preview

The issue I was thinking of is if you needed multiple "custom instructions" within a loop. Another related issue, if multiple tiles are considered, is the interconnect between the processor core and the tiles. Interconnect is expensive, so there's a trade off to be made. Profiling data showing a curve of unique accelerator functions for the targeted problem domains and their temporal relationship (e.g. there may be ten accelerator functions but they are executed several milliseconds apart or functions A and B tend to appear in an inner loop together) would help make the trade off.

I don't think having a standard processor coupled with programmable gates is a new idea. The key is in making it simple to use. A basic adder or multiplier is a well known piece of logic and would be included in a standard FPGA component library. Will arbitrary custom instructions require an engineer to develop the FPGA macro? Having a software and a hardware engineer working together to optimize execution time does not seem new to me. Is the simplification in the interface between the processor and FPGA gates?

They must have done some research into min and max gates required to implement logic for custom instructions across the targeted problem domains. An important question is the time required to reconfigure the FPGA gates. Multiple FPGA tiles will be needed since it'd take longer to reconfigure the FPGA gates then to jump to a new branch of code that had its own custom instruction. This may require a customization to the compiler as time to reconfigure FPGA gates may need to be taken into account in the order of execution (not a new problem; just another variable to take into account).

It could be very interesting, but more technical details are needed.

I agree that bankruptcy is not the answer. What I question is the $700 billion amount and the time frame in which the money will be used.

There is a lack of confidence that must be fixed. It seems like a smaller amount of money could be used to fix the confidence problem and get the "wheels of credit" turning again. There may also be a need to purchase some distressed securities. With confidence restored, it seems like financial institutions could step back into the picture to buy low and sell high.

I agree that the US government is not blameless, but I disagree that bankers should not be blamed for their role. If a banker's value is "managing risk in lending, reducing overall risk," then the banks still failed to supply this value add.

It may also be a fair statement that the institutions did not know the value of what they were buying because of the way they were packaged. I thought that was one of the obstacles facing the bailout--how to value some/most/all of the troubled financial instruments involved. This lack of clarity seems to add to the risk.

But is that what happened here? Financial institutions lent money to borrowers who could not afford the loan they were given. The financial institutions packaged up those extremely risky loans to pass the buck on to another institution.

It seems that the institutions did not manage risk. In a very generic view, bankers may have value. But as far as this financial crisis goes, they failed miserably.

A return to software rendering could present an interesting opportunity for Linux. A major barrier against using Linux is the lack of availability of A-list games. If a game no longer requires DirectX, then it would seem to be an easier task to port it to many operating systems. It would not be a magic fix, but it would be one more step toward the possibility of a mass market Linux on the desktop.