Abstract: A display device has a transmissive area and a reflective area. The transmissive area corresponds to a first sub-pixel, and the reflective area corresponds to a second sub-pixel. The display device includes a backlight module, a liquid crystal module, and an anti-reflective layer. The liquid crystal module is disposed on the backlight module and includes a first substrate, a component layer, and a reflective layer. The component layer is disposed on the first substrate and includes a first transistor and a second transistor. The first transistor is configured to drive the first sub-pixel, and the second transistor is configured to drive the second sub-pixel. The reflective layer is disposed on the component layer and corresponds to the reflective area. The anti-reflective layer is disposed on the liquid crystal module.

Abstract: A memory control method includes a processor initiating a memory access instruction to a cache controller to search a cache memory, an address detector checking if the memory access instruction is corresponding to predetermined conditions if a cache miss occurs, the address detector transmitting a signal to inform a replacement mask logic unit if the memory access instruction is corresponding to the predetermined conditions, and the replacement mask logic unit providing predetermined data to store the predetermined data into the cache memory.

Abstract: An execution method for convolution computation is disclosed, which includes: dividing an input image of N channels into a first tile to an X-th tile according to a feature tile; sequentially performing convolution computations on the data in the first tile to the X-th tile of the input image of the N channels, and storing the computation results as output data; mapping the data in each of the tiles by a kernel, and performing multiply-accumulate operations on the mapped data in each of the tiles, wherein each time the multiply-accumulate operation performed on the data mapped by the kernel is complete, the kernel is shifted to change the mapped data in said tile, and multiply-accumulate operation is performed on the changed mapped data until the multiply-accumulate operations performed on all of the data in said tile are complete, thereby finishing the convolution computation of said tile.