TweetFollow Us on Twitter

September 94 - BALANCE OF POWER

BALANCE OF POWER

Tuning PowerPCMemory Usage

DAVE EVANS

[IMAGE 017-019_Balance_of_Pwr_h1.GIF]

If you care about the performance of code you write for the Power Macintosh, memory usage should be your foremost concern. With the PowerPCTM601 processor today, and even more important with future processors, memory usage of your code will have the greatest effect on its performance. Poorly written code will execute at a fraction of its potential, and often very simple changes will greatly improve the execution speed of your critical code.

Processors are improving much faster than the memory subsystems that support them. As the PowerPC chips move from 80 MHz to 100 MHz and beyond, their thirst for data to process and instructions to execute will increasingly tax memory. Memory caches attempt to mitigate that thirst, and all PowerPC processors come equipped with built-in caches. But your code can work well with a cache or it can work very poorly with a cache. I'll show you why and discuss what you can do to optimize your memory usage.

CACHE BASICS
As you know, a cache is simply very fast RAM that the processor can access quickly and that it uses to store recently referenced data and code. On the PowerPC processors, any data stored in the cache can be accessed without stalling the processor's pipeline. Accesses to data not in the cache will take about 20 times as long reading from main memory, or even 1 million times as long if the access causes a page fault with virtual memory. Getting and keeping your performance-critical code and data in the cache are therefore key to your execution speed.

A cache is divided into small blocks calledcache lines . On the PowerPC 601, for example, the cache has 1024 cache line blocks, each holding 32 bytes. In addition, the 601 will fetch two blocks when it can, making the cache line size effectively 64 bytes.

The first PowerPC processors have set associative caches of different sizes. The 601 has an eight-way set associative, unified cache that's 32K in size, and the 603 has a two-way set associative, split cache with 8K for data and 8K for instruction code. The termset associative refers to the way the cache relates to main memory, which is important to your performance. In some simple caching schemes, each cache line maps directly to specific areas of main memory; any access to one of these areas loads bytes into that cache line. But on the PowerPC processor, sets of cache lines are combined and then mapped to memory. There are eight cache lines in each set on the 601, and two in each set on the 603. An access to one of the areas mapped to a set will load bytes into the last-used cache line of the set, keeping the most frequently used cache lines from being purged. This more complicated scheme typically yields much better performance than the directly mapped cache.

CACHE THRASHING
The cache will most affect your performance when you're accessing large amounts of data. A typical example of this is walking through arrays to perform some operation. The best strategy is to minimize cache collisions during your accesses, and the best tactic for this is to access your data as sequentially as possible. If you walk through memory sequentially, you'll load the cache every 64 bytes, but all 64 bytes will be available for fast processing. Here's an example:

unsigned longdata[64][1024];
for (row = 2; row < 64; row++)
    for (column = 0; column < 1024; column++)
        data[row][column] =
            data[row-1][column] + data[row-2][column];

This example performs additions on each element of a large matrix and accesses that matrix sequentially in memory. It walks across each row, adding elements and storing the result. But just inverting the loops can significantly change the way memory is accessed:

unsigned longdata[64][1024];
for (column = 0; column < 1024; column++)
    for (row = 2; row < 64; row++)
        data[row][column] =
            data[row-1][column] + data[row-2][column];

Reversing the loops leads to less than optimal performance since we perform each addition for all the columns before moving to the next element of a row. Instead of sequential access, this access pattern jumps across memory in even steps of 4K. Unfortunately, on the PowerPC processor these accesses map to the same set of cache lines, and every operation causes the cache to reload from main memory. This second example takes twice as long to execute the same calculation on a Power Macintosh 6100/60.

By paying attention to how your code accesses memory, you can avoid serious cache thrashing like that done by the second example. Things to look out for are loops that iterate for a power of 2 steps (128, 256, and so on)and code whose memory accesses are not close together.

An approach called blocking may help your loops. Often your code isn't as simple as above, and your memory accesses aren't regular during the loop. If you're walking two different arrays with different increments through memory, it may be impossible to serialize your accesses. Blocking performs the calculations in blocks of rows and columns. Instead of iterating across all the columns and then proceeding to the next row, you divide the dimensional space into blocks and calculate one whole block at a time. In this next example, we calculate the multiplication of two matrices.

long result[64][64], foo[64][128], bar[128][64];
for (row = 0; row < 64; row++)
    for (column = 0; column < 64; column++) {
        long    sum = 0;
        for (i = 0; i < 128; i++)
            sum += foo[row][i] * bar[i][column];
        result[row][column] = sum;
    }

As this algorithm walks through memory, it accesses result and foo sequentially, but bar is accessed in 256-byte steps. Accessing bar by jumping through memory causes cache misses, and sequential elements of bar are flushed from the cache before they're needed.

By performing this operation in small blocks, we can better use the cache. The key is to use all the elements of foo and bar that are in a cache line before moving on. One way to do this is to expand the loop and perform four operations in a single iteration:

long result[64][64], foo[64][128], bar[128][64];
for (row = 0; row < 64; row++)
    for (column = 0; column < 64; column += 4) {
        long    sum1 = 0, sum2 = 0;
        long    sum3 = 0, sum4 = 0;
        for (i = 0; i < 128; i++) {
            sum1 += foo[row][i] * bar[i][column];
            sum2 += foo[row][i] * bar[i][column+1];
            sum3 += foo[row][i] * bar[i][column+2];
            sum4 += foo[row][i] * bar[i][column+3];
    }
    result[row][column] = sum1;
    result[row][column+1] = sum2;
    result[row][column+2] = sum3;
    result[row][column+3] = sum4;
    }

This expanded loop calculates a block of four cells in each iteration. This executes faster because elements of bar are read from the cache and don't always cause cache misses as in the earlier example. Notice that in the expanded inner loop, a cache line of the bar matrix will be loaded the first time that it's referenced; then the following three references to bar will occur without stalling. Using the bar elements while they're still in the cache gives us a significant improvement.

CODE STYLE
Good compilers can pay attention to your memory accesses and will optimize how you access memory. For example, load and store operations can be reordered by the compiler to occur when the data is most likely to be available. The first time data is accessed it tends to cause a cache line to load, and subsequent accesses to nearby data must also wait for the cache load to complete. The compiler may be able to help by inserting a few instructions between the loads. This way the cache line will be fully loaded when the subsequent accesses are needed.

For more information on loop expansion and instruction reordering, see the Balance of Power column in develop Issue 18.*

You can help your compiler by using local variables when you can. These tell the compiler exactly how the data will be used, enabling it to easily reorder the loads and stores for this data.

You should also carefully note memory dereferences, especially double dereferences. Although it may be obvious to you, the compiler often can't tell whether two pointers address the same object in memory. The compiler may be prevented from reordering instructions because it can't tell whether two operations are really dependent on each other, just because they contain dereferences. Here's an example:

paramBlock->size = myStructure->size;
paramBlock->offset = myStructure->offset;

Although it appears obvious, the compiler usually can't tell if paramBlock references the same memory as myStructure. In the resulting binary, the compiler will be conservative and not reorder these operations for best execution. Replacing the dereference of myStructure with local variables for size and offset will allow the compiler to fully optimize this example.

INSTRUCTION THRASHING
Your code binary itself can cause the cache to thrash as it loads to be executed. This is very hard to detect and optimize. The basic problem is that your subroutines may map to the same areas of the cache, and frequent calls among them will stall to reload the cache. Some code profilers for RISC workstations have attempted to detect this problem, but for the Macintosh I can't suggest much help. Just changing the link order of your code and then executing profiles may have an effect; some link orders will thrash more than others.

DATA STRUCTURES
The layout of your data structures can greatly affect your cache usage and your memory usage in general. For example, memory accesses that cross 64-bit memory boundaries take twice as long to process, as this forces two bus transactions. On the PowerPC 601 processor, any misaligned data access within a memory boundary takes the standard amount of time, which (because of typical Macintosh data structures) is a valuable feature of the chip; future PowerPC processors, however, may take longer to access misaligned data. If you can align your data structures, do so now. A good tactic is to keep 64-bit data at the top of your structure, followed by your 32-bit data, and so on to prevent accidental misalignment of elements. Pad the end of the structure to an even 64-bit increment if you will have arrays of structures or will allocate them on the stack. And if certain parts of your structure are accessed much more often than other parts, keep these together so that they stay in the cache, and make sure they're aligned.

DON'T FORGET
The memory usage of your speed-critical code will greatly affect its performance today, and current problems will just get worse when PowerPC processors go above 100 MHz. Profile your code to find the most critical bottlenecks; then pay close attention to how that code addresses memory. You'll be rewarded with an excellent return on your investment.

DAVE EVANS occasionally uses the combinatorics skills he learned at the Massachusetts Institute of Technology, but more often he's been practicing his combination punches at a Thai kickboxing gym. Designing fast algorithms for Apple's OS Platforms Group is definitely rewarding, but developing a fast left hook really gets him pumped up. *

Thanks to Tom Adams, Mike Cappella, Rob Johnston, and Mike Neil for reviewing this column. *

 

Community Search:
MacTech Search:

Software Updates via MacUpdate

NetShade 6.3.1 - Browse privately using...
NetShade is an anonymous proxy and VPN app+service for Mac. Unblock your Internet through NetShade's high-speed proxy and VPN servers spanning seven countries. NetShade masks your IP address as you... Read more
Dragon Dictate 4.0.7 - Premium voice-rec...
With Dragon Dictate speech recognition software, you can use your voice to create and edit text or interact with your favorite Mac applications. Far more than just speech-to-text, Dragon Dictate lets... Read more
Persecond 1.0.2 - Timelapse video made e...
Persecond is the easy, fun way to create a beautiful timelapse video. Import an image sequence from any camera, trim the length of your video, adjust the speed and playback direction, and you’re done... Read more
GIMP 2.8.14p2 - Powerful, free image edi...
GIMP is a multi-platform photo manipulation tool. GIMP is an acronym for GNU Image Manipulation Program. The GIMP is suitable for a variety of image manipulation tasks, including photo retouching,... Read more
Sandvox 2.10.2 - Easily build eye-catchi...
Sandvox is for Mac users who want to create a professional looking website quickly and easily. With Sandvox, you don't need to be a Web genius to build a stylish, feature-rich, standards-compliant... Read more
LibreOffice 5.0.1.2 - Free, open-source...
LibreOffice is an office suite (word processor, spreadsheet, presentations, drawing tool) compatible with other major office suites. The Document Foundation is coordinating development and... Read more
f.lux 36.1 - Adjusts the color of your d...
f.lux makes the color of your computer's display adapt to the time of day, warm at night and like sunlight during the day. Ever notice how people texting at night have that eerie blue glow? Or wake... Read more
VirtualBox 5.0.2 - x86 virtualization so...
VirtualBox is a family of powerful x86 virtualization products for enterprise as well as home use. Not only is VirtualBox an extremely feature rich, high performance product for enterprise customers... Read more
File Juicer 4.43 - Extract images, video...
File Juicer is a drag-and-drop can opener and data archaeologist. Its specialty is to find and extract images, video, audio, or text from files which are hard to open in other ways. In computer... Read more
Apple MainStage 3.2 - Live performance t...
MainStage 3 makes it easy to bring to the stage all the same instruments and effects that you love in your recording. Everything from the Sound Library and Smart Controls you're familiar with from... Read more

ReBoard: Revolutionary Keyboard (Utilit...
ReBoard: Revolutionary Keyboard 1.0 Device: iOS Universal Category: Utilities Price: $1.99, Version: 1.0 (iTunes) Description: Do everything within the keyboard without switching apps! If you are in WhatsApp, how do you schedule a... | Read more »
Tiny Empire (Games)
Tiny Empire 1.1.3 Device: iOS Universal Category: Games Price: $2.99, Version: 1.1.3 (iTunes) Description: Launch cannonballs and blow tiny orcs into thousands of pieces in this intuitive fantasy-themed puzzle shooter! Embark on an... | Read more »
Astropad Mini (Productivity)
Astropad Mini 1.0 Device: iOS iPhone Category: Productivity Price: $4.99, Version: 1.0 (iTunes) Description: *** 50% off introductory price! ​*** Get the high-end experience of a Wacom tablet at a fraction of the price with Astropad... | Read more »
Emo Chorus (Music)
Emo Chorus 1.0.0 Device: iOS Universal Category: Music Price: $1.99, Version: 1.0.0 (iTunes) Description: Realistic Choir simulator ranging from simple Chorus emulation to full ensemble Choir with 128 members. ### introductory offer... | Read more »
Forest Spirit (Games)
Forest Spirit 1.0.5 Device: iOS Universal Category: Games Price: $2.99, Version: 1.0.5 (iTunes) Description: | Read more »
Ski Safari 2 (Games)
Ski Safari 2 1.0 Device: iOS Universal Category: Games Price: $1.99, Version: 1.0 (iTunes) Description: The world's most fantastical, fun, family-friendly skiing game is back and better than ever! Play as Sven's sister Evana, share... | Read more »
Lara Croft GO (Games)
Lara Croft GO 1.0.47768 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0.47768 (iTunes) Description: Lara Croft GO is a turn based puzzle-adventure set in a long-forgotten world. Explore the ruins of an ancient... | Read more »
Whispering Willows (Games)
Whispering Willows 1.23 Device: iOS Universal Category: Games Price: $4.99, Version: 1.23 (iTunes) Description: **LAUNCH SALE 50% OFF** - Whispering Willows is on sale for 50% off ($4.99) until September 9th. | Read more »
Calvino Noir (Games)
Calvino Noir 1.1 Device: iOS iPhone Category: Games Price: $3.99, Version: 1.1 (iTunes) Description: The film noir stealth game. Calvino Noir is the exploratory, sneaking adventure through the 1930s European criminal underworld.... | Read more »
Angel Sword (Games)
Angel Sword 1.0 Device: iOS Universal Category: Games Price: $6.99, Version: 1.0 (iTunes) Description: Prepare to adventure in the most epic full scale multiplayer 3D RPG for mobile! Experience amazing detailed graphics in full HD.... | Read more »

Price Scanner via MacPrices.net

Big Grips Lift Handle For iPad Air and iPad A...
KEM Ventures, Inc. which pioneered the extra-large, super-protective iPad case market with the introduction of Big Grips Frame and Stand in 2011, is launching Big Grips Lift featuring a new super-... Read more
Samsung Launches Galaxy Tab S2, Its Most Powe...
Samsung Electronics America, Inc. has announced the U.S. release of the Galaxy Tab S2, its thinnest, lightest, ultra-fast tablet. Blending form and function, elegant design and multitasking power,... Read more
Tablet Screen Sizes Expanding as iPad Pro App...
Larger screen sizes are gaining favor as the tablet transforms into a productivity device, with shipments growing 185 percent year-over-year in 2015. According to a new Strategy Analytics’ Tablet... Read more
Today Only: Save US$50 on Adobe Elements 13;...
Keep the memories. lose the distractions. Summer’s winding down and it’s time to turn almost perfect shots into picture perfect memories with Elements 13. And get the power to edit both photos and... Read more
1.4GHz Mac mini on sale for $449, save $50
Best Buy has the 1.4GHz Mac mini on sale for $50 off MSRP on their online store. Choose free shipping or free local store pickup (if available). Price for online orders only, in-store price may vary... Read more
12-inch 1.1GHz Gold MacBook on sale for $1149...
B&H Photo has the 12″ 1.1GHz Gold Retina MacBook on sale for $1149.99 including free shipping plus NY sales tax only. Their price is $150 off MSRP, and it’s the lowest price available for this... Read more
27-inch 3.3GHz 5K iMac on sale for $1849, sav...
Best Buy has the 27″ 3.3GHz 5K iMac on sale for $1849.99. Their price is $150 off MSRP, and it’s the lowest price available for this model. Choose free shipping or free local store pickup (if... Read more
Worldwide Tablet Shipments Expected to Declin...
Does Apple badly need a touchscreen convertible/hybrid laptop MacBook? Yes, judging from a new market forecast from the International Data Corporation (IDC) Worldwide Quarterly Tablet Tracker, which... Read more
Continued PC Shipment Shrinkage Expected Thro...
Worldwide PC shipments are expected to fall by -8.7 percent in 2015 and not stabilize until 2017, according to the latest International Data Corporation (IDC) Worldwide Quarterly PC Tracker data. The... Read more
Imminent iPhone 6s Announcement Leads To 103%...
NextWorth Solutions, with its online and in-store electronics trade-in programs including http://NextWorth.com, reports that it has experienced a 103 percent surge in quoted trade-in values over the... Read more

Jobs Board

*Apple* Retail Online Store: Customer Insigh...
**Job Summary** Apple Retail (Online Store) is seeking an experienced e-commerce analytics professional to join the Customer Insights Team. The Web e-Commerce Analyst Read more
*Apple* Music, Business Operations - Apple I...
Changing the world is all in a day039s work at Apple . If you love innovation, here039s your chance to make a career of it. You039ll work hard. But the job comes with Read more
WW *Apple* Retail Online Store: Customer In...
**Job Summary** The Apple Retail - Online Store is seeking an experienced web merchandising analytics professional to join the Customer Insights Team. The Web Read more
Senior Payments Security Manager - *Apple*...
**Job Summary** Apple , Inc. is looking for a highly motivated, innovative and hands-on senior payments security manager to join the Apple Pay security team. You will Read more
Software QA Engineer, *Apple* Pay Security...
**Job Summary** Imagine what you could do here. At Apple , great ideas have a way of becoming great products, services, and customer experiences very quickly. Bring Read more
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.