Jump to content
AIDA64 Discussion Forum
Glowing1196

Question on cache and memory benchmarks!

Recommended Posts

0eb30f2442a7d9335c2885ecac4bd11372f001a8

 

( The picture of testing result can also be seen here:http://imgsrc.baidu.com/forum/w%3D580/sign=5d8024603ac79f3d8fe1e4388aa0cdbc/0eb30f2442a7d9335c2885ecac4bd11372f001a8.jpg )

 

This is the testing result of my 4-way AMD Opteron 6147 machine, but some people keep telling me this result is impossible, which makes me a little doubtful now!

 

Could this be an error of Aida64, or it’s just a fact that some people refuse to believe?

 

Looking forward to your reply!

 

Best regards!

Share this post


Link to post
Share on other sites

1) Do you have 2 or 4 processor sockets populated?

 

2) Do all processors have DDR3-1333 memory installed?  So every processors use the same memory configuration?

 

In case you have 4 processor sockets populated, and every processors use the same DDR3-1333 memory configuration, that would mean you've got 16 memory channels total, each running at DDR3-1333 speed, which would mean a total memory bandwidth of 166.6 GBytes/sec.  Hence the results could well be accurate ;)

 

The confusion may come from the fact that AIDA64 (the main application itself) only supports up to 32 processor threads, so it cannot show you all processors on the Cache & Memory Benchmark Panel.  However, the multi-threaded memory benchmarks support up to 64 processor threads, so it can utilize all 48 processing threads you've got in your system (if you have all 4 processor sockets populated, each with a 12-core Magny-Cours CPU).

 


Regards,

Fiery

Share this post


Link to post
Share on other sites

1) Do you have 2 or 4 processor sockets populated?

 

2) Do all processors have DDR3-1333 memory installed?  So every processors use the same memory configuration?

 

In case you have 4 processor sockets populated, and every processors use the same DDR3-1333 memory configuration, that would mean you've got 16 memory channels total, each running at DDR3-1333 speed, which would mean a total memory bandwidth of 166.6 GBytes/sec.  Hence the results could well be accurate ;)

 

The confusion may come from the fact that AIDA64 (the main application itself) only supports up to 32 processor threads, so it cannot show you all processors on the Cache & Memory Benchmark Panel.  However, the multi-threaded memory benchmarks support up to 64 processor threads, so it can utilize all 48 processing threads you've got in your system (if you have all 4 processor sockets populated, each with a 12-core Magny-Cours CPU).

 

Regards,

Fiery

 

I became not sure about my knowledge of Opteron's memory controller after I read your reply, so I checked it in AMD's official PDF about Opteron. I got this from the PDF of AMD.

 

• Package G34
• 144-bit DDR3 SDRAM controller operating at frequencies up to 1333 MT/s (667 MHz)
• Supports up to twelve (12) registered DIMMs
• Supports up to eight (8) unbuffered DIMMs
• On-line spare feature provides single-rank DRAM redundancy
 
I think from this I can make sure that we can only get two memory channels. If so, there should only be 8 memory channels in a four-way Opteron server.

Share this post


Link to post
Share on other sites

It's two memory channels per processor node.  A 12-core Magny-Cours processor has 2 nodes, so a single processor package supports 4 memory channels.  It effectively works as two 6-core processors (each supporting 2 memory channels) put into a single CPU package.

Share this post


Link to post
Share on other sites

We've just extended the 32 threads benchmarking capabilities of AIDA64 to 640 threads, and added processor groups support as well.  Make sure to upgrade to the latest beta version of AIDA64 Extreme Edition available at:

 

http://www.aida64.com/downloads/aida64extremebuild2546y3mbp1kvdjzip

 

After upgrading to this new version, make sure to restart Windows to finalize the upgrade.

 

Using this release you can use all CPU, FPU and memory benchmarks of AIDA64 to measure the full 48-core performance of your configuration.

Share this post


Link to post
Share on other sites

Hi Fiery

 

Something has been changed to the bench

Before I had it

 

 

and now

 

 

Thanks

 

PS: it may also be because I installed the new bios for Ivy Bridge-E (Rampage IV Extreme 4310)

Share this post


Link to post
Share on other sites

It looks like it may be due to a BIOS issue.  We've checked both AIDA64 versions on our Intel DX79SI test system with Core i7-3960X CPU, but haven't found any difference in the scores obtained.  We did update the benchmark module between AIDA64 v3.00.2500 (stable release) and AIDA64 v3.00.2578 (latest beta release), but it only affects Ivy Bridge-E/EN/EP processors.

 

Since your memory latency scores seem unchanged, but the memory bandwidth scores seem to drop to half, it looks like if the memory controller was configured for dual-channel operation instead of quad-channel operation.  Although the memory controller (IMC) reports quad-channel mode, as AIDA64 reports it.

Share this post


Link to post
Share on other sites

The memory settings have not changed, still Quad Channel.
I'm watching the side of the bios, and C-State options (some options have changed by default, I believe)

I tested it tomorrow, and I come to tell you

 

Thanks Fiery

Share this post


Link to post
Share on other sites

I put forward last bios, and performance is good.
With the new bios, I configured the same (options like C-State have changed before I left on Auto, then I have no choice between "enable" or "disable")

I do not see what has changed

Share this post


Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...

  • Similar Content

    • By wichert
      Is the benchmarking function also made for vm's or only for physical machines?
      thanks in advance.
    • By xixou
      gppu test fail on 1950x CPU

       
       

       
      On second run CPU test is passing but GPU benchmark looks like values are only for 1 gtx1070 instead of 4 .
    • By Vlask
      i'd like to see simple GPU benchmark for testing basic values of graphic cards like:

      Pixel Fillrate (MPixel/s) - think can be found in some 3Dmarks
      Texel Fillrate (MTexel/s) - think can be found in some 3Dmarks
      Triangle/Vertices Rate (M/s) - don't know how gpu makers measure this, cant remember any benchmark for this one...

      Best will be based on Opengl 1.1 so also very old profi cards can be tested (3DLabs, Intergpraph and similar stuff) and test won't be tied to some version of DirectX.
      Fillrates can be measured by really old, outdated and no longer supported SPECglperf - https://www.spec.org/gwpg/pastissues/Feb2_02/opc.static/glperf.htm , but results have too many variants of results (see attached result file as warning how it should not look) and wont work on modern systems. 

      This kind of benchmark would be usefull for diagnostics between theoretical values of cards and real scenario. Also for detecting of number texture units and ROPS on cards with unknown specs - getting often mixed info from various sources about these at mobile chips or OEM cards (GPU makers ignoring them mostly and won't release any closer info). 
      FillRate.log
    • By Fiery
      Due to the enermous number of requests we've been receiving since the Ryzen market launch, concerning various confusions about AIDA64 and Ryzen, hereby we post a clarification. AIDA64 is currently not 100% compatible with the recently unveiled AMD Ryzen high-performance x86 processors. It's because AIDA64 still has a few issues that we need to fix. However, in order to fix those issues, we first need to run a series of very long benchmark tests on Ryzen, and that -- among with the bug fixes themselves -- will take several days to complete.
      As for the bugs and limitations we so far discovered:
      UPDATE: We have fixed #3, #4, #5 and #7 in the latest AIDA64 v5.90.4200 stable update, which is now 100% compatible with AMD Ryzen processors:
      https://www.aida64.com/downloads/latesta64xe
      1) A number of minor hardware detection issues were already fixed in the latest AIDA64 beta update.
      2) The list of Turbo and XFR PStates are invisible on Ryzen, so it's not possible to properly enumerate or track them using a software. When a core of the AMD Ryzen processor goes into idle, the core will report the clockspeed of the P2 power state (e.g. 2200MHz on the Ryzen 7 1800X) and enter into the core-c1 (CC1) or core-c6 (CC6) sleep state. While the VID remains detectable in these states, the states are power gated and the true frequency is not known to the OS or monitoring utilities. As indicated from the “fine-grained Pstate” commentary released at Ryzen Tech Day, the AMD Ryzen’s processor true frequencies in these modes are significantly lower than reported via the “last known” P2 reading. AMD engineering tells us that V/f changes can be executed at 1ms intervals, indicating that the act of monitoring the states with the resolution necessary to accurately capture this behavior would also prevent cores from entering into the ultra low-power CC1 or CC6 states.
      3) L1 cache bandwidth and latency scores, as well as memory bandwidth and latency scores are already accurately measured.
      4) L2 cache and L3 cache scores indicate a lower performance than the peak performance of Ryzen. The scores AIDA64 measure are actually not incorrect, they just show the average performance of the L2 and L3 caches rather than the peak performance. It will of course be fixed soon.
      5) Even though AIDA64 warns about a potential lack of optimization, the CPU and FPU benchmarks should be indicative of the full potential of Ryzen. We may be able to tweak e.g. the FPU Julia benchmark to squeeze even more performance out of Ryzen, but we don't expect the improvement to be substantial.
      6) The CPU Hash benchmark provides an exceptionally great score on Ryzen due to the hardware accelerated SHA instructions capability of Ryzen. It's absolutely normal that hardware acceleration boosts CPU computing performance by such a margin.
      7) AM4 motherboards are not yet supported by the latest AIDA64 stable build of v5.80.4000. Make sure to use the latest AIDA64 beta build to have accurate sensor measurements on ASRock, Asus, Biostar, Gigabyte, and MSI AM4 motherboards.
      We will post further updates to this topic as we progress with our bug fixing efforts on our Ryzen test systems.
    • By shotx
      Hi everyone.
      I'd like to know if there is any chance to export results from "Manage User Results" i've run 10s of benchmarks on different configuration but i can only remove them from right click and there are no other options. is there something i missed or maybe 3rd party addon that allows exporting these results?!
       
×
×
  • Create New...