发明名称 |
Mixed-width memory techniques for programmable logic devices |
摘要 |
Various techniques are provided to efficiently implement user designs in programmable logic devices (PLDs). In one example, a computer-implemented method includes receiving a design identifying operations to be performed by a PLD and synthesizing the design into a plurality of PLD components. The synthesizing includes detecting a mixed-mode memory operation in the design. The mixed-mode memory operation specifies memory access having different read and write data widths using a plurality of embedded memory blocks each having a fixed data width. The synthesizing further includes determining a reduced number of embedded memory blocks to implement the mixed-mode memory operation, and modifying the mixed-mode memory operation to remap the memory access to the reduced number of embedded memory blocks. |
申请公布号 |
US9576093(B2) |
申请公布日期 |
2017.02.21 |
申请号 |
US201414320169 |
申请日期 |
2014.06.30 |
申请人 |
LATTICE SEMICONDUCTOR CORPORATION |
发明人 |
Rajappan Venkatesan;Tandyala Mohana;Xue Hua |
分类号 |
G06F17/50 |
主分类号 |
G06F17/50 |
代理机构 |
Haynes and Boone, LLP |
代理人 |
Haynes and Boone, LLP |
主权项 |
1. A computer-implemented method comprising:
receiving a design identifying operations to be performed by a programmable logic device (PLD); and synthesizing the design into a plurality of PLD components, wherein the synthesizing comprises:
detecting a mixed-mode memory operation in the design, the mixed-mode memory operation specifying memory access having different read and write data widths using a plurality of embedded memory blocks each having a fixed data width, each of the plurality of embedded memory blocks being associated with a corresponding write enable signal to be used for enabling each embedded memory block for writing,determining a reduced number of embedded memory blocks to implement the mixed-mode memory operation, andmodifying the mixed-mode memory operation to remap the memory access to the reduced number of embedded memory blocks, the modifying comprising generating a write mask signal for each of the reduced number of embedded memory block, using the write enable signals, to allow a plurality of data portions to be written without overwriting each other in the reduced number of embedded memory blocks. |
地址 |
Hillsboro OR US |