GreenPAK speed test

dsniptechnology.com:

s

hey

PLL.

. e

ith

as

up

f

PGAs

,

oks like they also have M3 for FPGAs as well, they even mention using them for "free" which I assume means evaluation.

yes M1 is M0 optimized for FPGA

as far as I can tell it is really free for use in Xilinx FPGAs

" Free to use on FPGA Free use on FPGA for Cortex-M1 and Cortex-M3 For prototyping, research and commercial use "

An ARM processor with some extra programmable logic would be interesting too.

In my case, programmable code won't help. These Silegos (Silicon Lego) are just perfect ! And they have some things like comparators, etc. All I need them for is just the programmable logic gates and counters/delays. Being re-programmable is nice and I am making use of this but not necessary. I would be using it even without that feature.

I my products I am using them to create dead-time for FET drive as well as synchronous rectification logic. Maybe a couple other little tasks too. Still have to use 2 of them but the size amd being around

40 cents each makes it very useful.

Much smaller than the Xylinx CPLD I was using and less expensive. Really nice little devices.

ips

they

ne PLL.

ng.

ete

with

as

has

s up

of

20

ft

FPGAs

ce,

Looks like they also have M3 for FPGAs as well, they even mention using the m for "free" which I assume means evaluation.

I found similar info on the ARM web site without the restriction to Xilinx parts, but I could not find out how to get it. I'm sure there are many qua lifications. Ts & Cs.

--

  Rick C. 

  +- Get 1,000 miles of free Supercharging 
  +- Tesla referral code - https://ts.la/richard11209

How fast will that FPGA programmed as an ARM Cortex M3 run and how much will it cost ? Seems to me that a 20,000+ LUT FPGA is not going to be cheap ? Compared to just buying an ARM processor of the same complexity at least.

hips

e they

one PLL.

ing.

pete

s with

as

U has

ps up

t of

$20

oft

a h

r FPGAs

ace,

Looks like they also have M3 for FPGAs as well, they even mention using th em for "free" which I assume means evaluation.

yeh you have to have some special need to put it in the fpga when you can buy an MCU with more memory and preformance for a fraction of the price

chips

se they

one PLL.

ting.

mpete

Us with

e as

CU has

mps up

ot of

$20

Soft

a

sh

ir FPGAs

face,

Looks like they also have M3 for FPGAs as well, they even mention using t hem for "free" which I assume means evaluation.

x parts, but I could not find out how to get it. I'm sure there are many q ualifications. Ts & Cs.

You have been able to get the cores for evaluation and design from ARM for a long time, so you didn't need to get a license and pay until you actually use it

as I understand it they have then made a deal with Xilinx that long as it is used in a Xilinx fpga a license is included

chips

use they

y one PLL.

sting.

ompete

CUs with

re as

MCU has

umps up

lot of

e $20

Soft

e a

ash

eir FPGAs

rface,

. Looks like they also have M3 for FPGAs as well, they even mention using them for "free" which I assume means evaluation.

ce

I don't know why people get this backwards so often. You must have a speci al need to want a processor when you have a perfectly good FPGA.

Actually, an FPGA contains many, many tiny multiplexers connecting many, ma ny tiny bits of RAM in contrast to a processor which has the power of the h umongous multiplexer manipulating very large blocks of RAM and Flash. So t he processor has to run very, very fast to create virtual connections betwe en the many portions of memory. The FPGA in contrast has wires connected b y routing FETs that can be used to connect the tiny multiplexers and bits o f RAM as selected by the multiplexers.

While the processor can do many slow tasks by switching between them with i ts humongous multiplexer selecting which task to emulate now, the FPGA is a ctually processing each task in parallel using much simpler resources for e ach task, fast or slow, it doesn't care.

Which is better...? usually the one we are more familiar with. People ofte n talk as if it is silly to design something in an FPGA that doesn't requir e high speed or some other feature that makes it impossible to do in an MCU . I look at problems from the other perspective, I only put in an MCU the parts that are awkward to do in an FPGA.

In the board I sell by the thousands (making lots of money in the process) there was nothing that could not be done in the FPGA, so no MCU needed. Of course it is a daughter board in a bigger system with lots of processors r unning operating systems virtualizing other operating systems... and then t hey have bigger FPGAs than mine to do the real work.

--

  Rick C. 

  ++ Get 1,000 miles of free Supercharging 
  ++ Tesla referral code - https://ts.la/richard11209

) chips

ause they

ly one PLL.

esting.

compete

MCUs with

are as

MCU has

bumps up

lot of

he $20

. Soft

be a

lash

heir FPGAs

erface,

s. Looks like they also have M3 for FPGAs as well, they even mention using them for "free" which I assume means evaluation.

inx parts, but I could not find out how to get it. I'm sure there are many qualifications. Ts & Cs.

So no T&C to read, review by lawyers and sign? Bet there is. Just from Xi linx rather than ARM.

I read a lawyer on the Internet telling people to NOT read the T&C for webs ites. Then you can have a defense based on that, not that there is any gua rantee that it will work for you. But as soon as you acknowledge that you were aware of the terms, you lose that possibility. Maryland and Virginia (and many other states) have passed laws saying these "contracts" are enfor ceable. I think they should not do that. It's not at all practical for a person to know the Ts & Cs of very web site they visit. What if you were r equired to sign a contact, or more analogously, you automatically signed wh enever you stepped foot in door of a retail establishment? I think people would not be at all happy. But when surfing the Internet from our living r ooms we feel safer and don't challenge such silly laws.

Then when something goes awry, we are stuck.

Sheeple.

--

  Rick C. 

  --- Get 1,000 miles of free Supercharging 
  --- Tesla referral code - https://ts.la/richard11209

So, what does your board do ?

What is it ?

l) chips

cause they

nly one PLL.

resting.

compete

MCUs with

are as

e MCU has

bumps up

a lot of

the $20

o. Soft

be a

flash

their FPGAs

terface,

es. Looks like they also have M3 for FPGAs as well, they even mention usin g them for "free" which I assume means evaluation.

e

rice

cial need to want a processor when you have a perfectly good FPGA.

and vice versa

many tiny bits of RAM in contrast to a processor which has the power of the humongous multiplexer manipulating very large blocks of RAM and Flash. So the processor has to run very, very fast to create virtual connections bet ween the many portions of memory. The FPGA in contrast has wires connected by routing FETs that can be used to connect the tiny multiplexers and bits of RAM as selected by the multiplexers.

its humongous multiplexer selecting which task to emulate now, the FPGA is actually processing each task in parallel using much simpler resources for each task, fast or slow, it doesn't care.

sure, but do you want to write something like a UI or a language interprete r in rtl?

and if you need memory it is going to be much cheaper in an MCU

ten talk as if it is silly to design something in an FPGA that doesn't requ ire high speed or some other feature that makes it impossible to do in an M CU. I look at problems from the other perspective, I only put in an MCU th e parts that are awkward to do in an FPGA.

) there was nothing that could not be done in the FPGA, so no MCU needed. Of course it is a daughter board in a bigger system with lots of processors running operating systems virtualizing other operating systems... and then they have bigger FPGAs than mine to do the real work.

I don't know what your board does, maybe an FPGA is the perfect fit

al) chips

ecause they

only one PLL.

eresting.

o compete

e MCUs with

r are as

he MCU has

h bumps up

a lot of

the $20

oo. Soft

l be a

flash

their FPGAs

nterface,

ses. Looks like they also have M3 for FPGAs as well, they even mention usi ng them for "free" which I assume means evaluation.

ilinx parts, but I could not find out how to get it. I'm sure there are ma ny qualifications. Ts & Cs.

Xilinx rather than ARM.

why would it be any different than if you bought a Zynq that has a hardcore ARM cpu? the license is included with the chip

price

ecial need to want a processor when you have a perfectly good FPGA.

many tiny bits of RAM in contrast to a processor which has the power of th e humongous multiplexer manipulating very large blocks of RAM and Flash. S o the processor has to run very, very fast to create virtual connections be tween the many portions of memory. The FPGA in contrast has wires connecte d by routing FETs that can be used to connect the tiny multiplexers and bit s of RAM as selected by the multiplexers.

h its humongous multiplexer selecting which task to emulate now, the FPGA i s actually processing each task in parallel using much simpler resources fo r each task, fast or slow, it doesn't care.

ften talk as if it is silly to design something in an FPGA that doesn't req uire high speed or some other feature that makes it impossible to do in an MCU. I look at problems from the other perspective, I only put in an MCU t he parts that are awkward to do in an FPGA.

s) there was nothing that could not be done in the FPGA, so no MCU needed. Of course it is a daughter board in a bigger system with lots of processor s running operating systems virtualizing other operating systems... and the n they have bigger FPGAs than mine to do the real work.

It is an interface for audio and digital signals to networking equipment. There are two interfaces that can't be done in a CPU because they are custo m. One is a control interface that is similar to SPI, but optimized for sp eed, so unique (two data lines for example). The other is a high speed dat a interface (high being a relative term) which has several options for cloc king.

The internal logic uses a 16 bit stereo CODEC and combines the resulting da ta with a digital stream into packets that can be received at the other end and turned back into the data and time synchronized audio. The original i ncantation of this board was targeted to carrying IRIG B-120 time codes as digital bits rather than audio. When the synchronized data mode was added the time code was just carried as audio since higher data rates were going to happen from the data.

I believe nearly none of the units sold are used in this manner (US militar y testing missiles). They are mostly sold to bring audio into the network such as phone calls, intercoms, etc.

When my customer discusses the marketing of these units, it seems it is a s egment of networking that is being ignored by most vendors. My boards pigg y back on serial comms boards. They call this circuit to packet, CTP. Man y vendors no longer have product to solve these problems. My customer uses this product to gain leverage in winning contracts that require this capab ility even if these units are only a small share of the dollar amount.

Works for me!

--

  Rick C. 

  --+ Get 1,000 miles of free Supercharging 
  --+ Tesla referral code - https://ts.la/richard11209

n

C:

tal) chips

because they

only one PLL.

teresting.

to compete

he MCUs with

or are as

the MCU has

ch bumps up

e a lot of

.

n the $20

too. Soft

ll be a

r flash

n their FPGAs

interface,

uses. Looks like they also have M3 for FPGAs as well, they even mention us ing them for "free" which I assume means evaluation.

the

price

pecial need to want a processor when you have a perfectly good FPGA.

, many tiny bits of RAM in contrast to a processor which has the power of t he humongous multiplexer manipulating very large blocks of RAM and Flash. So the processor has to run very, very fast to create virtual connections b etween the many portions of memory. The FPGA in contrast has wires connect ed by routing FETs that can be used to connect the tiny multiplexers and bi ts of RAM as selected by the multiplexers.

th its humongous multiplexer selecting which task to emulate now, the FPGA is actually processing each task in parallel using much simpler resources f or each task, fast or slow, it doesn't care.

ter

In this vent device the alarms are based on UI settings. To be able to say this is all hardware the UI will be controlled by the FPGA. So yes, an HD L UI is no big deal.

What are you thinking of that would be a big deal in HDL?

All memory in a device is free once the device is selected. Why would it b e more expensive in an FPGA???

often talk as if it is silly to design something in an FPGA that doesn't re quire high speed or some other feature that makes it impossible to do in an MCU. I look at problems from the other perspective, I only put in an MCU the parts that are awkward to do in an FPGA.

ss) there was nothing that could not be done in the FPGA, so no MCU needed. Of course it is a daughter board in a bigger system with lots of processo rs running operating systems virtualizing other operating systems... and th en they have bigger FPGAs than mine to do the real work.

It was absolutely. But you fail to understand my point. Many, many design s can be done in FPGAs with no more trouble than in processors. But people who use processors are used to thinking in the messy, complex techniques o f making a sequentially executing machine appear to execute many processes at the same time.

This is a bias based on familiarity. I would have though the same way 20 y ears ago. Now that I have done some more complex designs in FPGAs I realiz e it really isn't harder necessarily and can be easier since FPGA tools are optimized for simulation. Working in simulation allows so much to be veri fied without turning on power to a board. I think people underestimate tha t as well.

I realize now I'm not going to win any converts by talking about it. Peopl e will keep using the tools they were taught. Now that they know the compl ex rules of making processors appear to process in parallel, there is littl e incentive to change their thinking. So they will continue to fight the s ame fights over and over.

Ok

--

  Rick C. 

  -+- Get 1,000 miles of free Supercharging 
  -+- Tesla referral code - https://ts.la/richard11209

ital) chips

because they

.

s only one PLL.

nteresting.

to compete

the MCUs with

or are as

the MCU has

ich bumps up

ee a lot of

e.

in the $20

too. Soft

ill be a

or flash

in their FPGAs

interface,

uses. Looks like they also have M3 for FPGAs as well, they even mention u sing them for "free" which I assume means evaluation.

Xilinx parts, but I could not find out how to get it. I'm sure there are many qualifications. Ts & Cs.

M u s

m Xilinx rather than ARM.

re

No, there is no license to sign to use a Zynq. Are you telling me you have to sign paperwork or click on the web page link that acknowledges you agre e to the contract to use a Zynq?

I had a GPS that required acknowledgement of the contract to make it work. Otherwise I've never seen that, web pages excepted. Digikey makes me agre e to something with each new tab I open. Silly.

Rick C.

-++ Get 1,000 miles of free Supercharging -++ Tesla referral code -

I have thought of using an FPGA for what I do (power electronics, inverters, chargers, etc with communications) but I thought the cost of an FPGA that had enough gates would be way too expensive. I use a fairly fast ARM processor (180MHz) and only these Greenpaks (a small and inexpensive FPGA) which was necessary for the fast stuff. The processor and Greenpaks cost less than $5.

Of course there are all the other additions that cannot be done with either an FPGA or a processor or combination of both. All the power stuff, drivers, aux power etc.

BUT, some of the other companies that make microinverters etc do use FPGAs rather than microprocessors.

I can see that getting in that "mode" of thought would definitely be a different mind-set at least to start with. I would like to understand that method better but for now, the processor is working well.

I'm not sure why anyone would need to put an ARM processor on an FPGA instead of just using an ARM processor and a less expensive and complicated FPGA in addition to the ARM processor, if it would work.

I can see if being useful maybe if that FPGA would allow the ARM core to run at an equivelant clock of sever gigaHz maybe.

You might set me straight on how much better an ARM micro running sequenced code on an FPGA would be if that were the only thing being done in that FPGA. Not talking about parallel operations but maybe there is something to that in addition ?

nsen

ty C:

igital) chips

ly because they

ly.

has only one PLL.

interesting.

Ts to compete

y the MCUs with

nd or are as

z, the MCU has

which bumps up

see a lot of

ice.

) in the $20

on too. Soft

still be a

M or flash

e in their FPGAs

PI interface,

ch uses. Looks like they also have M3 for FPGAs as well, they even mention using them for "free" which I assume means evaluation.

ow

not

of the

you

the price

a special need to want a processor when you have a perfectly good FPGA.

any, many tiny bits of RAM in contrast to a processor which has the power o f the humongous multiplexer manipulating very large blocks of RAM and Flash . So the processor has to run very, very fast to create virtual connection s between the many portions of memory. The FPGA in contrast has wires conn ected by routing FETs that can be used to connect the tiny multiplexers and bits of RAM as selected by the multiplexers.

with its humongous multiplexer selecting which task to emulate now, the FP GA is actually processing each task in parallel using much simpler resource s for each task, fast or slow, it doesn't care.

preter

say this is all hardware the UI will be controlled by the FPGA. So yes, an HDL UI is no big deal.

t be more expensive in an FPGA???

le often talk as if it is silly to design something in an FPGA that doesn't require high speed or some other feature that makes it impossible to do in an MCU. I look at problems from the other perspective, I only put in an M CU the parts that are awkward to do in an FPGA.

ocess) there was nothing that could not be done in the FPGA, so no MCU need ed. Of course it is a daughter board in a bigger system with lots of proce ssors running operating systems virtualizing other operating systems... and then they have bigger FPGAs than mine to do the real work.

igns can be done in FPGAs with no more trouble than in processors. But peo ple who use processors are used to thinking in the messy, complex technique s of making a sequentially executing machine appear to execute many process es at the same time.

0 years ago. Now that I have done some more complex designs in FPGAs I rea lize it really isn't harder necessarily and can be easier since FPGA tools are optimized for simulation. Working in simulation allows so much to be v erified without turning on power to a board. I think people underestimate that as well.

ople will keep using the tools they were taught. Now that they know the co mplex rules of making processors appear to process in parallel, there is li ttle incentive to change their thinking. So they will continue to fight th e same fights over and over.

I would be using a $2 FPGA on my current project, but the part I want to us e doesn't have LVDS receivers. I can add comparators or use a different pa rt from a different maker with lots of I/O and LVDS inputs. The other part is from Gowin a new company, so I'm trying to do all my homework on them a nd the using the parts.

If you have any real volume, you can get an FPGA company to quote you prici ng which will be much better than distribution offers. Not sure why that i s, but that's the way it is with FPGAs.

Many FPGAs have multipliers/DSP modules capable of running at 100's of MHz. For most apps a multiplier can be shared via multiplexing or depending on your app it can work from on chip memory. A coworker did that once in a d esign with fast and slow portions. The slow portion had lots of complex lo gic and arithmetic, so the "ALU" was shared to do several calcs. The fast parts were more logic oriented. This was test gear dealing with ATM packet s.

Control loops should be a breeze with math running nearly as fast as analog signals. lol

It helps if you understand logic rather than just banging code I think. Bu t my opinion may be prejudiced by my own experiences.

I think part of my success in FPGAs is that I follow the rules of small mod ules that are tested before integrating. In VHDL it creates a lot of typin g, but in the end development is faster because mistakes are caught earlier where you can find them more easily. But it takes some thought to know wh ere the demons are more likely.

--

  Rick C. 

  +-- Get 1,000 miles of free Supercharging 
  +-- Tesla referral code - https://ts.la/richard11209

digital) chips

bly because they

ily.

has only one PLL.

e interesting.

UTs to compete

hy the MCUs with

end or are as

Hz, the MCU has

which bumps up

I see a lot of

vice.

M) in the $20

oon too. Soft

still be a

AM or flash

se in their FPGAs

SPI interface,

uch uses. Looks like they also have M3 for FPGAs as well, they even mentio n using them for "free" which I assume means evaluation.

to Xilinx parts, but I could not find out how to get it. I'm sure there a re many qualifications. Ts & Cs.

ARM

you

g as

from Xilinx rather than ARM.

dcore

ave to sign paperwork or click on the web page link that acknowledges you a gree to the contract to use a Zynq?

k. Otherwise I've never seen that, web pages excepted. Digikey makes me a gree to something with each new tab I open. Silly.

If it's a soft core, the ARM would likely run slower in an FPGA unless the bottle neck in the ARM chip were something like Flash. In general an FPGA will run more slowly than any manner of dedicated chip. The routing adds d elay to every path. FPGAs can be fast simply because they can be tailored to the task rather than executing general code to do what you want. Think of a processor with one instruction, your task. Maybe that's not a good an alogy. But FPGAs aren't faster than processors, just more targeted so less wasted time doing things that aren't accomplishing the task, like fetching instructions.

For me it's not about speed. I just prefer the simplicity of coding the ha rdware to do what you need directly rather than thinking of what the proces sor is capable of or how the language is going to generate code to do the t ask. With HDL, if you describe the hardware properly, it will give you exa ctly what you ask for. That's way it's a Hardware Description Language.

--

  Rick C. 

  +-+ Get 1,000 miles of free Supercharging 
  +-+ Tesla referral code - https://ts.la/richard11209

sen

y C:

gital) chips

y because they

y.

as only one PLL.

interesting.

s to compete

the MCUs with

d or are as

, the MCU has

hich bumps up

see a lot of

ce.

in the $20

n too. Soft

till be a

or flash

in their FPGAs

I interface,

h uses. Looks like they also have M3 for FPGAs as well, they even mention using them for "free" which I assume means evaluation.

w

ot

f the

ou

he price

special need to want a processor when you have a perfectly good FPGA.

ny, many tiny bits of RAM in contrast to a processor which has the power of the humongous multiplexer manipulating very large blocks of RAM and Flash. So the processor has to run very, very fast to create virtual connections between the many portions of memory. The FPGA in contrast has wires conne cted by routing FETs that can be used to connect the tiny multiplexers and bits of RAM as selected by the multiplexers.

with its humongous multiplexer selecting which task to emulate now, the FPG A is actually processing each task in parallel using much simpler resources for each task, fast or slow, it doesn't care.

reter

ay this is all hardware the UI will be controlled by the FPGA. So yes, an HDL UI is no big deal.

I'm not taking a few leds, think graphical UI, icons, graphs, text formatti ng

be more expensive in an FPGA???

because an FPGA with the same amount of available memory is going to be much more expensive

e often talk as if it is silly to design something in an FPGA that doesn't require high speed or some other feature that makes it impossible to do in an MCU. I look at problems from the other perspective, I only put in an MC U the parts that are awkward to do in an FPGA.

sure if you have only an FPGA you try to put it in the FPGA, if you have an MCU you try yo put it in the MCU, if you have both you put it where it mak es the most sense, keeping in mind that a lot more people can write code th an HDL and the turn around for code it a lot shorter than HDL

cess) there was nothing that could not be done in the FPGA, so no MCU neede d. Of course it is a daughter board in a bigger system with lots of proces sors running operating systems virtualizing other operating systems... and then they have bigger FPGAs than mine to do the real work.

gns can be done in FPGAs with no more trouble than in processors. But peop le who use processors are used to thinking in the messy, complex techniques of making a sequentially executing machine appear to execute many processe s at the same time.

years ago. Now that I have done some more complex designs in FPGAs I real ize it really isn't harder necessarily and can be easier since FPGA tools a re optimized for simulation. Working in simulation allows so much to be ve rified without turning on power to a board. I think people underestimate t hat as well.

ple will keep using the tools they were taught. Now that they know the com plex rules of making processors appear to process in parallel, there is lit tle incentive to change their thinking. So they will continue to fight the same fights over and over.

you don't have to convert me, I have used FPGAs for 20+ years, but just bec ause you have a hammer not everything is a nail, sometimes a screw is bette r