TweetFollow Us on Twitter

June 94 - BALANCE OF POWER

BALANCE OF POWER

Enhancing PowerPC Native Speed

DAVE EVANS

[IMAGE 055-057_Balance_of_Power1.GIF]

When you convert your applications to native PowerPC code, they run lightning fast. To get the most out of RISC processors, however, you need to pay close attention to your code structure and execution. Fast code is no longer measured solely by an instruction timing table. The Power PC 601 processor includes pipelining, multi-issue and speculative execution, branch prediction, and a set associative cache. All these things make it hard to know what code will run fastest on a Power Macintosh.

Writing tight code for the PowerPC processor isn't hard, especially with a good optimizing compiler to help you. In this column I'll pass on some of what I've learned about tuning Power PC code. There are gotchas and coding habits to avoid, and there are techniques for squeezing the most from your speed-critical native code. For a good introduction to RISC pipelining and related concepts that appear in this column, see "Making the Leap to PowerPC" in Issue 16.

MEASURING YOUR SPEED
The power of RISC lies in the ability to execute one or more instructions every machine clock cycle, but RISC processors can do this only in the best of circumstances. At their worst they're as slow as CISC processors. The following loop, for example, averages only one calculation every 2.8 cycles:

float a[], b[], c[], d, e;
for (i=0; i < gArraySize; i++) {
  e = b[i] + c[i] / d;
  a[i] = MySubroutine(b[i], e);
}

By restructuring the code and using other techniques from this column, you can make significant improvements. This next loop generates the same result, yet averages one calculation every 1.9 cycles -- about 50% faster.

reciprocalD = 1 / d;
for (i=0; i < gArraySize; i+=2) {
  float result, localB, localC, localE;
  float result2, localB2, localC2, localE2;

  localB = b[i];
  localC = c[i];
  localB2 = b[i+1];
  localC2 = c[i+1];

  localE = localB + (localC * reciprocalD);
  localE2 = localB2 + (localC2 * reciprocalD);
  InlineSubroutine(&result, localB, localE);
  InlineSubroutine(&result2, localB2, localE2);

  a[i] = result;
  a[i+1] = result2;
}

The rest of this column explains the techniques I just used for that speed gain. They include expanding loops, scoping local variables, using inline routines, and using faster math operations.

UNDERSTANDING YOUR COMPILER
Your compiler is your best friend, and you should try your hardest to understand its point of view. You should understand how it looks at your code and what assumptions and optimizations it's allowed to make. The more you empathize with your compiler, the more you'll recognize opportunities for optimization.

An optimizing compiler reorders instructions to improve speed. Executing your code line by line usually isn't optimal, because the processor stalls to wait for dependent instructions. The compiler tries to move instr uctions that are independent into the stall points. For example, consider this code:

first = input * numerator;
second = first / denominator;
output = second + adjustment;

Each line depends on the previous line's result, and the compiler will be hard pressed to keep the pipeline full of useful work. This simple example could cause 46 stalled cycles on the PowerPC 601, so the compiler will look at other nearby code for independent instructions to move into the stall points.

EXPANDING YOUR LOOPS
Loops are often your most speed-critical code, and you can improve their performance in several ways. Loop expanding is one of the simplest methods. The idea is to perform more than one independent operation in a loop, so that the compiler can reorder more work in the pipeline and thus prevent the processor from stalling.

For example, in this loop there's too little work to keep the processor busy:

float a[], b[], c[], d;
for (i=0; i < multipleOfThree; i++) {
  a[i] = b[i] + c[i] * d;
}

If we know the data always occurs in certain sized increments, we can do more steps in each iteration, as in the following:

for (i=0; i < multipleOfThree; i+=3) {
  a[i] = b[i] + c[i] * d;
  a[i+1] = b[i+1] + c[i+1] * d;
  a[i+2] = b[i+2] + c[i+2] * d;
}

On a CISC processor the second loop wouldn't be much faster, but on the Power PC processor the second loop is twice as fast as the first. This is because the compiler can schedule independent instructions to keep the pipeline constantly moving. (If the data doesn't occur in nice increments, you can still expand the loop; just add a small loop at the end to handle the extra iterations.)Be careful not to expand a loop too much, though. Very large loops won't fit in the cache, causing cache misses for each iteration. In addition, the larger a loop gets, the less work can be done entirely in registers. Expand too much and the compiler will have to use memory  to store intermediate results, outweighing your marginal gains. Besides, you get the biggest gains from the first few expansions.

SCOPING YOUR VARIABLES
If you're new to RISC, you'll be impressed by the number of registers available on the PowerPC chip -- 32 general registers and 32 floating-point registers. By having so many, the processor can often avoid slow memory operations. Your compiler will take advantage of this when it can, but you can help it by carefully scoping your variables and using lots of local variables.

The "scope" of a variable is the area of code in which it is valid. Your compiler examines the scope of each variable when it schedules registers, and your code can provide valuable information about the usage of each variable. Here's an example:

for (i=0; i < gArraySize; i++) {
  a[i] = MyFirstRoutine(b[i], c[i]);
  b[i] = MySecondRoutine(a[i], c[i]);
} 

In this loop, the global variable gArraySize is scoped for the whole program. Because we call a subroutine in the loop, the compiler can't tell if gArraySize will change during each iteration. Since the subroutine might modify gArraySize, the compiler has to be conservative. It will reload gArraySize from memory on every iteration, and it won't optimize the loop any further. This is wastefully slow.

On the other hand, if we use a local  variable, we tell the compiler that gArraySize and c[i] won't be modified and that it's all right to just keep them handy in registers. In addition, we can store data as temporary variables scoped only within the loop. This tells the compiler how we intend to use the data, so that the compiler can use free registers and discard them after the loop. Here's what this would look like:

arraySize = gArraySize;
for (i=0; i < arraySize; i++) {
  float localC;
  localC = c[i];
  a[i] = MyFirstRoutine(b[i], localC);
  b[i] = MySecondRoutine(a[i], localC);
} 

These minor changes give the compiler more information about the data, in this instance accelerating the resulting code by 25%.

STYLING YOUR CODE
Be wary of code that looks complicated. If each line of source code contains complicated dereferences and typecasting, chances are the object code has wasteful memory instructions and inefficient register usage. A great compiler might optimize well anyway, but don't count on it. Judicious use of temporary variables (as mentioned above) will help the compiler understand exactly what you're doing -- plus your code will be easier to read.

Excessive memory dereferencing is a problem exacerbated by the heavy use of handles on the Macintosh. Code often contains double memory dereferences, which is important when memory can move. But when you can guarantee that memory won't  move, use a local pointer, so that you only dereference a handle once. This saves load instructions and allows fur ther optimizations. Casting data types is usually a free operation -- you're just telling the compiler that you know you're copying seemingly incompatible data. But it's not  free if the data types have different bit sizes, which adds conversion instructions. Again, avoid this by using local variables for the commonly casted data.

I've heard many times that branches are "free" on the PowerPC processor. It's true that often the pipeline can keep moving even though a branch is encountered, because the branch execution unit will try to resolve branches very early in the pipeline or will predict the direction of the branch. Still, the more subroutines you have, the less your compiler will be able to reorder and intelligently schedule instructions. Keep speed-critical code together, so that more of it can be pipelined and the compiler can schedule your registers better. Use inline routines for short operations, as I did in the improved version of the first example loop in this column.

KNOWING YOUR PROCESSOR
As with all processors, the PowerPC chip has performance tradeoffs you should know about. Some are processor model specific. For example, the PowerPC 601 has 32K of cache, while the 603 has 16K split evenly into an instruction cache and a data cache. But in general you should know about floating-point performance and the virtues of memory alignment.

Floating-point multiplication is wicked fast -- up to nine times  the speed of integer multiplication. Use floating-point multiplication if you can. Floating-point division takes 17 times as long, so when possible multiply by a reciprocal instead of dividing.

Memory accesses go fastest if addressed on 64-bit memory boundaries. Accesses to unaligned data stall while the processor loads different words and then shifts and splices them. For example, be sure to align floating-point data to 64-bit boundaries, or you'll stall for four cycles while the processor loads 32-bit halves with two 64-bit accesses.

MAKING THE DIFFERENCE
Native PowerPC code runs really fast, so in many cases you don't need to worry about tweaking its performance at all. For your speed-critical code, though, these tips I've given you can make the difference between "too slow" and "fast enough."

RECOMMENDED READING

  • High-Performance Computing  by Kevin Dowd (O'Reilly & Associates, Inc., 1993).
  • High-Performance Computer Architecture  by Harold S. Stone (Addison-Wesley, 1993).
  • PowerPC 601 RISC Microprocessor User's Manual (Motorola, 1993).

DAVE EVANS may be able to tune PowerPC code for Apple, but for the last year he's been repeatedly thwarted when tuning his 1978 Harley-Davidson XLCH motorcycle. Fixing engine stalls, poor timing, and rough starts proved difficult, but he was recently rewarded with the guttural purr of a well-tuned Harley. *

Code examples were compiled with the PPCC compiler using the speed optimization option, and then run on a Power Macintosh 6100/66 for profiling. A PowerPC 601 microsecond timing library is provided on this issue's CD. *

 

Community Search:
MacTech Search:

Software Updates via MacUpdate

Sketch 45 - Design app for UX/UI for iOS...
Sketch is an innovative and fresh look at vector drawing. Its intentionally minimalist design is based upon a drawing space of unlimited size and layers, free of palettes, panels, menus, windows, and... Read more
NeoFinder 7.1 - Catalog your external me...
NeoFinder (formerly CDFinder) rapidly organizes your data, either on external or internal disks, or any other volumes. It catalogs all your data, so you stay in control of your data archive or disk... Read more
TunnelBear 3.0.15 - Subscription-based p...
TunnelBear is a subscription-based virtual private network (VPN) service and companion app, enabling you to browse the internet privately and securely. Features Browse privately - Secure your data... Read more
Hopper Disassembler 4.2.5- - Binary disa...
Hopper Disassembler is a binary disassembler, decompiler, and debugger for 32-bit and 64-bit executables. It will let you disassemble any binary you want, and provide you all the information about... Read more
BetterTouchTool 2.261 - Customize Multi-...
BetterTouchTool adds many new, fully customizable gestures to the Magic Mouse, Multi-Touch MacBook trackpad, and Magic Trackpad. These gestures are customizable: Magic Mouse: Pinch in / out (zoom... Read more
Sketch 44.1 - Design app for UX/UI for i...
Sketch is an innovative and fresh look at vector drawing. Its intentionally minimalist design is based upon a drawing space of unlimited size and layers, free of palettes, panels, menus, windows, and... Read more
BetterTouchTool 2.260 - Customize Multi-...
BetterTouchTool adds many new, fully customizable gestures to the Magic Mouse, Multi-Touch MacBook trackpad, and Magic Trackpad. These gestures are customizable: Magic Mouse: Pinch in / out (zoom... Read more
Chromium 59.0.3071.115 - Fast and stable...
Chromium is an open-source browser project that aims to build a safer, faster, and more stable way for all Internet users to experience the web. Version 59.0.3071.115: This update has no Flash plug... Read more
SyncTwoFolders 2.2.3 - Syncs two user-sp...
SyncTwoFolders simply synchronizes two folders. It supports synchronization across mounted network drives and it is a possibility to run a simulation showing in a log what will be done. Please visit... Read more
Myriad 4.1 - $79.00
Myriad is, simply put, one of the best audio batch processors. Totally redesigned, it looks beautiful and delivers incredible performance. Let Myriad do the heavy lifting while you get back to doing... Read more

Latest Forum Discussions

See All

Missile Cards (Games)
Missile Cards 1.0.9 Device: iOS Universal Category: Games Price: $2.99, Version: 1.0.9 (iTunes) Description: "Missile Command meets Solitaire...only with more doomlasers, death, and explosions." | Read more »
Collect mini assassins in 'Assassin...
Assassin's Creed is traveling back in time to the Spanish Inquisition for its latest mobile entry, Assassin's Creed Rebellion. The game is giving the series a look that's a huge departure from its past design, recreating classic characters in a... | Read more »
Animal Crossing is still coming to mobil...
Animal Crossing is still coming to mobile in 2017, according to aWaypointinterview with Nintendo. Announced in 2016, the game was delayed without a defined release window. However, fans of Nintendo's fantasy slice of life game won't have to wait... | Read more »
Ravenscroft 275 Piano (Music)
Ravenscroft 275 Piano 1.0.0 Device: iOS Universal Category: Music Price: $35.99, Version: 1.0.0 (iTunes) Description: Experience the splendor of a Ravenscroft Grand with the most realistic sounding piano ever created for iOS. Launch... | Read more »
This War of Mine gets a new ending and m...
This War of Mine just got a big new update, featuring free DLC that adds a new ending to the game, among other exciting changes. The update is celebrating the game's two-year release anniversary. Apart from the new ending, which will be quite... | Read more »
Summon eight new heroes in Fire Emblem H...
Nintendo keeps coming at us with Fire Emblem Heroes updates, and it doesn't look like that trend is stopping anytime soon. The folks behind the game have just announced the new War of the Clerics Voting Gauntlet, expected to start next Tuesday. [... | Read more »
The best deals on the App Store this wee...
iOS publishers are pulling out all the stops this week -- there's a huge number of seriously great games at discounted prices this week. Let's not waste any time and get right down to business. [Read more] | Read more »
The House of da Vinci (Games)
The House of da Vinci 1.0.0 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0.0 (iTunes) Description: Enter The House of Da Vinci, a new must-try 3D puzzle adventure game. Solve mechanical puzzles, discover hidden... | Read more »
Solve the disappearance of history’s gre...
Blue Brain Games invites you to indulge in an immersive hands-on 3D puzzle adventure in similar vein to The Room series, with its debut release The House of Da Vinci. Set during the historic period of the Italian Renaissance (when Leonardo himself... | Read more »
Age of Rivals (Games)
Age of Rivals 3.3 Device: iOS Universal Category: Games Price: $.99, Version: 3.3 (iTunes) Description: Deep civilization-building strategy in a fast-paced card game! | Read more »

Price Scanner via MacPrices.net

Clearance 2016 13-inch MacBook Pros available...
B&H Photo has clearance 2016 13″ MacBook Pros in stock today for up to $210 off original MSRP. Shipping is free, and B&H charges NY & NJ sales tax only: - 13″ 2.9GHz/512GB Touch Bar... Read more
Apple Releases iOS 11 Public Beta; How To Get...
The official release of Apple’s latest mobile operating system iOS 11 is vaguely slated for the fall, but as of June 26, ordinary users can download an iOS 11 public beta. To download the iOS 11... Read more
Extend Life of MacBook Pro Retina 2.0TB With...
MacSales.com/Other World Computing has announced availability of the new OWC 2.0TB Aura Pro Solid State Drive for mid-2012 to early 2013 Apple MacBook Pro with Retina display. One of the fastest... Read more
BBEdit SummerFest 2017 Discount Ends Friday,...
You can get 20% off BBEdit for a limited time in Bare Bones Software’s http://www.eastgate.com/Tinderbox/Specials/SummerFest.html?mc_cid=f2101ca260&mc_eid=[UNIQID]SummerFest 2017 sale and... Read more
Use Apple’s Education discount to save up to...
Purchase a new Mac using Apple’s Education discount, and take up to $300 off MSRP. All teachers, students, and staff of any educational institution qualify for the discount. Shipping is free: - 15″ 2... Read more
Clearance 27-inch 3.3GHz 5K iMac available fo...
Amazon clearance 27″ 3.3GHz 5K iMacs (MK482LL/A) available for $1799.90 including free shipping. Their price is $500 off original MSRP, and it’s the lowest price available for this model from any... Read more
13-inch 1.8GHz/256GB MacBook Air on sale for...
B&H Photo has the updated 2017 13″ 1.8GHz/256GB MacBook Air (MQD42LL/A) in stock and on sale for $1129 including free shipping plus NY & NJ tax only. Their price is $70 off MSRP. Read more
27-inch 3.4GHz iMac on sale for $1699, save $...
B&H Photo has the new 2017 27″ 3.4GHz iMac (MNE92LL/A) in stock and on sale for $1699 including free shipping plus NY & NJ sales tax only. Their price is $100 off MSRP. Read more
21-inch 2.3GHz iMac on sale for $1049, save $...
B&H Photo has the new 2017 21″ 2.3GHz iMac (MMQA2LL/A) in stock and on sale for $1049 including free shipping plus NY & NJ tax only. Their price is $50 off MSRP. Read more
ABBYY TextGrabber 6 for iOS Implements Instan...
ABBYY has announced the release of TextGrabber 6.0.0, an important feature update to the company’s productivity app developed for iOS and Android devices. TextGrabber 6.0 now offers Real-Time... Read more

Jobs Board

*Apple* News Product Marketing Mgr., Publish...
…organizational consensus on strategy and vision for publisher tools, authoring, and Apple News Format.Carries this strategy and vision across the organization to Read more
*Apple* Retail - Multiple Positions - Apple,...
Job Description: Sales Specialist - Retail Customer Service and Sales Transform Apple Store visitors into loyal Apple customers. When customers enter the store, Read more
Security Data Analyst - *Apple* Information...
…data sources need to be collected to allow Information Security to better protect Apple employees and customers from a wide range of threats.Act as the subject matter Read more
Lead *Apple* Solutions Consultant - Apple I...
…integrity, and trust.Success Metrics/Key Performance Indicators:Quantitative* Year over Year growth in Apple Product and Beyond the Box sales in the assigned Point of Read more
*Apple* Solutions Consultant till v%u00E5r...
…ethics, integrity, and trust.Success Metrics/Key Performance Indicators:QuantitativeYear over Year growth in Apple Product and Beyond the Box sales in the assigned Point Read more
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.