[ANN] Opensource primecoin GPU miner beta-testing started! (Crossplatform)

Yes, I want implement all cgminer GPU control features (separately disabling, temperature monitoring), etc…

Kubuntu 13.10, 3xRadeon R9 290X, Catalyst 14.3:

Gentoo (with kernel 3.8 ), 1xRadeon R9 290X overclocked, Catalyst 14.3:

Same GPUs, but very different permormance, I will try to fix this issue…

Will test on c2075 if there is a windows binary.
Windows support will come next week, but I have not NVidia GPU's for testing.. miner can work too slow.[/quote]

does this work with ubuntu 12.4? If yes can you tell me how to install thanks.

Yes, it must work.
Install newest Catalyst drivers, AMD APP SDK and follow instructions in README.

[quote=“zppwxz, post:20, topic:2223”]how to mining ypool , use xpmminer .
Is it right? Now also does not support?[/quote]
Now only solo mining supported, XPT protocol will be implemented later.

Excellent stuff. Giving this a try right now. Will post back. Thank you for marking it open source

Noob question . What do i set for this directory ?

OPENCL_INCLUDE_DIRS (ADVANCED)

Much better progress:

./xpmclminer -b --opencl-platform “NVIDIA Corporation”
OpenCL platform available: NVIDIA Corporation
[0] GeForce GTX 780 Ti; 15 compute units
[1] GeForce GTX 750 Ti; 5 compute units

  • info: 4*8192 bytes allocated
  • info: 8*8192 bytes allocated
  • info: 4*8192 bytes allocated
  • info: 1*157286400 bytes allocated
  • info: 1*157286400 bytes allocated
  • info: 1*157286400 bytes allocated
  • info: 336*1 bytes allocated
  • info: 4*8 bytes allocated
  • info: 9232*60 bytes allocated
  • info: 276496*60 bytes allocated
  • info: 276496*60 bytes allocated
  • info: 276496*60 bytes allocated
  • info: 65552*60 bytes allocated
  • info: 4*8192 bytes allocated
  • info: 8*8192 bytes allocated
  • info: 4*8192 bytes allocated
  • info: 1*52428800 bytes allocated
  • info: 1*52428800 bytes allocated
  • info: 1*52428800 bytes allocated
  • info: 336*1 bytes allocated
  • info: 4*8 bytes allocated
  • info: 9232*20 bytes allocated
  • info: 276496*20 bytes allocated
  • info: 276496*20 bytes allocated
  • info: 276496*20 bytes allocated
  • info: 65552*20 bytes allocated
  • GPU 1 benchmark start:
  • info: 4*2097152 bytes allocated
  • info: 4*2097152 bytes allocated
  • info: 4*4194304 bytes allocated
    Multiply 256 bits CPU time: 4.039, GPU time: 0.032 (126.537 times faster)
  • info: 4*3145728 bytes allocated
  • info: 4*3145728 bytes allocated
  • info: 4*6291456 bytes allocated
    Multiply 384 bits CPU time: 7.369, GPU time: 0.088 (83.621 times faster)
  • info: 4*3670016 bytes allocated
  • info: 4*3670016 bytes allocated
  • info: 4*7340032 bytes allocated
    clWaitForEvents error!
  • Error(clAlloc): cannot allocate 44194304 elements at device ? * Error(clAlloc): cannot allocate 43145728 elements at device ? * info: 4*3145728 bytes allocated
    clWaitForEvents error!
  • Error(clAlloc): cannot allocate 45242880 elements at device ? * Error(clAlloc): cannot allocate 44194304 elements at device ? * info: 4*4194304 bytes allocated
    clWaitForEvents error!
  • Error(clAlloc): cannot allocate 4524288 elements at device ? * info: 4524288 bytes allocated
    clWaitForEvents error -9999!
  • Error(clAlloc): cannot allocate 4786432 elements at device ? * info: 4786432 bytes allocated
    clWaitForEvents error -9999!
  • Error(clAlloc): cannot allocate 4917504 elements at device ? * info: 4917504 bytes allocated
    clWaitForEvents error -9999!
    • sieve with checking results
  • Error(clAlloc): cannot allocate 4*24 elements at device ?sieveBenchmark error: cannot allocate memory for sieve bitfields
Multiply 256 bits CPU time: 4.039, GPU time: 0.032 (126.537 times faster) * info: 4*3145728 bytes allocated * info: 4*3145728 bytes allocated * info: 4*6291456 bytes allocated Multiply 384 bits CPU time: 7.369, GPU time: 0.088 (83.621 times faster) * info: 4*3670016 bytes allocated * info: 4*3670016 bytes allocated * info: 4*7340032 bytes allocated
You have launch debug build, try add -DCMAKE_BUILD_TYPE=Release when cmake launch

GeForce 780Ti:

Multiply 256 bits CPU time: 4.039, GPU time: [b]0.032[/b] Multiply 384 bits CPU time: 7.369, GPU time: [b]0.088[/b]
Radeon R9 290X:
Multiply 256 bits CPU time: 8.574, GPU time: [b]0.015[/b] Multiply 384 bits CPU time: 15.477, GPU time: [b]0.035[/b] Multiply 448 bits CPU time: 20.841, GPU time: 0.041

OpenCL code was optimized for AMD. NVidia required rewritting it with PTX assembly for good performance: 128 bit integer on cuda? - Stack Overflow

* Error(clAlloc): cannot allocate 4*4194304 elements at device ? * Error(clAlloc): cannot allocate 4*3145728 elements at device ? * info: 4*3145728 bytes allocated
Benchmarks does not free memory after allocation, it will be fixed. But now you can try:
export GPU_MAX_ALLOC_PERCENT=100
Or mining launch, it does not have extra allocations.
Noob question . What do i set for this directory ?

OPENCL_INCLUDE_DIRS (ADVANCED)


CMake can’t find OpenCL directory. Try add -DOPENCL_INCLUDE_DIRS=/opt/AMDAPP/include (here is your own path of AMD APP SDK) to cmake arguments.

Thanks. That now works but run into another exception when i try to compile. Using one of my SMOS rigs(Debian)

root@smos-1:~/xpmminer/src# cmake CMakeLists.txt -DOPENCL_INCLUDE_DIRS=/opt/AMDAPP/include
-- Found OpenCL: /usr/lib/libOpenCL.so
-- Configuring done
-- Generating done
-- Build files have been written to: /root/xpmminer/src
root@smos-1:~/xpmminer/src# make
Scanning dependencies of target blkmaker
[  7%] Building C object blkmaker/CMakeFiles/blkmaker.dir/base58.c.o
[ 14%] Building C object blkmaker/CMakeFiles/blkmaker.dir/blkmaker.c.o
[ 21%] Building C object blkmaker/CMakeFiles/blkmaker.dir/blkmaker_jansson.c.o
[ 28%] Building C object blkmaker/CMakeFiles/blkmaker.dir/blktemplate.c.o
[ 35%] Building C object blkmaker/CMakeFiles/blkmaker.dir/hex.c.o
Linking C static library libblkmaker.a
[ 35%] Built target blkmaker
Scanning dependencies of target common
[ 42%] Building CXX object common/CMakeFiles/common.dir/CSieveOfEratosthenesL1Ext.cpp.o
/root/xpmminer/src/common/CSieveOfEratosthenesL1Ext.cpp: In function ‘uint32_t longModuloByMul(uint32_t*, uint32_t, uint64_t, unsigned int)’:
/root/xpmminer/src/common/CSieveOfEratosthenesL1Ext.cpp:166: error: ‘__int128’ was not declared in this scope
/root/xpmminer/src/common/CSieveOfEratosthenesL1Ext.cpp:166: error: expected ‘;’ before ‘dividend’
/root/xpmminer/src/common/CSieveOfEratosthenesL1Ext.cpp:167: error: ‘dividend’ was not declared in this scope
make[2]: *** [common/CMakeFiles/common.dir/CSieveOfEratosthenesL1Ext.cpp.o] Error 1
make[1]: *** [common/CMakeFiles/common.dir/all] Error 2
make: *** [all] Error 2

OK, I commented out the 448-bit multiplication test before the benchmark will run without abending.

Now I received the following error in one of the benchmarks:
nonceAndHash query error -5!

./xpmclminer -b --opencl-platform “NVIDIA Corporation”
OpenCL platform available: NVIDIA Corporation
[0] GeForce GTX 780 Ti; 15 compute units
[1] GeForce GTX 750 Ti; 5 compute units

  • GPU 1 benchmark start:
    Multiply 256 bits CPU time: 3.884, GPU time: 0.032 (121.369 times faster)
    Multiply 384 bits CPU time: 7.343, GPU time: 0.088 (83.031 times faster)
    Modulo (512 % 384) CPU time: 0.027, GPU time: 0.000 (57.193 times faster)
    Modulo (640 % 512) CPU time: 0.028, GPU time: 0.001 (53.584 times faster)
    Fermat test 256 bits CPU time: 1.041, GPU time: 0.017 (61.780 times faster)
    Fermat test 384 bits CPU time: 2.825, GPU time: 0.048 (58.459 times faster)
    Fermat test 448 bits CPU time: 4.203, GPU time: 0.131 (32.008 times faster)

    • sieve with checking results
      (262144, real 1441792) GPU(time 15.393ms speed 93665.432) L1Ext/Fastest CPU(time 53.753ms speed 26822.540) 3.492 times faster
      (524288, real 2883584) GPU(time 28.218ms speed 102189.524) L1Ext/Fastest CPU(time 104.859ms speed 27499.633) 3.716 times faster
      (786432, real 4325376) GPU(time 42.229ms speed 102426.674) L1Ext/Fastest CPU(time 156.085ms speed 27711.670) 3.696 times faster
      (1048576, real 5767168) GPU(time 56.234ms speed 102556.603) L1Ext/Fastest CPU(time 206.937ms speed 27869.197) 3.680 times faster
      (1310720, real 7208960) GPU(time 70.204ms speed 102685.887) L1Ext/Fastest CPU(time 258.079ms speed 27933.152) 3.676 times faster
      (1572864, real 8650752) GPU(time 84.146ms speed 102806.455) L1Ext/Fastest CPU(time 310.008ms speed 27904.931) 3.684 times faster
      (1835008, real 10092544) GPU(time 98.154ms speed 102823.563) L1Ext/Fastest CPU(time 360.570ms speed 27990.526) 3.674 times faster
      (2097152, real 11534336) GPU(time 111.864ms speed 103110.348) L1Ext/Fastest CPU(time 411.753ms speed 28012.755) 3.681 times faster
    • sieve performance test
      (262144, real 1441792) GPU(time 57.593ms speed 25034.153) L1Ext/Fastest CPU(time 1707.408ms speed 844.433) 29.646 times faster
      (524288, real 2883584) GPU(time 113.511ms speed 25403.564) L1Ext/Fastest CPU(time 3158.952ms speed 912.829) 27.829 times faster
      (786432, real 4325376) GPU(time 151.361ms speed 28576.555) L1Ext/Fastest CPU(time 4690.843ms speed 922.089) 30.991 times faster
      (1048576, real 5767168) GPU(time 201.673ms speed 28596.629) L1Ext/Fastest CPU(time 6232.531ms speed 925.333) 30.904 times faster
      (1310720, real 7208960) GPU(time 251.842ms speed 28624.932) L1Ext/Fastest CPU(time 7752.144ms speed 929.931) 30.782 times faster
      (1572864, real 8650752) GPU(time 301.351ms speed 28706.565) L1Ext/Fastest CPU(time 9312.739ms speed 928.916) 30.903 times faster
      (1835008, real 10092544) GPU(time 358.971ms speed 28115.207) L1Ext/Fastest CPU(time 10823.481ms speed 932.467) 30.151 times faster
      (2097152, real 11534336) GPU(time 398.419ms speed 28950.266) L1Ext/Fastest CPU(time 12397.614ms speed 930.367) 31.117 times faster
    • mine with checking results
      [group=0] 0 results
  • [0] round time: 122.591 milliseconds, speed: 82.327 M
    [group=0] 118 results

  • [1] round time: 117.606 milliseconds, speed: 85.817 M
    [group=0] 125 results

  • [2] round time: 117.900 milliseconds, speed: 85.603 M
    [group=0] 74 results

  • [3] round time: 113.781 milliseconds, speed: 88.701 M
    [group=0] 108 results

  • [4] round time: 117.910 milliseconds, speed: 85.595 M
    [group=0] 103 results

  • [5] round time: 113.743 milliseconds, speed: 88.731 M
    [group=0] 111 results

  • [6] round time: 121.761 milliseconds, speed: 82.888 M
    [group=0] 79 results

  • [7] round time: 109.747 milliseconds, speed: 91.962 M
    [group=0] 81 results

  • [8] round time: 122.068 milliseconds, speed: 82.680 M
    [group=0] 168 results

  • [9] round time: 121.647 milliseconds, speed: 82.966 M
    [group=0] 70 results

  • [10] round time: 109.699 milliseconds, speed: 92.002 M
    [group=0] 53 results

  • [11] round time: 121.708 milliseconds, speed: 82.924 M
    [group=0] 129 results

  • [12] round time: 113.789 milliseconds, speed: 88.695 M
    [group=0] 85 results

  • [13] round time: 117.650 milliseconds, speed: 85.784 M
    [group=0] 133 results

  • [14] round time: 117.867 milliseconds, speed: 85.627 M
    [group=0] 72 results

  • [15] round time: 117.586 milliseconds, speed: 85.831 M
    [group=0] 112 results

  • [16] round time: 113.667 milliseconds, speed: 88.790 M
    [group=0] 124 results

  • [17] round time: 121.886 milliseconds, speed: 82.803 M
    [group=0] 119 results

  • [18] round time: 113.833 milliseconds, speed: 88.661 M
    [group=0] 68 results

  • [19] round time: 117.768 milliseconds, speed: 85.699 M
    [group=0] 142 results

  • [20] round time: 121.560 milliseconds, speed: 83.025 M
    [group=0] 82 results

  • [21] round time: 109.479 milliseconds, speed: 92.187 M
    [group=0] 134 results

  • [22] round time: 117.639 milliseconds, speed: 85.793 M
    [group=0] 110 results

  • [23] round time: 121.442 milliseconds, speed: 83.106 M
    [group=0] 86 results

  • [24] round time: 121.303 milliseconds, speed: 83.201 M
    [group=0] 76 results

  • [25] round time: 121.583 milliseconds, speed: 83.009 M
    [group=0] 142 results

  • [26] round time: 113.816 milliseconds, speed: 88.674 M
    [group=0] 71 results

  • [27] round time: 117.691 milliseconds, speed: 85.755 M
    [group=0] 181 results

  • [28] round time: 121.609 milliseconds, speed: 82.992 M
    [group=0] 78 results

  • [29] round time: 113.613 milliseconds, speed: 88.833 M
    [group=0] 74 results

  • [30] round time: 117.893 milliseconds, speed: 85.608 M
    [group=0] 96 results

  • [31] round time: 113.629 milliseconds, speed: 88.820 M

  • mine performance test
    nonceAndHash query error -5!

  • [0] round time: 20.528 milliseconds, speed: 29498.862 M
    nonceAndHash query error -5!

  • [1] round time: 0.261 milliseconds, speed: 2320125.057 M
    nonceAndHash query error -5!

  • [2] round time: 0.317 milliseconds, speed: 1910260.694 M
    nonceAndHash query error -5!

  • [3] round time: 0.253 milliseconds, speed: 2393488.696 M
    nonceAndHash query error -5!

  • [4] round time: 0.272 milliseconds, speed: 2226296.471 M
    nonceAndHash query error -5!

  • [5] round time: 0.532 milliseconds, speed: 1138256.842 M
    nonceAndHash query error -5!

  • [6] round time: 0.154 milliseconds, speed: 3932160.000 M
    nonceAndHash query error -5!

  • [7] round time: 0.140 milliseconds, speed: 4325376.000 M
    nonceAndHash query error -5!

  • [8] round time: 0.145 milliseconds, speed: 4176225.103 M
    nonceAndHash query error -5!

  • [9] round time: 0.632 milliseconds, speed: 958152.911 M
    nonceAndHash query error -5!

  • [10] round time: 0.448 milliseconds, speed: 1351680.000 M
    nonceAndHash query error -5!

  • [11] round time: 0.482 milliseconds, speed: 1256333.278 M
    nonceAndHash query error -5!

  • [12] round time: 0.528 milliseconds, speed: 1146880.000 M
    nonceAndHash query error -5!

  • [13] round time: 0.512 milliseconds, speed: 1182720.000 M
    nonceAndHash query error -5!

  • [14] round time: 0.566 milliseconds, speed: 1069880.989 M
    nonceAndHash query error -5!

  • [15] round time: 0.542 milliseconds, speed: 1117255.793 M
    nonceAndHash query error -5!

  • [16] round time: 0.574 milliseconds, speed: 1054969.756 M
    nonceAndHash query error -5!

  • [17] round time: 0.600 milliseconds, speed: 1009254.400 M
    nonceAndHash query error -5!

  • [18] round time: 0.600 milliseconds, speed: 1009254.400 M
    nonceAndHash query error -5!

  • [19] round time: 0.642 milliseconds, speed: 943228.411 M
    nonceAndHash query error -5!

  • [20] round time: 0.679 milliseconds, speed: 891830.103 M
    nonceAndHash query error -5!

  • [21] round time: 0.685 milliseconds, speed: 884018.453 M
    nonceAndHash query error -5!

  • [22] round time: 0.722 milliseconds, speed: 838715.568 M
    nonceAndHash query error -5!

  • [23] round time: 0.769 milliseconds, speed: 787454.668 M
    nonceAndHash query error -5!

  • [24] round time: 0.794 milliseconds, speed: 762660.756 M
    nonceAndHash query error -5!

  • [25] round time: 0.813 milliseconds, speed: 744837.196 M
    nonceAndHash query error -5!

  • [26] round time: 0.441 milliseconds, speed: 1373135.238 M
    nonceAndHash query error -5!

  • [27] round time: 0.300 milliseconds, speed: 2018508.800 M
    nonceAndHash query error -5!

  • [28] round time: 0.313 milliseconds, speed: 1934672.971 M
    nonceAndHash query error -5!

  • [29] round time: 0.316 milliseconds, speed: 1916305.823 M
    nonceAndHash query error -5!

  • [30] round time: 0.326 milliseconds, speed: 1857523.436 M
    nonceAndHash query error -5!

  • [31] round time: 0.343 milliseconds, speed: 1765459.592 M

  • GPU 2 benchmark start:
    Multiply 256 bits CPU time: 3.872, GPU time: 0.114 (33.943 times faster)
    Multiply 384 bits CPU time: 7.341, GPU time: 0.339 (21.655 times faster)
    Modulo (512 % 384) CPU time: 0.026, GPU time: 0.001 (19.124 times faster)
    Modulo (640 % 512) CPU time: 0.026, GPU time: 0.001 (17.721 times faster)
    Fermat test 256 bits CPU time: 1.036, GPU time: 0.067 (15.372 times faster)
    Fermat test 384 bits CPU time: 2.830, GPU time: 0.517 (5.475 times faster)
    Fermat test 448 bits CPU time: 4.189, GPU time: 0.797 (5.254 times faster)

    • sieve with checking results
      (262144, real 1441792) GPU(time 6.470ms speed 222842.658) L1Ext/Fastest CPU(time 53.199ms speed 27101.863) 8.222 times faster
      (524288, real 2883584) GPU(time 11.270ms speed 255863.709) L1Ext/Fastest CPU(time 104.289ms speed 27649.934) 9.254 times faster
      (786432, real 4325376) GPU(time 16.921ms speed 255621.772) L1Ext/Fastest CPU(time 154.854ms speed 27931.962) 9.152 times faster
      (1048576, real 5767168) GPU(time 22.506ms speed 256250.244) L1Ext/Fastest CPU(time 206.268ms speed 27959.587) 9.165 times faster
      (1310720, real 7208960) GPU(time 28.131ms speed 256263.908) L1Ext/Fastest CPU(time 256.184ms speed 28139.775) 9.107 times faster
      (1572864, real 8650752) GPU(time 37.499ms speed 230692.872) L1Ext/Fastest CPU(time 307.482ms speed 28134.174) 8.200 times faster
      (1835008, real 10092544) GPU(time 43.784ms speed 230507.583) L1Ext/Fastest CPU(time 357.172ms speed 28256.817) 8.158 times faster
      (2097152, real 11534336) GPU(time 49.940ms speed 230963.877) L1Ext/Fastest CPU(time 409.847ms speed 28143.029) 8.207 times faster
    • sieve performance test
      (262144, real 1441792) GPU(time 13.579ms speed 106178.069) L1Ext/Fastest CPU(time 569.322ms speed 2532.472) 41.927 times faster
      (524288, real 2883584) GPU(time 26.753ms speed 107785.445) L1Ext/Fastest CPU(time 1053.857ms speed 2736.219) 39.392 times faster
      (786432, real 4325376) GPU(time 39.944ms speed 108286.000) L1Ext/Fastest CPU(time 1564.133ms speed 2765.351) 39.158 times faster
      (1048576, real 5767168) GPU(time 52.928ms speed 108962.515) L1Ext/Fastest CPU(time 2075.748ms speed 2778.357) 39.218 times faster
      (1310720, real 7208960) GPU(time 66.130ms speed 109011.946) L1Ext/Fastest CPU(time 2582.826ms speed 2791.113) 39.057 times faster
      (1572864, real 8650752) GPU(time 79.551ms speed 108744.730) L1Ext/Fastest CPU(time 3110.989ms speed 2780.708) 39.107 times faster
      (1835008, real 10092544) GPU(time 92.689ms speed 108886.103) L1Ext/Fastest CPU(time 3611.612ms speed 2794.471) 38.965 times faster
      (2097152, real 11534336) GPU(time 105.919ms speed 108897.705) L1Ext/Fastest CPU(time 4131.650ms speed 2791.702) 39.008 times faster
    • mine with checking results
      [group=0] 0 results
  • [0] round time: 120.349 milliseconds, speed: 83.861 M
    [group=0] 88 results

  • [1] round time: 109.164 milliseconds, speed: 92.453 M
    [group=0] 135 results

  • [2] round time: 129.186 milliseconds, speed: 78.124 M
    [group=0] 85 results

  • [3] round time: 100.036 milliseconds, speed: 100.889 M
    [group=0] 94 results

  • [4] round time: 128.009 milliseconds, speed: 78.842 M
    [group=0] 140 results

  • [5] round time: 119.109 milliseconds, speed: 84.734 M
    [group=0] 108 results

  • [6] round time: 119.343 milliseconds, speed: 84.568 M
    [group=0] 55 results

  • [7] round time: 109.594 milliseconds, speed: 92.090 M
    [group=0] 121 results

  • [8] round time: 128.389 milliseconds, speed: 78.609 M
    [group=0] 84 results

  • [9] round time: 110.176 milliseconds, speed: 91.604 M
    [group=0] 119 results

  • [10] round time: 128.780 milliseconds, speed: 78.370 M
    [group=0] 61 results

  • [11] round time: 99.209 milliseconds, speed: 101.730 M
    [group=0] 86 results

  • [12] round time: 129.273 milliseconds, speed: 78.072 M
    [group=0] 118 results

  • [13] round time: 120.118 milliseconds, speed: 84.022 M
    [group=0] 88 results

  • [14] round time: 109.637 milliseconds, speed: 92.054 M
    [group=0] 112 results

  • [15] round time: 128.338 milliseconds, speed: 78.640 M
    [group=0] 165 results

  • [16] round time: 109.006 milliseconds, speed: 92.587 M
    [group=0] 62 results

  • [17] round time: 119.242 milliseconds, speed: 84.639 M
    [group=0] 95 results

  • [18] round time: 119.206 milliseconds, speed: 84.665 M
    [group=0] 154 results

  • [19] round time: 129.924 milliseconds, speed: 77.680 M
    [group=0] 79 results

  • [20] round time: 109.818 milliseconds, speed: 91.902 M
    [group=0] 74 results

  • [21] round time: 119.105 milliseconds, speed: 84.737 M
    [group=0] 110 results

  • [22] round time: 117.884 milliseconds, speed: 85.614 M
    [group=0] 110 results

  • [23] round time: 119.073 milliseconds, speed: 84.759 M
    [group=0] 90 results

  • [24] round time: 119.525 milliseconds, speed: 84.439 M
    [group=0] 130 results

  • [25] round time: 109.670 milliseconds, speed: 92.026 M
    [group=0] 77 results

  • [26] round time: 119.654 milliseconds, speed: 84.348 M
    [group=0] 104 results

  • [27] round time: 129.704 milliseconds, speed: 77.812 M
    [group=0] 130 results

  • [28] round time: 129.561 milliseconds, speed: 77.898 M
    [group=0] 151 results

  • [29] round time: 118.869 milliseconds, speed: 84.905 M
    [group=0] 77 results

  • [30] round time: 109.325 milliseconds, speed: 92.317 M
    [group=0] 90 results

  • [31] round time: 120.227 milliseconds, speed: 83.946 M

  • mine performance test
    nonceAndHash query error -5!

  • [0] round time: 13.925 milliseconds, speed: 14495.575 M
    nonceAndHash query error -5!

  • [1] round time: 0.100 milliseconds, speed: 2018508.800 M
    nonceAndHash query error -5!

  • [2] round time: 0.093 milliseconds, speed: 2170439.570 M
    nonceAndHash query error -5!

  • [3] round time: 0.101 milliseconds, speed: 1998523.564 M
    nonceAndHash query error -5!

  • [4] round time: 0.103 milliseconds, speed: 1959717.282 M
    nonceAndHash query error -5!

  • [5] round time: 0.113 milliseconds, speed: 1786290.973 M
    nonceAndHash query error -5!

  • [6] round time: 0.119 milliseconds, speed: 1696225.882 M
    nonceAndHash query error -5!

  • [7] round time: 0.124 milliseconds, speed: 1627829.677 M
    nonceAndHash query error -5!

  • [8] round time: 0.129 milliseconds, speed: 1564735.504 M
    nonceAndHash query error -5!

  • [9] round time: 0.142 milliseconds, speed: 1421485.070 M
    nonceAndHash query error -5!

  • [10] round time: 0.155 milliseconds, speed: 1302263.742 M
    nonceAndHash query error -5!

  • [11] round time: 0.161 milliseconds, speed: 1253732.174 M
    nonceAndHash query error -5!

  • [12] round time: 0.167 milliseconds, speed: 1208687.904 M
    nonceAndHash query error -5!

  • [13] round time: 0.174 milliseconds, speed: 1160062.529 M
    nonceAndHash query error -5!

  • [14] round time: 0.182 milliseconds, speed: 1109070.769 M
    nonceAndHash query error -5!

  • [15] round time: 0.188 milliseconds, speed: 1073674.894 M
    nonceAndHash query error -5!

  • [16] round time: 0.209 milliseconds, speed: 965793.684 M
    nonceAndHash query error -5!

  • [17] round time: 0.204 milliseconds, speed: 989465.098 M
    nonceAndHash query error -5!

  • [18] round time: 0.208 milliseconds, speed: 970436.923 M
    nonceAndHash query error -5!

  • [19] round time: 0.219 milliseconds, speed: 921693.516 M
    nonceAndHash query error -5!

  • [20] round time: 0.243 milliseconds, speed: 830662.058 M
    nonceAndHash query error -5!

  • [21] round time: 0.270 milliseconds, speed: 747595.852 M
    nonceAndHash query error -5!

  • [22] round time: 0.251 milliseconds, speed: 804186.773 M
    nonceAndHash query error -5!

  • [23] round time: 0.260 milliseconds, speed: 776349.538 M
    nonceAndHash query error -5!

  • [24] round time: 0.287 milliseconds, speed: 703313.171 M
    nonceAndHash query error -5!

  • [25] round time: 0.283 milliseconds, speed: 713253.993 M
    nonceAndHash query error -5!

  • [26] round time: 0.292 milliseconds, speed: 691270.137 M
    nonceAndHash query error -5!

  • [27] round time: 0.395 milliseconds, speed: 511014.886 M
    nonceAndHash query error -5!

  • [28] round time: 0.444 milliseconds, speed: 454619.099 M
    nonceAndHash query error -5!

  • [29] round time: 0.469 milliseconds, speed: 430385.672 M
    nonceAndHash query error -5!

  • [30] round time: 0.471 milliseconds, speed: 428558.132 M
    nonceAndHash query error -5!

  • [31] round time: 0.483 milliseconds, speed: 417910.725 M

@eXtremal.ik7

Would you please take into consideration the CPU core count when calculating your benchmark results. It seems as if the GPU is going up against a single CPU core.

Thanks. That now works but run into another exception when i try to compile. Using one of my SMOS rigs(Debian)
May be too old gcc version, 4.7 is minimum required (or clang 3.2) or 32bit OS used.
nonceAndHash query error -5!
-5 means out of resources (I think global memory). Try launch mining. If unsuccess, you can change threads number at OpenCL/utils.cpp line 209 (change ComputeUnits*4 to ComputeUnits*2).
Would you please take into consideration the CPU core count when calculating your benchmark results. It seems as if the GPU is going up against a single CPU core.
Yes, CPU need only for GPU results checking.

@eXtremal.ik7

I made the change you recommended and I still receive the same error:
nonceAndHash query error -5!

When mining:
CLKernelSearchNonce launch error -9999!
nonceAndHash query error -5!
Segmentation fault (core dumped)

Using Catalyst 13.12’s libamdocl64.so
Encountered this error:

Program received signal SIGSEGV, Segmentation fault.
0x00007fffed165c30 in SCIDV::ConvertToFor(bool) () from /usr/lib/libamdocl64.so

[quote=“primer10, post:32, topic:2223”]Using Catalyst 13.12’s libamdocl64.so
Encountered this error:

Program received signal SIGSEGV, Segmentation fault.
0x00007fffed165c30 in SCIDV::ConvertToFor(bool) () from /usr/lib/libamdocl64.so[/quote]
What with Catalyst 14.3 ?

[quote=“eXtremal.ik7, post:33, topic:2223”][quote=“primer10, post:32, topic:2223”]Using Catalyst 13.12’s libamdocl64.so
Encountered this error:

Program received signal SIGSEGV, Segmentation fault.
0x00007fffed165c30 in SCIDV::ConvertToFor(bool) () from /usr/lib/libamdocl64.so[/quote]
What with Catalyst 14.3 ?[/quote]

Sorry was looking at the previous posts, you did say use Catalyst 14.3 … was hoping it would work with Catalyst 13.12 … apparently not … any chances of making it work on 13.12?

In any case, stack:

Program received signal SIGSEGV, Segmentation fault.
0x00007fffed165c30 in SCIDV::ConvertToFor(bool) () from /usr/lib/libamdocl64.so
(gdb) bt
#0  0x00007fffed165c30 in SCIDV::ConvertToFor(bool) () from /usr/lib/libamdocl64.so
#1  0x00007fffed16751b in SCIDV::ProcessSCC() () from /usr/lib/libamdocl64.so
#2  0x00007fffed168f68 in SCC_BASE<SCInst>::SCC(SCInst*) () from /usr/lib/libamdocl64.so
#3  0x00007fffed166ebc in SCIDV::Traversal() () from /usr/lib/libamdocl64.so
#4  0x00007fffecef8482 in CompilerBase::GenerateCodeUsingNewIR(void*, bool) () from /usr/lib/libamdocl64.so
#5  0x00007fffecefdb6c in Compiler::Compile(ILProgram*) () from /usr/lib/libamdocl64.so
#6  0x00007fffecefe2a0 in Compiler::CompileShader(unsigned char*, unsigned char*, unsigned int const*, CompilerExternal*) () from /usr/lib/libamdocl64.so
#7  0x00007fffecefe67a in CompilerExternal::CompileShader(_SC_SRCSHADER const*, _SC_HWSHADER*) () from /usr/lib/libamdocl64.so
#8  0x00007fffed2bc904 in amdcl::scCompileSI::Compile(amdcl::_il_binary_rec&, unsigned long&) () from /usr/lib/libamdocl64.so
#9  0x00007fffed2f81a7 in amdcl::AMDIL::assemble(amdcl::_il_binary_rec*, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, amdcl::scCompileBase*) () from /usr/lib/libamdocl64.so
#10 0x00007fffed2f7ede in amdcl::AMDIL::compile(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> >, amdcl::scCompileBase*) () from /usr/lib/libamdocl64.so
#11 0x00007fffed2f79cb in amdcl::AMDIL::compile(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> >) () from /usr/lib/libamdocl64.so
#12 0x00007fffed2f3f8b in AMDILFEToISA(_acl_loader_data_0_8**, char const*, unsigned long) () from /usr/lib/libamdocl64.so
#13 0x00007fffed2f2dd5 in if_aclCompile(_acl_compiler_rec_0_8_1*, _acl_bif_rec_0_8_1*, char const*, _acl_type_enum_0_8, _acl_type_enum_0_8, void (*)(char const*, unsigned long)) () from /usr/lib/libamdocl64.so
#14 0x00007fffed2b0b24 in aclCompile () from /usr/lib/libamdocl64.so
#15 0x00007fffecbe27b0 in gpu::NullKernel::create(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, void const*, unsigned long) () from /usr/lib/libamdocl64.so
#16 0x00007fffecbe28e1 in gpu::Kernel::create(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, void const*, unsigned long) () from /usr/lib/libamdocl64.so
#17 0x00007fffecbf3296 in gpu::Program::createKernel(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, gpu::Kernel::InitData const*, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, bool*, void const*, unsigned long) () from /usr/lib/libamdocl64.so
#18 0x00007fffecbf24ba in gpu::NullProgram::linkImpl(amd::option::Options*) () from /usr/lib/libamdocl64.so
#19 0x00007fffecb8cca5 in device::Program::build(stlp_std::basic_string<char, stlp_std::char_traits<char>, stlp_std::allocator<char> > const&, char const*, amd::option::Options*) () from /usr/lib/libamdocl64.so
#20 0x00007fffecba066c in amd::Program::build(stlp_std::vector<amd::Device*, stlp_std::allocator<amd::Device*> > const&, char const*, void (*)(_cl_program*, void*), void*, bool) () from /usr/lib/libamdocl64.so
#21 0x00007fffecb81d97 in clBuildProgram () from /usr/lib/libamdocl64.so
#22 0x000000000040d132 in OpenCLInit(OpenCLPlatrormContext&, char const*, std::vector<unsigned int, std::allocator<unsigned int> >&, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, bool) ()
#23 0x0000000000405b9b in main ()

AMD compiler from 13.x has a lot of bugs. If you can’t use Catalyst 14.3, extract single file (libamdocl64.so) from package and replace old version (make reserve copy of original libamdocl64.so before).

AMD compiler from 13.x has a lot of bugs. If you can’t use Catalyst 14.3, extract single file (libamdocl64.so) from package and replace old version (make reserve copy of original libamdocl64.so before).[/quote]

cool!! It works now! many thanks!

[1] 2.032G, average: 2.035G
[2] 1.994G, average: 2.016G
 * speed: 4.026G, average: 4.050G

   * chains/1: 18242910 38004.886/sec
   * chains/2: 1390497 2896.779/sec
   * chains/3: 162057 337.608/sec
   * chains/4: 12720 26.499/sec
   * chains/5: 1071 2.231/sec
   * chains/6: 70 0.146/sec
   * chains/7: 3 0.006/sec 22.499/hour

1st: thanks to eXtremal.ik7 make miner opensource !
2nd:my rig has occur a problem: there are repeat following string all the time:

18-04-2014 00:29:00: Error JSON result is error 18-04-2014 00:29:06: Error JSON result is error 18-04-2014 00:29:10: Error JSON result is error 18-04-2014 00:29:14: Error JSON result is error 18-04-2014 00:29:18: Error JSON result is error

then I checked code ,find it print by “common/getblocktemplate.cpp” line 82; how to solve it? thanks!
My rig system info is:

OS: uname -a Linux 3.8.0-29-generic #42~precise1-Ubuntu SMP Wed Aug 14 16:19:23 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux

HW:
Intel E5 2670(ES) 2.6G
MEM 8G
3* AMD R290

Driver:
Linux_AMD_Catalyst_14.3_Beta_V1.0_B22_March12_2014
AMD APP SDK 2.9

[quote=“optimusprime, post:24, topic:2223”]Noob question . What do i set for this directory ?

OPENCL_INCLUDE_DIRS (ADVANCED)[/quote]

when cmake, it report a error message " Could NOT find OpenCL (missing: OPENCL_INCLUDE_DIRS)" then I followed the link:http://dokyunblog.blogspot.com/2013_05_01_archive.html
added:

Open

opencl-book-samples-read-only/cmake/FindOpenCL.cmake

add AMD straming SDK opencl include path as llike below

FIND_PATH(OPENCL_INCLUDE_DIRS CL/cl.h PATHS ${_OPENCL_INC_CAND} “/usr/local/cuda/include” “/opt/AMDAPP/include/”)

then solved.

[quote=“gee4xpm, post:38, topic:2223”]1st: thanks to eXtremal.ik7 make miner opensource !
2nd:my rig has occur a problem: there are repeat following string all the time:

18-04-2014 00:29:00: Error JSON result is error 18-04-2014 00:29:06: Error JSON result is error 18-04-2014 00:29:10: Error JSON result is error 18-04-2014 00:29:14: Error JSON result is error 18-04-2014 00:29:18: Error JSON result is error

then I checked code ,find it print by “common/getblocktemplate.cpp” line 82; how to solve it? thanks!
My rig system info is:

OS: uname -a Linux 3.8.0-29-generic #42~precise1-Ubuntu SMP Wed Aug 14 16:19:23 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux

HW:
Intel E5 2670(ES) 2.6G
MEM 8G
3* AMD R290

Driver:
Linux_AMD_Catalyst_14.3_Beta_V1.0_B22_March12_2014
AMD APP SDK 2.9

[/quote]

ur primecoind listening?