Solved

What is real quad core cpu?

I hear this a lot: Real Hex or quad core processors. Does that mean that the 4300, 6300 don't actually have the number of cores signified? If that is such the case then what would be a Real quad or hex core?
41 answers Last reply Best Answer
More about real quad core cpu
  1. one physical cpu with 4 cores is a quad core processor.quad means four.
  2. The intel i5's are all real quads, and so are all the amd chips. Either, really will do, and the price is an excellent indicator of ability.
  3. real quad would be a cpu with 4 cores vs an i3 wich is really 2 cores with hyperthreading meaning your system looks at it as 4 cores but really its only 2 and you dont get as good performance as a real quad core.
  4. no. they are not. intel does this with hyperthreading
    (i3-s are dual core but with ht they show 4 cores at the os, and with the i7 - 4cores/8threads)
    amd does the same but more on the hardware side. each piledriver/bulldozer module has 2 int cores and 1 fp core shared between them. so a 4xxx series has 2 modules, a 6xxx series has 3 modules and a 8xxx series has 4. A series apu-s have 1 or 2 modules (2-4 cores) and graphics integrated and athlon II 7xx series have 2 modules each but graphics disabled. before bulldozer/piledriver amd cores where the real deal. 2-6 cores.
  5. laviniuc said:
    no. they are not. intel does this with hyperthreading
    (i3-s are dual core but with ht they show 4 cores at the os, and with the i7 - 4cores/8threads)
    amd does the same but more on the hardware side. each piledriver/bulldozer module has 2 int cores and 1 fp core shared between them. so a 4xxx series has 2 modules, a 6xxx series has 3 modules and a 8xxx series has 4. A series apu-s have 1 or 2 modules (2-4 cores) and graphics integrated and athlon II 7xx series have 2 modules each but graphics disabled. before bulldozer/piledriver amd cores where the real deal. 2-6 cores.


    So if I decide to buy a REAL AMD quad core I should go with the 8xxx series? and what do you mean by int. and fp?
    please elaborate
  6. the amd 8xxx series are actually 8 core cpu's so they are better then quad core but cost more too.
  7. Best answer
    AMDs modules are true cores, just not as good as lets say the cores from the Phenoms IIs. Modules as stated above and share resources, so technically still true cores. The 83xx series which is the only gen u should buy are 8 cores and disabling cores to have 4 cores or the modules is pointless. For real cores that are not modules or hyper threaded, u have to go Phenom II x4 or x6 for six or an i5 but u said amd so yeah . There quite hard to find new these days, but there not that hard to find on ebay or some places.

    FP i believe is floating point and int. is integer cores, not sure exactly the difference but there u go. Amd advertises them as true cores as they are physically there on the die.
  8. So what is the difference between a module and a core?
    Modules share resources while Real cores don't?
    so that mean that all 8 cores in 8XXX series are sharing resources?
  9. module is a core. so when amd says 4 or quad core its really 4 cores. same when they say 8. they are 8 real cores
  10. Well the modules will share like L2/l3 cache where the Phenom II series each core had dedicated caches etc. All amd FX cpus are module based and share resources. The sharing of resources is a small hit against if they were dedicated, but it still works as an 8 core and programs that can utilize them will use them. People have tried to disabled the odd cores in the 8 cores to turn a module into a core on its own and not sharing resources as the other one is disabled, but i believe it did not improve anything that using it as an 8 core didnt already do, i think it was actually worse.

    As said a module houses two cores and then resources get split between the two cores in the module, so the cores are real as they are physically on the cpu and not a hyper threaded core that allows a intel core to process more than a single thread at a time by doing two per core, in which recognized by the OS as two cores. not sure if thats exactly accurate but close enough
  11. lazyboy947 said:
    Well the modules will share like L2/l3 cache where the Phenom II series each core had dedicated caches etc. All amd FX cpus are module based and share resources. The sharing of resources is a small hit against if they were dedicated, but it still works as an 8 core and programs that can utilize them will use them. People have tried to disabled the odd cores in the 8 cores to turn a module into a core on its own and not sharing resources as the other one is disabled, but i believe it did not improve anything that using it as an 8 core didnt already do, i think it was actually worse.

    As said a module houses two cores and then resources get split between the two cores in the module, so the cores are real as they are physically on the cpu and not a hyper threaded core that allows a intel core to process more than a single thread at a time by doing two per core, in which recognized by the OS as two cores. not sure if thats exactly accurate but close enough


    Thank you for your great help!
    Another question please, Would 6350 be a good choice? you said I should only buy something from the 8xxx series.
  12. the 6350 is just a higher clocked 6300 so a six core which at the moment the 6300 gets the most performance for the cost, and the 83xx series is the current piledriver cores and the 81xx or 61xx/62xx are bulldozer cores which are not as good and not worth the money so the 83xx, 63xx, 43xx series whether u want the 4, 6 or 8 core. For the cost of the 4300 and 6300 its best to go with the 6300 and matters on budget but the 8350 is best and the 8320 is just a 500mhz slower 8350, so yes the 6350 is good, but for the cost in the us its similar cost of the 8320 that is on sale at newegg for $130 and the 6300 should be around $110 and 8350 around $190.

    Edit: Scratch that, seems the 8320 went off sale today so is back to $160 at newegg and some sites have for $150
  13. AnEwG said:
    I hear this a lot: Real Hex or quad core processors. Does that mean that the 4300, 6300 don't actually have the number of cores signified? If that is such the case then what would be a Real quad or hex core?


    Beh, you just opened up a can of worms!

    "real" is a qualifier that unknowledgeable fanboys love to tack on to a product that they love in order to better validate it against its competition.

    Microprocessor engineers have a huge amount of leeway in how they arrange and present the hardware that they are designing. Most of the time this results in dramatically different designs that are wholly incompatible, such as MIPS vs ARM. However, different generations of the same design often require a bit more finesse to examine.

    For example, x86 microprocessors (all of them dating back to the Pentium anyway) have an instruction called CPUID. This instruction is used to set the state of the machine such that the model and capabilities of the microprocessor can be identified. Prior to this there was no explicit way to tell the difference between an 80486 and an 80386, or any of their predecessors; they all feature full backward compatibility so engineers had to write often unreliable heuristic routines in order to exploit differing behaviour in order to tell them apart. The reason for this is that while different generations of CPUs are different internally, they present themselves in a nearly identical fashion and software doesn't care.

    Presentation is as important in hardware as it is in software. This is what trips a lot of people up, presentation masks implementation. A "core" is not a concretely defined term. At best it can be loosely described as a discrete state tracking device. When talking about a device that performs arbitrary operations defined within an Instruction Set Architecture the definition expands a little bit. When that ISA is further narrowed to the IA32 instruction set and associated ISA extensions the presentation is that of a logical processor implementing the IA32 instruction set with associated ISA extensions. The implementation of that logical processor (as a physical core) is still entirely up to the designer.

    Although AMD and Intel both present their micro architectures in the same fashion (there are only minor logical differences) there are many, many physical differences between them. Many people assume that the brand new Haswell microarchitecture (4th Gen Core i7) is a descendant to the Ivybridge microarchitecture (3rd Gen Core i7) , which is a descendant of Sandybridge (2nd Gen Core i7), which is a descendant of Westmere (1.5 gen Core i7), which is a descendant of Nehalem (1st Gen Core i7), which is a descendant of Penryn (2nd Gen Core 2), which is a descendant of Conroe (1st Gen Core 2) which is a descendant of Prescott (3rd Gen Pentium 4). Wait, that's wrong... Conroe (Core 2, released in 2006) is a descendant of Yonah (1st Gen Core) which was a mobile-only microprocessor that is itself a descendant of the Pentium 3 (released in 1999) which is a member of the P6 family of microarchitectures. All 3 major revisions of the Pentium 4 micro architecture (collectively known as NetBurst) are a massive departure from anything that came before them, and nothing came after them in an evolutionary fashion. Thanks to architectural differences, a 2.3Ghz Core 2 Duo microprocessor could outperform a 3.5Ghz dual-core Pentium. In some cases a single core Core 2 Solo could outperform a dual-core pentium. Don't let core count fool you; cores are easy to reproduce, but the architecture of the core itself is hard to develop!.

    Lets link this concept of implementation and presentation together. At a bare minimum 4 building blocks are needed to make an ISA core work: an data source (typically exposed to the cores as an instruction cache and a data cache), a front end (instruction decoding, state tracking, register sets), a back end (integer execution, floating point execution, logic execution, address generation, memory access), and control logic (makes everything work together nicely).

    Each designer is free to take liberties with these as much as they want as long as the end result is logically equivalent to that expected by the instruction set.

    Starting with the first generation Core i7 microprocessors (Nehalem) Intel has decided to use fully discrete cores. Each core has its own L1 instruction cache, its own L1 data cache, its own L2 cache, its own back end, and two front ends. The backend of Intel's microarchitecture is powerful enough to serve two front-ends, each of which is presented to the operating system as a logical processor that execute the IA32 instruction set. This is the meat of Hyperthreading. All cores share an L3 cache and interconnect to the rest of the microprocessor.

    AMD has decided to use non-discrete cores. Each core has its own L1 data cache, its own front end, and a partial backend (Integer, logic, address, and memory). Each core shares the rest of the backend (floating point), the L1 instruction cache, and the L2 cache with one other core. Together these are presented to the operating system as a pair of logical processors that execute the IA32 instruction set. These core-pairs can be duplicated with ease to create 4,6, and 8 core microprocessors.

    So, keeping the above two designs in mind, what if a designer wants to create a 12 or 16 core microprocessor?

    Lets look at some competing claims.

    Intel claimed to have the first quad core microprocessor in late 2006 with the Core 2 Quad microprocessor.

    AMD claimed to have the first native quad core microprocessor in 2007 with the Phenom line of microprocessors.

    These are both true statements.

    The difference is that Intel's Core 2 Quad microprocessor is actually a pair of Core 2 Duo microprocessors glued together on a Multi-Chip-Module whereas AMD's Phenom was a microprocessor with all four cores on a single silicon die. Despite not being a "true" or "real" quad core microproessor, the Core 2 Quad crushed the Phenom in every single benchmark. Marketing departments suck.

    Intel's 8 core server CPUs are native 8 core microprocessors with all components on a single die. I'm not certain what approach they will use to create the upcoming 12 and 15 core microprocessors but AMD's 12 and 16 core server CPUs are in fact a pair of 6 and 8 core CPUs glued together on an MCM just like the Core 2 Quad.

    The takeaway from this mess is that the strength of a CPU has to be assessed on its own merits, not on the clock frequency, number of cores, or whether or not the cores are "native" or "real".
  14. If you want to play games, any intel i5 will be better, but amd 8 series chips are a little cheaper in the short
    term. But not much, because they need a £20 cooler. And use more electricity. In fact, theyre more expensive from the get go.
    http://www.scan.co.uk/products/amd-fx-8350-black-edition-vishera-8-core-s-am3plus-40ghz-16mb-total-cache-125w-retail
    plus cooler. take it back about price being indicator.
  15. fp yes, i meant the floating point unit and int the integer compute module. each amd "module" would work as true 2 core cpu when they have integer operations to do and as quads when dealing with pure floating point workloads.

    yes it's a far better approach compared to intel's hyperthreading but it's not a "true" dual core in each module either. (that's why when the bulldozer was launched, the "quad core" 41xx series was slower than the phenom II X4 cpu)
  16. It doesnt need an aftermarket cooler, most recommend one or will get one, and really a few watts going to make a difference? 84w/77w vs 125w? 40-60watts between fx 125w vs i7s isnt going to bankrupt anyone to make a problem lol and with high end gpus using around 200-300watts im sure if ur footing hundreds of dollars for pc parts ur not exactly worried on electricity consumption, only thing is heat production and the wattage as a result in the long run requires a better cooler, ran a 8150 and a friend a 1090t with stock for around a year and not extra cooler than case fans required.

    Edit: all amd and intel cpus other than the extreme lga 2011 and 9xxx series come with a stock heatsink fan........... unless oem purchased then there isnt one.
  17. chrisso said:
    If you want to play games, any intel i5 will be better, but amd 8 series chips are a little cheaper in the short
    term. But not much, because they need a £20 cooler. And use more electricity. In fact, theyre more expensive from the get go.
    http://www.scan.co.uk/products/amd-fx-8350-black-edition-vishera-8-core-s-am3plus-40ghz-16mb-total-cache-125w-retail
    plus cooler. take it back about price being indicator.


    I have AMD MB and I am not planning to buy Intel supporting one anytime soon because I have only got that MB recently but than you anyway.
  18. chrisso said:
    If you want to play games, any intel i5 will be better, but amd 8 series chips are a little cheaper in the short
    term. But not much, because they need a £20 cooler. And use more electricity. In fact, theyre more expensive from the get go.
    http://www.scan.co.uk/products/amd-fx-8350-black-edition-vishera-8-core-s-am3plus-40ghz-16mb-total-cache-125w-retail
    plus cooler. take it back about price being indicator.

    There are many games that eat up CPU for breakfast that perform better on the FX 8350, though in the huge majority of modern games they will perform very similarly. The FX 8350 almost never blows the i5 out of the water, while in games that favour single-threaded performance the i5 is significantly faster than the 8350.

    Depending on the price where you are, the 8350 will be saving quite a lot. Here the 8350 is about $200 while a 4670K is about $230. A decent 990 motherboard is about $120 while a good Z87 board is in the neighbourhood of $150. Ask nearly anyone who owns a 4670K - the stock Intel heatsink does a terrible job. In any situation where the CPU will be under significant load for long periods of time like in CPU-intensive games or rendering you will want an aftermarket cooler for both the 8350 and a 3570K or 4670K. In terms of electricity, unless you're paying like $0.50 per kwh it would take a very long time for the energy costs to make up the difference in initial price. At stock under load the 8350 uses roughly 60-70W more than a comparable i5, but overclocked the delta is around 125W. Under light use you're looking at less than 10W dif most of the time. Long story short, unless electricity is very expensive where you live, the 8350 would take the better half of a decade to cost more than a 3570K/4670K unless you leave your computer on heavy load 24/7.
  19. Ah, I remember when I thought electricity use came down to a bill that somebody paid.
    It Doesnt . Power use equates to ; Wear and tear on power supply units, motherboards,electronic components,HEAT, fan use, yes, the actual extra 50 watts, which amounts to $20 a year, and the end result of all that is shorter life spans and more expense.Is that system in any way whatsoever, cheaper? You can pretty much bank on the intel system lasting twice as long with lower maintenance costs. If I spend on the intel pc, I will be able to give
    it to one of my nephews in 5 years, whilst the AMD pc will have long been recycled. THAT is value for money.
  20. I see no logic in ur post lol pretty sure both systems no matter cpu assuming same everything and a quality board and just the opposing brand cpu both can last longer than the other and they both possibly die or last longer. so my 2009 phenom II x6 is dead and has already been recycled as i type?
  21. lazyboy947 said:
    the 6350 is just a higher clocked 6300 so a six core which at the moment the 6300 gets the most performance for the cost, and the 83xx series is the current piledriver cores and the 81xx or 61xx/62xx are bulldozer cores which are not as good and not worth the money so the 83xx, 63xx, 43xx series whether u want the 4, 6 or 8 core. For the cost of the 4300 and 6300 its best to go with the 6300 and matters on budget but the 8350 is best and the 8320 is just a 500mhz slower 8350, so yes the 6350 is good, but for the cost in the us its similar cost of the 8320 that is on sale at newegg for $130 and the 6300 should be around $110 and 8350 around $190.

    Edit: Scratch that, seems the 8320 went off sale today so is back to $160 at newegg and some sites have for $150


    so from the 8320 6350 6300 which do you think I should choose? Or maybe I should even go with the older phenom II processors at the top of Tom's hardware cpu hierarchy chart if I can find them? ( Phenom II X6 1100T BE,
    1090T BE
    Phenom II X4 Black
    Edition 980, 975, Phenom II X6 1075T
    Phenom II X4 Black
    Edition 970, 965, 955.
  22. Yeah, u probably will not find the 1100t or almost any high end Phenom II cpus for a reasonable price, might as well go with the fx series. The 83xx line is an upgrade path for those with the x6s and wins in multi thread performance and single thread is similar so just go with what meets ur budget. on a smaller budget 6300 and OC, dont wanna OC then 6350 and higher budget 8320 and OC, no OC go 8350.
  23. ^ Boom, electronics are random on when they die and how long they last and obviously how well u maintain the, Pretty sure intel cpus dont last longer just because there intel and have a lower tdp
  24. no one noticed my long winded but thorough explanation :(

    EDIT: spelling
  25. i did, and got the gist of it lol its around 1000 words lol. It makes sense in how the core2quads as u put it are similar to the amd server cpus and everything else in its mini essay glory lol
  26. Also, any stock i5 is better for gaming because the frame spread times are better.
    Any 'av' fps over the 'new 30' which is 60 fps is a waste. Standard Cinema film runs at 24 fps, and has done for years.
    http://en.wikipedia.org/wiki/Frame_rate

    The quality feel goes down far more from unreliability in frame rates. Nvidia know this, despite recent slacknesss in product life.
    Toms did a blind test on 2 systems, and 75% picked the nvidia card.But, nobody mentions this with cpu's.
    So, it costs more, wears out faster, wears out my parts faster, uses more electricity, cost wise,needs a £20 cooler and Doesnt perform as well. Whats not to Like?
  27. lazyboy947 said:
    i did, and got the gist of it lol its around 1000 words lol. It makes sense in how the core2quads as u put it are similar to the amd server cpus and everything else in its mini essay glory lol


    well at least it wasn't totally in vain!
  28. the removal of virtualization in k edition cpus?? lol. Im gonna assume u stick with nvidia on the gpu side as well? Do u have money to waste that u can give a $1200+ pc to ur nephew in 5 years and build a new pc?
  29. Pinhedd said:
    AnEwG said:
    I hear this a lot: Real Hex or quad core processors. Does that mean that the 4300, 6300 don't actually have the number of cores signified? If that is such the case then what would be a Real quad or hex core?


    Beh, you just opened up a can of worms!

    "real" is a qualifier that unknowledgeable fanboys love to tack on to a product that they love in order to better validate it against its competition.

    Microprocessor engineers have a huge amount of leeway in how they arrange and present the hardware that they are designing. Most of the time this results in dramatically different designs that are wholly incompatible, such as MIPS vs ARM. However, different generations of the same design often require a bit more finesse to examine.

    For example, x86 microprocessors (all of them dating back to the Pentium anyway) have an instruction called CPUID. This instruction is used to set the state of the machine such that the model and capabilities of the microprocessor can be identified. Prior to this there was no explicit way to tell the difference between an 80486 and an 80386, or any of their predecessors; they all feature full backward compatibility so engineers had to write often unreliable heuristic routines in order to exploit differing behaviour in order to tell them apart. The reason for this is that while different generations of CPUs are different internally, they present themselves in a nearly identical fashion and software doesn't care.

    Presentation is as important in hardware as it is in software. This is what trips a lot of people up, presentation masks implementation. A "core" is not a concretely defined term. At best it can be loosely described as a discrete state tracking device. When talking about a device that performs arbitrary operations defined within an Instruction Set Architecture the definition expands a little bit. When that ISA is further narrowed to the IA32 instruction set and associated ISA extensions the presentation is that of a logical processor implementing the IA32 instruction set with associated ISA extensions. The implementation of that logical processor (as a physical core) is still entirely up to the designer.

    Although AMD and Intel both present their micro architectures in the same fashion (there are only minor logical differences) there are many, many physical differences between them. Many people assume that the brand new Haswell microarchitecture (4th Gen Core i7) is a descendant to the Ivybridge microarchitecture (3rd Gen Core i7) , which is a descendant of Sandybridge (2nd Gen Core i7), which is a descendant of Westmere (1.5 gen Core i7), which is a descendant of Nehalem (1st Gen Core i7), which is a descendant of Penryn (2nd Gen Core 2), which is a descendant of Conroe (1st Gen Core 2) which is a descendant of Prescott (3rd Gen Pentium 4). Wait, that's wrong... Conroe (Core 2, released in 2006) is a descendant of Yonah (1st Gen Core) which was a mobile-only microprocessor that is itself a descendant of the Pentium 3 (released in 1999) which is a member of the P6 family of microarchitectures. All 3 major revisions of the Pentium 4 micro architecture (collectively known as NetBurst) are a massive departure from anything that came before them, and nothing came after them in an evolutionary fashion. Thanks to architectural differences, a 2.3Ghz Core 2 Duo microprocessor could outperform a 3.5Ghz dual-core Pentium. In some cases a single core Core 2 Solo could outperform a dual-core pentium. Don't let core count fool you; cores are easy to reproduce, but the architecture of the core itself is hard to develop!.

    Lets link this concept of implementation and presentation together. At a bare minimum 4 building blocks are needed to make an ISA core work: an data source (typically exposed to the cores as an instruction cache and a data cache), a front end (instruction decoding, state tracking, register sets), a back end (integer execution, floating point execution, logic execution, address generation, memory access), and control logic (makes everything work together nicely).

    Each designer is free to take liberties with these as much as they want as long as the end result is logically equivalent to that expected by the instruction set.

    Starting with the first generation Core i7 microprocessors (Nehalem) Intel has decided to use fully discrete cores. Each core has its own L1 instruction cache, its own L1 data cache, its own L2 cache, its own back end, and two front ends. The backend of Intel's microarchitecture is powerful enough to serve two front-ends, each of which is presented to the operating system as a logical processor that execute the IA32 instruction set. This is the meat of Hyperthreading. All cores share an L3 cache and interconnect to the rest of the microprocessor.

    AMD has decided to use non-discrete cores. Each core has its own L1 data cache, its own front end, and a partial backend (Integer, logic, address, and memory). Each core shares the rest of the backend (floating point), the L1 instruction cache, and the L2 cache with one other core. Together these are presented to the operating system as a pair of logical processors that execute the IA32 instruction set. These core-pairs can be duplicated with ease to create 4,6, and 8 core microprocessors.

    So, keeping the above two designs in mind, what if a designer wants to create a 12 or 16 core microprocessor?

    Lets look at some competing claims.

    Intel claimed to have the first quad core microprocessor in late 2006 with the Core 2 Quad microprocessor.

    AMD claimed to have the first native quad core microprocessor in 2007 with the Phenom line of microprocessors.

    These are both true statements.

    The difference is that Intel's Core 2 Quad microprocessor is actually a pair of Core 2 Duo microprocessors glued together on a Multi-Chip-Module whereas AMD's Phenom was a microprocessor with all four cores on a single silicon die. Despite not being a "true" or "real" quad core microproessor, the Core 2 Quad crushed the Phenom in every single benchmark. Marketing departments suck.

    Intel's 8 core server CPUs are native 8 core microprocessors with all components on a single die. I'm not certain what approach they will use to create the upcoming 12 and 15 core microprocessors but AMD's 12 and 16 core server CPUs are in fact a pair of 6 and 8 core CPUs glued together on an MCM just like the Core 2 Quad.

    The takeaway from this mess is that the strength of a CPU has to be assessed on its own merits, not on the clock frequency, number of cores, or whether or not the cores are "native" or "real".


    Anonymous said:
    chrisso said:
    If you want to play games, any intel i5 will be better, but amd 8 series chips are a little cheaper in the short
    term. But not much, because they need a £20 cooler. And use more electricity. In fact, theyre more expensive from the get go.
    http://www.scan.co.uk/products/amd-fx-8350-black-edition-vishera-8-core-s-am3plus-40ghz-16mb-total-cache-125w-retail
    plus cooler. take it back about price being indicator.

    There are many games that eat up CPU for breakfast that perform better on the FX 8350, though in the huge majority of modern games they will perform very similarly. The FX 8350 almost never blows the i5 out of the water, while in games that favour single-threaded performance the i5 is significantly faster than the 8350.

    Depending on the price where you are, the 8350 will be saving quite a lot. Here the 8350 is about $200 while a 4670K is about $230. A decent 990 motherboard is about $120 while a good Z87 board is in the neighbourhood of $150. Ask nearly anyone who owns a 4670K - the stock Intel heatsink does a terrible job. In any situation where the CPU will be under significant load for long periods of time like in CPU-intensive games or rendering you will want an aftermarket cooler for both the 8350 and a 3570K or 4670K. In terms of electricity, unless you're paying like $0.50 per kwh it would take a very long time for the energy costs to make up the difference in initial price. At stock under load the 8350 uses roughly 60-70W more than a comparable i5, but overclocked the delta is around 125W. Under light use you're looking at less than 10W dif most of the time. Long story short, unless electricity is very expensive where you live, the 8350 would take the better half of a decade to cost more than a 3570K/4670K unless you leave your computer on heavy load 24/7.


    Pinhedd said:
    no one noticed my long winded but thorough explanation :(

    EDIT: spelling


    I am sure it contains a lot of valuable information but I got lost at the fourth line or so :pt1cable:
    I am a noob man, I may revise your post in few months (or years), maybe by then I'll have enough knowledge on the subject. :D
  30. chrisso said:
    Also, any stock i5 is better for gaming because the frame spread times are better.
    Anything over the 'new 30' which is 60 fps is a waste. Standard Cinema film runs at 24 fps, and has done for years.
    http://en.wikipedia.org/wiki/Frame_rate

    The quality feel goes down far more from unreliability in frame rates. Nvidia know this, despite recent slacknesss.
    Toms did a blind test on 2 systems, and 75% picked the nvidia card.But, nobody mentions this with cpu's.
    So, it costs more, wears out faster, wears out my parts faster, uses more electricity, cost wise,needs a £20 cooler and Doesnt perform as well. Whats not to Like?


    There's far less radial motion in cinema than there is in a first person shooter video game. There's also no human input, so there's no sense of delayed response.
  31. BN91 said:
    the amd 8xxx series are actually 8 core cpu's so they are better then quad core but cost more too.


    Not exactly...

    8 Integer cores, but only 4 Floating point cores (4/2 for the fx4 quads and 6/3 for the fx6). Where as intel Quads have 4 integer and 4 fpu.
  32. RobCrezz said:
    BN91 said:
    the amd 8xxx series are actually 8 core cpu's so they are better then quad core but cost more too.


    Not exactly...

    8 Integer cores, but only 4 Floating point cores (4/2 for the fx4 quads and 6/3 for the fx6). Where as intel Quads have 4 integer and 4 fpu.


    Exactly why the 8 cores compete with the i5s FPU wise there the same lol
  33. Interestingly enough, the G0 stepping Q6600 was hashed up because of the phenom's imminent release, but intel didnt know the Phenom would suck.
    Intel dropped the price and made the G0 clockable by 50 %. A move that has never been repeated.
  34. RobCrezz said:
    BN91 said:
    the amd 8xxx series are actually 8 core cpu's so they are better then quad core but cost more too.


    Not exactly...

    8 Integer cores, but only 4 Floating point cores (4/2 for the fx4 quads and 6/3 for the fx6). Where as intel Quads have 4 integer and 4 fpu.


    Each Haswell core has four Integer units (ALU), one FP-Mult and one FP-Add. The FP units share the same execution pipe as two of the integer units. This adds up to either 4 scalar integer operations per clock cycle, or 2 scalar integer operations along with one scalar floating point add and one scalar floating point multiplication. There's vector units as well, but I'll ignore these. Assuming that they can all be kept busy at once and are fully pipelined, this allows for 16 integer operations to issue per clock cycle on a quad core Haswell.

    Each Bulldozer/Piledriver core has two integer units (ALU). Assuming that they can all be kept busy at once and are fully pipelined, this allows for 16 integer operations to issue per clock cycle on an octal core Piledriver. I'm not sure how the shared FP unit works into the execution pipe so I'll not comment on that but I do know that it's weaker than that found in Intel's Core i7 CPUs

    Under benchmarks specifically designed to test unconstrained ALU performance (such as hashing) Bulldozer has a slight edge due to its higher clock speed but Intel typically wins out in practice where memory architecture is a concern, almost always wins out in a clock-for-clock battle and always wins out in comparative power efficiency.
  35. It would take intel 12 months I estimate, to change manufacturing practises to enable haswells to be clocked like hell, and maybe if pushed 6 core versions. You can bet your lunchbox there are plans for such a drastic measure sitting in a vault tech esq basement.
  36. chrisso said:
    It would take intel 12 months I estimate, to change manufacturing practises to enable haswells to be clocked like hell, and maybe if pushed 6 core versions. You can bet your lunchbox there are plans for such a drastic measure sitting in a vault tech esq basement.


    Users routinely run Haswell microprocessors at speeds upwards of 4.2Ghz without issue. Going above 4.5Ghz becomes a chore for thermal reasons due to Intel's decision to use paste to bind the IHS to the die rather than solder.
  37. Anonymous said:
    chrisso said:
    If you want to play games, any intel i5 will be better, but amd 8 series chips are a little cheaper in the short
    term. But not much, because they need a £20 cooler. And use more electricity. In fact, theyre more expensive from the get go.
    http://www.scan.co.uk/products/amd-fx-8350-black-edition-vishera-8-core-s-am3plus-40ghz-16mb-total-cache-125w-retail
    plus cooler. take it back about price being indicator.

    There are many games that eat up CPU for breakfast that perform better on the FX 8350, though in the huge majority of modern games they will perform very similarly. The FX 8350 almost never blows the i5 out of the water, while in games that favour single-threaded performance the i5 is significantly faster than the 8350.

    Depending on the price where you are, the 8350 will be saving quite a lot. Here the 8350 is about $200 while a 4670K is about $230. A decent 990 motherboard is about $120 while a good Z87 board is in the neighbourhood of $150. Ask nearly anyone who owns a 4670K - the stock Intel heatsink does a terrible job. In any situation where the CPU will be under significant load for long periods of time like in CPU-intensive games or rendering you will want an aftermarket cooler for both the 8350 and a 3570K or 4670K. In terms of electricity, unless you're paying like $0.50 per kwh it would take a very long time for the energy costs to make up the difference in initial price. At stock under load the 8350 uses roughly 60-70W more than a comparable i5, but overclocked the delta is around 125W. Under light use you're looking at less than 10W dif most of the time. Long story short, unless electricity is very expensive where you live, the 8350 would take the better half of a decade to cost more than a 3570K/4670K unless you leave your computer on heavy load 24/7.


    Where I live any decent piece of equipment is 20% higher in price than in the US.
  38. chrisso said:
    It would take intel 12 months I estimate, to change manufacturing practises to enable haswells to be clocked like hell, and maybe if pushed 6 core versions. You can bet your lunchbox there are plans for such a drastic measure sitting in a vault tech esq basement.


    I dont think there is much holding the clockspeeds back at the moment, except for the the low quality die to heatspreader they are doing at the moment.

    My sandydbridge quad has been at 4.6Ghz for the majority of its life, I could probably get 5Ghz if I wished. But then sandy had the die soldered to the heatspreader.
  39. I havent been interested in unlocked cpu's, because by the time you have bought the better board etc
    the price is too high. 4.2 isnt much result % wise for the extra £50 over a stock set up.
Ask a new question

Read More

Quad Core Processors CPUs