Announcement

Collapse
No announcement yet.

Intel Core i5 8400 vs. i5 9400F Meltdown/Spectre/L1TF/MDS Mitigation Impact

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

  • #11
    These results are interesting, especially aver the Cascalake test https://www.phoronix.com/scan.php?pa...mds-xeon&num=5 , where you conclude that the H/W mitigations on Cascadelake make a pretty big impact.

    If looking at the geometric mean of all the benchmarks carried out, the EPYC 7601 averages out to about a 1% hit with its Spectre mitigations. The dual Xeon Platinum 8280 Cascadelake setup with its mostly hardware-based mitigations was slower by 4% with the relevant mitigations enabled . Meanwhile the dual Xeon Gold 6138 server that unfortunately doesn't have the hardware mitigations saw a 11% hit from the benchmarks run with these Spectre/Meltdown/L1TF/MDS mitigations.
    And now the results in this test are showing no difference at all. Which seems after seeing the above linked Cascade Lake test a little surprising.

    Then i looked into it and in this document by Intel ( https://www.intel.com/content/www/us...-hardware.html )

    It shows that the 9400F can come in 2 flavours, a Intel64 Family 6 Model 158 Stepping 12 and a Intel64 Family 6 Model 158 Stepping 13, where the "Model 12" doesn't have the hardware mitigations in the same fashion as Cascade Lake has, but the "Model 13" does have full H/W mitigations.

    In your review i can't see you mentioning if you tested a Intel64 Family 6 Model 158 Stepping 12 9400F Sku or a Intel64 Family 6 Model 158 Stepping 13 9400F Sku, however this could potentionally make quite the difference.

    Comment


    • #12
      Originally posted by Chronia View Post
      These results are interesting, especially aver the Cascalake test https://www.phoronix.com/scan.php?pa...mds-xeon&num=5 , where you conclude that the H/W mitigations on Cascadelake make a pretty big impact.



      And now the results in this test are showing no difference at all. Which seems after seeing the above linked Cascade Lake test a little surprising.

      Then i looked into it and in this document by Intel ( https://www.intel.com/content/www/us...-hardware.html )

      It shows that the 9400F can come in 2 flavours, a Intel64 Family 6 Model 158 Stepping 12 and a Intel64 Family 6 Model 158 Stepping 13, where the "Model 12" doesn't have the hardware mitigations in the same fashion as Cascade Lake has, but the "Model 13" does have full H/W mitigations.

      In your review i can't see you mentioning if you tested a Intel64 Family 6 Model 158 Stepping 12 9400F Sku or a Intel64 Family 6 Model 158 Stepping 13 9400F Sku, however this could potentionally make quite the difference.
      Wasn't aware of any stepping difference w.r.t. mitigations for the 9400F. But when checking just now, neither: this new retail 9400F is a Model 158 Stepping 10.
      Michael Larabel
      https://www.michaellarabel.com/

      Comment


      • #13
        Originally posted by Michael View Post

        Wasn't aware of any stepping difference w.r.t. mitigations for the 9400F. But when checking just now, neither: this new retail 9400F is a Model 158 Stepping 10.
        Sorry to bother you again, but "Model 158 Stepping 10" should be a 8000 series Sku (8400, 8700K e.t.c. are "Model 158 Stepping 10") would seem weird if the 9400F is a Model 158 Stepping 10 also. Are you sure thats not the 8400?

        Comment


        • #14
          Originally posted by Chronia View Post

          Sorry to bother you again, but "Model 158 Stepping 10" should be a 8000 series Sku (8400, 8700K e.t.c. are "Model 158 Stepping 10") would seem weird if the 9400F is a Model 158 Stepping 10 also. Are you sure thats not the 8400?
          It's stepping 10, just double checked the 9400F system.
          Michael Larabel
          https://www.michaellarabel.com/

          Comment


          • #15
            Originally posted by Michael View Post

            It's stepping 10, just double checked the 9400F system.
            What is the 8400 stepping ? Is this just a relabel ?

            Comment


            • #16
              Originally posted by Michael View Post

              It's stepping 10, just double checked the 9400F system.
              Thats interesting as Intels states that 9400F's with any form of hardware mitigations are either "model 158 stepping 12" or "model 158 stepping 13".

              With "model 158 stepping 12" having mitigations for Meltdown, L1TF/Foreshadow and MFBDS/RIDL and "model 158 stepping 13" having mitigations for Spectre V2, Meltdown, , Spectre V4, L1TF/Foreshadow and all MDS variants.

              the "model 158 stepping 10" is not on the list though for any hardware mitigations, so seeing the same results beween the 8400 and the 9400F is actually not that strange then if this 9400F you tested is actually a stepping without any hardware mitigations at all. Might be worth some further tests.

              Comment


              • #17
                Might explain why Michael got a "good deal" on his 9400.

                Comment


                • #18
                  Originally posted by rbmorse View Post
                  Might explain why Michael got a "good deal" on his 9400.
                  It was through NewEgg retail/new with no noted differences to any other 9400F models.
                  Michael Larabel
                  https://www.michaellarabel.com/

                  Comment


                  • #19
                    The "F" models are harvested CPUs which Intel previously did not sell. So it is not surprising that you see older steppings too.
                    Originally posted by tchiwam View Post
                    What is the 8400 stepping ? Is this just a relabel ?
                    I think there are two variants.
                    One is the 6-core die with just the graphics disabled (U0), and one is the 8-core die with two cores and the graphics disabled (P0, R0). I think only the R0 (stepping 13) is hardware mitigated.
                    Last edited by chithanh; 06 June 2019, 06:15 PM.

                    Comment


                    • #20
                      All of these later comments could be the seed for a complete article...

                      Comment

                      Working...
                      X