten.sub.complex_float', 'torch.ops.aten.sub.int_float', 'torch.ops.aten.sub.float_int', 'torch.ops.aten.sub.default', 'torch.ops.aten.where.self', 'torch.ops.aten.where.self_out', 'torch.ops.aten.where.ScalarSelf', 'torch.ops.aten.where.ScalarOther', 'torch.ops.aten.where.Scalar', 'torch.ops.aten.where.default', 'torch.ops.aten.sum.dim_IntList', 'torch.ops.aten.sum.default', 'torch.ops.aten.sum.dim_DimnameList', 'torch.ops.aten.sum.DimnameList_out', 'torch.ops.aten.sum.IntList_out', 'torch.ops.aten.sum.int', 'torch.ops.aten.sum.float', 'torch.ops.aten.sum.complex', 'torch.ops.aten.sum.bool', 'torch.ops.aten.prod.default', 'torch.ops.aten.prod.dim_int', 'torch.ops.aten.prod.dim_Dimname', 'torch.ops.aten.prod.Dimname_out', 'torch.ops.aten.prod.int_out', 'torch.ops.aten.std_mean.correction', 'torch.ops.aten.addr.default', 'torch.ops.aten.addr.out', 'torch.ops.aten.cat.default', 'torch.ops.aten.cat.names', 'torch.ops.aten.cat.names_out', 'torch.ops.aten.cat.out', 'torch.ops.aten.flip.default', 'torch.ops.aten.native_layer_norm.default', 'torch.ops.aten.permute.default', 'torch.ops.aten.roll.default', 'torch.ops.aten.rot90.default', 'torch.ops.aten.stack.default', 'torch.ops.aten.stack.out', 'torch.ops.aten.t.default', 'torch.ops.aten.unsqueeze.default', 'torch.ops.aten.trace.default', 'torch.ops.aten.celu.default', 'torch.ops.aten.celu.out', 'torch.ops.aten.relu.default', 'torch.ops.aten.relu.out', 'torch.ops.aten.leaky_relu.default', 'torch.ops.aten.leaky_relu.out', 'torch.ops.aten.mish.default', 'torch.ops.aten.mish.out', 'torch.ops.aten.softplus.default', 'torch.ops.aten.softplus.out', 'torch.ops.aten.hardtanh.default', 'torch.ops.aten.hardtanh.out', 'torch.ops.aten.gelu.default', 'torch.ops.aten.gelu.out', 'torch.ops.aten.special_i0e.default', 'torch.ops.aten.special_i0e.out', 'torch.ops.aten.special_i1.default', 'torch.ops.aten.special_i1.out', 'torch.ops.aten.special_i1e.default', 'torch.ops.aten.special_i1e.out', 'torch.ops.aten.logit.default', 'torch.ops.aten.logit.out', 'torch.ops.aten.special_zeta.default', 'torch.ops.aten.special_zeta.out', 'torch.ops.aten.special_zeta.self_scalar', 'torch.ops.aten.special_zeta.self_scalar_out', 'torch.ops.aten.special_zeta.other_scalar', 'torch.ops.aten.special_zeta.other_scalar_out']

updated_ref_dict.txt

====== resnext50_32x4d_forward_0 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs', 'torch.ops.aten.acos', 'torch.ops.aten.acosh', 'torch.ops.aten.asin', 'torch.ops.aten.atan', 'torch.ops.aten.bitwise_not', 'torch.ops.aten.ceil', 'torch.ops.aten.cos', 'torch.ops.aten.cosh', 'torch.ops.aten.digamma', 'torch.ops.aten.erf', 'torch.ops.aten.erfinv', 'torch.ops.aten.erfc', 'torch.ops.aten.exp', 'torch.ops.aten.expm1', 'torch.ops.aten.exp2', 'torch.ops.aten.floor', 'torch.ops.aten.frac', 'torch.ops.aten.isinf', 'torch.ops.aten.isnan', 'torch.ops.aten.special_i0', 'torch.ops.aten.lgamma', 'torch.ops.aten.log', 'torch.ops.aten.log1p', 'torch.ops.aten.log2', 'torch.ops.aten.log10', 'torch.ops.aten.nan_to_num', 'torch.ops.aten.neg', 'torch.ops.aten.reciprocal', 'torch.ops.aten.rsqrt', 'torch.ops.aten.sigmoid', 'torch.ops.aten.sign', 'torch.ops.aten.signbit', 'torch.ops.aten.sin', 'torch.ops.aten.sinh', 'torch.ops.aten.sqrt', 'torch.ops.aten.tan', 'torch.ops.aten.tanh', 'torch.ops.aten.add', 'torch.ops.aten.atan2', 'torch.ops.aten.bitwise_and', 'torch.ops.aten.bitwise_left_shift', 'torch.ops.aten.bitwise_or', 'torch.ops.aten.bitwise_right_shift', 'torch.ops.aten.bitwise_xor', 'torch.ops.aten.eq', 'torch.ops.aten.fmax', 'torch.ops.aten.fmin', 'torch.ops.aten.fmod', 'torch.ops.aten.gcd', 'torch.ops.aten.ge', 'torch.ops.aten.gt', 'torch.ops.aten.igamma', 'torch.ops.aten.igammac', 'torch.ops.aten.lcm', 'torch.ops.aten.le', 'torch.ops.aten.logical_and', 'torch.ops.aten.logical_not', 'torch.ops.aten.logical_or', 'torch.ops.aten.logical_xor', 'torch.ops.aten.lt', 'torch.ops.aten.maximum', 'torch.ops.aten.minimum', 'torch.ops.aten.mul', 'torch.ops.aten.ne', 'torch.ops.aten.nextafter', 'torch.ops.aten.pow', 'torch.ops.aten.remainder', 'torch.ops.aten.sub', 'torch.ops.aten.where', 'torch.ops.aten.sum', 'torch.ops.aten.prod', 'torch.ops.aten.std_mean', 'torch.ops.aten.addr', 'torch.ops.aten.cat', 'torch.ops.aten.flip', 'torch.ops.aten.native_layer_norm', 'torch.ops.aten.permute', 'torch.ops.aten.roll', 'torch.ops.aten.rot90', 'torch.ops.aten.stack', 'torch.ops.aten.t', 'torch.ops.aten.unsqueeze', 'torch.ops.aten.trace', 'torch.ops.aten.celu', 'torch.ops.aten.relu', 'torch.ops.aten.leaky_relu', 'torch.ops.aten.mish', 'torch.ops.aten.softplus', 'torch.ops.aten.hardtanh', 'torch.ops.aten.gelu', 'torch.ops.aten.special_i0e', 'torch.ops.aten.special_i1', 'torch.ops.aten.special_i1e', 'torch.ops.aten.logit', 'torch.ops.aten.special_zeta']
Num of partitions proposed: 53
partition #2 ['mul_157', 'mul_158']
partition #4 ['mul_154', 'mul_155']
partition #6 ['mul_151', 'mul_152']
partition #8 ['mul_149', 'mul_148']
partition #10 ['mul_145', 'mul_146']
partition #12 ['mul_143', 'mul_142']
partition #14 ['mul_139', 'mul_140']
partition #16 ['mul_137', 'mul_136']
partition #18 ['mul_134', 'mul_133']
partition #20 ['mul_130', 'mul_131']
partition #22 ['mul_128', 'mul_127']
partition #24 ['mul_124', 'mul_125']
partition #26 ['mul_121', 'mul_122']
partition #28 ['mul_118', 'mul_119']
partition #30 ['mul_116', 'mul_115']
partition #32 ['mul_112', 'mul_113']
partition #34 ['mul_110', 'mul_109']
partition #36 ['mul_107', 'mul_106']
partition #38 ['mul_104', 'mul_103']
partition #40 ['mul_101', 'mul_100']
partition #42 ['mul_98', 'mul_97']
partition #44 ['mul_94', 'mul_95']
partition #46 ['mul_91', 'mul_92']
partition #48 ['mul_89', 'mul_88']
partition #50 ['mul_86', 'mul_85']
partition #52 ['mul_83', 'mul_82']
partition #54 ['mul_80', 'mul_79']
partition #56 ['mul_77', 'mul_76']
partition #58 ['mul_73', 'mul_74']
partition #60 ['mul_70', 'mul_71']
partition #62 ['mul_68', 'mul_67']
partition #64 ['mul_64', 'mul_65']
partition #66 ['mul_62', 'mul_61']
partition #68 ['mul_59', 'mul_58']
partition #70 ['mul_56', 'mul_55']
partition #72 ['mul_53', 'mul_52']
partition #74 ['mul_49', 'mul_50']
partition #76 ['mul_47', 'mul_46']
partition #78 ['mul_43', 'mul_44']
partition #80 ['mul_41', 'mul_40']
partition #82 ['mul_38', 'mul_37']
partition #84 ['mul_35', 'mul_34']
partition #86 ['mul_31', 'mul_32']
partition #88 ['mul_29', 'mul_28']
partition #90 ['mul_26', 'mul_25']
partition #92 ['mul_23', 'mul_22']
partition #94 ['mul_20', 'mul_19']
partition #96 ['mul_17', 'mul_16']
partition #98 ['mul_13', 'mul_14']
partition #100 ['mul_11', 'mul_10']
partition #102 ['mul_8', 'mul_7']
partition #104 ['mul_5', 'mul_4']
partition #108 ['mul_1', 'mul_2']
Partioning time: 167.612 ms
Eager execution time: 4233.338 ms
nvFuser 1st call execution time: 28851.011 ms
nvFuser 2nd call execution time: 4614.273 ms
resnext50_32x4d_forward_0 failed! Tensor-likes are not close!

Mismatched elements: 32410 / 3211264 (1.0%)
Greatest absolute difference: 1.5019504757280604e+18 at index (6, 268, 22, 21) (up to 1e-05 allowed)
Greatest relative difference: 0.00010452292165946674 at index (6, 328, 22, 21) (up to 1e-05 allowed)

The failure occurred for item [19]
====== resnext50_32x4d_backward_0 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs', 'torch.ops.aten.acos', 'torch.ops.aten.acosh', 'torch.ops.aten.asin', 'torch.ops.aten.atan', 'torch.ops.aten.bitwise_not', 'torch.ops.aten.ceil', 'torch.ops.aten.cos', 'torch.ops.aten.cosh', 'torch.ops.aten.digamma', 'torch.ops.aten.erf', 'torch.ops.aten.erfinv', 'torch.ops.aten.erfc', 'torch.ops.aten.exp', 'torch.ops.aten.expm1', 'torch.ops.aten.exp2', 'torch.ops.aten.floor', 'torch.ops.aten.frac', 'torch.ops.aten.isinf', 'torch.ops.aten.isnan', 'torch.ops.aten.special_i0', 'torch.ops.aten.lgamma', 'torch.ops.aten.log', 'torch.ops.aten.log1p', 'torch.ops.aten.log2', 'torch.ops.aten.log10', 'torch.ops.aten.nan_to_num', 'torch.ops.aten.neg', 'torch.ops.aten.reciprocal', 'torch.ops.aten.rsqrt', 'torch.ops.aten.sigmoid', 'torch.ops.aten.sign', 'torch.ops.aten.signbit', 'torch.ops.aten.sin', 'torch.ops.aten.sinh', 'torch.ops.aten.sqrt', 'torch.ops.aten.tan', 'torch.ops.aten.tanh', 'torch.ops.aten.add', 'torch.ops.aten.atan2', 'torch.ops.aten.bitwise_and', 'torch.ops.aten.bitwise_left_shift', 'torch.ops.aten.bitwise_or', 'torch.ops.aten.bitwise_right_shift', 'torch.ops.aten.bitwise_xor', 'torch.ops.aten.eq', 'torch.ops.aten.fmax', 'torch.ops.aten.fmin', 'torch.ops.aten.fmod', 'torch.ops.aten.gcd', 'torch.ops.aten.ge', 'torch.ops.aten.gt', 'torch.ops.aten.igamma', 'torch.ops.aten.igammac', 'torch.ops.aten.lcm', 'torch.ops.aten.le', 'torch.ops.aten.logical_and', 'torch.ops.aten.logical_not', 'torch.ops.aten.logical_or', 'torch.ops.aten.logical_xor', 'torch.ops.aten.lt', 'torch.ops.aten.maximum', 'torch.ops.aten.minimum', 'torch.ops.aten.mul', 'torch.ops.aten.ne', 'torch.ops.aten.nextafter', 'torch.ops.aten.pow', 'torch.ops.aten.remainder', 'torch.ops.aten.sub', 'torch.ops.aten.where', 'torch.ops.aten.sum', 'torch.ops.aten.prod', 'torch.ops.aten.std_mean', 'torch.ops.aten.addr', 'torch.ops.aten.cat', 'torch.ops.aten.flip', 'torch.ops.aten.native_layer_norm', 'torch.ops.aten.permute', 'torch.ops.aten.roll', 'torch.ops.aten.rot90', 'torch.ops.aten.stack', 'torch.ops.aten.t', 'torch.ops.aten.unsqueeze', 'torch.ops.aten.trace', 'torch.ops.aten.celu', 'torch.ops.aten.relu', 'torch.ops.aten.leaky_relu', 'torch.ops.aten.mish', 'torch.ops.aten.softplus', 'torch.ops.aten.hardtanh', 'torch.ops.aten.gelu', 'torch.ops.aten.special_i0e', 'torch.ops.aten.special_i1', 'torch.ops.aten.special_i1e', 'torch.ops.aten.logit', 'torch.ops.aten.special_zeta']
Num of partitions proposed: 0
Partioning time: 72.669 ms
Eager execution time: 40.734 ms
nvFuser 1st call execution time: 147.460 ms
nvFuser 2nd call execution time: 144.853 ms
resnext50_32x4d_backward_0 has 0 fusion groups, Passed!
====== nvidia_deeprecommender_backward_0 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs', 'torch.ops.aten.acos', 'torch.ops.aten.acosh', 'torch.ops.aten.asin', 'torch.ops.aten.atan', 'torch.ops.aten.bitwise_not', 'torch.ops.aten.ceil', 'torch.ops.aten.cos', 'torch.ops.aten.cosh', 'torch.ops.aten.digamma', 'torch.ops.aten.erf', 'torch.ops.aten.erfinv', 'torch.ops.aten.erfc', 'torch.ops.aten.exp', 'torch.ops.aten.expm1', 'torch.ops.aten.exp2', 'torch.ops.aten.floor', 'torch.ops.aten.frac', 'torch.ops.aten.isinf', 'torch.ops.aten.isnan', 'torch.ops.aten.special_i0', 'torch.ops.aten.lgamma', 'torch.ops.aten.log', 'torch.ops.aten.log1p', 'torch.ops.aten.log2', 'torch.ops.aten.log10', 'torch.ops.aten.nan_to_num', 'torch.ops.aten.neg', 'torch.ops.aten.reciprocal', 'torch.ops.aten.rsqrt', 'torch.ops.aten.sigmoid', 'torch.ops.aten.sign', 'torch.ops.aten.signbit', 'torch.ops.aten.sin', 'torch.ops.aten.sinh', 'torch.ops.aten.sqrt', 'torch.ops.aten.tan', 'torch.ops.aten.tanh', 'torch.ops.aten.add', 'torch.ops.aten.atan2', 'torch.ops.aten.bitwise_and', 'torch.ops.aten.bitwise_left_shift', 'torch.ops.aten.bitwise_or', 'torch.ops.aten.bitwise_right_shift', 'torch.ops.aten.bitwise_xor', 'torch.ops.aten.eq', 'torch.ops.aten.fmax', 'torch.ops.aten.fmin', 'torch.ops.aten.fmod', 'torch.ops.aten.gcd', 'torch.ops.aten.ge', 'torch.ops.aten.gt', 'torch.ops.aten.igamma', 'torch.ops.aten.igammac', 'torch.ops.aten.lcm', 'torch.ops.aten.le', 'torch.ops.aten.logical_and', 'torch.ops.aten.logical_not', 'torch.ops.aten.logical_or', 'torch.ops.aten.logical_xor', 'torch.ops.aten.lt', 'torch.ops.aten.maximum', 'torch.ops.aten.minimum', 'torch.ops.aten.mul', 'torch.ops.aten.ne', 'torch.ops.aten.nextafter', 'torch.ops.aten.pow', 'torch.ops.aten.remainder', 'torch.ops.aten.sub', 'torch.ops.aten.where', 'torch.ops.aten.sum', 'torch.ops.aten.prod', 'torch.ops.aten.std_mean', 'torch.ops.aten.addr', 'torch.ops.aten.cat', 'torch.ops.aten.flip', 'torch.ops.aten.native_layer_norm', 'torch.ops.aten.permute', 'torch.ops.aten.roll', 'torch.ops.aten.rot90', 'torch.ops.aten.stack', 'torch.ops.aten.t', 'torch.ops.aten.unsqueeze', 'torch.ops.aten.trace', 'torch.ops.aten.celu', 'torch.ops.aten.relu', 'torch.ops.aten.leaky_relu', 'torch.ops.aten.mish', 'torch.ops.aten.softplus', 'torch.ops.aten.hardtanh', 'torch.ops.aten.gelu', 'torch.ops.aten.special_i0e', 'torch.ops.aten.special_i1', 'torch.ops.aten.special_i1e', 'torch.ops.aten.logit', 'torch.ops.aten.special_zeta']
Num of partitions proposed: 6
partition #1 ['mul_25', 'mul_28', 'mul_26']
partition #5 ['mul_21', 'mul_20', 'mul_23']
partition #9 ['mul_16', 'mul_18', 'mul_15']
partition #13 ['mul_13', 'mul_10', 'mul_11']
partition #17 ['mul_8', 'mul_6', 'mul_5']
partition #21 ['mul_1', 'mul_3', 'mul']
Partioning time: 10.758 ms
Eager execution time: 19.699 ms
nvFuser 1st call execution time: 2188.614 ms
nvFuser 2nd call execution time: 35.050 ms
nvidia_deeprecommender_backward_0 has 6 fusion groups, Passed!
====== nvidia_deeprecommender_forward_0 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs', 'torch.ops.aten.acos', 'torch.ops.aten.acosh', 'torch.ops.aten.asin', 'torch.ops.aten.atan', 'torch.ops.aten.bitwise_not', 'torch.ops.aten.ceil', 'torch.ops.aten.cos', 'torch.ops.aten.cosh', 'torch.ops.aten.digamma', 'torch.ops.aten.erf', 'torch.ops.aten.erfinv', 'torch.ops.aten.erfc', 'torch.ops.aten.exp', 'torch.ops.aten.expm1', 'torch.ops.aten.exp2', 'torch.ops.aten.floor', 'torch.ops.aten.frac', 'torch.ops.aten.isinf', 'torch.ops.aten.isnan', 'torch.ops.aten.special_i0', 'torch.ops.aten.lgamma', 'torch.ops.aten.log', 'torch.ops.aten.log1p', 'torch.ops.aten.log2', 'torch.ops.aten.log10', 'torch.ops.aten.nan_to_num', 'torch.ops.aten.neg', 'torch.ops.aten.reciprocal', 'torch.ops.aten.rsqrt', 'torch.ops.aten.sigmoid', 'torch.ops.aten.sign', 'torch.ops.aten.signbit', 'torch.ops.aten.sin', 'torch.ops.aten.sinh', 'torch.ops.aten.sqrt', 'torch.ops.aten.tan', 'torch.ops.aten.tanh', 'torch.ops.aten.add', 'torch.ops.aten.atan2', 'torch.ops.aten.bitwise_and', 'torch.ops.aten.bitwise_left_shift', 'torch.ops.aten.bitwise_or', 'torch.ops.aten.bitwise_right_shift', 'torch.ops.aten.bitwise_xor', 'torch.ops.aten.eq', 'torch.ops.aten.fmax', 'torch.ops.aten.fmin', 'torch.ops.aten.fmod', 'torch.ops.aten.gcd', 'torch.ops.aten.ge', 'torch.ops.aten.gt', 'torch.ops.aten.igamma', 'torch.ops.aten.igammac', 'torch.ops.aten.lcm', 'torch.ops.aten.le', 'torch.ops.aten.logical_and', 'torch.ops.aten.logical_not', 'torch.ops.aten.logical_or', 'torch.ops.aten.logical_xor', 'torch.ops.aten.lt', 'torch.ops.aten.maximum', 'torch.ops.aten.minimum', 'torch.ops.aten.mul', 'torch.ops.aten.ne', 'torch.ops.aten.nextafter', 'torch.ops.aten.pow', 'torch.ops.aten.remainder', 'torch.ops.aten.sub', 'torch.ops.aten.where', 'torch.ops.aten.sum', 'torch.ops.aten.prod', 'torch.ops.aten.std_mean', 'torch.ops.aten.addr', 'torch.ops.aten.cat', 'torch.ops.aten.flip', 'torch.ops.aten.native_layer_norm', 'torch.ops.aten.permute', 'torch.ops.aten.roll', 'torch.ops.aten.rot90', 'torch.ops.aten.stack', 'torch.ops.aten.t', 'torch.ops.aten.unsqueeze', 'torch.ops.aten.trace', 'torch.ops.aten.celu', 'torch.ops.aten.relu', 'torch.ops.aten.leaky_relu', 'torch.ops.aten.mish', 'torch.ops.aten.softplus', 'torch.ops.aten.hardtanh', 'torch.ops.aten.gelu', 'torch.ops.aten.special_i0e', 'torch.ops.aten.special_i1', 'torch.ops.aten.special_i1e', 'torch.ops.aten.logit', 'torch.ops.aten.special_zeta']
Num of partitions proposed: 0
Partioning time: 7.311 ms
Eager execution time: 14.359 ms
nvFuser 1st call execution time: 30.493 ms
nvFuser 2nd call execution time: 30.498 ms
nvidia_deeprecommender_forward_0 has 0 fusion groups, Passed!
====== moco_forward_4 ======
Generating testing data...
...Aten2aten called ...
['getattr', '_operator.getitem', 'torch.ops.aten.abs', 'torch.ops.aten.acos', 'torch.ops.aten.acosh', 'torch.ops.aten.asin', 'torch.ops.aten.atan', 'torch.ops.aten.bitwise_not', 'torch.ops.aten.ceil', 'torch.ops.aten.cos', 'torch.ops.aten.cosh', 'torch.ops.aten.digamma', 'torch.ops.aten.erf', 'torch.ops.aten.erfinv', 'torch.ops.aten.erfc', 'torch.ops.aten.exp', 'torch.ops.aten.expm1', 'torch.ops.aten.exp2', 'torch.ops.aten.floor', 'torch.ops.aten.frac', 'torch.ops.aten.isinf', 'torch.ops.aten.isnan', 'torch.ops.aten.special_i0', 'torch.ops.aten.lgamma', 'torch.ops.aten.log', 'torch.ops.aten.log1p', 'torch.ops.aten.log2', 'torch.ops.aten.log10', 'torch.ops.aten.nan_to_num', 'torch.ops.aten.neg', 'torch.ops.aten.reciprocal', 'torch.ops.aten.rsqrt', 'torch.ops.aten.sigmoid', 'torch.ops.aten.sign', 'torch.ops.aten.signbit', 'torch.ops.aten.sin', 'torch.ops.aten.sinh', 'torch.ops.aten.sqrt', 'torch.ops.aten.tan', 'torch.ops.aten.tanh', 'torch.ops.aten.add', 'torch.ops.aten.atan2', 'torch.ops.aten.bitwise_and', 'torch.ops.aten.bitwise_left_shift', 'torch.ops.aten.bitwise_or', 'torch.ops.aten.bitwise_right_shift', 'torch.ops.aten.bitwise_xor', 'torch.ops.aten.eq', 'torch.ops.aten.fmax', 'torch.ops.aten.fmin', 'torch.ops.aten.fmod', 'torch.ops.aten.gcd', 'torch.ops.aten.ge', 'torch.ops.aten.gt', 'torch.ops.aten.igamma', 'torch.ops.aten.igammac', 'torch.ops.aten.lcm', 'torch.ops.aten.le', 'torch.ops.aten.logical_and', 'torch.ops.aten.logical_not', 'torch.ops.aten.logical_or', 'torch.ops.aten.logical_xor', 'torch.ops.aten.lt', 'torch.ops.aten.maximum', 'torch.ops.aten.minimum', 'torch.ops.aten.mul', 'torch.ops.aten.ne', 'torch.ops.aten.nextafter', 'torch.ops.aten.pow', 'torch.ops.aten.remainder', 'torch.ops.aten.sub', 'torch.ops.aten.where', 'torch.ops.aten.sum', 'torch.ops.aten.prod', 'torch.ops.aten.std_mean', 'torch.ops.aten.addr', 'torch.ops.aten.cat', 'torch.ops.aten.flip', 'torch.ops.aten.native_layer_norm', 'torch.ops.aten.permute', 'torch.ops.aten.roll', 'torch.ops.aten.rot90', 'torch.ops.aten.stack', 'torch.ops.aten.t', 'torch.ops.aten.unsqueeze', 'torch.ops.aten.trace', 'torch.ops.aten.celu', 'torch.ops.aten.relu', 'torch.ops.aten.leaky_relu', 'torch.ops.aten.mish', 'torch.ops.aten.softplus', 'torch.ops.aten.hardtanh', 'torch.ops.aten.gelu', 'torch.ops.aten.special_i0e', 'torch.ops.aten.special_i1', 'torch.ops.aten.special_i1e', 'torch.ops.aten.logit', 'torch.ops.aten.special_zeta']