hardware news

FX 8150, aka Bulldozer, the new 8-core processor from AMD

2011-11-06T03:10:00.000-08:00

1_Introduction

Five years after the advent of its first Phenom Stars using the architecture, AMD is preparing to upgrade its offer for x86 processors. Of course, we did have along the way a revision of the Stars architecture with the arrival of Phenom II, but nothing fundamentally new and especially nothing that can not challenge the dominance of Intel ultra-niche on the performance in particular.

In this season, and not without some delay, AMD finally launches its new architecture by the name of code Bulldozer. AMD and to revive the brand for the occasion FX, as the first processor architecture using Bulldozer FX are baptized, a name that will remind many memories for fans of Athlon 64. But if at the time the Athlon FX processors were simple heart, the new FX offers us in the late 2011 AMD models are 8-core, no less!

The return of the FX brand is it synonymous with performance feedback? How to position the new FX processors face the current supply of Intel? These questions will be answered in the following pages.

2_Bulldozer architecture: space for modules

2.1_Architecture made of modules revisited

With Phenom and Phenom II, AMD K10 architecture we proposed, codenamed Stars. Relatively effective in certain areas, but it struggled to stand comparison with the offer from Intel. The gap condition became even more acute since the appearance of Sandy Bridge processors, the famous second-generation Core. The arrival of the first real sign Bulldozer new micro-architecture from AMD Phenom or even be ahead. Some would argue, in fact, that architecture is a derivative of K10 K8 Athlon 64 ... We will not go into these debates preferring to take you on an overview of the features of this architecture.

Among the objectives of AMD in the development of Bulldozer there are energy efficiency, modularity of the architecture or the fact to support the operating frequencies to the effectiveness of the architecture, a rather risky gamble we shall see.

The big news of the Bulldozer architecture is above all the CMT (Cluster Multithreading). This is an approach quite interesting and rather different from what we usually see, especially at Intel where the SMT (Simultaneous Multithreading) reigns supreme. With Bulldozer, AMD challenges, in a sense, the notion of heart run x86. One of the basic concepts of Bulldozer is in fact what AMD calls a module. Bulldozer is a module consists of two execution cores x86. Two true hearts? Not quite ... Our two hearts will indeed share a number of resources as the party responsible for data fetch (ie they are loaded), but also the instruction decoding unit or the one in charge of the calculations on floating. The second level cache is shared between both cores of the same module which here is clearly the element the least innovative.

Concept module Bulldozer

But why share units between our hearts in a single module rather than duplicating? The reason is simple: save transistors course and therefore the die area, but also optimize the consumption of the processor. Typically, it is recognized that in the x86 unit in charge of decoding is quite voracious energy. The shared between two cores to optimize parameters such energy. More pragmatically, other units are rarely sought or continuously at full capacity. This is particularly true of the unit dedicated to calculations on floating-point numbers. In fact, the pool between two hearts is actually quite relevant since it is then truly sought. Each module Bulldozer therefore has two cores and two threads can run simultaneously.

Note flexibility induced by this operation: if one thread is running within the module, it has access to all shared resources. To this is added a certain fluidity modularity for AMD. The smelter will feature the launch of variants 6 and 8 core processors of its FX: in the first case the processor will consist of three modules Bulldozer in the second it will carry a total of four modules. Furthermore this design is supposed to a rise in frequency facilitated in accordance with the objectives stated above. We remember that the material AMD had some difficulties in recent years.

The hearts of 8 FX 8150 seen by Windows

2.2_Beyond the modules!

The modules are not the only new Bulldozer architecture, far from it. Thus, the front-end is also changing. This block, which ensures the constant supply of instruction execution units, is now shared between the cores of the same module. It has therefore been revised accordingly to ensure a sustained throughput. Here AMD's engineers have focused most of their attention on the management of connections. Recall that a connection is nothing more than a jump in the code. Clearly we move from one end to another code if a condition is and the idea is to provide connections to speed prefetching or data necessary for the successful continuation of the code.

Thus, the prediction pipelines and power are now decoupled while AMD introduced a number of mechanisms well known ... Intel. There are, collage, management of direct and indirect branches with a buffer at two levels, the loop detection or the presence of a trace cache to store, as on Nehalem micro-instructions already decoded. On the decoding unit dedicated to this function can handle up to four Bulldozer instructions per cycle, against the previous three Phenom.

Following on Clubic.com: FX 8150, aka Bulldozer, the new 8-core processor from AMD: Architecture Bulldozer: up to modules

Computer and high tech

Focus on front-end

As for the cache, the Bulldozer module has 64 KB of memory for first-level instructions running on two routes: it is shared between the cores. Each heart also embeds its own first-level cache with 16 KB for data. By L1D cache is 4-way associative. Question performance, this cache is supposed to have been optimized with, among others, the development of techniques to predict the location of the path of the requested data in the cache.

By the way the arrival of a fusion solution. Like Intel (definitely!) Bulldozer is capable of decoding multiple instructions in a single statement: AMD is called fusion branch.

3_ An architecture that has the heart, head for the DDR3 1866

3.1_ Focus on the hearts!

Du Côté des Cœurs d'Exécution de 86 Every module de Bulldozer, le pipeline de l'ONU Retrouvé à 4 Étages (Contre 3 précédemment). Il Est découpé AVEC UN Côté d'ALU ous Deux Unités d'Exécution Arithmétiques et Logiques et 2 AGU ous Unités de Génération d'adresses. Par rapport un Phenom n'avez le pipeline de 3 Étages etait Composé de Trois ALU, Un Cœur d'Exécution Bulldozer NE may donc executer les instructions entières Qué Deux cycle d'horloge nominale Contre 3 versez Un Cœur Phenom. C'EST UN désavantage Théorique Qui ne Tien Pas du Compte seconde Cœur d'Exécution et Qui ne Considère Pas l'aspect Consommation énergétique. Rappelons qu'un module de Bulldozer AVEC SES Deux Cœurs d'Exécution HNE cense être de Nettement Moins vorace Qué Deux Cœurs Phenom.

En Ce Qui Concerne Le Registre, celui-ci Profite D'Une improvement with significative l'Arrivée d'un PRF. Là Encore l'architecture de Sandy Bridge Intel BNO d'une recemment familiarise with this notion. Le PRF HNE UNE Sorte d'index Qui RELIE les Registres nominale Utilise le moteur d'Exécution out-of-commander un Chaleurs entrées de Dans la mémoire tampon. L'Avantage Premier HNE ici de Stocker des entrées de taille supérieure.

Nos Deux Cœurs d'Exécution soi partagent UNE unité centrale chargée des Opérations en 128 bits. Ladite unit HNE composee de deux de canalisations de 128 bits peuvent être de Qui Combinés fr UNE Seule unit 256 bits, y reviendrons BNO. De Type FMAC les pipelines en question peuvent éffectuer fr UNE Seule passe des Opérations de multiplication et d'addition sur des Nombres à virgule flottante et sans CE Aucun arrondi Durant le Calcul versez Précision UNE Maximale. Une Fois unifiées en 256 bits, CES Deux Unités peuvent traiter les instructions Alors AVX Au Rythme D'Une instruction de cycle d'horloge nominale. Le passage à l'ONU PRF Evoque, plus haut HNE of course justifié par L'arrivée de la charge de prix en AVX.

FPU shared core Bulldozer

Since we mentioned the instructions, it's good to add that the management of AVX, AMD adds support SSE instructions SSE 4.1 and 4.2. As if this were not enough, it also adds its own poetically named XOP instructions and not to mention the FMA4 CVT16. These are instructions for completing the AVX and SSE5 from the project a time announced by AMD but never materialized. The FMA4 (Fuse multiply add) is an instruction that stores the result of an operation in a register after performing additional in a single cycle multiplication and addition. Intel uses for its part FMA3 one where the result of said operation is placed in a register previously used. In this regard, the successor to Bulldozer will FMA3, joining the Intel camp. These instructions could make significant gains in high performance applications (applications of computing, scientific, etc.). Only now it's a safe bet that the compilers do not benefit, especially if AMD has already announced that abandoned in the future for FMA4 FMA3 ...

Instructions supported by Bulldozer

Note finally the management of AES for everything related to hardware acceleration related to encryption and decryption operations using the standard of the same name.

What about memory?

We mentioned a little earlier arrangement of the first-level caches. Of course, the Bulldozer architecture not only of this single level cache. So AMD has a second level cache type associations. Arranged on 16 channels, it is shared between the cores and size rises to 2 MB per module then.

A third level of cache is also planned with a maximum of 8 MB shared between all the modules making up the processor. Always voluntary, the L3 cache has 64 tracks. The third level of cache is not inclusive and includes all the data ejected from the L2 cache. In total, therefore, an FX processor architecture Bulldozer can have DE16 MB cache! It is not nothing. As for the latency of caches we found 3 cycles for the L1, L2 for 18, which is very good and 65 for the L3. As feared the latter value is quite high. This is more so a Core of a second-generation latency L3 cache is 57 cycles

Beyond the caches, the Bulldozer architecture integrates the memory controller of course. It was right here in a DDR3 memory controller type dual channel, each channel being interfaced with 8 bits of 64 bits for error correction. The controller supports relatively high frequencies. Thus, with two bars can be installed in the DDR3-1866 on its operating system in practice to 933 MHz. Attention, with four bars it necessarily falls to 800 MHz maximum frequency or the DDR3-1600. AMD also points to support a supply voltage of 1.25 volts for DDR3.

DDR3-1866 and FX 8150

Mini DisplayPort Cables / HDMI declared illegal

2011-07-12T04:04:00.000-07:00

HDMI Org, the organization guarantees the standard of the same name, wants the cables to convert Mini DisplayPort to HDMI port being withdrawn from sale because they are not licensed and therefore illegal, a new evil that threatens to some firms.

"The HDMI specification defines an HDMI cable only to have HDMI connectors at both ends. Everything else is not a licensed use of the specification and is therefore not allowed, "says HDMI Org in a statement that explains that, since the cables Mini DisplayPort / HDMI male / male have never been tested and licensed, they are illegal and should be removed from the market.

For their part, the cables offer a DisplayPort socket on one side and an HDMI socket on the other are allowed to the extent that it is possible to connect an HDMI cable terminated it.

This new risk of a blow to companies like Apple or Toshiba that use this type of cable on their products. HDMI Org "recognizes that there may be a need in the market for this type of product. However, for the moment, there is no way to produce its cables in a lawful manner. "Let us hope that the brands that use this cable will try to launch a test phase to legalize it.

More on Clubic.com: Mini DisplayPort Cables / HDMI declared illegal
IT and high tech

Consumption, Overclocking and Conclusion

2011-03-28T00:32:00.000-07:00

Consumption

We naturally seek to verify the power consumption of different processors that folder. For this we use a power meter that is the consumption of the entire machine, ie directly in the decision. We proceed in two steps: a break, one in charge with Prime 95.

At rest the consumption of our processor requires no special comment. Two processors out of the lot, however: the Core i7 2600K with a consumption system within 120 Watts and the Phenom II X6 1100T with the same consumption. Under load, the story is different: the Core i7 system 990x peaked at over 330 watts or a few extra watts against the Core i7 980X. Nevertheless, in charge of the Phenom II X6 1100T is less greedy ... as the Core i7 2600K!

Overclocking

Unable to close the test let alone overclocking. That side, we were pleasantly surprised. Not only did we reach 4 GHz in a jiffy, but we managed to reach 4.2 and 4.4 GHz without any problems and stably. We have suddenly found our ambitions for reach 5 GHz. Goal succeeded because we've run the Core i7 990x to 5 GHz with 167 MHz system bus and a coefficient to 30x. If the system starts smoothly we had to manually adjust some tension so that Windows 7 will not load completely blue screen (or black). No way, however, achieve a stable 5.4 GHz ... despite several attempts!

Various tests including an overclocking at 5 GHz

Conclusion

Delayed many times, then finally launched in haste, the Core i7 990x is the absolute fastest Intel processors, no doubt about that. It is also a good way for Intel to erase an image somewhat tarnished with the case of the bug Sandy Bridge.

While the new platform Intel Socket LGA-1155 has the ignition delay - the fault of a bug found in chipsets Series 6 after marketing - Intel seems to prolong the life of his high-end platform in LGA-1366. It was believed the Socket LGA 1366 and sentenced there in truth this stimulus Intel platform by giving it life ... Beyond the launch of Core i7 990x, the arrival in several motherboard manufacturers new references based on the chipset X58 is a sign that does not disappoint! Even Intel is ready to play by giving her offspring with the Smackover DX58SO2.

Returning briefly to the Core i7 990x: if it is the fastest processor at the time, Intel does not force his talent as this new standard is a mere speed-bump. Without a new revision of the die, it merely an increase of 133 MHz nominal frequency is not very long but it can occupy the land by the release of new chips AMD Bulldozer. As for the first hexa-core processors based on Intel's Sandy Bridge architecture, their output would have been postponed to the latest news ... this may be explaining this. We find still in our tests for the game, the second generation Core processors (ie the Sandy Bridge) are better than the new Core i7 990x.

A final word on the price of the Core i7 990x, indecent necessarily a price: it will cost a little less than 1000 euros to acquire the beast. But this newcomer is still a merit: it is mechanically cut the price of Core i7 970 and 960 and in significant proportions! It may ultimately be her only interest?

Les performances : Tests jeux - 3/3

2011-03-28T00:11:00.000-07:00

Call Of Duty 4 v1.7 - 1024x768x32

Sous Call Of Duty 4, le plus rapide des processeurs est le Core i7 2600K. Le Core i7 990X termine second avec des performances 1% supérieures face au Core i7 980X. Face au Phenom II X6 1100T, le gain de performances pour le Core i7 990X est de l'ordre de 23%.

Crysis Warhead v1.1 - 1024x768x32 - Réglages Mainstream - x64/DX10

Same observation in Crysis where the Core i7 2600K dominates. However, the advantage is much smaller face to the Core i7 990x. The latter is ahead by a hair's Core i7 980X while all of our Core processors, with performance very close. Facing the fastest Phenom II, the Core i7 990x is 31% faster.

Far Cry 2 - v1.03

The Core i7 2600K is still the fastest performance here with 9% higher against the Core i7 990x. The latter delivers similar performance to the Core i7 980X. Remains impressive gap between Core and Phenom i7 II, about 37% if you consider the Core i7 990x and 50% with the Core i7 2600K.

Enemy Territory Quake Wars - v1.5 - 1024x768x32

We close our series of tests with Quake Wars, which propels the Core i7 990x in front, the Core i7 2600K. Faced with the Core i7 980X, the newcomer is 2% faster. And of course, facing the Phenom II X6 1100T, the gap is indecent: 58% more performance for Intel.

Performance: application testing - 2 / 3

2011-03-27T23:47:00.000-07:00

Cinebench 11.5

Cinebench evaluates the performance of our processor by performing the rendering of a 3D scene. The six execution cores of our Core i7 990x propel the top of the standings with performances almost 4% higher than the Core i7 980X. Faced with the Core i7 2600K, the fastest processors Sandy Bridge, the Core i7 990x is 34% faster. The delta front of the Phenom II X6 1100T, yet it also has six cores running, climbing to 56%.

Adobe Photoshop CS4

We measure time in Photoshop CS4 necessary to implement a filter on a high resolution TIF image. The results are expressed in seconds, the reading of the chart is reversed. In mind, we find the Core i7 2600K, followed by a second near the Core i7 990x. The gain against the Core i7 980X is not clear, but face the Phenom, Core i7 is outrageously in mind.

File compression - WinRAR 3.92 x64

Performance: Synthetic Tests - 1 / 3

2011-03-27T23:27:00.000-07:00

To test the performance of the Core i7 990x, we used the following platform:

     * Motherboard Asus P6T Deluxe (BIOS 2209)
     * 4 GB DDR3-1600 Corsair @ 1333 MHz
     * RAID 0 Western Digital Raptor 300
     * Hard Drive Seagate 7200.11 1TB
     * Graphics Card AMD Radeon HD 5850

On this platform, operating under Windows 7 Ultimate 64-bit edition, we will test the Core i7 950, Core i7 970, Core i7 975X, 980X Core i7 and Core i7 990x. We will compare the course of recent Core i7 990x Sandy Bridge Socket LGA-1155 on the platform as detailed below:

     * Asus Maximus Formula IV (BIOS 0901)
     * 4 GB DDR3-1600 Corsair @ 1333 MHz
     * RAID 0 Western Digital Raptor 300
     * Hard Drive Seagate 7200.11 1TB
     * Graphics Card AMD Radeon HD 5850

Always driven by Windows 7, this configuration articulated around the P67 chipset, we tested the Core i7 2600K. Finally, we had to test the heart of AMD processors. Why we chose the following platform:

     * Asus M4A79T Deluxe (BIOS 3303)
     * 4 GB DDR3-1600 Corsair @ 1333 MHz
     * RAID 0 Western Digital Raptor 300
     * Hard Drive Seagate 7200.11 1TB
     * Graphics Card AMD Radeon HD 5850

Here we test the following AMD Phenom namely 1090T and 1100T II X6 and the Phenom X4 965.

3DMark Vantage - CPU Test

The test processor 3DMark Vantage gives preference to 990x Core i7, the processor is simply the fastest. The performance gain against the Core i7 980X reaches 4%, while the gap with the fastest Phenom processors, the Phenom II X6 1100T is enormous: 98%! Based on 3DMark Vantage, the Core i7 990x would be twice as powerful than a Phenom II X6. 2600K compared to the Core i7, Core i7 990x is well ahead with its number of execution cores greater.

PCMark Vantage - Gaming Reviews

The memory test of PCMark Vantage embodies Socket LGA1366 Core i7 in: they offer the best performance. Faced with the Phenom, the gap in terms of memory performance amounts to 23% in favor of the founder of Santa Clara. Note, however, the correct positioning of the Core i7 2600K who finished fourth even though it does not have a triple-channel memory controller as opposed to other Core i7.

Sandra 2010 - Processor Test

Change creamery with a look at the synthetic performance recorded by Sandra 2010. Here the Core i7 990x dominating performance with 3% above the Core i7 980X. The theoretical gap with the Core i7 2600K is significant: more than 40% for the Core i7 990x. As the delta with the Phenom, it is still impressive.

Sandra 2010 - Memory Test

The test memory performance theoretical advocates of processors in Socket LGA-1366. We note, however, a theoretical maximum throughput slightly lower for models hexa-core. They see their memory bandwidth from 22 GB / s on average to 19 GB / s. It's always more than the 18 Gb / s Core i7 2600K and far more than the Phenom memory bandwidth which hovers around 12 GB / s.

ScienceMark 2.0 x64 - Primordia

ScienceMark evaluates the performance of our processors by doing several computationally intensive. Not at all multithreaded ScienceMark depends primarily on the operating frequency of our processor. This explains the first place of the Core i7 2600K which with its 3.8 GHz frequency maximum Turbo 6.7% faster than the Core i7 990x (3.7 GHz maximum frequency with Turbo). For the rest, the Core i7 is 990x shows 4% faster than its predecessor, the Core i7 980X. Faced with the Phenom II X6 1100T, the Core i7 990x is 19% faster.

A new X58 motherboard: Intel DX58SO2

2011-03-27T23:03:00.000-07:00

Intel DX58SO2

To accompany the Core i7 990x, we focus on DX58SO2, motherboard most upscale catalog for Intel Socket LGA-1366. Released a few months ago, it was last fall, the DX58SO2 is an evolution of the Smackover DX58SO alias. Essentially, Intel is reviewing some of the card design, especially at the radiator, and adds - oh miracle! - a support for USB 3.0 and Serial ATA 6-Gb / s, two features absent from Intel X58 chipset motherboards that drives high-end platform for LGA-1366.

At ATX, motherboard is adorned with a black eight-layer PCB with a socket LGA-1366 and six DDR3 memory slots. We find the power connector ATX 24-pin connector and a standard ATX 2x 12 volts. If Intel did ignore the Molex connectors to stabilize the power of PCI-Express, there are three PCI-Express 2.0 x16 type: the first two are wired in 16x, the third operating mode 8x. And Intel to certify its motherboard supports SLI and CrossFireX. With one PCI slot, the card has two PCI-Express 1. The cooling of components DX58SO2 is provided by radiators electric blue interconnected by a heat pipe. Southbridge, or more exactly the ICH, it is topped with a single radiator. In terms of cooling, Intel shows little on the generous number of connectors for fans: Can not link the example above our fans Cosmos case to the motherboard, no connector being placed on the upper PCB.

Motherboard Intel DX58SO2

Side features, the menu offers classic connectors Serial-ATA 3 Gb / s, number six, with two connectors Serial-ATA 6 Gb / s additional managed by a chip Marvell88SE9128 and identified by blocks of color. There is also a Renesas chip to manage the only two USB 3.0 ports and no connector available for connecting the card to any USB 3.0 ports on your case.

Looking more closely at this second-generation Smackover we note the presence of a second controller in charge of both Marvell eSATA connectors offered by the card. Network side, we proposed two Intel Gigabit controllers of its own manufacture, which will not surprise anyone. Regarding the audio finally seems to have abandoned Intel Solutions Analog Devices, since we are dealing here with a Realtek ALC892.

Diodes with various debbuging, a digital display for diagnostic codes, and a disk activity LED card offers buttons start or fast reset. In terms of connectivity, the menu offers six USB 2.0 ports, two USB 3.0 ports, a FireWire connector, two RJ45 ports, two eSATA connectors and audio connectors to a ramp with an optical output. Intel delivers its DX58SO2 with some unexpected accessories: a mouse pad, a sheet of stickers and a module Wi-Fi USB (!). If the box contains two types of SLI dongle, no trace of a manual: it will simply illustrated a diagram of startup, which frankly is succinct.