Page 1 of 2 12 LastLast
Results 1 to 25 of 41

Thread: Memory Timing Benchmark (CL/tRCD/tRP/tRAS/CR/tRC/tRFC/tREF)

  1. #1
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82

    Memory Timing Benchmark (CL/tRCD/tRP/tRAS/CR/tRC/tRFC/tREF)

    Hello. it's newbie on this forum.
    I'm not sure that whether I can upload this kind of bench on this board. (this board seems to consist of reviews of "a certain model of" HW... am I right?)
    Please announce me whenever I (unintentionally of course ;-)) forbid the rules of this forum.


    ...okay. then let's back to the main context.
    I benched my memory with several different ram timing settings. Tests include:
    1. Super PI 32M digits of Pi calculation
    2. Lavalys Everest Cache & Memory Benchmark
    3. Video Transcoding (1080p TP -> mkv using H.264)

    and tested ram timing items are:
    1. CL: 6~11
    2. tRCD: 9~11
    3. tRP: 6~11
    4. tRAS: 24~30
    5. Command Rate: 1 / 2
    6. tRC: 15~40
    7. tRFC: 90ns / 110ns / 160ns / 300ns 350ns
    8. tREF: 3.9ms / 7.8ms

    (for the test, except tRC and tREF, the lowest value is default. tRC and tREF have their highest value as default)

    and other system setup is:



    - CPU: AMD Phenom II X6 @ 4.0GHz / NB 2.75GHz
    - M/B: ASUS M4A89GTD-PRO USB3
    - RAM: G.SKILL PIS PC3-19200 CL9 4GB (2GB x 2) @ 2000MHz
    - Storage: Intel X25-M G2 80GB
    - PSU: PC Power & Cooling Silencer 910W 80PLUS Silver


    Super PI test

    Note: sorry for 'magic graph'. since it takes numerous min. for 32M Pi caculation, results are differred only by a very second. so it's unavoidable to show 'meaningful' graphs.

    1. CL Test


    2. tRCD Test


    3. tRP Test


    4. tRAS Test


    5. Command Rate Test


    6. tRC Test


    7. tRFC Test


    tRFC and tREF are indexed by actual time (second) while others by clock count. It's because they directly indicate characteristics of electrical working mechanism of a memory chip. Both are related to a memory's refresh rate, tREF determines how frequently a chip shall be refreshed and tRFC determines the time interval from the moment of 'refresh' (memory access is unavailable) to when a memory access is back to available. So in case of tREF, the bigger value the better at performance, but the contrary is more likely at stability.

    8. tREF Test


    As of now, we covered all 8 elements. Let's see overall analysis.

    Overall Analysis: Super PI


    (...sorry for Korean letter. actually I uploaded this bench to my private blog) The title of the graph is that 'how a ram timing value affects performance when we change just '1-degree' of ram timing option provided by BIOS'. As you see, tREF affects the most but not more than 1%, and followed by tRFC-Command Rate-CL. It's impressive that well-known items such as CL, tRCD affect far less than 'minor' items such as tREF and tRFC.

    Then let's go to next test result - Everest Cache & Memory Benchmark


    Everest Cache & Memory Benchmark
    - Memory Bandwidth test -

    Each Everest test consists of two parts: Bandwidth and Latency.
    Let's cover the bandwidth results first.

    1. CL Test


    2. tRCD Test


    3. tRP Test


    4. tRAS Test


    5. Command Rate Test


    6. tRC Test


    7. tRFC Test


    8. tREF Test


    Like Super PI test and unlike other ram timings, bigger tREF value is better at performance.

    Let's see overall analysis.

    Overall Analysis: Read Bandwidth


    Overall Analysis: Write Bandwidth


    Overall Analysis: Copy Bandwidth


    In read bandwidth test, 4 most-affective ram-timing items are flatted around 2%. Command Rate-tREF-CL-tRFC are said affective items and other 4 ram-timings merely affect performance. But write bandwidth remains nearly unchanged during various ram-timing values has changed. In case of copy bandwidth, only tREF and tRFC exceed the affectiveness of 1% and others remain below 1%. In other words, only tREF and tRFC are actually affect copy bandwidth.

    Then let's go to latency test.

    - Latency test -

    1. CL Test


    In latency test, change of CL value derives nearly a linear trendine.

    2. tRCD Test


    Seems merely changed, but it's not 'that small' compared to latter results.
    ...At least the trendline is undoubtedly linear.

    3. tRP Test


    Little fluctuation is appeared, but it seems random empirical error.

    4. tRAS Test


    5. Command Rate Test


    6. tRC Test


    Guess there's only superior advantage on the value "tRC 25"? I guess not.

    7. tRFC Test


    8. tREF Test


    Overall Analysis: Latency


    Latency test seems more dependant to ram-timing values than two previous tests (Super PI & Bandwidth). 3 items exceed 1% of affectiveness and among them, 2 exceed 2.5% to performance. 2.5% performance increment upon no CPU / RAM clock change is not just a small variation.

    Then let's go to the last test: video transcoding.


    Video Transcoding test

    This test is to measure the time of converting 1920x1080 TP file to MKV, same resolution. H.264 codec is used. No GPGPU acceleration.

    1. CL Test


    2. tRCD Test


    3. tRP Test


    4. tRAS Test


    5. Command Rate Test


    6. tRC Test


    7. tRFC Test


    8. tREF Test


    Overall Analysis: Video Transcoding time


    Similar to Super PI test, no items reached 1% and tREF marks the top. below CL, affectivenesses cannot even reach one third percent. But still remember: nearly 1% reduction in transcoding time with CPU & RAM clock remain unchanged is not 'that' small.


    So, by far, we covered 3 areas: Pi calculation, Synthetic bench, and Video transcoding. Let's see how a ram-timing's affectiveness differ through that benchmark areas.

    Affectiveness among test areas


    As you see, tRP/tRAS and tRC have nearly "no" impact on performance.
    Then let's calculate average affectiveness:
    Average = {Super PI + (Read + Write + Copy)/3 + Latency + Encoding}/4
    (name of each term indicate a ram-timing's affectiveness on that test area)

    Average affectiveness by Ram-timing


    For average, affectiveness CL-Command Rate-tRFC are nearly flat around 1% and tREF and tRCD are around three quarter % and a half % respectively.


    I think it would be the best for me to help other guys to think like below among various specs of rams:
    "6-9-6 vs 7-7-7? since CL's affectiveness on Super PI is bigger than twice of tRCD's affectiveness, former model would be faster than latter on Super PI."

    Thanks for reading SCROLLious () post. Have a nice day~

    ps. this bench had also been uploaded to my private blog: http://udteam.tistory.com/192

    ps2. 24/7 running setting of my system is:



    Last edited by DGLee; 12-04-2010 at 05:31 PM.

  2. #2
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    If other category than here seems more proper, please move it to that category :-)
    I'm not yet familiar to this forum system, not familiar to English also :-(

  3. #3
    Xtreme Member
    Join Date
    Jun 2007
    Location
    Sthlm
    Posts
    269
    Very nice review. Thanks for all the info.

  4. #4
    Xtreme Member
    Join Date
    Oct 2009
    Location
    Louisville, KY
    Posts
    413
    Wow...

    This is awesome! I can't believe you ran 32M so many times! I'd die lol


    i7 920 / X58A-OC / Dominator GT 2000 7-8-7 / 5870 Lightning

  5. #5
    Xtreme Member
    Join Date
    Jun 2008
    Location
    holland
    Posts
    340
    nice review!

  6. #6
    Registered User
    Join Date
    Dec 2009
    Posts
    11
    pretty solid review if I ever saw one.

  7. #7
    Registered User
    Join Date
    Jul 2009
    Location
    Belgium
    Posts
    21
    very nice review

  8. #8
    I am Xtreme
    Join Date
    Sep 2006
    Posts
    10,374
    so 6-9-6-21 is faster than 7-7-7-21 in pi32M ? think it depends on the ram kit used, speeds etc... I got a 4sec lead with the Hypers at 7-7-7-21 vs 6-8-6-21 (Gskill Flares) at 1800Mhz... with 6-6-6-18 with the GTX 2 I get over 12 secs lead...

    Nice extensive testing there... good ideas
    Last edited by Leeghoofd; 12-05-2010 at 07:04 AM.
    Question : Why do some overclockers switch into d*ckmode when money is involved

    Remark : They call me Pro Asus Saaya yupp, I agree

  9. #9
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by Leeghoofd View Post
    so 6-9-6-21 is faster than 7-7-7-21 in pi32M ? think it depends on the ram kit used, speeds etc... I got a 4sec lead with the Hypers at 7-7-7-21 vs 6-8-6-21 (Gskill Flares) at 1800Mhz... with 6-6-6-18 with the GTX 2 I get over 12 secs lead...
    maybe hyper's other sub ram timing items are tighter than flare's...?
    Last edited by DGLee; 12-05-2010 at 07:33 AM.

  10. #10
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    0xdeadbeef, bassplayer, dopestuff, Arkuatika, bartolomius, Leeghoofd - thanks for comments

  11. #11
    I am Xtreme
    Join Date
    Sep 2006
    Posts
    10,374
    Quote Originally Posted by DGLee View Post
    maybe hyper's other sub ram timing items are tighter than flare's...
    My conclusion was : PSC's aren't bad at all, though for benching Hyper is king... Though they are EOL...

    For daily users PSC is perfect I tested them in games and hardly noticed any difference between the Hypers !!

    For me 1800Mhz C6 is more than sufficient on AMD... At and above 2000 efficiency is less on most of the Asus AMD boards ( except the CH IV Extreme) compared to lower ram clocks...
    Last edited by Leeghoofd; 12-05-2010 at 07:20 AM.
    Question : Why do some overclockers switch into d*ckmode when money is involved

    Remark : They call me Pro Asus Saaya yupp, I agree

  12. #12
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by Leeghoofd View Post
    so 6-9-6-21 is faster than 7-7-7-21 in pi32M ? think it depends on the ram kit used, speeds etc... I got a 4sec lead with the Hypers at 7-7-7-21 vs 6-8-6-21 (Gskill Flares) at 1800Mhz... with 6-6-6-18 with the GTX 2 I get over 12 secs lead...
    Oh my, I checked my post again and confirmed that you're right.
    For Super PI, tRCD's affectiveness is nearly same as CL's.
    (my wrong assumption was that CL's contribution is twice bigger than tRCD's.)



    In case of comparing 7-7-7 and 6-9-6, 7-7-7 earns two times of tRCD's affectiveness and loses one CL's and one tRP's: 0.264% x 2 - 0.282% - 0.080% = 0.166% lead.
    In case of 7-7-7 and 6-8-6 however, 6-8-6 seems to lead since it reduces another tRCD - if an actual test result says the contrary, the difference may be derived by other sub ram timings.

    Anyway... I'd used Elpida Hyper (G.SKILL Perfect Storm) also and it was the best ram I'd ever seen - but it died so suddenly. how sad... (my 24/7 use of that ram is 1600 / 6-6-5-15 or 2000 / 7-7-8-21)
    Last edited by DGLee; 12-05-2010 at 10:24 AM.

  13. #13
    Xtreme Addict
    Join Date
    Dec 2002
    Location
    Sweden
    Posts
    1,261
    very nice test! learned me some new things. will check your test sometimes in future.
    Vishera 8320@ 5ghz | Gigabyte UD3 | 8gb TridentX 2400 c10| Powercolor 6850 | Thermalight Silver Arrow (bench Super KAZE 3k) | Samsung 830 128gbx2 Raid 0| Fractal case

  14. #14
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by Tomasis View Post
    very nice test! learned me some new things. will check your test sometimes in future.
    Thanks can't wait your test
    question: how can I edit my system information?
    -> Oh I just realized how to edit signature.
    Last edited by DGLee; 12-05-2010 at 09:41 AM.
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

  15. #15
    Xtreme Member
    Join Date
    Jul 2008
    Location
    Czech Republic
    Posts
    290
    very nice test...very good for many beginners in benchmarking

  16. #16
    I am Xtreme
    Join Date
    Dec 2008
    Location
    France
    Posts
    9,060
    Some good info here, thanks for posting this up!
    Donate to XS forums
    Quote Originally Posted by jayhall0315 View Post
    If you are really extreme, you never let informed facts or the scientific method hold you back from your journey to the wrong answer.

  17. #17
    Aussie God
    Join Date
    Feb 2005
    Location
    Copenhagen, Denmark
    Posts
    4,596
    Nice testing, but, bare in mind, THIS varies ALOT on platforms, its not that simple, unfortunately.
    Competition ranking;
    2005; Netbyte, Karise/Denmark #1 @ PiFast
    2008; AOCM II, Minfeld/Germany #2 @ 01SE/AM3/8M (w. Oliver)
    2009; AMD-OC, Viborg/Denmark #2 @ max freq Gigabyte TweaKING, Paris/France #4 @ 32M/01SE (w. Vanovich)
    2010: Gigabyte P55, Hamburg/Germany #6 @ wprime 1024/SPI 1M (w. THC) AOCM III, Minfeld/Germany #6 @ 01SE/AM3/1M/8M (w. NeoForce)

    Spectating;
    2010; GOOC 2010 Many thanks to Gigabyte!


  18. #18
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by M.Beier View Post
    Nice testing, but, bare in mind, THIS varies ALOT on platforms, its not that simple, unfortunately.
    yup maybe other platforms (ex: INTEL 1156) have different results. I wish I could do & compare results of further tests among several different platforms.
    (and... though... still I think this benchmark is valid, at least for AM3 platform!)
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

  19. #19
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Blue Storm, zalbard, M.Beier - thanks a lot for reading my post
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

  20. #20
    I am Xtreme FlanK3r's Avatar
    Join Date
    May 2008
    Location
    Czech republic
    Posts
    6,823
    very good result, good info about tREF a tREC for me!
    ROG Power PCs - Intel and AMD
    CPUs:i9-7900X, i9-9900K, i7-6950X, i7-5960X, i7-8086K, i7-8700K, 4x i7-7700K, i3-7350K, 2x i7-6700K, i5-6600K, R7-2700X, 4x R5 2600X, R5 2400G, R3 1200, R7-1800X, R7-1700X, 3x AMD FX-9590, 1x AMD FX-9370, 4x AMD FX-8350,1x AMD FX-8320,1x AMD FX-8300, 2x AMD FX-6300,2x AMD FX-4300, 3x AMD FX-8150, 2x AMD FX-8120 125 and 95W, AMD X2 555 BE, AMD x4 965 BE C2 and C3, AMD X4 970 BE, AMD x4 975 BE, AMD x4 980 BE, AMD X6 1090T BE, AMD X6 1100T BE, A10-7870K, Athlon 845, Athlon 860K,AMD A10-7850K, AMD A10-6800K, A8-6600K, 2x AMD A10-5800K, AMD A10-5600K, AMD A8-3850, AMD A8-3870K, 2x AMD A64 3000+, AMD 64+ X2 4600+ EE, Intel i7-980X, Intel i7-2600K, Intel i7-3770K,2x i7-4770K, Intel i7-3930KAMD Cinebench R10 challenge AMD Cinebench R15 thread Intel Cinebench R15 thread

  21. #21
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by FlanK3r View Post
    very good result, good info about tREF a tREC for me!
    Glad to hear that
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

  22. #22
    Admin
    Join Date
    Mar 2003
    Location
    North Texas
    Posts
    5,551
    DGLee -

    Welcome to XtremeSystems Thank you for the great review.
    UNDER THE ICE .com
    Phase Change Cooling

    is the remedy

  23. #23
    Pie assassin
    Join Date
    Nov 2007
    Location
    Where lights collide
    Posts
    2,275
    very nice breakdown. well done excel sheet!
    Last edited by ZenEffect; 12-06-2010 at 05:15 PM.
    Current Status - Testing & Research

  24. #24
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by runmc View Post
    DGLee -

    Welcome to XtremeSystems Thank you for the great review.
    Hello admin. especially glad to receive a reply from you
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

  25. #25
    Registered User
    Join Date
    Oct 2010
    Location
    South Korea
    Posts
    82
    Quote Originally Posted by ZenEffect View Post
    very nice breakdown. well done excel sheet!
    thanks! another benchmark is reserved for this topic
    My Blog: http://udteam.tistory.com

    CPU: AMD FX-8150P
    Cooler: Antec KÜHLER H2O 920
    M/B: ASUS CROSSHAIR V FORMULA
    RAM: Samsung DDR3 PC3-10600 4GB x 2
    VGA: HIS & Sapphire Radeon HD 6990 4GB x 2
    Storage: Intel SSD 510 Series 120GB + Seagate Barracuda Green 2TB
    PSU: Antec True Power Quattro 1200
    Case: Lian Li PC-X500FX
    O/S: Microsoft Windows 7 Enterprise 64-bit

Page 1 of 2 12 LastLast

Bookmarks

Bookmarks

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •