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

Hopper Disassembler 4.3.10- - Binary dis...
Hopper Disassembler is a binary disassembler, decompiler, and debugger for 32- and 64-bit executables. It will let you disassemble any binary you want, and provide you all the information about its... Read more
Hopper Disassembler 4.3.10- - Binary dis...
Hopper Disassembler is a binary disassembler, decompiler, and debugger for 32- and 64-bit executables. It will let you disassemble any binary you want, and provide you all the information about its... Read more
Paparazzi! 1.0b7 - Make user-defined siz...
Paparazzi! is a small utility for OS X that makes screenshots of webpages. This very simple tool takes screenshots of websites which do not fit on one screen. You specify the desired width, minimal... Read more
Amadeus Pro 2.4.4 - Multitrack sound rec...
Amadeus Pro lets you use your Mac for any audio-related task, such as live audio recording, digitizing tapes and records, converting between a variety of sound formats, etc. Thanks to its outstanding... Read more
Google Chrome 63.0.3239.108 - Modern and...
Google Chrome is a Web browser by Google, created to be a modern platform for Web pages and applications. It utilizes very fast loading of Web pages and has a V8 engine, which is a custom built... Read more
Apple Configurator 2.6 - Configure and d...
Apple Configurator makes it easy to deploy iPad, iPhone, iPod touch, and Apple TV devices in your school or business. Use Apple Configurator to quickly configure large numbers of devices connected to... Read more
WhatRoute 2.0.26 - Geographically trace...
WhatRoute is designed to find the names of all the routers an IP packet passes through on its way from your Mac to a destination host. It also measures the round-trip time from your Mac to the router... Read more
Remotix 5.0.4 - Access all your computer...
Remotix is a fast and powerful application to easily access multiple Macs (and PCs) from your own Mac. Features Complete Apple Screen Sharing support - including Mac OS X login, clipboard... Read more
WhatRoute 2.0.26 - Geographically trace...
WhatRoute is designed to find the names of all the routers an IP packet passes through on its way from your Mac to a destination host. It also measures the round-trip time from your Mac to the router... Read more
Google Chrome 63.0.3239.108 - Modern and...
Google Chrome is a Web browser by Google, created to be a modern platform for Web pages and applications. It utilizes very fast loading of Web pages and has a V8 engine, which is a custom built... Read more

Latest Forum Discussions

See All

WWE Mayhem guide - beginner tips and tri...
WWE Mayhem brings all of the familiar faces from your favorite wrestling league to mobile in this exciting new fighting game. Build up a team of your favorite WWE superstars and fight your way to the championship title, or battle against your... | Read more »
The best new games we played this week -...
We've made it through another week, so let's treat ourselves to some of the best new games to launch in the past few days. It was another exciting week with some long-awaited indie games making their debut, and some big console titles making the... | Read more »
Match blocks to pull off dance moves in...
Ferdinand: Unstoppabull is a brand new match three puzzler based on the animated movie of (almost) the same name. As you can expect, you have to match blocks together to complete a bunch of puzzling levels and earn a high score. [Read more] | Read more »
Lineage 2: Revolution’s end of year upda...
Now available in 54 countries worldwide, Lineage 2: Revolution is continuing its global quest to be the most popular mobile MMORPG by launching a jam-packed end of year update. Complete with many subtle tweaks to help improve users’ online... | Read more »
The 5 best Star Wars games on iOS
The time has almost come.Star Wars: The Last Jedifinally hits theaters in the cinematic event that might be bigger than Christmas. To celebrate, we're taking a look at the best--and only the best--Star Warsmobile games to date. [Read more] | Read more »
Life Is Strange (Games)
Life Is Strange 1.1 Device: iOS Universal Category: Games Price: $2.99, Version: 1.1 (iTunes) Description: Life Is Strange is a five part episodic game that sets out to revolutionize story-based choice and consequence games by... | Read more »
Oddworld: New 'n' Tasty (Game...
Oddworld: New 'n' Tasty 1.0 Device: iOS Universal Category: Games Price: $7.99, Version: 1.0 (iTunes) Description: ** PLEASE NOTE: Requires 3.6GB free space to install. Runs at variable resolutions based on device capabilities.... | Read more »
Gorogoa (Games)
Gorogoa 1.0 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0 (iTunes) Description: Gorogoa is an elegant evolution of the puzzle genre, told through a beautifully hand-drawn story designed and illustrated by Jason... | Read more »
Why Guns of Boom will be big for mobile...
Earlier this week, Game Insight, the minds that brought you Guns of Boom, revealed plans for an esports mode in the popular FPS title, with big implications for the game's future. Guns of Boom has been quite popular for some time now, so it's... | Read more »
The best mobile games to play on lazy ho...
With the holidays in full swing, there's hopefully going to be a lot of time off work lazing around the house. With all of that free time, it's a perfect opportunity to catch up on some mobile games that you might have missed out on earlier this... | Read more »

Price Scanner via MacPrices.net

The lowest prices on Apple 13″ MacBook Pros t...
Save $300-$300 on the purchase of a 2017 13″ MacBook Pro this weekend with Certified Refurbished models at Apple. In many cases, Apple’s refurbished prices are the lowest available for each model... Read more
Lowest prices of the Holiday season: 15″ Appl...
Save $360-$420 on the purchase of a 2017 15″ MacBook Pro with Certified Refurbished models at Apple. In many cases, Apple’s refurbished prices are the lowest available for each model from any... Read more
Apple discounts Beats products by up to 30% t...
Apple has Beats by Dr. Dre (BeatsX, Powerbeats3 Wireless, and Beats Solo3 Wireless) on sale for up to 30% off their retail price from now until December 26th: – BeatsX: Was $149.95, now $99 –... Read more
Updated Price Trackers: Macs, iPads, iPhones,...
Scan our Apple Price Trackers for the latest information on sales, bundles, and availability on systems from Apple’s authorized internet/catalog resellers. We update the trackers continuously: – 15″... Read more
How to preorder a new iMac Pro and pay zero s...
B&H Photo and Adorama are accepting preorders on multiple configurations of the new Apple iMac Pro. Both resellers charge sales tax for residents of NY & NJ only, and shipping is free.... Read more
Apple Macs back in stock at Amazon with model...
Amazon has MacBook Pros, MacBook Airs, MacBooks, and iMacs on sale for up to $200 off MSRP as part of their Holiday/Christmas sale. Shipping is free. Note that stock of some Macs may come and go (and... Read more
Apple offering free overnight delivery on all...
Apple is now offering free overnight delivery on all in stock products until 3pm local time on December 22nd. This includes new as well as refurbished computers. Click here for more information. Read more
Beats Holiday sale at B&H, headphones and...
B&H Photo has Beats by Dr. Dre headphones, earphones, and speakers on sale for up to $80 off MSRP as part of their Holiday sale. Expedited shipping is free, and B&H charges sales tax to NY... Read more
Holiday sale: Apple resellers offer 2017 15″...
MacMall has 15″ MacBook Pros on sale for $220-$300 off MSRP, each including free shipping: – 15″ 2.8GHz MacBook Pro Space Gray (MPTR2LL/A): $2179, $220 off MSRP – 15″ 2.8GHz MacBook Pro Silver (... Read more
Holiday sale: Apple resellers offer 13″ MacBo...
B&H Photo has 13″ MacBook Pros on sale for up to $150 off MSRP. Shipping is free, and B&H charges sales tax for NY & NJ residents only: – 13-inch 2.3GHz/128GB Space Gray MacBook Pro (... Read more

Jobs Board

*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
*Apple* Retail - Multiple Positions - Apple,...
Job Description:SalesSpecialist - Retail Customer Service and SalesTransform Apple Store visitors into loyal Apple customers. When customers enter the store, 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
*Apple* Retail - Multiple Positions - Apple,...
Job Description:SalesSpecialist - Retail Customer Service and SalesTransform Apple Store visitors into loyal Apple customers. When customers enter the store, 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
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.