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

Paragraphs 1.0.1 - Writing tool just for...
Paragraphs is an app just for writers. It was built for one thing and one thing only: writing. It gives you everything you need to create brilliant prose and does away with the rest. Everything in... Read more
BlueStacks App Player 0.9.21 - Run Andro...
BlueStacks App Player lets you run your Android apps fast and fullscreen on your Mac. Version 0.9.21: Note: Now requires OS X 10.8 or later running on a 64-bit Intel processor. Initial stable... Read more
Apple iTunes 12.2 - Play Apple Music...
Apple iTunes lets you organize and stream Apple Music, download and watch video and listen to Podcasts. It can automatically download new music, app, and book purchases across all your devices and... Read more
Apple Security Update 2015-005 - For OS...
Apple Security Update 2015-005 is recommended for all users and improves the security of OS X. For detailed information about the security content of this update, please visit: http://support.apple.... Read more
Apple HP Printer Drivers 3.1 - For OS X...
Apple HP Printer Drivers includes the latest HP printing and scanning software for OS X Lion or later. For information about supported printer models, see this page. Version 3.1: The latest printing... Read more
Epson Printer Drivers 3.1 - For OS X 10....
Epson Printer Drivers installs the latest software for your EPSON printer or scanner for OS X Yosemite, OS X Mavericks, OS X Mountain Lion, and OS X Lion. For more information about printing and... Read more
Xcode 6.4 - Integrated development envir...
Xcode provides everything developers need to create great applications for Mac, iPhone, and iPad. Xcode brings user interface design, coding, testing, and debugging into a united workflow. The Xcode... Read more
OS X Yosemite 10.10.4 - Apple's lat...
OS X Yosemite is Apple's newest operating system for Mac. An elegant design that feels entirely fresh, yet inherently familiar. The apps you use every day, enhanced with new features. And a... Read more
Dash 3.0.2 - Instant search and offline...
Dash is an API Documentation Browser and Code Snippet Manager. Dash helps you store snippets of code, as well as instantly search and browse documentation for almost any API you might use (for a full... Read more
FontExplorer X Pro 5.0 - Font management...
FontExplorer X Pro is optimized for professional use; it's the solution that gives you the power you need to manage all your fonts. Now you can more easily manage, activate and organize your... Read more

Heroki (Games)
Heroki 1.0 Device: iOS Universal Category: Games Price: $7.99, Version: 1.0 (iTunes) Description: CLEAR THE SKIES FOR A NEW HERO!The peaceful sky village of Levantia is in danger! The dastardly Dr. N. Forchin and his accomplice,... | Read more »
Hands-On With Raceline CC
Set for release soon, Rebellion’s motorbike racing game, Raceline CC certainly looks stylish. But how does it play? I got my hands on a preview build to answer exactly that. | Read more »
Siegefall - Tips, Tricks, and Strategies...
So, you fancy establishing a base and ruling the world again. Siegefall is a convenient place to do that, but how about some great tips and tricks on how best to go about it? Here are a few ideas on how to get ahead as a beginner to this medieval... | Read more »
The WWE Comes to Racing Rivals - Because...
Racing Rivals is a racing game that's all about, well, rivalry. And who knows rivalry better than WWE superstars (shhhh, that was rhetorical)? [Read more] | Read more »
Hey, Who Put Apple Music in My SoundHoun...
One of the App Store's popular music discovery sources - SoundHound - has already been updated to include Apple's own music discovery source - Apple Music. That was fast! [Read more] | Read more »
Arcane Legends has a New Expansion Calle...
Arcane Legends has been going strong since it debuted at the tail end of 2012. So well, in fact, that it's already up to its sixth expansion. [Read more] | Read more »
Vector 2 is Officially a Thing and it...
Vector is a pretty cool parkour-driven runner that's gotten a pretty decent following since it first came out - although personally I think more people could stand to show it some love. Anyway, Nekki has announced that a sequel isofficially on its... | Read more »
Get Ready to Trucksform and Roll Out (an...
It looks like NuOxygen is bringing the truck-transforming racer Trucksform (get it?) to iOS in a couple of weeks. Although really it's more of an auto-driver than a racer. But still, transforming trucks! [Read more] | Read more »
This Week at 148Apps:June 22-26, 2015
June's Summer Journey Continues With 148Apps How do you know what apps are worth your time and money? Just look to the review team at 148Apps. We sort through the chaos and find the apps you're looking for. The ones we love become Editor’s Choice,... | Read more »
LEGO® Minifigures Online (Games)
LEGO® Minifigures Online 1.0.1 Device: iOS iPhone Category: Games Price: $4.99, Version: 1.0.1 (iTunes) Description: | Read more »

Price Scanner via MacPrices.net

Logo Pop Free Vector Logo Design App For OS X...
128bit Technologies has released of Logo Pop Free 1.2 for Mac OS X, a vector based, full-fledged, logo design app available exclusively on the Mac App Store for the agreeable price of absolutely free... Read more
21-inch 1.4GHz iMac on sale for $999, save $1...
B&H Photo has new 21″ 1.4GHz iMac on sale for $999 including free shipping plus NY sales tax only. Their price is $100 off MSRP. Best Buy has the 21″ 1.4GHz iMac on sale for $999.99 on their... Read more
16GB iPad mini 3 on sale for $339, save $60
B&H Photo has the 16GB iPad mini 3 WiFi on sale for $339 including free shipping plus NY tax only. Their price is $60 off MSRP. Read more
Save up to $40 on iPad Air 2, NY tax only, fr...
B&H Photo has iPad Air 2s on sale for up to $40 off MSRP including free shipping plus NY sales tax only: - 16GB iPad Air 2 WiFi: $489 $10 off - 64GB iPad Air 2 WiFi: $559 $40 off - 128GB iPad Air... Read more
Apple Releases OS X 10.10.4 With WIFi Fix, iO...
On Tuesday, Apple released final versions of OS X 10.10.4 and iOS 8.4, as well as updates for the Safari browser for OS X Yosemite, Mavericks, and Mountain Lion. The OS X 10.10.4 update focuses on... Read more
Dual-Band High-Gain Antennas for Home Wi-Fi N...
Linksys has announced what it claims are the first dual-band, omni-directional high-gain antennas for the consumer market. The new Linksys high-gain antennas available in a 2- and 4-pack (WRT004ANT... Read more
Apple refurbished 2014 15-inch Retina MacBook...
The Apple Store has Apple Certified Refurbished 2014 15″ 2.2GHz Retina MacBook Pros available for $1609, $390 off original MSRP. Apple’s one-year warranty is included, and shipping is free. They have... Read more
Clearance 2014 MacBook Airs available for up...
Adorama has 2014 MacBook Airs on sale for up to $301 off original MSRP including NY + NJ sales tax and free shipping: - 11″ 256GB MacBook Air: $798 $301 off original MSRP - 13″ 128GB MacBook Air: $... Read more
5K iMacs on sale for $100 off MSRP, free ship...
B&H Photo has the new 27″ 3.3GHz 5K iMac on sale for $1899.99 including free shipping plus NY tax only. Their price is $100 off MSRP. They have the 27″ 3.5GHz 5K iMac on sale for $2199, also $100... Read more
27-inch 3.2GHz iMac on sale for $1679, save $...
B&H Photo has the 27″ 3.2GHz iMac on sale for $1679.99 including free shipping plus NY sales tax only. Their price is $120 off MSRP. Read more

Jobs Board

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
Project Manager - *Apple* Pay Security - Ap...
**Job Summary** The Apple Pay Security team is seeking a highly organized, results-driven Project Manager to drive the development of Apple Pay Security. If you are Read more
Web Developer, *Apple* Online Store Innovat...
**Job Summary** The Apple Online Store Innovation Lab team is seeking a talented individual with strong web development and design skills to prototype future Apple Read more
*Apple* TV Live Streaming Frameworks Test En...
**Job Summary** Work and contribute towards the engineering of Apple 's state-of-the-art products involving video, audio, and graphics in Interactive Media Group (IMG) at Read more
Project Manager, WW *Apple* Fulfillment Ope...
…a senior project manager / business analyst to work within our Worldwide Apple Fulfillment Operations and the Business Process Re-engineering team. This role will work Read more
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.