n256-7440p-8t version: V3.0
Release date: November 11, 2015
Machine Summary: 
  Distributed Processes: 7440
  Threads per processes: 8
Global Problem Dimensions: 
  Global nx: 4096
  Global ny: 3840
  Global nz: 7936
Processor Dimensions: 
  npx: 16
  npy: 15
  npz: 31
Local Domain Dimensions: 
  nx: 256
  ny: 256
  nz: 256
########## Problem Summary  ##########: 
Setup Information: 
  Setup Time: 5.24965
Linear System Information: 
  Number of Equations: 124822487040
  Number of Nonzero Terms: 3368790583288
Multigrid Information: 
  Number of coarse grid levels: 3
  Coarse Grids: 
    Grid Level: 1
    Number of Equations: 15602810880
    Number of Nonzero Terms: 420921799672
    Number of Presmoother Steps: 1
    Number of Postsmoother Steps: 1
    Grid Level: 2
    Number of Equations: 1950351360
    Number of Nonzero Terms: 52570987000
    Number of Presmoother Steps: 1
    Number of Postsmoother Steps: 1
    Grid Level: 3
    Number of Equations: 243793920
    Number of Nonzero Terms: 6560322808
    Number of Presmoother Steps: 1
    Number of Postsmoother Steps: 1
########## Memory Use Summary  ##########: 
Memory Use Information: 
  Total memory used for data (Gbytes): 89240.6
  Memory used for OptimizeProblem data (Gbytes): 0
  Bytes per equation (Total memory / Number of Equations): 714.94
  Memory used for linear system and CG (Gbytes): 78536.8
  Coarse Grids: 
    Grid Level: 1
    Memory used: 9383.19
    Grid Level: 2
    Memory used: 1173.65
    Grid Level: 3
    Memory used: 146.897
########## V&V Testing Summary  ##########: 
Spectral Convergence Tests: 
  Result: PASSED
  Unpreconditioned: 
    Maximum iteration count: 11
    Expected iteration count: 12
  Preconditioned: 
    Maximum iteration count: 2
    Expected iteration count: 2
Departure from Symmetry |x'Ay-y'Ax|/(2*||x||*||A||*||y||)/epsilon: 
  Result: PASSED
  Departure for SpMV: 0
  Departure for MG: 0
########## Iterations Summary  ##########: 
Iteration Count Information: 
  Result: PASSED
  Reference CG iterations per set: 50
  Optimized CG iterations per set: 51
  Total number of reference iterations: 3800
  Total number of optimized iterations: 3876
########## Reproducibility Summary  ##########: 
Reproducibility Information: 
  Result: PASSED
  Scaled residual mean: 0.00483793
  Scaled residual variance: 5.30581e-36
########## Performance Summary (times in sec) ##########: 
Benchmark Time Summary: 
  Optimization phase: 2.85958
  DDOT: 24.4906
  WAXPBY: 79.2029
  SpMV: 615.863
  MG: 2734.33
  ALL_reduce: 145.698
  Total: 3599.59
Floating Point Operations Summary: 
  Raw DDOT: 2.92184e+15
  Raw WAXPBY: 2.92184e+15
  Raw SpMV: 2.66269e+16
  Raw MG: 1.49029e+17
  Total: 1.81499e+17
  Total with convergence overhead: 1.7794e+17
GB/s Summary: 
  Raw Read B/W: 310557
  Raw Write B/W: 71769
  Raw Total B/W: 382326
  Total with convergence and optimization phase overhead: 368520
GFLOP/s Summary: 
  Raw DDOT: 119305
  Raw WAXPBY: 36890.6
  Raw SpMV: 43235.1
  Raw MG: 54502.8
  Raw Total: 50422.1
  Total with convergence overhead: 49433.5
  Total with convergence and optimization phase overhead: 48601.3
User Optimization Overheads: 
  Problem setup time (sec): 5.24965
  Optimization phase time (sec): 2.85958
  Optimization phase time vs reference SpMV+MG time: 1.32014
DDOT Timing Variations: 
  Min DDOT MPI_Allreduce time: 91.6603
  Max DDOT MPI_Allreduce time: 161.947
  Avg DDOT MPI_Allreduce time: 129.288
__________ Final Summary __________: 
  HPCG result is VALID with a GFLOP/s rating of: 48601.3
      HPCG 2.4 Rating (for historical value) is: 49136.8
  Reference version of ComputeDotProduct used: Performance results are most likely suboptimal
  Please upload results from the YAML file contents to: http://hpcg-benchmark.org