970 memory allocation issue revisited

Discussion in 'Videocards - NVIDIA GeForce' started by alanm, Jan 23, 2015.

Thread Status:
Not open for further replies.
  1. MrH

    MrH Ancient Guru

    Messages:
    2,809
    Likes Received:
    14
    GPU:
    MSI GTX 1080 Armour
    Jesus, I recently bought a MSI 970 4G and this isn't what I needed. I really hope this can be fixed with a firmware/software update.
     
  2. SuperAverage

    SuperAverage Master Guru

    Messages:
    247
    Likes Received:
    2
    GPU:
    Gigabyte xtreme 1080
    Not really.

    Are you not paying attention?

    I can tell English is not your first language, so I'm sorry if we are losing something in translation.

    Usable doesn't just mean you can fill it with information. Usable means that information is USABLE by an application. It's advertised as 4gb of 7GHz 256 bit memory, not 3.5gb of 7GHz 256 bit memory + .5gb of 1/25th bandwidth memory.

    I'm surprised I need to explain this.
     
  3. Razoola

    Razoola Member Guru

    Messages:
    125
    Likes Received:
    2
    GPU:
    GTX980 (MSI gaming)
    Here is my results. Is there any reason why the last 2 tests fail for me?

    Code:
    Nai's Benchmark, edited by VultureX
      Device: GeForce GTX 970 (4.00 GB)
      Memory Bus Width (bits): 256
      Peak Theoretical DRAM Bandwidth (GB/s): 224.320000
    
    Allocating Memory . . .
    Chunk Size: 128 MiByte
    Allocated 30 Chunks
    Allocated 3840 MiByte
    Benchmarking DRAM
    DRAM-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):155.50 GByte/s
    DRAM-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):155.46 GByte/s
    DRAM-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):155.48 GByte/s
    DRAM-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):155.43 GByte/s
    DRAM-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):155.27 GByte/s
    DRAM-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):155.45 GByte/s
    DRAM-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):155.51 GByte/s
    DRAM-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):155.51 GByte/s
    DRAM-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):155.54 GByte/s
    DRAM-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):155.52 GByte/s
    DRAM-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):155.31 GByte/s
    DRAM-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):155.50 GByte/s
    DRAM-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):155.52 GByte/s
    DRAM-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):155.53 GByte/s
    DRAM-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):155.54 GByte/s
    DRAM-Bandwidth of Chunk no. 15 (1920 MiByte to 2048 MiByte):155.54 GByte/s
    DRAM-Bandwidth of Chunk no. 16 (2048 MiByte to 2176 MiByte):155.46 GByte/s
    DRAM-Bandwidth of Chunk no. 17 (2176 MiByte to 2304 MiByte):155.51 GByte/s
    DRAM-Bandwidth of Chunk no. 18 (2304 MiByte to 2432 MiByte):155.46 GByte/s
    DRAM-Bandwidth of Chunk no. 19 (2432 MiByte to 2560 MiByte):155.51 GByte/s
    DRAM-Bandwidth of Chunk no. 20 (2560 MiByte to 2688 MiByte):155.56 GByte/s
    DRAM-Bandwidth of Chunk no. 21 (2688 MiByte to 2816 MiByte):155.52 GByte/s
    DRAM-Bandwidth of Chunk no. 22 (2816 MiByte to 2944 MiByte):155.55 GByte/s
    DRAM-Bandwidth of Chunk no. 23 (2944 MiByte to 3072 MiByte):155.52 GByte/s
    DRAM-Bandwidth of Chunk no. 24 (3072 MiByte to 3200 MiByte):22.35 GByte/s
    DRAM-Bandwidth of Chunk no. 25 (3200 MiByte to 3328 MiByte):22.35 GByte/s
    DRAM-Bandwidth of Chunk no. 26 (3328 MiByte to 3456 MiByte):22.35 GByte/s
    DRAM-Bandwidth of Chunk no. 27 (3456 MiByte to 3584 MiByte):27.52 GByte/s
    DRAM-Bandwidth of Chunk no. 28 (3584 MiByte to 3712 MiByte): 5.97 GByte/s
    DRAM-Bandwidth of Chunk no. 29 (3712 MiByte to 3840 MiByte): 5.92 GByte/s
    Benchmarking L2-Cache
    L2-Cache-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):415.14 GByte/s
    L2-Cache-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):415.13 GByte/s
    L2-Cache-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):414.99 GByte/s
    L2-Cache-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):415.15 GByte/s
    L2-Cache-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):415.40 GByte/s
    L2-Cache-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):415.24 GByte/s
    L2-Cache-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):415.07 GByte/s
    L2-Cache-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):414.96 GByte/s
    L2-Cache-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):414.99 GByte/s
    L2-Cache-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):414.99 GByte/s
    L2-Cache-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):415.20 GByte/s
    L2-Cache-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):415.10 GByte/s
    L2-Cache-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):415.19 GByte/s
    L2-Cache-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):415.28 GByte/s
    L2-Cache-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):415.08 GByte/s
    L2-Cache-Bandwidth of Chunk no. 15 (1920 MiByte to 2048 MiByte):415.21 GByte/s
    L2-Cache-Bandwidth of Chunk no. 16 (2048 MiByte to 2176 MiByte):415.07 GByte/s
    L2-Cache-Bandwidth of Chunk no. 17 (2176 MiByte to 2304 MiByte):415.30 GByte/s
    L2-Cache-Bandwidth of Chunk no. 18 (2304 MiByte to 2432 MiByte):415.09 GByte/s
    L2-Cache-Bandwidth of Chunk no. 19 (2432 MiByte to 2560 MiByte):415.07 GByte/s
    L2-Cache-Bandwidth of Chunk no. 20 (2560 MiByte to 2688 MiByte):415.08 GByte/s
    L2-Cache-Bandwidth of Chunk no. 21 (2688 MiByte to 2816 MiByte):415.01 GByte/s
    L2-Cache-Bandwidth of Chunk no. 22 (2816 MiByte to 2944 MiByte):415.09 GByte/s
    L2-Cache-Bandwidth of Chunk no. 23 (2944 MiByte to 3072 MiByte):415.14 GByte/s
    L2-Cache-Bandwidth of Chunk no. 24 (3072 MiByte to 3200 MiByte):74.00 GByte/s
    L2-Cache-Bandwidth of Chunk no. 25 (3200 MiByte to 3328 MiByte):74.00 GByte/s
    L2-Cache-Bandwidth of Chunk no. 26 (3328 MiByte to 3456 MiByte):74.00 GByte/s
    L2-Cache-Bandwidth of Chunk no. 27 (3456 MiByte to 3584 MiByte):90.22 GByte/s
    Kernel launch failed: unknown error
    Kernel launch failed: unknown error
    Press any key to continue . . .
    
     
  4. Cakefish

    Cakefish New Member

    Messages:
    8
    Likes Received:
    0
    GPU:
    NVIDIA GTX 980M 4GB
    What is even weirder is that your 980M is getting wildly different results to my own...
     

  5. Turanis

    Turanis Ancient Guru

    Messages:
    1,779
    Likes Received:
    475
    GPU:
    Gigabyte RX500
    If someone find a way to test GTX 970 to see if really had 64 ROPs (rumors say had 52 ROPs) and find this card dont have it ...
    Then nvidia is doomed and sued by many users,not just money back. :D
     
  6. Öhr

    Öhr Master Guru

    Messages:
    317
    Likes Received:
    56
    GPU:
    AMD RX 5700XT @ H₂O
    I did not. Though now, as I have connected my monitors to the 970 again, i get the 3.5GiB with 512MiB chunk size... strange...
     
  7. Loophole35

    Loophole35 Ancient Guru

    Messages:
    9,793
    Likes Received:
    1,148
    GPU:
    EVGA 1080ti SC
    Interesting this is on my 670 just look at these results

    Code:
    Nai's Benchmark, edited by VultureX
      Device: GeForce GTX 670 (2.00 GB)
      Memory Bus Width (bits): 256
      Peak Theoretical DRAM Bandwidth (GB/s): 198.656000
    
    Allocating Memory . . .
    Chunk Size: 128 MiByte
    Allocated 15 Chunks
    Allocated 1920 MiByte
    Benchmarking DRAM
    DRAM-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):159.97 GByte/s
    DRAM-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):160.25 GByte/s
    DRAM-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):160.12 GByte/s
    DRAM-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):160.09 GByte/s
    DRAM-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):159.93 GByte/s
    DRAM-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):159.90 GByte/s
    DRAM-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):159.83 GByte/s
    DRAM-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):160.06 GByte/s
    DRAM-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):160.16 GByte/s
    DRAM-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):160.17 GByte/s
    DRAM-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):160.00 GByte/s
    DRAM-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):159.85 GByte/s
    DRAM-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):158.89 GByte/s
    DRAM-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte): 8.21 GByte/s
    DRAM-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte): 3.30 GByte/s
    Benchmarking L2-Cache
    L2-Cache-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):289.68 GByte/s
    L2-Cache-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):289.69 GByte/s
    L2-Cache-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):289.69 GByte/s
    Kernel launch failed: the launch timed out and was terminated
    Kernel launch failed: the launch timed out and was terminated
    Press any key to continue . . .

    Will run it on my 780 in a second. Has anyone run it on a AMD 7950 yet?
     
  8. cpy2

    cpy2 Active Member

    Messages:
    69
    Likes Received:
    24
    GPU:
    ****
    I have SLI 2x 970G1 and i can say it's same here except driver crash at last few blocks because i'm too lazy to switch to iGPU and do a headless mode. But people claiming that they had same results in headless mode.
     
  9. Im2bad

    Im2bad Master Guru

    Messages:
    791
    Likes Received:
    0
    GPU:
    3080 Gaming X Trio
    It's CUDA, doesn't work on Radeons. Someone would have to port it.
     
  10. Headd

    Headd Active Member

    Messages:
    75
    Likes Received:
    5
    GPU:
    GTX970
    yeah it looks like GTX970 isnt 256bit card.This post should by place as sticky so everyone can read it.
     

  11. goranm

    goranm Member

    Messages:
    15
    Likes Received:
    0
    GPU:
    Gigabyte GTX 970 G1
    Anyone noticed that it doesn't respond to memory clock. You can set it to 7GHz or 8Ghz it will always produce same result of 155GB/s. On the other hand GPU overclock or under clock is producing higher/lower L2 cache bandwidth. Strange I must say...
     
  12. fellix

    fellix Master Guru

    Messages:
    202
    Likes Received:
    43
    GPU:
    KFA² GTX 1080 Ti
    There are 64 ROPs, it just can't utilize them all most of the time since the pixel throughput depends also on the number of SMMs.

    By the way, someone posted a video illustrating the memory issue:

    https://www.youtube.com/watch?v=ZQE6p5r1tYE
     
  13. Loophole35

    Loophole35 Ancient Guru

    Messages:
    9,793
    Likes Received:
    1,148
    GPU:
    EVGA 1080ti SC
    Okay just ran it on my 780 and its results are right.
    Code:
    Nai's Benchmark, edited by VultureX
      Device: GeForce GTX 780 (3.00 GB)
      Memory Bus Width (bits): 384
      Peak Theoretical DRAM Bandwidth (GB/s): 288.384000
    
    Allocating Memory . . .
    Chunk Size: 128 MiByte
    Allocated 22 Chunks
    Allocated 2816 MiByte
    Benchmarking DRAM
    DRAM-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):249.40 GByte/s
    DRAM-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):251.34 GByte/s
    DRAM-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):250.22 GByte/s
    DRAM-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):249.63 GByte/s
    DRAM-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):249.36 GByte/s
    DRAM-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):249.41 GByte/s
    DRAM-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):251.33 GByte/s
    DRAM-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):251.38 GByte/s
    DRAM-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):250.70 GByte/s
    DRAM-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):249.33 GByte/s
    DRAM-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):249.37 GByte/s
    DRAM-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):249.61 GByte/s
    DRAM-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):249.80 GByte/s
    DRAM-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):249.90 GByte/s
    DRAM-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):249.16 GByte/s
    DRAM-Bandwidth of Chunk no. 15 (1920 MiByte to 2048 MiByte):248.83 GByte/s
    DRAM-Bandwidth of Chunk no. 16 (2048 MiByte to 2176 MiByte):249.05 GByte/s
    DRAM-Bandwidth of Chunk no. 17 (2176 MiByte to 2304 MiByte):249.89 GByte/s
    DRAM-Bandwidth of Chunk no. 18 (2304 MiByte to 2432 MiByte):249.66 GByte/s
    DRAM-Bandwidth of Chunk no. 19 (2432 MiByte to 2560 MiByte):249.56 GByte/s
    DRAM-Bandwidth of Chunk no. 20 (2560 MiByte to 2688 MiByte):248.98 GByte/s
    DRAM-Bandwidth of Chunk no. 21 (2688 MiByte to 2816 MiByte):249.21 GByte/s
    Benchmarking L2-Cache
    L2-Cache-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):395.03 GByte/s
    L2-Cache-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):395.01 GByte/s
    L2-Cache-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):395.05 GByte/s
    L2-Cache-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):395.02 GByte/s
    L2-Cache-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):395.15 GByte/s
    L2-Cache-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):395.02 GByte/s
    L2-Cache-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):395.08 GByte/s
    L2-Cache-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):395.04 GByte/s
    L2-Cache-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):394.97 GByte/s
    L2-Cache-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):395.00 GByte/s
    L2-Cache-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):395.11 GByte/s
    L2-Cache-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):395.03 GByte/s
    L2-Cache-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):394.98 GByte/s
    L2-Cache-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):395.01 GByte/s
    L2-Cache-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):395.04 GByte/s
    L2-Cache-Bandwidth of Chunk no. 15 (1920 MiByte to 2048 MiByte):395.01 GByte/s
    L2-Cache-Bandwidth of Chunk no. 16 (2048 MiByte to 2176 MiByte):395.08 GByte/s
    L2-Cache-Bandwidth of Chunk no. 17 (2176 MiByte to 2304 MiByte):395.08 GByte/s
    L2-Cache-Bandwidth of Chunk no. 18 (2304 MiByte to 2432 MiByte):395.00 GByte/s
    L2-Cache-Bandwidth of Chunk no. 19 (2432 MiByte to 2560 MiByte):394.97 GByte/s
    L2-Cache-Bandwidth of Chunk no. 20 (2560 MiByte to 2688 MiByte):395.11 GByte/s
    L2-Cache-Bandwidth of Chunk no. 21 (2688 MiByte to 2816 MiByte):395.02 GByte/s
    Press any key to continue . . .
     
  14. looniam

    looniam Member Guru

    Messages:
    191
    Likes Received:
    7
    GPU:
    RTX3060 bcuz
    having the same mobo i can tell you to boot into the bios, go to system agent and make sure you have the primary gpu as "auto" and enable the igpu.

    boot into windows and just switch the cable . .window may need the intel hd 2000 driver though . .

    edit:
    [​IMG]
     
    Last edited: Jan 24, 2015
  15. SuperAverage

    SuperAverage Master Guru

    Messages:
    247
    Likes Received:
    2
    GPU:
    Gigabyte xtreme 1080
    I posted this. I'm not saying it IS the memory issue that causes this. I said it may or may not have something to do with it.
     

  16. DLG

    DLG Active Member

    Messages:
    67
    Likes Received:
    0
    GPU:
    Zotac AMP 1080Ti
    780 for the win !!
     
  17. Öhr

    Öhr Master Guru

    Messages:
    317
    Likes Received:
    56
    GPU:
    AMD RX 5700XT @ H₂O
    Good job, have a cookie.
     
  18. rm082e

    rm082e Master Guru

    Messages:
    690
    Likes Received:
    232
    GPU:
    3080 - QHD@165hz
    Well, having just bout a pair of 970s for SLI, this should be interesting... :(
     
  19. alanm

    alanm Ancient Guru

    Messages:
    10,680
    Likes Received:
    2,775
    GPU:
    Asus 2080 Dual OC
    I ran FC4 maxed with MSAAx8 and got to 3790 vram usage and yes, performance tanked, but none of the artifacts as shown in the vid.
     
  20. JohnLai

    JohnLai Member Guru

    Messages:
    136
    Likes Received:
    7
    GPU:
    ASUS GTX 970 3.5+0.5GB
    Now I only need to see 780 TI performance for some comparison......
     
Thread Status:
Not open for further replies.

Share This Page