Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Last revisionBoth sides next revision
fpga_architecture_for_computing [2022/08/20 11:15] – [Students] editfpga_architecture_for_computing [2022/08/20 11:19] – [Demo and Downloads] edit
Line 64: Line 64:
   * Our initial concept is based on factoring out the concerns for data orchestration from the compute kernels. The in-fabric computation kernels interacting with only the simple on-chip SRAM blocks for data input and output ([[https://users.ece.cmu.edu/~jhoe/distribution/2011/fpga11.pdf |Chung, FPGA'2011]]). Separately, a set of control threads—expressed in a multithreaded C-like language—manage (1) the data movements between the off-chip DRAM and on-chip SRAMs, and also (2) the invocations of the kernels over time.  The CoRAM compiler automatically infers and synthesizes from the control threads both the required data transfer paths and the state-machine controllers in support of the computation kernels.    * Our initial concept is based on factoring out the concerns for data orchestration from the compute kernels. The in-fabric computation kernels interacting with only the simple on-chip SRAM blocks for data input and output ([[https://users.ece.cmu.edu/~jhoe/distribution/2011/fpga11.pdf |Chung, FPGA'2011]]). Separately, a set of control threads—expressed in a multithreaded C-like language—manage (1) the data movements between the off-chip DRAM and on-chip SRAMs, and also (2) the invocations of the kernels over time.  The CoRAM compiler automatically infers and synthesizes from the control threads both the required data transfer paths and the state-machine controllers in support of the computation kernels. 
   * We later introduced a soft-logic CoRAM abstraction layer with further elevated kernel and control thread application-level interfaces that directly support the high-level semantics of commonly-used in-memory data structure types (e.g., streams, arrays, linked lists, and trees) ([[https://users.ece.cmu.edu/~jhoe/distribution/2015/fpl2015.pdf |Weisz, FPL'2015]]).     * We later introduced a soft-logic CoRAM abstraction layer with further elevated kernel and control thread application-level interfaces that directly support the high-level semantics of commonly-used in-memory data structure types (e.g., streams, arrays, linked lists, and trees) ([[https://users.ece.cmu.edu/~jhoe/distribution/2015/fpl2015.pdf |Weisz, FPL'2015]]).  
-  * We developed the [[https://research.ece.cmu.edu/calcm/new_connect/connect/  |CONNECT NoC Generator]] in support of CoRAM.+  * We developed the [[https://github.com/crossroadsfpga/connect  |CONNECT NoC Generator]] in support of CoRAM.
          
  
Line 107: Line 107:
     * [[http://research.ece.cmu.edu/~coram/doku.php?id=corflow_beta |CoRAM-classic demo and downloads]]     * [[http://research.ece.cmu.edu/~coram/doku.php?id=corflow_beta |CoRAM-classic demo and downloads]]
     * [[http://research.ece.cmu.edu/~coram/doku.php?id=fpga_2013_tutorial | CoRAM-classic Tutorial at FPGA-2013]]     * [[http://research.ece.cmu.edu/~coram/doku.php?id=fpga_2013_tutorial | CoRAM-classic Tutorial at FPGA-2013]]
-    * [[http://research.ece.cmu.edu/calcm/connect |CONNECT NoC Generator]]+    * [[https://github.com/crossroadsfpga/connect |CONNECT NoC Generator]]
     * [[http://research.ece.cmu.edu/calcm/connect_hls |CONNECT NoC in Vivado-HLS synthesizable C]]     * [[http://research.ece.cmu.edu/calcm/connect_hls |CONNECT NoC in Vivado-HLS synthesizable C]]