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

Airmail 3.2.9 - Powerful, minimal email...
Airmail is an mail client with fast performance and intuitive interaction. Support for iCloud, MS Exchange, Gmail, Google Apps, IMAP, POP3, Yahoo!, AOL, Outlook.com, Live.com. Airmail was designed... Read more
Microsoft Remote Desktop 8.0.39 - Connec...
With Microsoft Remote Desktop, you can connect to a remote PC and your work resources from almost anywhere. Experience the power of Windows with RemoteFX in a Remote Desktop client designed to help... Read more
Posterino 3.3.7 - Create posters, collag...
Posterino offers enhanced customization and flexibility including a variety of new, stylish templates featuring grids of identical or odd-sized image boxes. You can customize the size and shape of... Read more
Airmail 3.2.8 - Powerful, minimal email...
Airmail is an mail client with fast performance and intuitive interaction. Support for iCloud, MS Exchange, Gmail, Google Apps, IMAP, POP3, Yahoo!, AOL, Outlook.com, Live.com. Airmail was designed... Read more
WhatRoute 2.0.21 - 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
Airmail 3.2.8 - Powerful, minimal email...
Airmail is an mail client with fast performance and intuitive interaction. Support for iCloud, MS Exchange, Gmail, Google Apps, IMAP, POP3, Yahoo!, AOL, Outlook.com, Live.com. Airmail was designed... Read more
WhatRoute 2.0.21 - 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
iFFmpeg 6.3.5 - Convert multimedia files...
iFFmpeg is a comprehensive media tool to convert movie, audio and media files between formats. The FFmpeg command line instructions can be very hard to master/understand, so iFFmpeg does all the hard... Read more
Opera 45.0.2552.812 - High-performance W...
Opera is a fast and secure browser trusted by millions of users. With the intuitive interface, Speed Dial and visual bookmarks for organizing favorite sites, news feature with fresh, relevant content... Read more
Microsoft Office 2016 15.34 - Popular pr...
Microsoft Office 2016 - Unmistakably Office, designed for Mac. The new versions of Word, Excel, PowerPoint, Outlook and OneNote provide the best of both worlds for Mac users - the familiar Office... Read more

Latest Forum Discussions

See All

Honor 8 Pro, a great choice for gamers
Honor is making strides to bring its brand to the forefront of mobile gaming with its latest phone, the Honor 8 Pro. The Pro sets itself apart from its predecessor, the Honor 8, with a host of premium updates that boost the device’s graphical and... | Read more »
The 4 best outdoor adventure apps
Now that we're well into the pleasant, warmer months, it's time to start making the most of the great outdoors. Spring and summer are ideal times for a bit of trekking or exploration. You don't have to go it alone, though. There are plenty of... | Read more »
Things 3 (Productivity)
Things 3 3.0.1 Device: iOS iPhone Category: Productivity Price: $7.99, Version: 3.0.1 (iTunes) Description: Meet the all-new Things! A complete rethinking of the original, award-winning task manager – with a perfect balance between... | Read more »
Oddball mash-up Arkanoid vs Space Invade...
In a move no one was really expecting, Square Enix has put forth an Arkanoid/Space Invaders mash-up aptly titled Arkanoid vs Space Invaders. The game launched today on both iOS and Android and the reviews are actually quite good. [Read more] | Read more »
Arkanoid vs Space Invaders (Games)
Arkanoid vs Space Invaders 1.0 Device: iOS Universal Category: Games Price: $3.99, Version: 1.0 (iTunes) Description: LAUNCH SALE: GET THE GAME AT 20% OFF! Two of the most iconic classic games ever made meet in Arkanoid vs Space... | Read more »
The best new games we played this week
Things got off to a bit of a slow start this week, but as we steadily creep towards Friday a bunch of great games have started cropping up. If you're looking for a quality new release to play this weekend, we've got you covered. Here's a handy... | Read more »
No Stick Shooter (Games)
No Stick Shooter 1.0 Device: iOS Universal Category: Games Price: $1.99, Version: 1.0 (iTunes) Description: Happy Robot presents a fresh take on the classic retro-arcade shooters we all know and love. Featuring 30 levels of non-stop... | Read more »
Chroma Squad (Games)
Chroma Squad 1.0.85 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0.85 (iTunes) Description: | Read more »
Old Man's Journey (Games)
Old Man's Journey 1.0 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0 (iTunes) Description: A heartfelt game about life, loss and hope. Old Man’s Journey is a soul-searching puzzle adventure game about life’s... | Read more »
Beholder (Games)
Beholder 1.0 Device: iOS Universal Category: Games Price: $4.99, Version: 1.0 (iTunes) Description: Welcome to a grim dystopian future. "Beholder is stressful on a moral level, but as a game, it’s simple and entertaining" - Game... | Read more »

Price Scanner via MacPrices.net

Five To Six Million 10.5-inch iPad Pro Tablet...
Digitimes’ Siu Han and Joseph Tsai report that upstream supply chain shipments for Apple’s new 10.5-inch iPad Pro have been increasing, with monthly shipment volume expected to hit 600,000 units by... Read more
Georgia Tech Students Win Toyota and Net Impa...
Earlier this year, a team of students at Georgia Tech realized that there was a critical gap in transportation services for people who use wheelchairs, and wondered if the solution could be in the... Read more
13-inch 2.0GHz Space Gray MacBook Pro on sale...
Amazon has the 13″ 2.0GHz Space Gray non-Touch Bar MacBook Pro (MLL42LL/A) on sale for $1299.99 including free shipping. Their price is $200 off MSRP, and it’s currently the lowest price available... Read more
Roundup of 15-inch MacBook Pro sale prices, m...
B&H Photo has the new 2016 15″ Apple Touch Bar MacBook Pros in stock today and on sale for up to $200 off MSRP. Shipping is free, and B&H charges NY & NJ sales tax only: - 15″ 2.7GHz... Read more
15-inch 2.2GHz Retina MacBook Pro on sale for...
B&H Photo has the 2015 15″ 2.2GHz Retina MacBook Pro (MJLQ2LL/A) on sale for $1849 including free shipping plus NY & NJ sales tax only. Their price is $150 off MSRP. Read more
21-inch iMacs on sale for $100 off MSRP, save...
B&H Photo has 21″ iMacs on sale for $100 off MSRP, each including free shipping plus NY & NJ sales tax only: - 21″ 3.1GHz iMac 4K: $1399.99 $100 off MSRP - 21″ 2.8GHz iMac: $1199.99 $100 off... Read more
Groupon Survey Finds Families Will Spend One-...
With warmer weather finally arriving in most parts of the country and the school year winding down to a close, Groupon (http://www.groupon.com) asked 1,000 U.S. parents how much time their families... Read more
Panasonic Anounces Toughbook 33 2-in-1 Rugged...
Panasonic has announced the U.S. availability of the Panasonic Toughbook 33, claimed to be the first fully-rugged 2-in-1 detachable laptop that features a 3:2 display. Inspired by the hard-working... Read more
9-inch 32GB iPad Pros available for up to $10...
Amazon resellers are offering new 9″ 32GB iPad Pros for up to $101 off MSRP, starting at $498, including free shipping. Colors may be Space Gray, Silver, Gold, or Rose Gold, depending on the reseller... Read more
Back in stock: Apple refurbished Mac minis st...
Apple has Certified Refurbished Mac minis available starting at $419. Apple’s one-year warranty is included with each mini, and shipping is free: - 1.4GHz Mac mini: $419 $80 off MSRP - 2.6GHz Mac... Read more

Jobs Board

Director, *Apple* Program - ERP & Cloud...
…make a real difference. Come, shine with us! Astellas is announcing a Director, Apple Program - ERP & Cloud Platform Architecture Lead opportunity in Northbrook, IL. Read more
*Apple* Mobile Master - Best Buy (United Sta...
**508102BR** **Job Title:** Apple Mobile Master **Location Number:** 000511-Athens-Store **Job Description:** **What does a Best Buy Apple Mobile Master do?** At Read more
*Apple* Media Products - Commerce Engineerin...
Apple Media Products - Commerce Engineering Manager Job Number: 57037480 Santa Clara Valley, California, United States Posted: Apr. 18, 2017 Weekly Hours: 40.00 Job Read more
Geek Squad *Apple* Master Consultation Agen...
**500444BR** **Job Title:** Geek Squad Apple Master Consultation Agent **Location Number:** 000103-City Of Industry-Store **Job Description:** **What does a Geek Read more
Security Engineer, *Apple* Retail - Apple I...
Changing the world is all in a day's work at Apple . If you love innovation, here's your chance to make a career of it. You'll work hard. But the job comes with more Read more
All contents are Copyright 1984-2011 by Xplain Corporation. All rights reserved. Theme designed by Icreon.