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. *

 
AAPL
$103.39
Apple Inc.
+0.89
MSFT
$44.97
Microsoft Corpora
-0.46
GOOG
$574.33
Google Inc.
+2.73

MacTech Search:
Community Search:

Software Updates via MacUpdate

NetShade 6.0.2 - Browse privately using...
NetShade is an Internet security tool that conceals your IP address on the web. NetShade routes your Web connection through either a public anonymous proxy server, or one of NetShade's own dedicated... Read more
Mac DVDRipper Pro 5.0 - Copy, backup, an...
Mac DVDRipper Pro is the DVD backup solution that lets you protect your DVDs from scratches, save your batteries by reading your movies from your hard disk, manage your collection with just a few... Read more
pwSafe 3.1 - Secure password management...
pwSafe provides simple and secure password management across devices and computers. pwSafe uses iCloud to keep your password databases backed-up and synced between Macs and iOS devices. It is... Read more
StatsBar 1.8 - Monitor system processes...
StatsBar gives you a comprehensive and detailed analysis of the following areas of your Mac: CPU usage Memory usage Disk usage Network and bandwidth usage Battery power and health (MacBooks only)... Read more
Path Finder 6.5.5 - Powerful, award-winn...
Path Finder is a file browser that combines the familiar Finder interface with the powerful utilities and innovative features. Just a small selection of the Path Finder 6 feature set: Dual pane... Read more
QuarkXPress 10.2.1 - Desktop publishing...
With QuarkXPress, you can communicate in all the ways you need to -- and always look professional -- in print and digital media, all in a single tool. Features include: Easy to Use -- QuarkXPress is... Read more
Skype 6.19.0.450 - Voice-over-internet p...
Skype allows you to talk to friends, family and co-workers across the Internet without the inconvenience of long distance telephone charges. Using peer-to-peer data transmission technology, Skype... Read more
VueScan 9.4.41 - Scanner software with a...
VueScan is a scanning program that works with most high-quality flatbed and film scanners to produce scans that have excellent color fidelity and color balance. VueScan is easy to use, and has... Read more
Cloud 3.0.0 - File sharing from your men...
Cloud is simple file sharing for the Mac. Drag a file from your Mac to the CloudApp icon in the menubar and we take care of the rest. A link to the file will automatically be copied to your clipboard... Read more
LibreOffice 4.3.1.2 - Free Open Source o...
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

Latest Forum Discussions

See All

Alien Creeps TD Review
Alien Creeps TD Review By Jennifer Allen on September 2nd, 2014 Our Rating: :: EXPENSIVE DEFENSESUniversal App - Designed for iPhone and iPad Alien Creeps TD would be a fun if unremarkable Tower Defense game, but its heavy focus on... | Read more »
Function Space, a Social Network App for...
Function Space, a Social Network App for Science, Launches on iOS Posted by Ellis Spice on September 2nd, 2014 [ permalink ] | Read more »
Treasure Tombs: Ra Deal Coming from Bulk...
Treasure Tombs: Ra Deal Coming from Bulkypix and Dark Tonic This Fall Posted by Jessica Fisher on September 2nd, 2014 [ permalink ] Dark Tonic and | Read more »
Tiny Tower Vegas Review
Tiny Tower Vegas Review By Jennifer Allen on September 2nd, 2014 Our Rating: :: STEADY DEVELOPMENTUniversal App - Designed for iPhone and iPad Build a huge tower again but Vegas-style in Tiny Tower Vegas.   | Read more »
The Manhattan Project Review
The Manhattan Project Review By Andrew Fisher on September 2nd, 2014 Our Rating: :: ROCKET SCIENCEUniversal App - Designed for iPhone and iPad The Manhattan Project offers a great Euro-style gameplay experience, but it is totally... | Read more »
Rhonna Designs Magic (Photography)
Rhonna Designs Magic 1.0 Device: iOS Universal Category: Photography Price: $1.99, Version: 1.0 (iTunes) Description: Want to sprinkle *magic* on your photos? With RD Magic, you can add colors, filters, light leaks, bokeh, edges,... | Read more »
This Week at 148Apps: August 25-29, 2014
Shiny Happy App Reviews   | Read more »
Qube Kingdom – Tips, Tricks, Strategies,...
Qube Kingdom is a tower defense game from DeNA. You rally your troops – magicians, archers, knights, barbarians, and others – and fight against an evil menace looking to dominate your kingdom of tiny squares. Planning a war isn’t easy, so here are a... | Read more »
Qube Kingdom Review
Qube Kingdom Review By Nadia Oxford on August 29th, 2014 Our Rating: :: KIND OF A SQUARE KINGDOMUniversal App - Designed for iPhone and iPad Qube Kingdom has cute visuals, but it’s a pretty basic tower defense game at heart.   | Read more »
Fire in the Hole Review
Fire in the Hole Review By Rob Thomas on August 29th, 2014 Our Rating: :: WALK THE PLANKUniversal App - Designed for iPhone and iPad Seafoam’s Fire in the Hole looks like a bright, 8-bit throwback, but there’s not enough booty to... | Read more »

Price Scanner via MacPrices.net

Apple refurbished iPads available for up to $...
Apple is offering Certified Refurbished iPad Airs for up to $140 off MSRP. Apple’s one-year warranty is included with each model, and shipping is free. Stock tends to come and go with some of these... Read more
Are We Now In The Post-Post-PC Era?
A longtime and thoroughgoing laptop aficionado, I was more than a little dismayed by Steve Jobs’s declaration back in 2010 when he sprang the iPad on an unsuspecting world. that we’d entered a “post-... Read more
PC Outlook Improves, But 2014 Shipments Still...
According to the International Data Corporation (IDC) Worldwide Quarterly PC Tracker, worldwide PC shipments are expected to fall by -3.7 percent in 2014. To hat’s actually an improvement from the... Read more
IDC Lowers Tablet Sales Projections for 2014...
Following a second consecutive quarter of softer than expected demand, International Data Corporation (IDC) has lowered its worldwide tablet plus 2-in-1 forecast for 2014 to 233.1 million units. The... Read more
Apple now offering refurbished 21-inch 1.4GHz...
The Apple Store is now offering Apple Certified Refurbished 21″ 1.4GHz iMacs for $929 including free shipping plus Apple’s standard one-year warranty. Their price is $170 off the cost of new models,... Read more
Save $50 on the 2.5GHz Mac mini, on sale for...
B&H Photo has the 2.5GHz Mac mini on sale for $549.99 including free shipping. That’s $50 off MSRP, and B&H will also include a free copy of Parallels Desktop software. NY sales tax only. Read more
Save up to $300 on an iMac with Apple refurbi...
The Apple Store has Apple Certified Refurbished iMacs available for up to $300 off the cost of new models. Apple’s one-year warranty is standard, and shipping is free. These are the best prices on... Read more
The Rise of Phablets
Carlisle & Gallagher Consulting Group, a businesses and technology consulting firm focused solely on the financial services industry, has released an infographic depicting the convergence of... Read more
Bad Driver Database App Allows Good Drivers t...
Bad Driver Database 1.4 by Facile Group is a new iOS and Android app that lets users instantly input and see how many times a careless, reckless or just plain stupid driver has been added to the... Read more
Eddy – Cloud Music Player for iPhone/iPad Fre...
Ukraine based CapableBits announces the release of Eddy, its tiny, but smart and powerful cloud music player for iPhone and iPad that allows users to stream or download music directly from cloud... Read more

Jobs Board

*Apple* Retail - Multiple Positions (US) - A...
Sales Specialist - Retail Customer Service and Sales Transform Apple Store visitors into loyal Apple customers. When customers enter the store, you're also the Read more
*Apple* Retail - Multiple Positions (US) - A...
Sales Specialist - Retail Customer Service and Sales Transform Apple Store visitors into loyal Apple customers. When customers enter the store, you're also the Read more
*Apple* Retail - Multiple Positions (US) - A...
Sales Specialist - Retail Customer Service and Sales Transform Apple Store visitors into loyal Apple customers. When customers enter the store, you're also the Read more
*Apple* Retail - Multiple Positions (US) - A...
Sales Specialist - Retail Customer Service and Sales Transform Apple Store visitors into loyal Apple customers. When customers enter the store, you're also the Read more
Senior Event Manager, *Apple* Retail Market...
…This senior level position is responsible for leading and imagining the Apple Retail Team's global event strategy. Delivering an overarching brand story; in-store, Read more
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.