Abstract: A hardware accelerator is provided. The hardware accelerator includes a first memory; a source address generation unit coupled to the first memory; a data collection unit coupled to the first memory; a first data queue coupled to the data collection unit; a data dispersion unit coupled to the first data queue; a destination address generation unit coupled to the data dispersion unit; an address queue coupled to the destination address generation unit; a second data queue coupled to the data dispersion unit; and a second memory coupled to the second data queue. The hardware accelerator can perform anyone or any combination of tensor stride, tensor reshape and tensor transpose to achieve tensorflow depth-to-space permutation or tensorflow space-to-depth permutation.

Abstract: A method for fabricating semiconductor device includes first forming a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, performing an atomic layer deposition (ALD) process or a high-density plasma (HDP) process to form a passivation layer on the first MTJ and the second MTJ, performing an etching process to remove the passivation layer adjacent to the first MTJ and the second MTJ, and then forming an ultra low-k (ULK) dielectric layer on the passivation layer.

Abstract: A semiconductor device includes a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, a passivation layer on the first MTJ and the second MTJ, and an ultra low-k (ULK) dielectric layer on the passivation layer. Preferably, a top surface of the passivation layer between the first MTJ and the second MTJ is lower than a top surface of the passivation layer directly on top of the first MTJ.

Abstract: A method for fabricating semiconductor device includes the steps of: forming a first magnetic tunneling junction (MTJ) on a substrate; forming a first ultra low-k (ULK) dielectric layer on the first MTJ; performing a first etching process to remove part of the first ULK dielectric layer and form a damaged layer on the first ULK dielectric layer; and forming a second ULK dielectric layer on the damaged layer.

Abstract: A method for fabricating semiconductor device includes first forming a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, performing an atomic layer deposition (ALD) process or a high-density plasma (HDP) process to form a passivation layer on the first MTJ and the second MTJ, performing an etching process to remove the passivation layer adjacent to the first MTJ and the second MTJ, and then forming an ultra low-k (ULK) dielectric layer on the passivation layer.

Abstract: A semiconductor device includes a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, a passivation layer on the first MTJ and the second MTJ, and an ultra low-k (ULK) dielectric layer on the passivation layer. Preferably, a top surface of the passivation layer between the first MTJ and the second MTJ is lower than a top surface of the passivation layer directly on top of the first MTJ.

Abstract: A method for fabricating semiconductor device includes the steps of: forming a first magnetic tunneling junction (MTJ) on a substrate; forming a first ultra low-k (ULK) dielectric layer on the first MTJ; performing a first etching process to remove part of the first ULK dielectric layer and forming a damaged layer on the first ULK dielectric layer; and forming a second ULK dielectric layer on the damaged layer.

Abstract: A mixed-precision artificial intelligence (AI) processor and an operating method thereof are provided. The AI processor includes a first calculation module, a second calculation module and a control module. The first calculation module is configured to perform calculation based on the data with a first format. The second calculation module is configured to perform calculation based on the data with a second format different from the first format. The control module is coupled to the first calculation module and the second calculation module to select one of the first calculation module or the second calculation module to perform calculation based on an input data according to a calculation strategy.

Abstract: An artificial intelligence (AI) calculation circuit is provided. The AI calculation circuit can support various integer and floating-point calculations through the adjustment of circuit configuration. Integer multiplication and floating-point mantissa multiplication share the multiplication unit, integer comparison and floating-point comparison share the same comparison unit, integer addition and floating-point addition share the same addition unit.

Abstract: A hardware accelerator is provided. The hardware accelerator includes a first memory; a source address generation unit coupled to the first memory; a data collection unit coupled to the first memory; a first data queue coupled to the data collection unit; a data dispersion unit coupled to the first data queue; a destination address generation unit coupled to the data dispersion unit; an address queue coupled to the destination address generation unit; a second data queue coupled to the data dispersion unit; and a second memory coupled to the second data queue. The hardware accelerator can perform anyone or any combination of tensor stride, tensor reshape and tensor transpose to achieve tensorflow depth-to-space permutation or tensorflow space-to-depth permutation.

Abstract: A computing device for floating-point mathematic operation using look-up table is provided. The computing device includes: a bit arrangement unit used for receiving a floating-point input data and performing a bit arrangement or a format conversion on the floating-point input data to generate multiple index blocks; a first look-up table unit group used for receiving the index blocks and performing look-up operation using the index blocks as index to generate a plurality of look-up table results; and an operation unit used for performing operation on the look-up table results of the first look-up table unit group to generate an operation output.

Abstract: A method for fabricating semiconductor device includes first forming a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, performing an atomic layer deposition (ALD) process or a high-density plasma (HDP) process to form a passivation layer on the first MTJ and the second MTJ, performing an etching process to remove the passivation layer adjacent to the first MTJ and the second MTJ, and then forming an ultra low-k (ULK) dielectric layer on the passivation layer.

Abstract: A semiconductor device includes a first magnetic tunneling junction (MTJ) and a second MTJ on a substrate, a passivation layer on the first MTJ and the second MTJ, and an ultra low-k (ULK) dielectric layer on the passivation layer. Preferably, a top surface of the passivation layer between the first MTJ and the second MTJ is lower than a top surface of the passivation layer directly on top of the first MTJ.

Abstract: A method for fabricating semiconductor device includes the steps of: forming a first magnetic tunneling junction (MTJ) on a substrate; forming a first ultra low-k (ULK) dielectric layer on the first MTJ; performing a first etching process to remove part of the first ULK dielectric layer and forming a damaged layer on the first ULK dielectric layer; and forming a second ULK dielectric layer on the damaged layer.

Abstract: A method for fabricating semiconductor device includes the steps of: forming a first magnetic tunneling junction (MTJ) on a substrate; forming a first ultra low-k (ULK) dielectric layer on the first MTJ; performing a first etching process to remove part of the first ULK dielectric layer and forming a damaged layer on the first ULK dielectric layer; and forming a second ULK dielectric layer on the damaged layer.

Abstract: The present invention provides a method for forming a semiconductor structure. The method including: Firstly, a substrate is provided, a first region and a second region are defined thereon, next, a gate dielectric layer and a work function metal layer are sequentially formed on the substrate within the first region and within the second region. Afterwards, a dielectric layer is formed on the work function metal layer within the second region, a hydrogen gas treatment is then performed on the substrate, and the work function metal layer is removed within the first region.

Abstract: A method for fabricating semiconductor device includes the steps of: forming a first magnetic tunneling junction (MTJ) on a substrate; forming a first ultra low-k (ULK) dielectric layer on the first MTJ; performing a first etching process to remove part of the first ULK dielectric layer and forming a damaged layer on the first ULK dielectric layer; and forming a second ULK dielectric layer on the damaged layer.

Abstract: The present invention provides a method for forming a semiconductor structure. The method including: Firstly, a substrate is provided, a first region and a second region are defined thereon, next, a gate dielectric layer and a work function metal layer are sequentially formed on the substrate within the first region and within the second region. Afterwards, a dielectric layer is formed on the work function metal layer within the second region, a hydrogen gas treatment is then performed on the substrate, and the work function metal layer is removed within the first region.

Abstract: The present invention provides a method for forming a semiconductor structure. The method including: Firstly, a substrate is provided, a first region and a second region are defined thereon, next, a gate dielectric layer and a work function metal layer are sequentially formed on the substrate within the first region and within the second region. Afterwards, a dielectric layer is formed on the work function metal layer within the second region, a hydrogen gas treatment is then performed on the substrate, and the work function metal layer is removed within the first region.

Abstract: A semiconductor device with reinforced gate spacers and a method of fabricating the same. The semiconductor device includes low-k dielectric gate spacers adjacent to a gate structure. A high-k dielectric material is disposed over an upper surface of the low-k dielectric gate spacers to prevent unnecessary contact between the gate structure and a self-aligned contact structure. The high-k dielectric material may be disposed, if desired, over an upper surface of the gate structure to provide additional isolation of the gate structure from the self-aligned contact structure.