George- > I don't believe they had a configurable option for it. Though > I no longer use it (and I actually don't they are around anymore), but what > exactly is the issue with using the IDLE in conjunction with an HPI > interface? You've got my curiousity up. In looking at the "TMS320C6000 DSP Power-Down Logic and Modes Reference Guide" document (SPRU728B) more closely: a) HPI should be Ok with IDLE instruction or PD1 power-down mode b) PD2 and PD3 modes should work Ok on C67xx (what was I thinking before?) c) in PD2 and PD3 modes the document says that "peripheral operation is not assured..." So PD2 and PD3 modes would be the situation where an external processor would need to be aware and avoid using HPI. PD3 completely stops the clock... darn, that sounds good. I need to try that. I wouldn't be surprised if the wake-up interrupt has to be level-triggered in that state, without a clock handy. -Jeff

Hi Jeff: I don't believe they had a configurable option for it. Though I no longer use it (and I actually don't they are around anymore), but what exactly is the issue with using the IDLE in conjunction with an HPI interface? You've got my curiousity up. - George > > George- > I hope the 3p makes that a configurable RTOS option. What happens for example if an > external processor is using HPI? > > -Jeff > >

George- > Hi Anoop, Bernhard: > > From what you said Anoop, what Bernhard is saying <is> probably > what you want to do, i.e., a SW Reset. The CSL functions can easily > be used to insure that the processor is in fact brought back to the > default conditions at reset, and by jumping to 0x00000000, you're > back at the starting gate. > > That said, there is a legitimate reason for using the IDLE instruction. I've > seen a third party RTOS's source code where they use it post-initialization. > (Can't go into it, because I'm not at liberty to discuss). The RTOS's task > scheduler kicks off the first task on it's task list via the TIMER interrupt > (Remember, IDLE effectively Halts the CPU <until> an interrupt is > received), thus the CPU is then no longer sitting there in a halted state. > No, this wasn't DSP-BIOS, but I'd guess that they probably do what I > just mentioned. I hope the 3p makes that a configurable RTOS option. What happens for example if an external processor is using HPI? -Jeff

This seems to match my thinking as well. There have been enhancements by adding PD2 and PD3 specifically for C64xx devices. Regds JS >Jeff Brower wrote: > > Jagadeesh- > > > If the real reason you want to halt the DSP, is to save power, then a better > > way to do it would be to use the power down modes. > > For C67xx devices (I believe the original poster was using DSK C6711), my > understanding is the IDLE instruction is the same as writing values to the PWRD field > in the CSR that cause PD1 power down mode, and PD2 and PD3 modes are not available. > > In PD1, the CPU is halted but clock PLL continues to run. > > My conclusion is that for C67xx devices, a) IDLE instruction is as good as it gets, > and b) the benefit is not as much as for other C6xxx devices that support PD2 and > PD3. > > If that's not accurate, please someone correct me. > > -Jeff > > > -----Original Message----- > > From: Jeff Brower [mailto:] > > Sent: Sunday, February 20, 2005 12:18 AM > > To: Bhooshan Iyer > > Cc: > > Subject: Re: [c6x] Re: Halting the DSP > > > > Hi Bhooshan- > > > > > Isnt IDLE like an infinite "branch to itself", if so does it really > > > help save power? Does TI mention anywhere about power savings due to > > > IDLE? > > > > It does NOPs, which are supposed to save power. Did you know there is a > > "TMS320C6000 > > DSP Power-Down Logic and Modes Reference Guide" document? I did not, but > > there is, > > seems like it came out in Aug 2004 and was revised Jan 2005: > > > > http://focus.ti.com/lit/ug/spru728b/spru728b.pdf > > > > On pg 9: > > > > "In addition to power-down modes described in this document, > > the IDLE instruction provides lower CPU power consumption > > by executing continuous NOPs. The IDLE instruction terminates > > only upon servicing an interrupt." > > > > How much power is saved by hard-coded NOPs vs. a code loop that does the > > same thing? > > That's not quantified, but I suppose a bit might be saved by not executing > > NOPs from > > P cache, which is a piece of SRAM. > > > > -Jeff > > > > > On Sat, 19 Feb 2005 10:41:41 -0600, Jeff Brower <> > > wrote: > > > > > > > > Mike- > > > > > > > > > 1. there is no functional reason to halt [or try to halt] a c6000 > > DSP. > > > > > > > > Is reducing power consumption a valid reason to make frequent use of > > IDLE/interrupt > > > > combination? > > > > . > > > > . > > > > . > > > > > > > > > Of course, if we all add bullet proof hardware and software, we would > > > > > not be thinking about reset after power up. > > > > > > > > There is always the cosmic ray with the name of your product on it :-) > > I know that's > > > > truly nanoscopic writing not yet developed by mankind, but it's there. > > > > > > > > -Jeff > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > -- > > > ------------------------------- > > > "I've missed more than 9000 shots in my career. > > > I've lost almost 300 games. 26 times I've been trusted to take the > > > game winning shot and missed. > > > I've failed over and over again in my life. > > > And that is why I succeed." > > > -- Michael Jordan > > > -------------------------------- > > > > > > > > > > > > > > > > > > > >

Mike- > > > 1. there is no functional reason to halt [or try to halt] a c6000 DSP. > > Is reducing power consumption a valid reason to make frequent use of > > IDLE/interrupt combination? > Valid yes, functional no. The idle instruction can save you power, > but I know of any functional reason to use it. Maybe I am a bit > extreme with my meanings... mikedunn If saving power whenever possible is an application objective, what else can be done on the C67xx? I'm not clear on the difference between PD1 mode and IDLE instruction, if any. I'm assuming either one consumes less power than a short code loop that branches to itself and does NOPs, but how much less power? -Jeff

Jeff,

Jeff Brower <j...@signalogic.com> wrote:

Mike-

> 1. there is no functional reason to halt [or try to halt] a c6000 DSP.

Is reducing power consumption a valid reason to make frequent use of IDLE/interrupt combination?

Valid yes, functional no. The idle instruction can save you power, but I know of any functional reason to use it. Maybe I am a bit extreme with my meanings... mikedunn

> Of course, if we all add bullet proof hardware and software, we would
> not be thinking about reset after power up.

There is always the cosmic ray with the name of your product on it :-) I know that's
truly nanoscopic writing not yet developed by mankind, but it's there.

I guess that I should have not been my sarcastic self. For the record, we should always do our best, within our constraints, to develop hardware and software that is immune to as many outside influences as possible. After we have done this, we should assume that the system will fail anyway. At this point we should decide if we have the need and will to recover from such an error... mikedunn

-Jeff

Jagadeesh- > If the real reason you want to halt the DSP, is to save power, then a better > way to do it would be to use the power down modes. For C67xx devices (I believe the original poster was using DSK C6711), my understanding is the IDLE instruction is the same as writing values to the PWRD field in the CSR that cause PD1 power down mode, and PD2 and PD3 modes are not available. In PD1, the CPU is halted but clock PLL continues to run. My conclusion is that for C67xx devices, a) IDLE instruction is as good as it gets, and b) the benefit is not as much as for other C6xxx devices that support PD2 and PD3. If that's not accurate, please someone correct me. -Jeff > -----Original Message----- > From: Jeff Brower [mailto:] > Sent: Sunday, February 20, 2005 12:18 AM > To: Bhooshan Iyer > Cc: > Subject: Re: [c6x] Re: Halting the DSP > > Hi Bhooshan- > > > Isnt IDLE like an infinite "branch to itself", if so does it really > > help save power? Does TI mention anywhere about power savings due to > > IDLE? > > It does NOPs, which are supposed to save power. Did you know there is a > "TMS320C6000 > DSP Power-Down Logic and Modes Reference Guide" document? I did not, but > there is, > seems like it came out in Aug 2004 and was revised Jan 2005: > > http://focus.ti.com/lit/ug/spru728b/spru728b.pdf > > On pg 9: > > "In addition to power-down modes described in this document, > the IDLE instruction provides lower CPU power consumption > by executing continuous NOPs. The IDLE instruction terminates > only upon servicing an interrupt." > > How much power is saved by hard-coded NOPs vs. a code loop that does the > same thing? > That's not quantified, but I suppose a bit might be saved by not executing > NOPs from > P cache, which is a piece of SRAM. > > -Jeff > > > On Sat, 19 Feb 2005 10:41:41 -0600, Jeff Brower <> > wrote: > > > > > > Mike- > > > > > > > 1. there is no functional reason to halt [or try to halt] a c6000 > DSP. > > > > > > Is reducing power consumption a valid reason to make frequent use of > IDLE/interrupt > > > combination? > > > . > > > . > > > . > > > > > > > Of course, if we all add bullet proof hardware and software, we would > > > > not be thinking about reset after power up. > > > > > > There is always the cosmic ray with the name of your product on it :-) > I know that's > > > truly nanoscopic writing not yet developed by mankind, but it's there. > > > > > > -Jeff > > > > > > > > > > > > > > > > > > > > > > > > > > > > -- > > ------------------------------- > > "I've missed more than 9000 shots in my career. > > I've lost almost 300 games. 26 times I've been trusted to take the > > game winning shot and missed. > > I've failed over and over again in my life. > > And that is why I succeed." > > -- Michael Jordan > > -------------------------------- > >

Jeff-- Isnt IDLE like an infinite "branch to itself", if so does it really help save power? Does TI mention anywhere about power savings due to IDLE? --Bhooshan On Sat, 19 Feb 2005 10:41:41 -0600, Jeff Brower <> wrote: > > Mike- > > > 1. there is no functional reason to halt [or try to halt] a c6000 DSP. > > Is reducing power consumption a valid reason to make frequent use of IDLE/interrupt > combination? > . > . > . > > > Of course, if we all add bullet proof hardware and software, we would > > not be thinking about reset after power up. > > There is always the cosmic ray with the name of your product on it :-) I know that's > truly nanoscopic writing not yet developed by mankind, but it's there. > > -Jeff -- ------------------------------- "I've missed more than 9000 shots in my career. I've lost almost 300 games. 26 times I've been trusted to take the game winning shot and missed. I've failed over and over again in my life. And that is why I succeed." -- Michael Jordan --------------------------------

Hi Bhooshan- > Isnt IDLE like an infinite "branch to itself", if so does it really > help save power? Does TI mention anywhere about power savings due to > IDLE? It does NOPs, which are supposed to save power. Did you know there is a "TMS320C6000 DSP Power-Down Logic and Modes Reference Guide" document? I did not, but there is, seems like it came out in Aug 2004 and was revised Jan 2005: http://focus.ti.com/lit/ug/spru728b/spru728b.pdf On pg 9: "In addition to power-down modes described in this document, the IDLE instruction provides lower CPU power consumption by executing continuous NOPs. The IDLE instruction terminates only upon servicing an interrupt." How much power is saved by hard-coded NOPs vs. a code loop that does the same thing? That's not quantified, but I suppose a bit might be saved by not executing NOPs from P cache, which is a piece of SRAM. -Jeff > On Sat, 19 Feb 2005 10:41:41 -0600, Jeff Brower <> wrote: > > > > Mike- > > > > > 1. there is no functional reason to halt [or try to halt] a c6000 DSP. > > > > Is reducing power consumption a valid reason to make frequent use of IDLE/interrupt > > combination? > > . > > . > > . > > > > > Of course, if we all add bullet proof hardware and software, we would > > > not be thinking about reset after power up. > > > > There is always the cosmic ray with the name of your product on it :-) I know that's > > truly nanoscopic writing not yet developed by mankind, but it's there. > > > > -Jeff > > > > > > > > > > > > > > > > > > -- > ------------------------------- > "I've missed more than 9000 shots in my career. > I've lost almost 300 games. 26 times I've been trusted to take the > game winning shot and missed. > I've failed over and over again in my life. > And that is why I succeed." > -- Michael Jordan > --------------------------------