Intel vs PowerPC Processors - Essay Example

A comparative study of Intel Processing Processor to PowerPC Processing Processor INTRODUCTION: PowerPC is a RISC microprocessor architecture,created by Apple-IBM-Motorola (also known as AIM) alliance in 1991. Originally, PowerPCs were intended for Desktop Personal Computers, these CPUs have become popular in embedded and high-performance applications also. PowerPC was cornerstone of AIM's PReP (PowerPC Reference Platform) and CHRP (Common Hardware Reference Platform) initiatives in 1990s, but the architecture found the most success in the Personal Computer market in Apple's Macintosh lines from 1994 to 2006, before the Apple's transition to Intel. PowerPC is largely based on IBM's earlier POWER architecture, and retains a high level of compatibility with it; the architectures have remained close enough that the same programs and Operating Systems will run on both if some care is taken in preparation; newer chips in the POWER series implement the full PowerPC instruction set. The original POWER microprocessor, one of the first superscalar RISC implementations, was a high performance, multi-chip design. IBM soon realized that they would need a single-chip microprocessor and to eliminate some POWER processor instructions to scale their RS/6000 line from lower-end to high-end machines, and work on a single-chip POWER microprocessor, called the RSC (stands for RISC Single Chip) began. In early 1991 IBM realized that their design could potentially become a high-volume microprocessor used across the industry. IBM approached Apple with the goal of collaborating on the development of a family of single-chip microprocessors based on the POWER architecture. Soon after, Apple, as one of Motorola's largest customers of desktop class microprocessors, asked Motorola o join the discussions because of their long relationship, their more extensive experience with manufacturing high-volume microprocessors than IBM and to serve as a second source for the microprocessors. This three way collaboration became known as AIM alliance, for Apple, IBM, Motorola. In 1991, the PowerPC was just one facet of a larger alliance between these three companies. On the other side was the growing dominance of Microsoft and Windows in personal computing and of Intel processors. At the time, most of the Personal Computer industry was shipping systems based on Intel 80386 and 80486 chips, which had CISC architecture and development of the Pentium Processor was well underway. The PowerPC chips was one of several joint ventures involving the three, in their efforts to counter the growing Microsoft-Intel dominance of personal computing. The PowerPC is designed along RISC principles, and allows for a superscalar implementation. Versions of the design exist in both 32-bit and 64-bit implementations. Starting with the basic POWER specifications, the PowerPC added some features, including: Support for operation in both big-endian and little-endian modes - the PowerPC can switch from one mode to the other at runtime. This feature is not supported in the PowerPC G5. Single-precision forms of some floating point instructions, in addition to only double-precision forms. Additional floating point instructions at the behest of Apple. A complete 64-bit specification, which is backward compatible with the 32-bit mode. Removal of some of the more esoteric POWER instructions, some of which could be emulated by the Operating Systems, if necessary. A paged memory management architecture which is used extensively in server and PC systems. Addition of a new memory management architecture called Book-E, replacing the conventional paged memory management architecture for embedded applications. Book-E is application software compatible with existing PowerPC implementations, but requires minor changes to the Operating Systems. Operating Systems that work on the PowerPC architecture are generally divided into those which are oriented towards general-purpose PowerPC systems, and those oriented towards the embedded PowerPC systems. A 64-bit PowerPC application which does not need 64-bit math runs slightly slower than if it were compiled in 32-bit mode. This is due to the fact that 64-bit pointers and longs consume twice as much memory as their 32-bit counterparts. So the CPU cache will be able to hold fewer data and memory accesses will be more frequent compared to 32-bit compilation modes. This is not true in general as, for example, on the EM64T architecture of Intel, only 8 registers are available in "legacy" 32-bit mode, while 16 are available in the 64-bit mode, an increase which can speed up procedures with large numbers of local variables and cut down memory accesses. Therefore, it is not necessary to run a fully 64-bit operating system on a 64-bit PowerPC system. All of the advantages of the 64-bit architecture can virtually be obtained by using a 64-bit kernel with 32-bit system software. A tiny minority of software requires a 64-bit build, typically those dealing with more than 3 GB of virtual memory or 64-bit integer math. 2. ANALYSIS OF CPU INTENSIVE TESTS: The G5 is touted by Apple is the "World's Fastest Personal Computer." Though the Dual Xeon might not have been fully tested, it edges out the fastest G5. What is interesting is the fact that the dual processor G5 / 2.5 GHz blows away dual processor Xeon 2.4 GHz. In other words, here's two dual processor machines running at about the same clock speed. Yet, the G5 wins. That gives Mac fanatics something to cheer about. PC fanatics can cheer about the fact that there are PCs running at over 3 GHz. 3. HYPERTHREADING: Both the Pentium and Xeon processors had hyper-threading turned on. It's an interesting and effective feature. When running an application, it thinks the Xeon had four processors. And the 3D applications speeds with hyper-threading enabled are as much as approximately 25% faster than when it was disabled. Though the G5 supports multi-threading, it does NOT support hyper-threading. Intel has come out with new "Pentium M" processor, also known as Banians and branded as "Centrino", although this is actually the combination of the chipset, the Pentium M processor and an integrated 802.11b Wi-Fi card. It looks like a 1.6 GHz Pentium M system is roughly equal to a 2.2 GHz Pentium 4-M system. For most people, a dual processor machine will seem faster than a machine with single processor running at twice the speed. That's because most people would be checking e-mail, playing music, etc., i.e., a bunch of things at the same time. People that will be using a program that will consume all the CPU cycles of a processor (for example, Gamers) would benefit from the faster single processor. But, as dual processors are becoming more common, and folks write more games that are multi-threaded, then gamers will start to benefit from multiple processors. A battery of tests was run including various applications. It seems a reasonable range of things to throw at the systems. In any case, when the results were tallied up: 3.06 GHz Pentium 4 with Hyper threading system: total time 150 seconds 1.42 GHz Dual Processor PowerMac System: total time 162 seconds 1.25 GHz Dual Processor PowerMac system: total time 170 seconds 1.0 GHz Dual Processor PowerMac system: total time 225 seconds In a nutshell, a PowerMac G4 Dual Processor 1.42 GHz versus an Intel Pentium 4 Single Processor 3.06 GHz with hyper threading has been pitted. A PowerMac Dual Processor 1.25 and PowerMac 1.0 system were also thrown in. Based on the above, a Dual Processor 1.42 G4 system with 166 FSB and DDR PC 2700 should be roughly equal to a single processor 2.84 GHz Pentium 4 system with 533 FSB and RDRAM PC1066, all else being equal. 150 seconds (3.06 P4) / 162 seconds (Dual Processor 1.42 G4) = about 8% faster overall. The Dual Processor 1.25 G4 system should be about equal to a 2.5 GHz Pentium 4 system. 150 seconds / 170 seconds = about 12% faster. The dual processor 1.25 is actually closer in real performance to about 2.7 GHz Penium 4 (3.06 / 2.7 = 13% faster) Finally, the dual processor 1.0 GHz G4 should be about equal to a 2.0 GHz Pentium 4 (150 seconds / 225 seconds = about 33% faster). The dual processor 1.0 is closer to about a 2.3 Pentium 4 processor (3.06 / 2.3 = 33% faster). 4. CONCLUSION: It can, therefore, be concluded that the Dual Processor G4 systems are at least equal to a double clock-speed single processor Pentium systems, possibly ore at lower speeds. So, if you want to know roughly how the G4 stacks up: For single processor G4s: Add 50% to the clock-speed to get the Pentium 4 equivalence. For dual processor G4s: Double the clock-speed of one of the processors to get the Pentium 4 equivalence. :WORKS CITED: 1. Shanley T. (2006). PowerPC System Architecture, Colorado: Mindshare Inc. Read More