Sign in with
Sign up | Sign in

AMD FX Vs. Intel Core i3: Exploring Game Performance With Cheap GPUs

AMD FX Vs. Intel Core i3: Exploring Game Performance With Cheap GPUs
By

Following our sub-£160 gaming CPU comparison, we put Intel's Core i3-2100 and AMD's FX-4100 under the microscope. This time, we test a number of different graphics cards from AMD to see how GPUs affect perceived processor bottlenecks.

At the end of January, we published our analysis of the sub-£160 gaming processor market called Picking A Sub-£160 Gaming CPU: FX, An APU, Or A Pentium?. We were surprised to find that Intel’s budget-oriented LGA 1155 offerings are surprisingly capable when it comes to handling modern titles. In fact, the £90 Core i3-2100 beat out AMD's entire line-up including top-tier Phenom IIs, Athlon IIs, APUs, and even the new FX models. Although they're easier to overclock, AMD’s best efforts could only achieve parity with the Core i3-2100, and Intel's Core i5 was so far ahead of the sub-£160 pack that it sat in a league of its own.

Now, we used a very high-end Radeon HD 7970 graphics card in that article because we wanted to isolate CPU performance. You can't draw conclusions about a CPU's potential when you're faced with a graphics card bottleneck, after all. But some of our readers rightly pointed out that, when it comes to building an inexpensive machine, our combination is unrealistic. A £90 CPU would never accompany a £450 graphics card. And if we used an entry-level GPU, the resulting bottleneck would have masked the differences between processors to a greater extent. The counter, of course, is that a cheaper graphics card would have also imposed lower resolutions and detail settings, shifting load back in the direction of the CPU.

As you know, though, we put a big emphasis on addressing your feedback, so we went back to the lab to run some follow-up data on two of the most interesting £90 options from our previous story. Intel's Core i3-2100 is the low-cost processor to beat, so we made sure to include it. On the other hand, with AMD's Phenom II and Athlon II lines disappearing from store shelves, the £90 FX-4100 represents that company’s best low-priced option.

Every game's workload is different, but Intel’s i3-2100, on average, achieved 18% higher minimum frame rates and 11% higher average frame rates compared to the FX-4100 in our previous story. As we said, though, that was with a Radeon HD 7970. This time around, we’re using a broader range of graphics cards ranging from the Radeon HD 5570 up to the Radeon HD 6950 to see if the bottleneck situation changes.


AMD FX-4100Intel Core i3-2100
Codename: ZambeziSandy Bridge
Process: 32 nm 32 nm
Cores (Threads): 4 (4)
2 (4)
Clock Speed (Turbo): 3.6 (3.8) GHz
3.1 GHz
Interface: Socket AM3+LGA 1155
L3 Cache: 8 MB3 MB
Thermal Envelope:
95 W
65 W
Online Price:
£90
£90


We also received some feedback on our test platform's memory configuration; it was suggested that AMD's FX might perform better complemented by higher memory data rates. So, this time we're using 8 GB (2 x 4 GB) of Corsair Vengeance DDR3-1600 at 8-8-8-24 timings.

Ask a Category Expert

Create a new thread in the UK Article comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 11 comments.
This thread is closed for comments
  • 0 Hide
    Anonymous , 23 February 2012 13:59
    This is an uncharacteristically sloppy report by THG. A significant fraction of the graphs do not have the correct y-axis range for the data.
  • -1 Hide
    13thmonkey , 23 February 2012 15:06
    Is there not a way that you can test Bf3 better, i'm seeing a few people who have claimed much better frames on online bf3 going from dual to quad.
    perhaps rent a server, pay some people to stand around and not do anything, and have the testing machine run a constant path thinking noshar docks, running from under the railway bridge to the B flag, whilst being watched by say 10 people.
    I've seen my frames jump when going to full server to empty so it has to be partly loaded, hence you need the audience. PITA, but it might give you a more realistic test, i'd hope it was the observation that causes load and not just potential impacts.
    Also this page doesn't let me submit unless in compat mode, but most others do...
  • -2 Hide
    13thmonkey , 23 February 2012 23:48
    whats up with the starcraft II results, the average certain is below 16, looks more like 30-40, whats with the ever climbing frame rates, did any look at the graphs and the words, and wonder if it all made sense.
  • 0 Hide
    cleeve , 24 February 2012 01:34
    13thmonkeywhats up with the starcraft II results, the average certain is below 16, looks more like 30-40, whats with the ever climbing frame rates, did any look at the graphs and the words, and wonder if it all made sense.


    The data is valid, I'm not sure what else to answer you with. If you think there's an error and want to look over it personally PM me and I'll send you the excel spreadsheets.
  • -1 Hide
    13thmonkey , 24 February 2012 01:43
    Its the constantly climbing frame rate, assuming x axis is time, it climbs off the top of the graph and yet you claim to have low frame rates. Have PM'd.
  • 1 Hide
    williehmmm , 24 February 2012 01:53
    13thmonkeywhats up with the starcraft II results, the average certain is below 16, looks more like 30-40, whats with the ever climbing frame rates, did any look at the graphs and the words, and wonder if it all made sense.


    I think it was explained by units being destroyed, then removed from the battlefield, therefore less to render, over time less and less, therefore higher frame rates at the end.
  • 0 Hide
    williehmmm , 24 February 2012 01:54
    Yup, as I read in the article.
  • 0 Hide
    mitunchidamparam , 24 February 2012 03:16
    Quote:
    I think it was explained by units being destroyed, then removed from the battlefield, therefore less to render, over time less and less, therefore higher frame rates at the end.

    Is that because of the GPU bottle neck or CPU?
  • -1 Hide
    jrtolson , 28 February 2012 09:15
    did u not know the people that run this site are on Intel's Payroll :-P
  • 0 Hide
    bemused_fred , 5 May 2012 20:42
    jrtolsondid u not know the people that run this site are on Intel's Payroll :-P


    Wait, I'm confused. What about the normal people who like intel's CPUs? Are they on the payroll too?
  • 0 Hide
    Anonymous , 20 May 2012 17:21
    I'm not impressed. AMD's quad-core chips clocked almost 20% higher still barely match the speed of a baseline dual-core i3 (which also puts out 30w less heat). In fact, AMD's 2012 quad-core chips are still no faster than Intel's early 2010 i3-530's dual-core "Westmere" (socket 1156) architecture clock-for-clock. Almost 2.5 years behind in performance.

    AMD seriously need a whole new architecture. Piling on more cores / clock speed is just "Intel P4 reloaded".