Golf Clubs

Cuisinart CSB-76 SmartStick 200-Watt Immersion Hand Blender The versatile stick design of the Cuisinart Smart stick Hand Blender lets users blend ingredients right in pots, pitchers, bowls, or clear plastic beaker that’s included. A powerful 200-watt motor operates with an easy one-touch control. Blends drinks, purees soup, mixes pancake and crepe batters in seconds! Both stainless steel blending shaft and beaker are dishwasher-safe….

Hamilton Beach Big Mouth Juice Extractor 67650 $65.00 Juice extractor-Drink your fruits and vegetables-Fits whole foods for fast, easy juicing-Powerful 1.1 HP motor-Dishwasher safe parts-Stainless steel strainer-Easy to assemble and store-Cleaning brush included for easy pulp removal-Juice cup included…

Oster 6706 6-Cup Plastic Jar 10-Speed Blender, Black $20.88 BLE 10 SPEED PLASTIC JAR BLENDER…

Speed Stick Deodorant, Active Fresh, 3 oz. $3.95 Powerful clear deodorant; leaves no white residue. Provides odor protection that lasts all day. Clean masculine scent. Patented comfort guard applicator for comfort and control….

Tournament Poker: No Limit Texas Hold’em $1.00 Tournament Poker: No Limit Texas Hold’Em lets you practice your tournament skills and experience what the pros do. Whether you play at a friendly local poker night, a card room in Vegas or the World Series of Poker, this is the game you need!…

Need For Speed: Prostreet $8.99 …

La Crosse Technology Weather Direct WD-3308U-WAL 4 Day Internet Powered Wireless Forecaster $30.99 THE ENEMY WIND is one of The Weather Channel’s most popular documentaries. It deals with tornadoes, their behavior and how they are generated. As it explores our historical relationship with tornadoes, THE ENEMY WIND discusses recent research into improving our ability to forecast storms and shows the work of a group of nerveless adventurers, the tornado chasers. This video explains how researcher…

Hayward SP1580X15 Power-Flo LX Series 1-1/2-Horsepower Above-Ground Pool Pump with Cord $141.90 Hayward Economy Above Ground Pump Perfect for most above ground pools, this economical pump by Hayward combines durable, corrosion proof construction with advanced features and performance. Features Self Priming1 1/2 inch intake & discharge, high performance impeller, heat resistant, double sided seal for long motor life and a 6 foot, 120 volt power cord….

Nelson 1865 Raintrain Traveling Sprinkler $47.99 NELSON RAIN TRAIN TRAVEL SPRINKLER *Covers up to 13500 square feet *Travels up to 200 feet *Propels across the lawn following the pattern you lay out with the hose *Equipped with 3 speed settings *Designed to automatically shut off at any given point along your hose track *Ideal for medium to large lawns *Cast iron body with chip resistant powder-coat paint…

Lasko 2521 16 Oscillating Stand Fan $19.99 Lasko 16inch Oscillating Stand Fan Weight: 9.25 lbs. Size: 18inch L x 17inch W x 47inch H. 3 Quiet Speeds. Tilt-Back Feature. Fully-Adjustable Height. Easy-Grip Rotary Control. Simple No Tool Assembly. Ideal for All Rooms. ETL Listed. Wide-Area Oscillation…

Ultraviolet $2.99 …

Sony 3DBNDL/ALICE 3D Deluxe Starter Kit, Black $121.49 Enjoy an incredible, high-quality 3D entertainment experience when you combine this 3D deluxe starter kit with a compatible BRAVIA 3D HDTV. The starter kit includes two pairs of 3D active glasses, a 3D sync transmitter, Disney’s Alice in Wonderland 3D Blu-ray Disc, and an HDMI cable. 3D Active Glasses. 3D Sync Transmitter. Key Features 3D Active Glasses: Sony’s innovative design b…

Ride Like a Pro DVD Vol. 5 – Jerry Motorman Palladino $24.95 If you’ve ever seen Motor Officers handle their heavy-weight cruisers with the ease of a child’s toy and wondered in amazement how they do it, wonder no more. This DVD will show you how to use the 3 simple Motor Officer techniques the cops have been trained in for more than 60 years. Until now, these training secrets have not been available to the general public. I have developed a simple step by …

Sound Conditioner Sound Screen SleepMate Electro-Mechanical White Noise Machine This Sleep Mate Sound Conditioner product produces the sounds of nature and surround you with an environment of “conditioned” sound. Are loud neighbors, your spouse’s snoring or other irritating noises keeping you awake at night? This is no longer a problem when you have this noise sleep machine. These sleep machine devices employ the latest technology to create soothing, natural sounds that effec…

Berman Center Athena Waterproof Mini Massager …

Moroccan Oil Hair Treatment 3.4 Oz Bottle with Blue Box $35.99 MoroccanOil is an oil treatment for all hair types. Moroccan Oil is alcohol-free and has a patented weightless formula with no build up. Softens thick unmanageable hair and restores shine and softness to dull lifeless hair. Instantly absorbed into the hair. Moroccan Oil will help eliminate frizz, speeds up styling time by 40%, and provides long-term conditioning to all hair types. Moroccan Oil con…

Sandisk 16GB MicroSDHC Memory Card, Class 4 $2.90 SanDisk is proud to announce our newest format and capacity to the SD card family: microSD High Capacity (microSDHC) 16GB flash card. Not all devices support microSDHC 16.0GB cards. Please contact your device manufacturer for details. To ensure compatibility, look for the microSDHC logo on the product or packaging of your new phone or PDA. Please note that eXpansys vouchers cannot be used when pur…

SanDisk Extreme 32GB 45MB/s SDHC Flash Memory Card SDSDX-032G-X46,Black $34.95 Delivering class 10 video performances, the Extreme HD Video SDHC UHS-I memory card from SanDisk has read/write speeds up to 30 MB/sec and a large storage capacity for HD videos.General:Product Type : Flash memory cardStorage Capacity : 32 GBWidth : 24 mmDepth : 32 mmHeight : 2.1 mmWeight : 1.5 gCompatibility : Non-specificMemory:Speed Rating : 30 MB/s (read) 30 MB/s (write)SD Speed Class : Class …

SanDisk 16 GB microSDHC Flash Memory Card SDSDQ-016G (Bulk Packaging) – Class 2 $2.72 SanDisk is proud to announce our newest format and capacity to the SD card family: microSD High Capacity (microSDHC) 16GB flash card. Not all devices support microSDHC 16.0GB cards. Please contact your device manufacturer for details. To ensure compatibility, look for the microSDHC logo on the product or packaging of your new phone or PDA….

SPEED STACK BERRY 18oz 24/CS $41.00 SPEED STACK BERRY 18oz 24/CS…

Braun DigiFrame 1560 (Black, 15, USB, JPEG, MP3, Video, 1Go, 1024×768) $170.99 Type: Digital Photo Frames Braun DigiFrame 1560 Features Elegant digital photo frame with large high quality 15“ LCD to play your digital photos, video clips and MP3 music files. PC independent Digital Photo Frame with elegant black wooden frame High quality big 15“ LCD, resolution 1024 x 768 Pixels IR-remote control and easy to use screen menu Internal 1 GB memory Supports different types of memory cards: CF (Compact Flash), MS (MemoryStick), MS Pro Duo (MS Duo), MS Pro Stick (MS Pro), SD (Secure Digital), MMC (Multi Media Card), XD (XD Picture Card) and USB memory sticks (USB host function) Supports digital photos in JPEG-Format Slide show mode with transitional styles and variable speed Zoom function, rotating photos, brightness control Supports video clips in MPEG1/2/4 format MP3 music playback Landscape and portrait format Two built-in stereo speakers USB 2.0 Power supply via AC adapter (AC 100 – 240V (50/60 Hz) – DC 12 V / 3A) Shipping Weight: 7.04lb

Mobile Action i-gotU GT-800 PRO Sports & Travel Computer $139.99 “Mobile Action i-gotU GT-800 “”PRO”" Sports & Travel Computer Features i-gotU GT-800 Pro is a sophisticated GPS & Sports Computer that’s handy for various outdoor and sports activities. Its 1.4“ backlit LCD screen details all the essential GPS information you need to know on the go, including speed, distance, altitude, time, pace and much more. This light-weighted GPS device can be as portable as wrist-fitting or strapped onto your bike; furthermore, the IPX7 waterproof feature enhances i-gotU GT-800 Pro with better operability in various weather conditions. Together with @trip PC software, photo geotagging and sharing online have just gotten easier than ever. i-gotU GT-800 Pro is truly the best travelmate that a photographer, outdoorman or athlete can ever have. System Requirements: PC with Windows 7, Vista, XP PC with USB 1.1 or 2.0 or 3.0 Download the latest software for your i-gotU GPS Sports & Travel Computer from Mobile Action website. ENHANCEMENTS of GT-800 Pro : GT800PRO Shipping Weight: 0.41lb Technical Details Display essential information, including current speed, average speed, distance, altitude, pace, laps, moving time, current time, battery indicator, pedometer, satellite status… etc. IPX 7 waterproof design, perfect for outdoor activities. Built-in barometric altimeter with high precision, ideal for mountain and biking adventures. Location Navigation – navigates to the point of intersest with distance and directional info. Long battery life with built-in motion sensor. Built-in pedometer for a healthy lifestyle. Built-in stopwatch to measure up to 23hr, 59mins, 59secs. Programmable GPS logging interval from 1sec~60secs. Easy-to-use @trip PC software, share your trips with @trip online service. Auto geotagging photos quickly, compatible with all digital camera. Sports Analyzer software to organize and analyze your workouts, including tracks, charts and calorie burned. ”

Samsung Series 7 11.6 Windows 7 Slate PC (1.6GHz, 4GB RAM, 128GB SSD, Windows 7 Pro) $1504.99 “Samsung Series 7 11.6″” Windows 7 Slate PC Features The Windows 7 OS allows you to run all your favorite office software. You can share documents with co-workers without any compatibility issues. And our Samsung touch interface gives you easy, instant access to all your programs. Exclusive Fast Start Technology When inspiration hits, make sure you have a laptop that can keep up. With Samsung’s exclusive Fast Start technology, close the lid to enter a hybrid sleep mode, then simply open it to be up and running again in as little as two seconds. A Full PC in a Sleek Form Factor Samsung Series 7 slate PCs offer the power and speed of a full-size PC, yet they’re a mere half-inch thick and weigh less than a pound. They’re an amazing marriage of power and design. Multi-touch Screen 1366 x 768 WXGA Display – 4 GB RAM – 128 GB SSD – Intel HD 3000 Graphics Card – Bluetooth – Yes – Genuine Windows 7 Professional – HDMI Shipping Weight: 4.12lb ”

#740 Pro Wood Outdoor Hockey School Set (EA) $175.99 Extra thick reinforced outdoor plastic blades for proven success. Wood shafts, 12 extra long 56" sticks, 2 speed control balls, and an instruction booklet.

$119.47 shipped–$112.41 shipped–Hobbywing Platinum-100A-PRO Brushless Motor ESC Speed Controller $119.47 Brand: Hobbywing. Model: Platinum-100A-PRO. Continuous current: 100A. Burst current: 150A up to 10 seconds. Input Voltage: 2-6 cells lithium battery or 5-18 cells NIMH battery.

$128.82 shipped–$121.21 shipped–Hobbywing Platinum-70A-HV-PRO Brushless Motor ESC Speed Controller $128.82 Brand: Hobbywing. Model: Platinum-70A-HV-PRO. Continuous current: 70A. Burst current: 105A up to 10 seconds. Input Voltage: 5-12 cells lithium battery or 15-36 cells NIMH battery. BEC: None. Control Signal Transmission: optically coupled system.

$13.21 shipped–$13.21 shipped–2GB Memory Stick Pro Duo Ultra II (Black) $13.21 Store videos and digital photos on this memory card that’s compatible with both Memory Stick PRO and Memory Stick PRO Duo media cards. The fast 9MB/sec. write speed means less time between shots for fast-action photography.

$188.43 shipped–$186.53 shipped–HSP Troian-pro Brushless 1/16 Scale Electric Powered Off-Road RTR Buggy (No. 94185Pro) $188.43 High speed 1/16th scale electric powered Off-Road RC car buggy.

$222.49 shipped–$209.23 shipped–Hobbywing Platinum-120A-HV-PRO Brushless Motor ESC Speed Controller $222.49 Brand: Hobbywing. Model: Platinum-120A-HV-PRO. Continuous current: 120A. Burst current: 180A up to 10 seconds. Input Voltage: 5-12 cells lithium battery or 15-36 cells NIMH battery. BEC: None.

$4.49 shipped–$4.15 shipped–USB Cable Pro for iPhone/Nokia/Blackberry/HTC Cell Phones $4.49 USB cable pro provides high speed USB2.0 data transfers while charging your cell phone through the USB interface.

$61.05 shipped–$57.55 shipped–Hobbywing Platinum-40A-PRO Brushless Motor ESC Speed Controller $61.05 Brand: Hobbywing. Model: Platinum-40A-PRO. Continuous current: 40A. Burst current: 60A up to 10 seconds. Input Voltage: 2-6 cells lithium battery or 5-18 cells NIMH battery.

$81.66 shipped–$76.88 shipped–Hobbywing Platinum-60A-PRO Brushless Motor ESC Speed Controller $81.66 Brand: Hobbywing. Model: Platinum-60A-PRO. Continuous current: 60A. Burst current: 90A up to 10 seconds. Input Voltage: 2-6 cells lithium battery or 5-18 cells NIMH battery.

$96.46 shipped–$90.78 shipped–Hobbywing Platinum-80A-PRO Brushless Motor ESC Speed Controller $96.46 Brand: Hobbywing. Model: Platinum-80A-PRO. Continuous current: 80A. Burst current: 120A up to 10 seconds. Input Voltage: 2-6 cells lithium battery or 5-18 cells NIMH battery.

100′ Strait-Line Chalk Reel 2031318DS $11.5 The Irwin 2031318DS is a Speedline Pro Chalk Line 3x Speed. This Irwin Chalk Reel is 3 times faster than traditional chalk reels. Features: 3 times Faster than traditional chalk reels 3.5:1 Gear ratio Metal handle Nylon/Polyester braided line Light-weight ABS plastic housing Wide pronged hook What s In the Box: Irwin 2031318DS Speedline Pro Chalk Line 3x Speed

101 Tips and Tricks for Acoustic Guitar $11.96 New – From tips on arranging and speed-picking, to the maintenance of your guitar (and you!) and beyond, 101 Tips and Tricks for Acoustic Guitar is chock full of “unplugged” pointers to help everyone from the beginning student to the seasoned pro. Here, you’ll learn how to: evaluate a vintage guitar, repair a crack in an emergency, protect your guitar during air travel, make your own bottleneck, learn a flamenco strumming technique, master the convex barre, manage performance anxiety, discover n

101 Tips and Tricks for Acoustic Guitar $20.1 New – From tips on arranging and speed-picking, to the maintenance of your guitar (and you!) and beyond, 101 Tips and Tricks for Acoustic Guitar is chock full of “unplugged” pointers to help everyone from the beginning student to the seasoned pro. Here, you’ll learn how to: evaluate a vintage guitar, repair a crack in an emergency, protect your guitar during air travel, make your own bottleneck, learn a flamenco strumming technique, master the convex barre, manage performance anxiety, discover n

101 Tips and Tricks for Acoustic Guitar $6.18 From tips on arranging and speed-picking, to the maintenance of your guitar (and you!) and beyond, 101 Tips and Tricks for Acoustic Guitar is chock full of “unplugged” pointers to help everyone from the beginning student to the seasoned pro. Here, you’ll learn how to: evaluate a vintage guitar, repair a crack in an emergency, protect your guitar during air travel, make your own bottleneck, learn a flamenco strumming technique, master the convex barre, manage performance anxiety, discover new performance venues, and much more. The CD includes demonstration tracks.

101 Tips and Tricks for Acoustic Guitar $11.96 Used – From tips on arranging and speed-picking, to the maintenance of your guitar (and you!) and beyond, 101 Tips and Tricks for Acoustic Guitar is chock full of “unplugged” pointers to help everyone from the beginning student to the seasoned pro. Here, you’ll learn how to: evaluate a vintage guitar, repair a crack in an emergency, protect your guitar during air travel, make your own bottleneck, learn a flamenco strumming technique, master the convex barre, manage performance anxiety, discover

10FT/3M B116C-010B PRO-ULTRA $44.39 Accell 3m Supreme HDMI High-Speed Cable with Ethernet

115GB G.Skill Phoenix Evo 2.5-inch SATA Solid State Disk MLC (280MB/sec read, 270MB/sec write) $138.24 115GB G.Skill SATA 2.5-inch SSD, based on the SandForce SF-1222 controller. Read speed up to 280MB/sec and write speed up to 270MB/sec. Phoenix EVO range is based on high quality 2xnm NAND flash chips and IOPS up to 35,000.G.Skill is pleased to announce its new Phoenix EVO SSD, utilizing the performance leading controller SandForce SF-1222 and high quality 2xnm NAND flash chips. The Phoenix EVO drive contains 115GB with rated speed of read/write 280/270 MB/sec.Keeping pace with the flash manufacturers transition from 3xnm to 2xnm, G.Skill has utilized 2xnm flash chips for its award winning SSD, the Phoenix family. To ensure the best performance and reliability during the transition, G.Skill has teamed up closely with SandForce and has run G.Skill Phoenix EVO through a wide range of rigorous tests with the latest firmware. All Phoenix EVO drives only use strictly selected original flash chips from key suppliers to guarantee the top reliability and stability.Although 2xnm based Phoenix EVO requires more over-provisioning space and less performance comparing with G.Skill current 3xnm based Phoenix Pro drive, it certainly is a great choice for cost effectiveness and delivers a positive impact on affordability for the customer.G.Skill Phoenix EVO SSD comes with 3 years warranty and the G.Skill technical team is always ready to provide consumers with complete technical support via online forums, telephone and email.

Speed Pro

A Tour of the Pentium(r) Pro Processor Microarchitecture

Introduction

One of the Pentium(r) Pro processor’s primary goals was to significantly exceed the performance

of the 100MHz Pentium(r) processor while being manufactured on the same semiconductor process. Using the same process as a volume production processor practically assured that the Pentium Pro processor would be manufacturable, but it meant that Intel had to focus on an improved microarchitecture for ALL of the performance gains. This guided tour describes how multiple architectural techniques – some proven in mainframe computers, some proposed in academia and some we innovated ourselves – were carefully interwoven, modified, enhanced, tuned and implemented to produce the Pentium Pro microprocessor. This unique combination of architectural features, which Intel describes as Dynamic Execution, enabled the first Pentium Pro processor silicon to exceed the original performance goal.

Building from an already high platform

The Pentium processor set an impressive performance standard with its pipelined,

superscalar microarchitecture. The Pentium processor’s pipelined implementation uses five

stages to extract high throughput from the silicon – the Pentium Pro processor moves to a

decoupled, 12-stage, superpipelined implementation, trading less work per pipestage for

more stages. The Pentium Pro processor reduced its pipestage time by 33 percent, compared

with a Pentium processor, which means the Pentium Pro processor can have a 33% higher clock

speed than a Pentium processor and still be equally easy to produce from a semiconductor

manufacturing process (i.e., transistor speed) perspective.

 

The Pentium processor’s superscalar microarchitecture, with its ability to execute two

instructions per clock, would be difficult to exceed without a new approach.

The new approach used by the Pentium Pro processor removes the constraint of linear

instruction sequencing between the traditional “fetch” and “execute” phases, and opens up

a wide instruction window using an instruction pool. This approach allows the “execute”

phase of the Pentium Pro processor to have much more visibility into the program’s

instruction stream so that better scheduling may take place. It requires the instruction

“fetch/decode” phase of the Pentium Pro processor to be much more intelligent in terms of

predicting program flow. Optimized scheduling requires the fundamental “execute” phase to

be replaced by decoupled “dispatch/execute” and “retire” phases. This allows instructions

to be started in any order but always be completed in the original program order. The

Pentium Pro processor is implemented as three independent engines coupled with an

instruction pool as shown in Figure 1 below.

 

What is the fundamental problem to solve?

Before starting our tour on how the Pentium Pro processor achieves its high performance it

is important to note why this three- independent-engine approach was taken. A fundamental

fact of today’s microprocessor implementations must be appreciated: most CPU cores are not

fully utilized.

The first instruction in this example is a load of r1 that, at run time, causes a cache miss.

A traditional CPU core must wait for its bus interface unit to read this data from main

memory and return it before moving on to instruction 2. This CPU stalls while waiting for

this data and is thus being under-utilized.

While CPU speeds have increased 10-fold over the past 10 years, the speed of main memory

devices has only increased by 60 percent. This increasing memory latency, relative to the

CPU core speed, is a fundamental problem that the Pentium Pro processor set out to solve.

One approach would be to place the burden of this problem onto the chipset but a

high-performance CPU that needs very high speed, specialized, support components is not a

good solution for a volume production system.

A brute-force approach to this problem is, of course, increasing the size of the L2 cache to reduce the miss ratio. While effective, this is another expensive solution, especially considering the speed requirements of today’s L2 cache SRAM components. Instead, the Pentium Pro processor is designed from an overall system implementation perspective which will allow higher performance systems to be designed with cheaper memory subsystem designs.

Pentium Pro processor takes an innovative approach

To avoid this memory latency problem the Pentium Pro processor “looks-ahead” into its instruction pool at subsequent instructions and will do useful work rather than be stalled. In the example in Figure 2, instruction 2 is not executable since it depends upon the result of instruction 1; however both instructions 3 and 4 are executable. The Pentium Pro processor speculatively executes instructions 3 and 4. We cannot commit the results of this speculative execution to permanent machine state (i.e., the programmer-visible registers) since we must maintain the original program order, so the results are instead stored back in the instruction pool awaiting in-order retirement. The core executes instructions depending upon their readiness to execute and not on their original program order (it is a true dataflow engine). This approach has the side effect that instructions are typically executed out-of-order.

The cache miss on instruction 1 will take many internal clocks, so the Pentium Pro processor core continues to look ahead for other instructions that could be speculatively executed and is typically looking 20 to 30 instructions in front of the program counter. Within this 20- to 30- instruction window there will be, on average, five branches that the fetch/decode unit must correctly predict if the dispatch/execute unit is to do useful work. The sparse register set of an Intel Architecture (IA) processor will create many false dependencies on registers so the dispatch/execute unit will rename the IA registers to enable additional forward progress. The retire unit owns the physical IA register set and results are only committed to permanent machine state when it removes completed instructions from the pool in original program order.

Dynamic Execution technology can be summarized as optimally adjusting instruction execution by predicting program flow, analysing the program’s dataflow graph to choose the best order to execute the instructions, then having the ability to speculatively execute instructions in the preferred order. The Pentium Pro processor dynamically adjusts its work, as defined by the incoming instruction stream, to minimize overall execution time.

Overview of the stops on the tour

We have previewed how the Pentium Pro processor takes an innovative approach to overcome a key system constraint. Now let’s take a closer look inside the Pentium Pro processor to understand how it implements Dynamic Execution. Figure 3 below extends the basic block diagram to include the cache and memory interfaces – these will also be stops on our tour. We shall travel down the Pentium Pro processor pipeline to understand the role of each unit:

•The FETCH/DECODE unit: An in-order unit that takes as input the user program instruction stream from the instruction cache, and decodes them into a series of micro-operations (uops) that represent the dataflow of that instruction stream. The program pre-fetch is itself speculative.

•The DISPATCH/EXECUTE unit: An out-of-order unit that accepts the dataflow stream, schedules execution of the uops subject to data dependencies and resource availability and temporarily stores the results of these speculative executions.

•The RETIRE unit: An in-order unit that knows how and when to commit (“retire”) the temporary, speculative results to permanent architectural state.

•The BUS INTERFACE unit: A partially ordered unit responsible for connecting the three internal units to the real world. The bus interface unit communicates directly with the L2 cache supporting up to four concurrent cache accesses. The bus interface unit also controls a transaction bus, with MESI snooping protocol, to system memory.

Tour stop #1: The FETCH/DECODE unit.

 

Let’s start the tour at the Instruction Cache (ICache), a nearby place for instructions to reside so that they can be looked up quickly when the CPU needs them. The Next_IP unit provides the ICache index, based on inputs from the Branch Target Buffer (BTB), trap/interrupt status, and branch-misprediction indications from the integer execution section. The 512 entry BTB uses an extension of Yeh’s algorithm to provide greater than 90 percent prediction accuracy. For now, let’s assume that nothing exceptional is happening, and that the BTB is correct in its predictions. (The Pentium Pro processor integrates features that allow for the rapid recovery from a mis-prediction, but more of that later.)

The ICache fetches the cache line corresponding to the index from the Next_IP, and the next line, and presents 16 aligned bytes to the decoder. Two lines are read because the IA instruction stream is byte-aligned, and code often branches to the middle or end of a cache line. This part of the pipeline takes three clocks, including the time to rotate the prefetched bytes so that they are justified for the instruction decoders (ID). The beginning and end of the IA instructions are marked.

Three parallel decoders accept this stream of marked bytes, and proceed to find and decode the IA instructions contained therein. The decoder converts the IA instructions into triadic uops (two logical sources, one logical destination per uop). Most IA instructions are converted directly into single uops, some instructions are decoded into one-to-four uops and the complex instructions require microcode (the box labeled MIS in Figure 4, this microcode is just a set of preprogrammed sequences of normal uops). Some instructions, called prefix bytes, modify the following instruction giving the decoder a lot of work to do. The uops are enqueued, and sent to the Register Alias Table (RAT) unit, where the logical IA-based register references are converted into Pentium Pro processor physical register references, and to the Allocator stage, which adds status information to the uops and enters them into the instruction pool. The instruction pool is implemented as an array of Content Addressable Memory called the ReOrder Buffer (ROB).

We have now reached the end of the in-order pipe.

Tour stop #2: The DISPATCH/EXECUTE unit

The dispatch unit selects uops from the instruction pool depending upon their status. If the status indicates that a uop has all of its operands then the dispatch unit checks to see if the execution resource needed by that uop is also available. If both are true, it removes that uop and sends it to the resource where it is executed. The results of the uop are later returned to the pool. There are five ports on the Reservation Station and the multiple resources are accessed as shown in Figure 5 below:

The Pentium Pro processor can schedule at a peak rate of 5 uops per clock, one to each resource port, but a sustained rate of 3 uops per clock is typical. The activity of this scheduling process is the quintessential out-of-order process; uops are dispatched to the execution resources strictly according to dataflow constraints and resource availability, without regard to the original ordering of the program.

Note that the actual algorithm employed by this execution-scheduling process is vitally important to performance. If only one uop per resource becomes data-ready per clock cycle, then there is no choice. But if several are available, which should it choose? It could choose randomly, or first-come-first-served. Ideally it would choose whichever uop would shorten the overall dataflow graph of the program being run. Since there is no way to really know that at run-time, it approximates by using a pseudo FIFO scheduling algorithm favoring back-to-back uops.

Note that many of the uops are branches, because many IA instructions are branches. The Branch Target Buffer will correctly predict most of these branches but it can’t correctly predict them all. Consider a BTB that’s correctly predicting the backward branch at the bottom of a loop: eventually that loop is going to terminate, and when it does, that branch will be mispredicted. Branch uops are tagged (in the in-order pipeline) with their fallthrough address and the destination that was predicted for them. When the branch executes, what the branch actually did is compared against what the prediction hardware said it would do. If those coincide, then the branch eventually retires, and most of the speculatively executed work behind it in the instruction pool is good.

But if they do not coincide (a branch was predicted as taken but fell through, or was predicted as not taken and it actually did take the branch) then the Jump Execution Unit (JEU) changes the status of all of the uops behind the branch to remove them from the instruction pool. In that case the proper branch destination is provided to the BTB which restarts the whole pipeline from the new target address.

Tour stop #3: The RETIRE unit

The retire unit is also checking the status of uops in the instruction pool – it is looking for uops that have executed and can be removed from the pool. Once removed, the uops’ original architectural target is written as per the original IA instruction. The retirement unit must not only notice which uops are complete, it must also re-impose the original program order on them. It must also do this in the face of interrupts, traps, faults, breakpoints and mis- predictions.

There are two clock cycles devoted to the retirement process. The retirement unit must first read the instruction pool to find the potential candidates for retirement and determine which of these candidates are next in the original program order. Then it writes the results of this cycle’s retirements to both the Instruction Pool and the RRF. The retirement unit is capable of retiring 3 uops per clock.

Tour stop #4: BUS INTERFACE unit

There are two types of memory access: loads and stores. Loads only need to specify the memory address to be accessed, the width of the data being retrieved, and the destination register. Loads are encoded into a single uop. Stores need to provide a memory address, a data width, and the data to be written. Stores therefore require two uops, one to generate the address, one to generate the data. These uops are scheduled independently to maximize their concurrency, but must re-combine in the store buffer for the store to complete.

Stores are never performed speculatively, there being no transparent way to undo them. Stores are also never re- ordered among themselves. The Store Buffer dispatches a store only when the store has both its address and its data, and there are no older stores awaiting dispatch.

What impact will a speculative core have on the real world? Early in the Pentium Pro processor project, we studied the importance of memory access reordering. The basic conclusions were as follows:

•Stores must be constrained from passing other stores, for only a small impact on performance.

•Stores can be constrained from passing loads, for an inconsequential performance loss.

•Constraining loads from passing other loads or from passing stores creates a significant impact on performance.

So what we need is a memory subsystem architecture that allows loads to pass stores. And we need to make it possible for loads to pass loads. The Memory Order Buffer (MOB) accomplishes this task by acting like a reservation station and Re-Order Buffer, in that it holds suspended loads and stores, redispatching them when the blocking condition (dependency or resource) disappears.

 

About the Author

Itech troubleshooter is an advanced web development, high skilled professional software Solution Company located in New Delhi founded by, PRABHAKAR MISHRA in the year 2008.The company provides vast range of services to each and every customer in reaching their respective targeted spectators and their valuable information in fix and on steady affordable price. Today, you can easily get a lot of quality services by this company on just dialing a call to the company which includes services like website designing , web application development , Application development , Maintenance , Re-engineering , Flash development , SEO , SEO Services , Computer AMC , Computer Networking , Wireless Networking , Data Recovery , ERP Solution .

What is the fastest that the supra can run in need for speed pro street?

the fastest i have gone is 6.09 at 251 but is there any way i can go faster by like doing custom suspension upgrades and please tell me whats the fastest some of the others go in the 1/4 mile and its for ps3.

i used 2 hav a supra in 99′…cya:)

Speed PRO iPhone App Review CrazyMikesapps.com