Bookmark and Share

Tags

32nm 40nm 45nm AMD Apple ASUS ATI ATIC Atom Business Cypress E-Book Evergreen Fermi Flash Geforce Globalfoundries GT300 Intel Microsoft Mubadala Nokia Nvidia Radeon Semiconductor Sony SSD TSMC USB Windows

News

Performance of highly-anticipated code-named Prescott processor, the third-generation NetBurst microprocessor from Intel, may appear to be generally slower than speed of currently available Pentium 4 “Northwood” chips. The reason for that is deep pipeline implemented to bolster clock-speeds of the CPU.

According to a report from ZDNet, industry sources anticipate Prescott’s pipeline to feature about 30 stages, 10 more compared to Northwood core.

Deeper pipeline allows dividing each command into smaller parts, which appear easier and faster to execute than the entire command. Such approach allows to pump up the clock-speeds, but will lead to increased overall time required for execution of each command and also cause some delays as a consequence of branch mis-prediction and necessity to reload the pipeline..

Historically CPU makers have been enlarging pipelines, though, because of massive efforts to improve performance, both architectural and clock-speed related, the impact of deeper branch was not too dramatic. The only time a company was criticized for too deep pipeline was in 2000, when Intel released its original Pentium 4 “Willamette” processor that fell behind competing AMD Athlon CPUs in terms of performance. Though, being able to rapidly ramp the clock-speeds, Intel’s Pentium 4 CPUs got performance crown in mid-2002 with its Pentium 4 processors at 2.53GHz. Unfortunately, high core frequencies lead to massive power consumption what may potentially limit maximum clock-speeds of CPUs.

In order to avoid vivid performance drops because of deeper pipeline Intel has been constantly improving its NetBurst Pentium 4 processors. To accomplish this with Prescott, the Santa Clara, California-based chipmaker incorporated a number of important improvements into the chip. One is more efficient branch-prediction mechanism minimizing a number of situations when microprocessor has to reload its pipeline. Another one are enlarged caches that allow CPUs to handle more data “onboard” spending less time pumping data via processor system bus. Nevertheless, it is still to be found out how Prescott and Northwood chips behave on the same frequency.

Additional information on performance and architecture of Intel Pentium 4 “Prescott” will be available at launch, on the 2nd of February 2004.

Discussion

Comments currently: 0

You must log in to add comments.

Forgot password? Registration

remember me



Related news

Latest News

Sunday, November 22, 2009

11:34 am | Voice Communications Set to Decline in Two Years – Analysts. Analysts Predict Dramatic Increase of VoIP Popularity

Saturday, November 21, 2009

11:44 pm | Barnes and Noble: Nook E-Book Readers Are Sold Out. E-Book Reader from B&N Sold Out Before Release

7:53 am | Cell Network Operators Set to Become Largest Mobile Internet Devices Sellers – Analysts. Mobile Network Operators to Gain Strength in Devices

Friday, November 20, 2009

10:11 pm | ATI Seeks Its Best to Ensure More Radeon HD 5-Series Supplies – Company. Additional Number of DirectX 11 Graphics Boards is Incoming

11:56 am | Fusion-io’s SSD Setup Reaches 1TB/s Aggregate Bandwidth. Fusion-io Gets Contracts from Government, Creates World’s Fastest SSD Setup

10:06 am | Notebook – the Most Desired Christmas Gift, Says CEA. Notebooks, Players and HDTVs Top Christmas Presents Wish List

9:11 am | Ebay Completes Skype Sell Off. Skype No Longer Belongs to Ebay