LOTS of reasons. Here's just a few: - Not everyone has an OGD1. In fact, hardly anyone does. - So we can do design space exploration without special hardware. - So we can do power simulations that you can't do in an FPGA. - So prospective users/licensees can do functional and power simulation without special hardware. - So that researchers can do GPU simulations (performance, power, reliability) of an open architecture.
We're developing an ARCHITECTURE. We can do 90% of that in pure software. At some point, we'll have a synthesizable design in Verilog, but we'll even simulate THAT in software. Running it for real in an FPGA is a fairly late stage. Long before that, we'll know all of the performance and scheduling issues. On Tue, May 29, 2012 at 1:25 PM, Dieter BSD <[email protected]> wrote: > What's this about needing a simulator? What happened to > using the OGD1 to develop the design on? > _______________________________________________ > Open-graphics mailing list > [email protected] > http://lists.duskglow.com/mailman/listinfo/open-graphics > List service provided by Duskglow Consulting, LLC (www.duskglow.com) -- Timothy Normand Miller http://www.cse.ohio-state.edu/~millerti Open Graphics Project _______________________________________________ Open-graphics mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-graphics List service provided by Duskglow Consulting, LLC (www.duskglow.com)
