Announcement

Collapse
No announcement yet.

Another reason for me not to buy AMD anymore

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

  • Another reason for me not to buy AMD anymore

    Now they are cheating on their processor clockspeeds: http://www.xbitlabs.com/news/cpu/dis...igh_Loads.html

  • #2
    Hm, I'm not a native english speaker but the english in the article is rather poor.

    The quote at the end does have an opening quotation mark but not a closing one. They also don't say where they got that quote from. Googling it only shows http://www.hitechreview.com/it-produ...er-load/42259/ and http://news.softpedia.com/news/AMD-T...e-342157.shtml referencing that article.

    Come on, even phoronix is better journalism.

    Phoronix may even have measured the actual performance loss.

    Comment


    • #3
      I don't see this as cheating, all cpus will throttle if their thermal specs are exceeded.

      Comment


      • #4
        Originally posted by curaga View Post
        I don't see this as cheating, all cpus will throttle if their thermal specs are exceeded.
        The thermal specs should not be exceeded when the CPU is running at its advertised normal speed. If it does it is mislabelled and should be sold as lower-spec modell that runs at a speed it can bear without having to downclock itself when used as intended.

        Comment


        • #5
          Originally posted by Vim_User View Post
          The thermal specs should not be exceeded when the CPU is running at its advertised normal speed. If it does it is mislabelled and should be sold as lower-spec modell that runs at a speed it can bear without having to downclock itself when used as intended.
          The thermal specs are given for a specific ambient temperature. Running a processor at it's advertised normal speed in winter in northern Scotland and mid-summer in southern Spain will likely result in very different temperatures for the same workload.

          Comment


          • #6
            Of course those test shouldn't be done at 50C ambient temperature, and I seriously doubt they were. In that case the Intel APUs should have the same problem, which they hadn't.

            Comment


            • #7
              I think it's a case of consumer vs server workload. Consumer cpus (or gpus, see furmark) are not assumed to run at 100% for hours, so they're not thermally specced to withstand that, so that marketing can claim higher default numbers.

              Server cpus typically are specced for such workloads.

              Whether this is false advertising for consumer items is up for debate.

              Comment


              • #8
                Originally posted by curaga View Post
                I think it's a case of consumer vs server workload. Consumer cpus (or gpus, see furmark) are not assumed to run at 100% for hours, so they're not thermally specced to withstand that, so that marketing can claim higher default numbers.

                Server cpus typically are specced for such workloads.

                Whether this is false advertising for consumer items is up for debate.
                My consumer Phenom II X6 (125W version) can run under 100% load for hours without downclocking itself, the same is true for my laptop's Athlon QL-66 and was true for my former Core 2 Quads (Q6600 and Q9550) and Athlon X2 5200+ and any CPU I used before that.
                I can't see any reason why I should expect it to be different with newer CPUs, consumer or not. If a CPU is advertised as 3.8GHz model it has to run 3.8GHz, not 3.4GHz.

                Comment


                • #9
                  AFAIK thermal throttling to stay within a power envelope is a pretty new feature for CPUs (ours and others). I'm not sure the other CPUs you mentioned are even able to do that.

                  Comment


                  • #10
                    I don't think it is a good hardware design when the cpu consumes by default too much power that it has to lower clockspeeds on certain loads. Intel has power saving cpus as well, there the default clock is lower by default - the rest is done using turbo steps (for i5+). Turbo boost has of course a power usage limit (can be set in firmware for oc). So basically AMD should rebrand the cpus and use a lower default and more turbo steps. A cpu that does not run a specified speed under all loads is a joke.

                    Comment


                    • #11
                      Originally posted by Vim_User View Post
                      My consumer Phenom II X6 (125W version) can run under 100% load for hours without downclocking itself, the same is true for my laptop's Athlon QL-66 and was true for my former Core 2 Quads (Q6600 and Q9550) and Athlon X2 5200+ and any CPU I used before that.
                      I can't see any reason why I should expect it to be different with newer CPUs, consumer or not. If a CPU is advertised as 3.8GHz model it has to run 3.8GHz, not 3.4GHz.
                      Those older cpus simply use other methods of throttling than downclocking. (assuming they did reach thermal limits; depends on cooling, ambient temp etc.)

                      The most common way I remember was to delay instructions (start inserting nops every now and then).

                      Comment


                      • #12
                        Originally posted by bridgman View Post
                        AFAIK thermal throttling to stay within a power envelope is a pretty new feature for CPUs (ours and others). I'm not sure the other CPUs you mentioned are even able to do that.
                        Since the Phenom II X6 has a turbo function it better knows about its power envelope. The point is not that CPUs do that, but that a CPU that is advertized as 3.8 GHz CPU is not able to sustain that speed under load. While Kano thinks that such a CPU is a joke I would go a step further and say that such a CPU is a fraud.

                        Comment


                        • #13
                          Originally posted by curaga View Post
                          Those older cpus simply use other methods of throttling than downclocking. (assuming they did reach thermal limits; depends on cooling, ambient temp etc.)

                          The most common way I remember was to delay instructions (start inserting nops every now and then).
                          Those older CPUs are able to downclock themselves if they reach their maximum temperature, but they never do that under default conditions.

                          Comment


                          • #14
                            Originally posted by Vim_User View Post
                            Those older CPUs are able to downclock themselves if they reach their maximum temperature, but they never do that under default conditions.
                            Maybe not on Linux, because the OS support wasn't there, but if you search around Windows-oriented forums you'll find all kinds of questions about clock reduction over the last few years, particularly when running stress tests.

                            Newer CPUs make more clock decisions on-chip without requiring OS intervention.

                            Comment


                            • #15
                              Originally posted by curaga View Post
                              I think it's a case of consumer vs server workload. Consumer cpus (or gpus, see furmark) are not assumed to run at 100% for hours, so they're not thermally specced to withstand that, so that marketing can claim higher default numbers.

                              Server cpus typically are specced for such workloads.

                              Whether this is false advertising for consumer items is up for debate.
                              You must be kidding. Right?

                              It is a very serious flaw if the product is not 100% stable in the most serious workload imaginable, in continuous operation. The problem with furmark was that it was a harder workload than engineers could imagine. No natural workload is as demanding.

                              Comment

                              Working...
                              X