I'm thinking about doing a similar course in the spring, so looking forward to hearing how yours goes!
-
-
yeah there's room for a lot of different tools here! the ones I want are those that displace hand-written instcombine and isel.
-
Another example: I just wrote a fragment shader to draw a checkerboard pattern for debugging. There are a lot of ways I can think of to do this and if I actually cared about perf it would be annoying. Would be nice for a tool to just tell me which technique is fastest.
- 1 more reply
New conversation -
-
-
In my case (PNG prediction during decoding), I knew what I wanted to do, and I could write some basic code, but I wasn’t sure if there was some clever trick I was missing. A superoptimizer would be useful to point out tricks that I missed.
-
The model for STOKE is too naive though. It doesn’t know about critical path, superscalar, loop stream, etc. It only counts per-instruction cost. It’s good at high level things, but many of the details it could learn. It’s also missing concurrency correctness and debugging

- 3 more replies
New conversation -
-
-
That’s
@dril_rs?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.