Jump to content

What's up with AMD's CPU's?

First of all I would like to start by saying that the last thing I want to do is start and AMD vs Intel CPU war. My question is this: I see AMD CPUs all over the place with 4, 6 or 8 cores at 4.00+ GHz stock speed at very low prices compared to Intel's. Why are AMD CPUs so cheap compared to intel's while at the same time providing more cores/higher spped? Take Intel's 5960x and AMD's FX 9590 for example. Both have 8 cores, while the AMD one has a much higher stock speed and at the same time costs a quarter of the Intel one. So what exactly is the difference?

 

PS: please refrain from posting answers like "5960x has more lanes/threads/supports DDR 4 ram". I already know all this (and I know that the 5960x is better than the FX 9590, duh), my question is why exactly is there a performance difference between the two if their specs so similar?

Link to comment
Share on other sites

Link to post
Share on other sites

Intel cpus are faster in real life for same core number/frequency.

Also those amds 8 cores are not really full cores. They work in pairs and inside of every pair they share some stuff.

Link to comment
Share on other sites

Link to post
Share on other sites

Their CPUs are cheaper because they're worse. The IPC is far lower, therefore performance is worse. As well, AMD's CPUs are running on a 2+ year old platform, Intel's chips are as new as can be for now.

Main Rig: CPU: AMD Ryzen 7 5800X | RAM: 32GB (2x16GB) KLEVV CRAS XR RGB DDR4-3600 | Motherboard: Gigabyte B550I AORUS PRO AX | Storage: 512GB SKHynix PC401, 1TB Samsung 970 EVO Plus, 2x Micron 1100 256GB SATA SSDs | GPU: EVGA RTX 3080 FTW3 Ultra 10GB | Cooling: ThermalTake Floe 280mm w/ be quiet! Pure Wings 3 | Case: Sliger SM580 (Black) | PSU: Lian Li SP 850W

 

Server: CPU: AMD Ryzen 3 3100 | RAM: 32GB (2x16GB) Crucial DDR4 Pro | Motherboard: ASUS PRIME B550-PLUS AC-HES | Storage: 128GB Samsung PM961, 4TB Seagate IronWolf | GPU: AMD FirePro WX 3100 | Cooling: EK-AIO Elite 360 D-RGB | Case: Corsair 5000D Airflow (White) | PSU: Seasonic Focus GM-850

 

Miscellaneous: Dell Optiplex 7060 Micro (i5-8500T/16GB/512GB), Lenovo ThinkCentre M715q Tiny (R5 2400GE/16GB/256GB), Dell Optiplex 7040 SFF (i5-6400/8GB/128GB)

Link to comment
Share on other sites

Link to post
Share on other sites

bulldozer is  a pile of shit they've been rehashing for the past few years now. They might be competitive again if and when they release a new architecture, which promises to have their own version of SMT and not be a pile of shit. 

muh specs 

Gaming and HTPC (reparations)- ASUS 1080, MSI X99A SLI Plus, 5820k- 4.5GHz @ 1.25v, asetek based 360mm AIO, RM 1000x, 16GB memory, 750D with front USB 2.0 replaced with 3.0  ports, 2 250GB 850 EVOs in Raid 0 (why not, only has games on it), some hard drives

Screens- Acer preditor XB241H (1080p, 144Hz Gsync), LG 1080p ultrawide, (all mounted) directly wired to TV in other room

Stuff- k70 with reds, steel series rival, g13, full desk covering mouse mat

All parts black

Workstation(desk)- 3770k, 970 reference, 16GB of some crucial memory, a motherboard of some kind I don't remember, Micomsoft SC-512N1-L/DVI, CM Storm Trooper (It's got a handle, can you handle that?), 240mm Asetek based AIO, Crucial M550 256GB (upgrade soon), some hard drives, disc drives, and hot swap bays

Screens- 3  ASUS VN248H-P IPS 1080p screens mounted on a stand, some old tv on the wall above it. 

Stuff- Epicgear defiant (solderless swappable switches), g600, moutned mic and other stuff. 

Laptop docking area- 2 1440p korean monitors mounted, one AHVA matte, one samsung PLS gloss (very annoying, yes). Trashy Razer blackwidow chroma...I mean like the J key doesn't click anymore. I got a model M i use on it to, but its time for a new keyboard. Some edgy Utechsmart mouse similar to g600. Hooked to laptop dock for both of my dell precision laptops. (not only docking area)

Shelf- i7-2600 non-k (has vt-d), 380t, some ASUS sandy itx board, intel quad nic. Currently hosts shared files, setting up as pfsense box in VM. Also acts as spare gaming PC with a 580 or whatever someone brings. Hooked into laptop dock area via usb switch

Link to comment
Share on other sites

Link to post
Share on other sites

The FX architecture is nearly a decade old. Add to that, an FX 8-core has the same max theoretical IPC (instructions per cycle) as an intel i5 quad core. That automatically means that each Intel core is capable of twice the instructions of 2 AMD cores per cycle, if all things were equal, which they are not. The make up of an Intel core is different than an AMD core. And, once you add hyper threading, you add an additional IPC for each extra thread. 

 

if you were to compare a 5960X to an FX 8-core (any FX 8-core), you are looking at ~64 (i believe) maximum IPC for a 5960X, compared to ~28 maximum IPC on the FX 8-core. 

R9 3900XT | Tomahawk B550 | Ventus OC RTX 3090 | Photon 1050W | 32GB DDR4 | TUF GT501 Case | Vizio 4K 50'' HDR

 

Link to comment
Share on other sites

Link to post
Share on other sites

AMD doesn't perform as well, so it is priced more competitively.

The current AMD architecture is rather dated. Bulldozer launched in 2011 and was pretty much the same as the Phenom II lineup that launched in 09.

The 9590 launched at a price much closer to the 5960x before being laughed out of the room. I like the FX lineup but that was ridiculous.

Right now the FX CPU's are between Ivy bridge i3's and i5's in terms of performance, but don't really compete with Haswell even at the i3 level. (At least as far as gaming is concerned, a 9590 is pretty close to a haswell i5 in multithreaded situations)

Most of the new stuff AMD has done in the last few years has been with its APU lineup. They haven't released any real revisions since the Piledriver lineup in 2012. (Just new SKUs of piledriver) Zen is slated to come out somewhere around the end of 2016, so we have awhile to wait yet to see if AMD can start competing again in performance.

4K // R5 3600 // RTX2080Ti

Link to comment
Share on other sites

Link to post
Share on other sites

The FX architecture is nearly a decade old. Add to that, an FX 8-core has the same max theoretical IPC (instructions per cycle) as an intel i5 quad core. That automatically means that each Intel core is capable of twice the instructions of 2 AMD cores per cycle, if all things were equal, which they are not. The make up of an Intel core is different than an AMD core. And, once you add hyper threading, you add an additional IPC for each extra thread. 

 

if you were to compare a 5960X to an FX 8-core (any FX 8-core), you are looking at ~64 (i believe) maximum IPC for a 5960X, compared to ~28 maximum IPC on the FX 8-core. 

Nearly a decade?

The oldest i found was 2012

n0ah1897, on 05 Mar 2014 - 2:08 PM, said:  "Computers are like girls. It's whats in the inside that matters.  I don't know about you, but I like my girls like I like my cases. Just as beautiful on the inside as the outside."

Link to comment
Share on other sites

Link to post
Share on other sites

Nearly a decade?

The oldest i found was 2012

 

Maybe I was stretching it a bit, but it took them forever to launch the architecture. It was brought into the public eye about 8 years ago, but they were developing it before then. There were even supposed to be 16 core/8 module Desktop CPU's iirc.

 

http://www.bit-tech.net/news/hardware/2007/07/28/amd_goes_modular/1

http://www.pcper.com/reviews/Processors/AMD-Analyst-Day-Barcelona-Fusion-and-Beyond/AMDs-Bulldozer-and-Bobcat

 

and when it released

http://www.anandtech.com/show/4955/the-bulldozer-review-amd-fx8150-tested

R9 3900XT | Tomahawk B550 | Ventus OC RTX 3090 | Photon 1050W | 32GB DDR4 | TUF GT501 Case | Vizio 4K 50'' HDR

 

Link to comment
Share on other sites

Link to post
Share on other sites

First of all I would like to start by saying that the last thing I want to do is start and AMD vs Intel CPU war. My question is this: I see AMD CPUs all over the place with 4, 6 or 8 cores at 4.00+ GHz stock speed at very low prices compared to Intel's. Why are AMD CPUs so cheap compared to intel's while at the same time providing more cores/higher spped? Take Intel's 5960x and AMD's FX 9590 for example. Both have 8 cores, while the AMD one has a much higher stock speed and at the same time costs a quarter of the Intel one. So what exactly is the difference?

 

PS: please refrain from posting answers like "5960x has more lanes/threads/supports DDR 4 ram". I already know all this (and I know that the 5960x is better than the FX 9590, duh), my question is why exactly is there a performance difference between the two if their specs so similar?

 

Because of architecture and IPC.  That is the name of the game.  Not cores and Ghz.  AMD is WAY, and I mean WAY WAY WAY behind Intel when it comes to per core performance, which is king for the vast majority of tasks.  Programs that make use of all 8 cores are a very niche area.

"I genuinely dislike the promulgation of false information, especially to people who are asking for help selecting new parts."

Link to comment
Share on other sites

Link to post
Share on other sites

There you go, that's why...AMD FX vishera core performance is 62% slower than intel running at the same clockspeed:

 

http://cpu.userbenchmark.com/Compare/Intel-Core-i7-4790K-vs-AMD-FX-8350/2384vs1489

| CPU: Core i7-8700K @ 4.89ghz - 1.21v  Motherboard: Asus ROG STRIX Z370-E GAMING  CPU Cooler: Corsair H100i V2 |
| GPU: MSI RTX 3080Ti Ventus 3X OC  RAM: 32GB T-Force Delta RGB 3066mhz |
| Displays: Acer Predator XB270HU 1440p Gsync 144hz IPS Gaming monitor | Oculus Quest 2 VR

Link to comment
Share on other sites

Link to post
Share on other sites

First of all I would like to start by saying that the last thing I want to do is start and AMD vs Intel CPU war. My question is this: I see AMD CPUs all over the place with 4, 6 or 8 cores at 4.00+ GHz stock speed at very low prices compared to Intel's. Why are AMD CPUs so cheap compared to intel's while at the same time providing more cores/higher spped? Take Intel's 5960x and AMD's FX 9590 for example. Both have 8 cores, while the AMD one has a much higher stock speed and at the same time costs a quarter of the Intel one. So what exactly is the difference?

PS: please refrain from posting answers like "5960x has more lanes/threads/supports DDR 4 ram". I already know all this (and I know that the 5960x is better than the FX 9590, duh), my question is why exactly is there a performance difference between the two if their specs so similar?

Try to think of it this way. AMDs 8 cores are as fast as intels 4 without hyperthreading.

9590/9370/8370/8350/8320 = 4690K

6350/6300 = Core I3

For multithreaded performance, for gaming performance the I3's trounce the 8 cores

Core I7 5960X / Gigabyte X99 SOC Force / Kingston 16GB DDR4 3000 / EVGA GTX 980 Classified's In Quad SLI / EVGA 1600W G2

Core I7 6700K / Asus Z170 Maximus VIII Hero / Corsair 16GB DDR4 3000 / MSI R9 290X Lightning / EVGA 1600W T2

Link to comment
Share on other sites

Link to post
Share on other sites

There you go, that's why...AMD FX vishera core performance is 62% slower than intel running at the same clockspeed:

 

http://cpu.userbenchmark.com/Compare/Intel-Core-i7-4790K-vs-AMD-FX-8350/2384vs1489

 

About 38% slower. Reciprocals.

 

62% faster = 1.62

 

1 ÷ 1.62 = 0.62

 

0.62 * 1.62 = 1

 

0.62 = 1 - 0.38

 

62% faster (or 162%/1.62x of original value) <-> 38% slower (or 0.62%/0.62x of original value)

100% faster (or 200%/2x of original value) <-> 50% slower (or 50%/0.5x of original value)

200% faster (or 300%/3x of original value) <-> 25% slower

 

Problem with % faster/slower is you're adding or subtracting an amount to a number that you then multiply.

 

(yay math)

Intel i5-4690K @ 3.8GHz || Gigabyte Z97X-SLI || 8GB G.Skill Ripjaws X 1600MHz || Asus GTX 760 2GB @ 1150 / 6400 || 128GB A-Data SX900 + 1TB Toshiba 7200RPM || Corsair RM650 || Fractal 3500W

Link to comment
Share on other sites

Link to post
Share on other sites

About 38% slower. Reciprocals.

yeah right...i worded this the wrong way...sry!

Still, 62% faster for haswell then i guess :)

| CPU: Core i7-8700K @ 4.89ghz - 1.21v  Motherboard: Asus ROG STRIX Z370-E GAMING  CPU Cooler: Corsair H100i V2 |
| GPU: MSI RTX 3080Ti Ventus 3X OC  RAM: 32GB T-Force Delta RGB 3066mhz |
| Displays: Acer Predator XB270HU 1440p Gsync 144hz IPS Gaming monitor | Oculus Quest 2 VR

Link to comment
Share on other sites

Link to post
Share on other sites

Amd should really change their platform and concentrate on cpus too and not just apus and also bring in a new architecture

If they don't increase the competition this side of the market will remain stagnant

Link to comment
Share on other sites

Link to post
Share on other sites

Amd should really change their platform and concentrate on cpus too and not just apus and also bring in a new architecture

If they don't increase the competition this side of the market will remain stagnant

 

I'm guessing AMD is waiting until Zen because there is nothing they can do with the Bulldozer family architectures in the mainstream/enthusiast segments. Releasing more Steamroller or Excavator desktop CPUs, including FX-6/8 CPUs, would be a waste since the performance increase is marginal. They're focusing on mobile where they can actually make some gains... Excavator should bring some significant improvements to clock speed at low wattages. They can't quickly pump out a totally new architecture right now because they don't have much money for R&D, plus are probably limited in which silicon can be produced and for how long it's going to be produced. Finally they need to make sure that the majority of the previous generation chips have already been sold before they can ship new ones... kinda like how R9 300 series is taking so long to release since there are still so many R9 200 cards on shelves.

 

And I think that Intel will still advance the same. Even if AMD was totally out of the picture, Intel would need to release compelling products for people to continue giving them money. Nobody upgrades unless there is something worthwhile to upgrade to.

Intel i5-4690K @ 3.8GHz || Gigabyte Z97X-SLI || 8GB G.Skill Ripjaws X 1600MHz || Asus GTX 760 2GB @ 1150 / 6400 || 128GB A-Data SX900 + 1TB Toshiba 7200RPM || Corsair RM650 || Fractal 3500W

Link to comment
Share on other sites

Link to post
Share on other sites

Think of the AMD 6 and 8 cores differently. Cinebench recognizes my FX6350 as a 3 core with 6 threads even though it's advertised as a 6 core CPU it really isn't.

Main Rig CPU: AMD Ryzen 7 5700x GPU: Asus TUF Gaming RX5700XT MBASUS AM4 TUF Gaming X570-Plus RAM: 64GB Corsair Dominator Platinum 3200 CPU Cooler: Cooler Master Master Liquid LC240E SSD: Crucial 250gb M.2 + Crucial 500gb SSD HDD: PSU: Thermaltake Toughpower Gran RGB 850W 80+ Gold Case: Corsair Carbide 275R KB: Glorious GMMK 85% MOUSE: Razer Naga Trinity HEADSET: Go XLR with Shure SM7B mic and beyerdynamic DT 990

 

unRAID Plex Server CPU: Intel i7 6700 GPU: Nvidia Quadro P2000 MB: Asus B150M-C RAM: Crucial Ballistix 32gb DDR4 3000MT/s CPU Cooler: Stock Intel SSD: Western Digital 500GB Red HDD: 4TB Seagate Baracude 3x 4TB Seagate Ironwolf PSU: EVGA BT 80+ Bronze 450W Case: Cooler Master HAF XB EVO KB: Cheap Logitech KB + Mouse combo

Link to comment
Share on other sites

Link to post
Share on other sites

The FX architecture is nearly a decade old. Add to that, an FX 8-core has the same max theoretical IPC (instructions per cycle) as an intel i5 quad core. That automatically means that each Intel core is capable of twice the instructions of 2 AMD cores per cycle, if all things were equal, which they are not. The make up of an Intel core is different than an AMD core. And, once you add hyper threading, you add an additional IPC for each extra thread. 

 

if you were to compare a 5960X to an FX 8-core (any FX 8-core), you are looking at ~64 (i believe) maximum IPC for a 5960X, compared to ~28 maximum IPC on the FX 8-core. 

Isn't it still based on the K7 architecture or something?

 

Think of the AMD 6 and 8 cores differently. Cinebench recognizes my FX6350 as a 3 core with 6 threads even though it's advertised as a 6 core CPU it really isn't.

AIRC, it's 3 modules split into two cores. Which is just three larger cores split in half. I think.

Main rig on profile

VAULT - File Server

Spoiler

Intel Core i5 11400 w/ Shadow Rock LP, 2x16GB SP GAMING 3200MHz CL16, ASUS PRIME Z590-A, 2x LSI 9211-8i, Fractal Define 7, 256GB Team MP33, 3x 6TB WD Red Pro (general storage), 3x 1TB Seagate Barracuda (dumping ground), 3x 8TB WD White-Label (Plex) (all 3 arrays in their respective Windows Parity storage spaces), Corsair RM750x, Windows 11 Education

Sleeper HP Pavilion A6137C

Spoiler

Intel Core i7 6700K @ 4.4GHz, 4x8GB G.SKILL Ares 1800MHz CL10, ASUS Z170M-E D3, 128GB Team MP33, 1TB Seagate Barracuda, 320GB Samsung Spinpoint (for video capture), MSI GTX 970 100ME, EVGA 650G1, Windows 10 Pro

Mac Mini (Late 2020)

Spoiler

Apple M1, 8GB RAM, 256GB, macOS Sonoma

Consoles: Softmodded 1.4 Xbox w/ 500GB HDD, Xbox 360 Elite 120GB Falcon, XB1X w/2TB MX500, Xbox Series X, PS1 1001, PS2 Slim 70000 w/ FreeMcBoot, PS4 Pro 7015B 1TB (retired), PS5 Digital, Nintendo Switch OLED, Nintendo Wii RVL-001 (black)

Link to comment
Share on other sites

Link to post
Share on other sites

This was informal to me. It was cool to see rational comparisons and explanations.

 

...For the most part. Still a few dildos flaming like children, haha.

Link to comment
Share on other sites

Link to post
Share on other sites

 

Isn't it still based on the K7 architecture or something?

 

AIRC, it's 3 modules split into two cores. Which is just three larger cores split in half. I think.

 

No, I don't think so. Most of Zambezi was a new design/implementation compared to K7/8/10/10h, for example they moved to a 4 way front end decode but because of the increased core count effective instruction throughput across all threads was lower.

 

And pretty much, it's 3 modules each with 2 integer processing 'cores' that share the front end resources and the single FPU for each module can be used as two 128bit decoders.

Link to comment
Share on other sites

Link to post
Share on other sites

No, I don't think so. Most of Zambezi was a new design/implementation compared to K7/8/10/10h, for example they moved to a 4 way front end decode but because of the increased core count effective instruction throughput across all threads was lower.

 

And pretty much, it's 3 modules each with 2 integer processing 'cores' that share the front end resources and the single FPU for each module can be used as two 128bit decoders.

Neato. For an LGA 775 guy, you know a lot about the newer Kx architectures (compared to good 'ol K6 which I like the most).

Main rig on profile

VAULT - File Server

Spoiler

Intel Core i5 11400 w/ Shadow Rock LP, 2x16GB SP GAMING 3200MHz CL16, ASUS PRIME Z590-A, 2x LSI 9211-8i, Fractal Define 7, 256GB Team MP33, 3x 6TB WD Red Pro (general storage), 3x 1TB Seagate Barracuda (dumping ground), 3x 8TB WD White-Label (Plex) (all 3 arrays in their respective Windows Parity storage spaces), Corsair RM750x, Windows 11 Education

Sleeper HP Pavilion A6137C

Spoiler

Intel Core i7 6700K @ 4.4GHz, 4x8GB G.SKILL Ares 1800MHz CL10, ASUS Z170M-E D3, 128GB Team MP33, 1TB Seagate Barracuda, 320GB Samsung Spinpoint (for video capture), MSI GTX 970 100ME, EVGA 650G1, Windows 10 Pro

Mac Mini (Late 2020)

Spoiler

Apple M1, 8GB RAM, 256GB, macOS Sonoma

Consoles: Softmodded 1.4 Xbox w/ 500GB HDD, Xbox 360 Elite 120GB Falcon, XB1X w/2TB MX500, Xbox Series X, PS1 1001, PS2 Slim 70000 w/ FreeMcBoot, PS4 Pro 7015B 1TB (retired), PS5 Digital, Nintendo Switch OLED, Nintendo Wii RVL-001 (black)

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×