The presentation at GPGPU'09 went well yesterday. I lasted several minutes over budget [as usual], but I felt good about it. When I get home and find my credentials to the GPU VSIPL website, I'll upload my presentation and cite my paper.
Today was the first day of ASPLOS. I wound up sleeping in and missed the keynote, but I sat at the keynote speaker's table during lunch. He's a Google guy and regaled the group with clever ideas, charm, and wit.
The trouble with conferences is they fill you with a billion great ideas and no time to implement them. The wild and crazy idea session included:
* bubble wrap cores - disposable CPU cores so you can run several hotter and faster and burn them out quickly
* on-chip power - nuclear or piezoelectric
* neuro-implants - CPUs in your brain
* purely speculative cores - run parts of your program long before you ever get to them
2 of 3 beer vouchers remain.
2 comments:
i like the purely speculative cores. I wonder, could you use the multiple cores by having your program split into two at every decision? I know you couldn't get too many decisions ahead, but they are talking about 1024 cores, thats like 10 decisions.
Once it seems clear which way you are heading, just reuse the cores
Downside: speculation wastes power, and so has become less popular as an architectural tool over the years. Today power is the #1 limiting factor in chip design. GPUs (for example) eschew it entirely, and CPUs are far less aggressive about speculation than they used to be.
Also the amount of wires to bring all the results to the same place when you reconverge becomes another limiting factor (and indeed is part of the power cost).
Post a Comment