Looks like the AM17xx and AM18xx devices do not include the vector floating point co-processor.
Is that correct?
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Hi Mukul,
Just wanted to understand this a little more. Is the co-processor VFP9-S optional which may/may not be integrated with the ARM9 processor? In the absence of this, does one have to use the ARM core only for doing floating-point calculations?
Thanks.
Anuj Aggarwal said:Just wanted to understand this a little more. Is the co-processor VFP9-S optional which may/may not be integrated with the ARM9 processor?
Since it is a coprocessor, I believe your assessment is true, it is upto the chip architects on whether this needs to be integrated
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ddi0238c/BABCJJCI.html
I don't think any of our ARM9 based processors, have this coprocessor.
I have forwarded your query on floating point calc to Sitara team. I don't have a good answer on how ARM9 can/cannot be used for floating point calcs.
Anuj,
None of the current ARM9 based parts have a FP accelerator (VFP9-S), so you would have to use the ARM core for doing floating point calculations.
But please don't forget other chips such as OMAP-L138 and OMAP-L137 which have both the ARM9 + DSP cores should you need more floating point than ARM alone can provide.