Tuesday, April 26, 2016

batch processing

Unisys phasing out decades-old mainframe processor for x86 chips

unisys server
Credit: Unisys
Unisys is phasing out its decades-old mainframe processor, which lags behind in speed and scalability compared to newer chips.
The chip is used in some of Unisys’ ClearPath flagship mainframes, but the company is moving to Intel’s x86 chips in Libra and Dorado servers in the ClearPath line, it said Tuesday. Unisys also announced 12 high-end servers with Intel’s Xeon server chip E5-2600 v2 chip, leaving its proprietary mainframe processor out of the mix. The servers are aimed at Unisys customers in running legacy applications in financial services, telecommunications and transportation markets.
The aging CMOS chip will be “sunsetted” in Libra servers by the end of August and in the Dorado line by the end of 2015, said Unisys spokesman Brian Daly. Dorado 880E and 890E mainframes will use the CMOS chip until the servers are phased out, which is set to happen by the end of 2015.
“It has not gone away yet because we haven’t surpassed the performance characteristics,” said Brian Herkalo, director of ClearPath portfolio management at Unisys, regarding the CMOS chip.

X86 wins

x86 processors are faster and more power efficient, which makes them a more attractive option, Herkalo said. They are also compatible with the latest components and interconnects, and common hardware infrastructure makes it easier for new Libra and Dorado servers to talk to systems based on Windows and Linux in data centers, Herkalo said.
The switch to x86 processors won’t affect existing Unisys customers looking to upgrade older mainframes with faster systems. x86 Dorado servers will continue to support the ClearPath OS 2200 operating system, while the Libra line will support the ClearPath MCP operating system. Both the OSes will execute tasks on Intel’s Xeon server chips through a firmware layer that translates the OS code for execution on x86 chips.
As Intel comes out with new processor technologies, ClearPath servers will get faster, Herkalo said. x86 architecture also allows Unisys to use many of the latest technologies to boost security and increase throughput among a network of servers in data centers.
The fastest Libra 8300 server scales to 9,000 million instructions per second, compared to 5,800 million instructions per second with its highest-performing server with the proprietary mainframe processor.

The death of proprietary processors

“We’re seeing the same gains on the Dorado side,” Herkalo said.
Unisys’ move to commodity hardware to replace its mainframe processor follows the footsteps of Hewlett-Packard, which is providing a pathway to move from the mainframe-focused Itanium to x86 server chips, both owned by Intel. Historically, less expensive chips have replaced more expensive mainframe chips—x86 faces a threat from the cheaper ARM server processors, which are still being developed and tested.
The servers introduced Tuesday, which don’t run Linux or Windows, are designed to operate as black boxes sitting at a higher layer in data centers through which transactions are processed. The servers can create partitions with dedicated processor cores and memory units to run specific applications, for example, mobile, e-commerce or databases. Transactions generated through database applications on Linux and Windows servers in data centers will pass through a firewall on Libra and Dorado servers before being transmitted to external computers.
The Dorado and Libra servers are equipped with the Infiniband interconnect for a throughput of 56Gbps. Unisys technology called S-Par sets up the partitions on the servers with its own cores and I/O ports.
Libra 8300 servers start at US$5.6 million. The Libra 6300 series starts at $1.2 million and the 4300 series starts at $900,000.
The new Dorado line includes the 6300 servers, which start at $2 million, the 4380 and 4390, which start at $665,000; and the 4350 and 4370, which start at $325,000.
The servers will ship late this month, Unisys said.


Unisys phasing out decades-old mainframe processor for x86 chips

unisys server
Credit: Unisys
Unisys is phasing out its decades-old mainframe processor, which lags behind in speed and scalability compared to newer chips.
The chip is used in some of Unisys’ ClearPath flagship mainframes, but the company is moving to Intel’s x86 chips in Libra and Dorado servers in the ClearPath line, it said Tuesday. Unisys also announced 12 high-end servers with Intel’s Xeon server chip E5-2600 v2 chip, leaving its proprietary mainframe processor out of the mix. The servers are aimed at Unisys customers in running legacy applications in financial services, telecommunications and transportation markets.
The aging CMOS chip will be “sunsetted” in Libra servers by the end of August and in the Dorado line by the end of 2015, said Unisys spokesman Brian Daly. Dorado 880E and 890E mainframes will use the CMOS chip until the servers are phased out, which is set to happen by the end of 2015.
“It has not gone away yet because we haven’t surpassed the performance characteristics,” said Brian Herkalo, director of ClearPath portfolio management at Unisys, regarding the CMOS chip.

X86 wins

x86 processors are faster and more power efficient, which makes them a more attractive option, Herkalo said. They are also compatible with the latest components and interconnects, and common hardware infrastructure makes it easier for new Libra and Dorado servers to talk to systems based on Windows and Linux in data centers, Herkalo said.
The switch to x86 processors won’t affect existing Unisys customers looking to upgrade older mainframes with faster systems. x86 Dorado servers will continue to support the ClearPath OS 2200 operating system, while the Libra line will support the ClearPath MCP operating system. Both the OSes will execute tasks on Intel’s Xeon server chips through a firmware layer that translates the OS code for execution on x86 chips.
As Intel comes out with new processor technologies, ClearPath servers will get faster, Herkalo said. x86 architecture also allows Unisys to use many of the latest technologies to boost security and increase throughput among a network of servers in data centers.
The fastest Libra 8300 server scales to 9,000 million instructions per second, compared to 5,800 million instructions per second with its highest-performing server with the proprietary mainframe processor.

The death of proprietary processors

“We’re seeing the same gains on the Dorado side,” Herkalo said.
Unisys’ move to commodity hardware to replace its mainframe processor follows the footsteps of Hewlett-Packard, which is providing a pathway to move from the mainframe-focused Itanium to x86 server chips, both owned by Intel. Historically, less expensive chips have replaced more expensive mainframe chips—x86 faces a threat from the cheaper ARM server processors, which are still being developed and tested.
The servers introduced Tuesday, which don’t run Linux or Windows, are designed to operate as black boxes sitting at a higher layer in data centers through which transactions are processed. The servers can create partitions with dedicated processor cores and memory units to run specific applications, for example, mobile, e-commerce or databases. Transactions generated through database applications on Linux and Windows servers in data centers will pass through a firewall on Libra and Dorado servers before being transmitted to external computers.
The Dorado and Libra servers are equipped with the Infiniband interconnect for a throughput of 56Gbps. Unisys technology called S-Par sets up the partitions on the servers with its own cores and I/O ports.
Libra 8300 servers start at US$5.6 million. The Libra 6300 series starts at $1.2 million and the 4300 series starts at $900,000.
The new Dorado line includes the 6300 servers, which start at $2 million, the 4380 and 4390, which start at $665,000; and the 4350 and 4370, which start at $325,000.
The servers will ship late this month, Unisys said.

batch processing



Executing a series of non-interactive jobs all at one time. The term originated in the days when users entered programs on punch cards. They would give a batch of these programmed cards to the system operator, who would feed them into the computer.
Batch jobs can be stored up during working hours and then executed during the evening or whenever the computer is idle. Batch processing is particularly useful for operations that require the computer or a peripheral device for an extended period of time. Once a batch job begins, it continues until it is done or until an error occurs. Note that batch processing implies that there is no interaction with the user while the program is being executed.
An example of batch processing is the way that credit card companies process billing. The customer does not receive a bill for each separate credit card purchase but one monthly bill for all of that month��s purchases. The bill is created through batch processing, where all of the data are collected and held until the bill is processed as a batch at the end of the billing cycle.
The Challenges of Cloud Integration

The opposite of batch processing is transaction processing or interactive processing. In interactive processing, the application responds to commands as soon as you enter them.
 

No comments:

Post a Comment