Announcement

Collapse
No announcement yet.

DDR3-800MHz To DDR3-2133MHz Memory Testing With AMD's Kaveri

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • DDR3-800MHz To DDR3-2133MHz Memory Testing With AMD's Kaveri

    Phoronix: DDR3-800MHz To DDR3-2133MHz Memory Testing With AMD's Kaveri

    For those trying to skimp on a system memory purchase for a new AMD Kaveri system or just curious about the impact the system memory bandwidth has on the latest-generation APUs, here are some benchmarks looking at the overall system memory performance when testing all major DDR3 system memory speeds between DDR3-800MHz and DDR3-2133MHz.

    http://www.phoronix.com/vr.php?view=19708

  • #2
    I find it rather disturbing for the fact that the i7 4770k performs almost twice as fast (CPU wise) than the a10-7850. Especially since the i7 runs with 1600mhz memory while the a10-7850 can go much higher.

    It's been 7 years since I last build my computer (I was mostly guided in my choice by someone else tbh). I'm considering to buy an i7 3820 (Ivy-Bridge e, no iGPU ... yay!), but according to cpu-world.com this CPU does not even perform as well as i7 4770 which even has an iGPU. Confusing...

    Comment


    • #3
      xonotic with r_glsl_skeletal 1 should give a flatter diagram
      less memory access

      Comment


      • #4
        Michael, any chance to test 2400MHz RAM ?

        Comment


        • #5
          As mentioned in article multiple times, he is going to.

          Comment


          • #6
            Originally posted by AJSB View Post
            Michael, any chance to test 2400MHz RAM ?
            learn to read the article before posting in the forum ... please! This is going to many forum-posters out there - not only you AJSB...

            Comment


            • #7
              It's pretty interresting how many of the performance results scales about 1:1 with the increase of memory speed.
              I wonder how far that image would remain, in a scenario where there wasn't a limit to the speed of the memory.

              Also, not knowing all that much about it, this could be proof that the APU itself is capable of much more, but is severely bottlenecked by memory-access. One could speculate what'd happen, if AMD had doubled the memory bandwidth.

              I guess it kinda makes sense. I'm not at all sure, but if I'm right, the clock speed on videocard memory isn't all that high, but the bandwidth is very big.

              Comment


              • #8
                Originally posted by Rexilion View Post
                I find it rather disturbing for the fact that the i7 4770k performs almost twice as fast (CPU wise) than the a10-7850. Especially since the i7 runs with 1600mhz memory while the a10-7850 can go much higher.

                It's been 7 years since I last build my computer (I was mostly guided in my choice by someone else tbh). I'm considering to buy an i7 3820 (Ivy-Bridge e, no iGPU ... yay!), but according to cpu-world.com this CPU does not even perform as well as i7 4770 which even has an iGPU. Confusing...
                Why does that strike you as odd? Intel cores have been as powerful as two AMD cores for a very long time now. The A10-7850K is only a quad core FX-based processor. To compare to the i7 4770K, you would need the FX-8320/50. As there are no octo-core APUs, you won't find quad core i7s being dethroned by an APU in regular CPU benchmarks. However, AMD recently released some documentation for a new 16 core processor which may or may not be an upcoming desktop processor. Perhaps an 8 core APU will come along next year.

                Comment


                • #9
                  Originally posted by Rexilion View Post
                  I find it rather disturbing for the fact that the i7 4770k performs almost twice as fast (CPU wise) than the a10-7850. Especially since the i7 runs with 1600mhz memory while the a10-7850 can go much higher.

                  It's been 7 years since I last build my computer (I was mostly guided in my choice by someone else tbh). I'm considering to buy an i7 3820 (Ivy-Bridge e, no iGPU ... yay!), but according to cpu-world.com this CPU does not even perform as well as i7 4770 which even has an iGPU. Confusing...
                  Don't trust sites like cpu-world...

                  Want advice? I will give you some.

                  If the heaviest thing you will do is gaming, you don't need an i7. I would advise a Core i5 4670. You will get about the same performance for 30% less money. Gaming doesn't need hyper threading or 8 threads...

                  Comment


                  • #10
                    what about timings? dont they have influence on the performance?
                    seeing the results i really must wonder why AMD did choose not to go all the way and go for GDDR5 and put some pressure on Intel. Or at least triple-channel...

                    Comment


                    • #11
                      Originally posted by jakubo View Post
                      what about timings? dont they have influence on the performance?
                      seeing the results i really must wonder why AMD did choose not to go all the way and go for GDDR5 and put some pressure on Intel. Or at least triple-channel...
                      The timings don't have much affect since the bottleneck is primarily a bandwidth one rather than a latency one. I remember that it was originally planned to have GDDR5 embedded on the chip but that was canned for the first gen Kaveri -- perhaps due to budget constraints. Instead of triple channel, I don't see why they couldn't just go straight for quad channel.

                      Comment


                      • #12
                        Originally posted by jakubo View Post
                        what about timings? dont they have influence on the performance?
                        seeing the results i really must wonder why AMD did choose not to go all the way and go for GDDR5 and put some pressure on Intel. Or at least triple-channel...
                        Expensive memory modules, I guess.

                        Comment


                        • #13
                          Originally posted by mmstick View Post
                          The timings don't have much affect since the bottleneck is primarily a bandwidth one rather than a latency one. I remember that it was originally planned to have GDDR5 embedded on the chip but that was canned for the first gen Kaveri -- perhaps due to budget constraints. Instead of triple channel, I don't see why they couldn't just go straight for quad channel.
                          Documents indicate that kaveri may have support for quad-channel and GDDR5 memory, but that it has been disabled. I suppose a different package would be needed for quad-channel, and GDDR5 requires very short traces, so it would likely only work right with BGA systems where everything is soldered down.
                          http://www.anandtech.com/show/7702/a...e-gddr5-option

                          Wow, the GPU tests scale linearly with memory bandwidth available... that means the GPU is very bandwidth starved? Maybe they could have gotten much better performance by tuning the memory controller? Benchmarks indicate that the AMD memory controllers are less efficient than the Intel memory controllers.
                          Last edited by grigi; 01-21-2014, 05:58 AM. Reason: wasn't finished

                          Comment


                          • #14
                            Originally posted by Rexilion View Post
                            I find it rather disturbing for the fact that the i7 4770k performs almost twice as fast (CPU wise) than the a10-7850. Especially since the i7 runs with 1600mhz memory while the a10-7850 can go much higher.

                            It's been 7 years since I last build my computer (I was mostly guided in my choice by someone else tbh). I'm considering to buy an i7 3820 (Ivy-Bridge e, no iGPU ... yay!), but according to cpu-world.com this CPU does not even perform as well as i7 4770 which even has an iGPU. Confusing...
                            You're comparing a 300US cpu to a 190US CPU... Gee Gorge can I pet the rabbits. The thing is Benchmarks can lie in Intels favor but the truth is the Kaveri (like other CPUS in it's bloodline) Is pretty memory starved and lack of a L3 hurts it's performance. Does that make it a bad dual module? No it makes it a pretty darn good one just with room for improvement...

                            That being said if they make a 4 mod steamroller based FX I would buy that in a heartbeat.

                            Comment


                            • #15
                              Originally posted by nightmarex View Post
                              You're comparing a 300US cpu to a 190US CPU... Gee Gorge can I pet the rabbits. The thing is Benchmarks can lie in Intels favor but the truth is the Kaveri (like other CPUS in it's bloodline) Is pretty memory starved and lack of a L3 hurts it's performance. Does that make it a bad dual module? No it makes it a pretty darn good one just with room for improvement...

                              That being said if they make a 4 mod steamroller based FX I would buy that in a heartbeat.
                              The truth is, Intels are far better in fpu performance and their memory controller is more efficient. They also consume less power.

                              AMD is just cheaper/price competitive on low end and with a better igpu, though it is quite bandwidth starved and you don't get to see its real performance.

                              Also HSA and Mantle are vaporware, especially on Linux. By the time AMD brings the software that exploits them, Carizzo or its succesor will be available...

                              Comment

                              Working...
                              X