I’m slightly confused here but I don’t think we’ll get an answer until the final spec is released at the end of the year. It sounds like SATA-E will compliment the current SATA-III ports, it isn’t designed to replace it. So, we might get desktops with 2xSATA-E and 8xSATA-iII ports instead of 8xSATA-E.
I doubt we’d see any widespread support until 2015. Laptops are being sold more than desktops and they traditionally lag behind new interface support.
I think Apple is likely to support the uSATA standard for MBA/iPad first on the market. It’d be interesting to see how it all work out in the end.
Come on now. We all know the real reason is that it will let them either reduce the laptops volume by at least 10-20mm^3 or alternately increase the battery volume by the same amount.
Right, the LUCRATIVE MBA SSD market. Plenty of companies are getting rich off that right now. You do understand how MBA SSDs work? Perhaps you'd like to tell us next about all those people getting rich selling SSDs to put into iPads.
Correct, I think you'll only get full bandwidth to one or two ports at most on a desktop board. The spec will likely be backwards compatible though, so you'll be able to use a 6Gbps SATA drive on all ports.
8 / 16Gbps is basically PCI-E 3.0 1x and 2x. PCI-E is actually Full Duplex, unlike the Half Duplex SATA Connection, which would become a problem in high speed data transmission. PCI-E is a powered connection. No more additional power plug for SSD devices. I believe they should have used PCI-E 4x as well, giving 4GB/s connection. Although they could just let PCI-E 4.0 2x in the future to handle it. But Given we are finally moving to PCI-Express. And SATA protocol has no relevance with the inner of SSD working. Why are we still sticking with SATA then? Apart from Software compatibility reason. I am also not aware of any Power Management features in PCI-E that go down to the level of SSD which are mW. Or has PCI-E 3.0 changed that?
Now i just hope they could fast track the release. So Ivy Bridge MB maker will be well prepared.
Full duplex would still be useful when you're using port multipliers or SATA/SAS expanders, where you are communicating with more than one independent drive over a single cable, and some might be reading or writing at the same time. I don't know enough about port multipliers to say if they exploit the capability though.
Also with full duplex you can in theory issue new commands to the drive while a read is underway. Again, don't know enough about the SATA protocol to say if this is done.
You're not accounting for the fact most drives have cache, which will be read from even at times when the physical drive is seeking (HDD) or an address is having an IO performed on in the flash (SSD).
I don't know where you are making up your information, but SATA isn't and has never been full-duplex. If you want a full-duplex drive you will need to go with SAS.
SATA is and always has been half-duplex. SCSI and SAS on the other hand is full-duplex. I can't stand people who assume things and then try to pass that false information along as fact. Do your homework! Using your flawed logic, i can connect a full-duplex Ethernet cable to a half-duplex router, and that will make it full-duplex.
Forgive me if readers have already seen this point discussed elsewhere:
Occam's Razor: the simplest solution is always the best solution.
Now that the PCIe 3.0 specification calls for 8 GHz clock speeds and 128b/130b "jumbo frames" at the chipset level, is it not logical to extend this "topology" outwards over flexible SATA cables? and SAS cables too?
A "SATA-IV" standard should support the same features: 8 GHz clock speeds and 128b/130b "jumbo frames" yielding "8G/8b" or 1.0 GB/second raw bandwidth over a single SATA cable.
One key advantage of these 2 features is that they allow each x1 PCIe 3.0 lane to "sync" with a single SATA cable, greatly simplifying capacity planning AND greatly reducing the operational overhead in controller firmware.
With the obsolete 8b/10b "legacy frame", SATA firmware is constantly adding and removing 1 start bit and 1 stop bit from each data byte transmitted!
That's an extra 20% overhead which the PCIe 3.0 spec wisely eliminated.
Also, if you look carefully at one of the 2 "SATA Express" connectors, there are "keys" which prevent a SATA cable from connecting: (cf. "keys that reject the SATA cables"); so, that mechanical connector is called "SATA Express" but it doesn't work with a standard SATA cable or connector.
In the long run, I also think that we should be designing motherboards and add-on controllers that support the concept of "overclocking" data storage subsystems, just as we now routinely overclock CPU and DRAM clocks.
This can be implemented with a variety of methods that are widely in use now, e.g. hardware jumpers, Option ROM settings and even auto-detection, and hopefully new methods that will be developed and proven in the visible future.
The lack of such features is frankly retarding "bleeding edge" experimentation and progress feasible with new storage technologies, imho.
Lastly, I am picking up a distinct bias which maintains that the highest performing storage technologies must also carry THE highest prices.
You can observe this trend in Nand flash SSDs: highest WRITE speeds require the LARGEST capacities (partially due to the number of parallel controllers).
I believe it's time to challenge that bias openly, so that enthusiasts, gamers and DIY builders can enjoy very high-speed storage, perhaps at the expense of less capacity.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
15 Comments
Back to Article
MikhailT - Thursday, August 11, 2011 - link
I’m slightly confused here but I don’t think we’ll get an answer until the final spec is released at the end of the year. It sounds like SATA-E will compliment the current SATA-III ports, it isn’t designed to replace it. So, we might get desktops with 2xSATA-E and 8xSATA-iII ports instead of 8xSATA-E.I doubt we’d see any widespread support until 2015. Laptops are being sold more than desktops and they traditionally lag behind new interface support.
I think Apple is likely to support the uSATA standard for MBA/iPad first on the market. It’d be interesting to see how it all work out in the end.
icrf - Thursday, August 11, 2011 - link
I could see Apple putting it in the MBA, but just as much because it means they can solder in the SSD and kill the after market.DanNeely - Thursday, August 11, 2011 - link
Come on now. We all know the real reason is that it will let them either reduce the laptops volume by at least 10-20mm^3 or alternately increase the battery volume by the same amount.*rolls eyes*
name99 - Thursday, August 11, 2011 - link
Right, the LUCRATIVE MBA SSD market. Plenty of companies are getting rich off that right now. You do understand how MBA SSDs work?Perhaps you'd like to tell us next about all those people getting rich selling SSDs to put into iPads.
Anand Lal Shimpi - Thursday, August 11, 2011 - link
Correct, I think you'll only get full bandwidth to one or two ports at most on a desktop board. The spec will likely be backwards compatible though, so you'll be able to use a 6Gbps SATA drive on all ports.Take care,
Anand
Jambe - Thursday, August 11, 2011 - link
Is the actual silicon involved in a native PCIe controller more expensive than sata controllers, or is it just the R&D costs involved atp?I would love to have a PCIe SSD in conjunction with bulk disk storage on SATA.
iwod - Thursday, August 11, 2011 - link
I have been calling for this for a long time.8 / 16Gbps is basically PCI-E 3.0 1x and 2x.
PCI-E is actually Full Duplex, unlike the Half Duplex SATA Connection, which would become a problem in high speed data transmission.
PCI-E is a powered connection. No more additional power plug for SSD devices.
I believe they should have used PCI-E 4x as well, giving 4GB/s connection. Although they could just let PCI-E 4.0 2x in the future to handle it.
But Given we are finally moving to PCI-Express. And SATA protocol has no relevance with the inner of SSD working. Why are we still sticking with SATA then? Apart from Software compatibility reason.
I am also not aware of any Power Management features in PCI-E that go down to the level of SSD which are mW. Or has PCI-E 3.0 changed that?
Now i just hope they could fast track the release. So Ivy Bridge MB maker will be well prepared.
FaaR - Thursday, August 11, 2011 - link
SATA is, and always has been full duplex. It has separate send and receive wires in the cable.zorxd - Thursday, August 11, 2011 - link
Anyway the drive itself is half duplex. You can't write to a location while you are reading an other one.Metaluna - Thursday, August 11, 2011 - link
Full duplex would still be useful when you're using port multipliers or SATA/SAS expanders, where you are communicating with more than one independent drive over a single cable, and some might be reading or writing at the same time. I don't know enough about port multipliers to say if they exploit the capability though.Also with full duplex you can in theory issue new commands to the drive while a read is underway. Again, don't know enough about the SATA protocol to say if this is done.
deed02392 - Sunday, April 22, 2012 - link
You're not accounting for the fact most drives have cache, which will be read from even at times when the physical drive is seeking (HDD) or an address is having an IO performed on in the flash (SSD).peterfares - Monday, September 24, 2012 - link
Why not? SSDs can do that just fine or should be able to.Practice - Friday, August 9, 2013 - link
I don't know where you are making up your information, but SATA isn't and has never been full-duplex. If you want a full-duplex drive you will need to go with SAS.Stormprobe - Saturday, July 5, 2014 - link
SATA is and always has been half-duplex. SCSI and SAS on the other hand is full-duplex. I can't stand people who assume things and then try to pass that false information along as fact. Do your homework!Using your flawed logic, i can connect a full-duplex Ethernet cable to a half-duplex router, and that will make it full-duplex.
supremelaw - Thursday, April 12, 2012 - link
Forgive me if readers have already seen this point discussed elsewhere:Occam's Razor: the simplest solution is always the best solution.
Now that the PCIe 3.0 specification calls for 8 GHz clock speeds
and 128b/130b "jumbo frames" at the chipset level,
is it not logical to extend this "topology" outwards over
flexible SATA cables? and SAS cables too?
A "SATA-IV" standard should support the same features:
8 GHz clock speeds and 128b/130b "jumbo frames"
yielding "8G/8b" or 1.0 GB/second raw bandwidth
over a single SATA cable.
One key advantage of these 2 features is that
they allow each x1 PCIe 3.0 lane to "sync"
with a single SATA cable, greatly simplifying
capacity planning AND greatly reducing the
operational overhead in controller firmware.
With the obsolete 8b/10b "legacy frame",
SATA firmware is constantly adding and removing
1 start bit and 1 stop bit from each data byte transmitted!
That's an extra 20% overhead which the PCIe 3.0 spec wisely eliminated.
Also, if you look carefully at one of the 2 "SATA Express" connectors,
there are "keys" which prevent a SATA cable from connecting:
(cf. "keys that reject the SATA cables");
so, that mechanical connector is called "SATA Express" but
it doesn't work with a standard SATA cable or connector.
In the long run, I also think that we should be designing
motherboards and add-on controllers that support the
concept of "overclocking" data storage subsystems,
just as we now routinely overclock CPU and DRAM
clocks.
This can be implemented with a variety of methods
that are widely in use now, e.g. hardware jumpers,
Option ROM settings and even auto-detection,
and hopefully new methods that will be developed
and proven in the visible future.
The lack of such features is frankly retarding
"bleeding edge" experimentation and progress
feasible with new storage technologies, imho.
Lastly, I am picking up a distinct bias which
maintains that the highest performing storage
technologies must also carry THE highest prices.
You can observe this trend in Nand flash SSDs:
highest WRITE speeds require the LARGEST capacities
(partially due to the number of parallel controllers).
I believe it's time to challenge that bias openly,
so that enthusiasts, gamers and DIY builders
can enjoy very high-speed storage, perhaps at the
expense of less capacity.
MRFS