[root@RX350s7ambertest FactorIX_production_NPT]# less mdout_intmva2_gpu4node-4pro_0818-1

          -------------------------------------------------------
          Amber 12 SANDER                              2012
          -------------------------------------------------------

| PMEMD implementation of SANDER, Release 12

| Run on 08/16/2013 at 11:01:27

  [-O]verwriting output

File Assignments:
|   MDIN: mdin
|  MDOUT: mdout_intmva2_gpu4node-4pro_0818-1
| INPCRD: inpcrd
|   PARM: prmtop
| RESTRT: restrt
|   REFC: refc
|  MDVEL: mdvel
|   MDEN: mden
|  MDCRD: mdcrd
| MDINFO: mdinfo
|LOGFILE: logfile


 Here is the input file:

 Typical Production MD NVT
 &cntrl
  ntx=5, irest=1,
  ntc=2, ntf=2,
  nstlim=10000,
  ntpr=1000, ntwx=1000,
  ntwr=10000,
  dt=0.002, cut=8.,
  ntt=1, tautp=10.0,
  temp0=300.0,
  ntb=2, ntp=1, taup=10.0,
  ioutfm=1,
 /




|--------------------- INFORMATION ----------------------
| GPU (CUDA) Version of PMEMD in use: NVIDIA GPU IN USE.
|                     Version 12.3
|
|                      04/24/2013
|
| Implementation by:
|                    Ross C. Walker     (SDSC)
|                    Scott Le Grand     (nVIDIA)
|                    Duncan Poole       (nVIDIA)
|
| CAUTION: The CUDA code is currently experimental.
|          You use it at your own risk. Be sure to
|          check ALL results carefully.
|
| Precision model in use:
|      [SPFP] - Mixed Single/Double/Fixed Point Precision.
|               (Default)
|
|--------------------------------------------------------

|----------------- CITATION INFORMATION -----------------
|
|    When publishing work that utilized the CUDA version
|    of AMBER, please cite the following in addition to
|    the regular AMBER citations:
|
|  - Romelia Salomon-Ferrer; Andreas W. Goetz; Duncan
|    Poole; Scott Le Grand; Ross C. Walker "Routine
|    microsecond molecular dynamics simulations with
|    AMBER - Part II: Particle Mesh Ewald", J. Chem.
|    Theory Comput., 2012, (In review).
|
|  - Andreas W. Goetz; Mark J. Williamson; Dong Xu;
|    Duncan Poole; Scott Le Grand; Ross C. Walker
|    "Routine microsecond molecular dynamics simulations
|    with AMBER - Part I: Generalized Born", J. Chem.
|    Theory Comput., 2012, 8 (5), pp1542-1555.
|
|  - Scott Le Grand; Andreas W. Goetz; Ross C. Walker
|    "SPFP: Speed without compromise - a mixed precision
|    model for GPU accelerated molecular dynamics
|    simulations.", Comp. Phys. Comm., 2013, 184
|    pp374-380, DOI: 10.1016/j.cpc.2012.09.022
|
|--------------------------------------------------------

|------------------- GPU DEVICE INFO --------------------
|
|                         Task ID:      0
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      0
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      1
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      1
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      2
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      0
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      3
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      1
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|--------------------------------------------------------

| INFO:    Axis order optimization will be used.


| Conditional Compilation Defines Used:
| DIRFRC_COMTRANS
| DIRFRC_EFS
| DIRFRC_NOVEC
| MPI
| PUBFFT
| FFTLOADBAL_2PROC

          -------------------------------------------------------
          Amber 12 SANDER                              2012
          -------------------------------------------------------

| PMEMD implementation of SANDER, Release 12

| Run on 08/16/2013 at 11:45:26

  [-O]verwriting output

File Assignments:
|   MDIN: mdin
|  MDOUT: mdout_intmva2_gpu4node-4pro_0818-1
| INPCRD: inpcrd
|   PARM: prmtop
| RESTRT: restrt
|   REFC: refc
|  MDVEL: mdvel
|   MDEN: mden
|  MDCRD: mdcrd
| MDINFO: mdinfo
|LOGFILE: logfile


 Here is the input file:

 Typical Production MD NVT
 &cntrl
  ntx=5, irest=1,
  ntc=2, ntf=2,
  nstlim=10000,
  ntpr=1000, ntwx=1000,
  ntwr=10000,
  dt=0.002, cut=8.,
  ntt=1, tautp=10.0,
  temp0=300.0,
  ntb=2, ntp=1, taup=10.0,
  ioutfm=1,
 /




|--------------------- INFORMATION ----------------------
| GPU (CUDA) Version of PMEMD in use: NVIDIA GPU IN USE.
|                     Version 12.3
|
|                      04/24/2013
[root@RX350s7ambertest FactorIX_production_NPT]#
[root@RX350s7ambertest FactorIX_production_NPT]# cat mdout_intmva2_gpu4node-4pro_0818-1

          -------------------------------------------------------
          Amber 12 SANDER                              2012
          -------------------------------------------------------

| PMEMD implementation of SANDER, Release 12

| Run on 08/16/2013 at 11:45:26

  [-O]verwriting output

File Assignments:
|   MDIN: mdin
|  MDOUT: mdout_intmva2_gpu4node-4pro_0818-1
| INPCRD: inpcrd
|   PARM: prmtop
| RESTRT: restrt
|   REFC: refc
|  MDVEL: mdvel
|   MDEN: mden
|  MDCRD: mdcrd
| MDINFO: mdinfo
|LOGFILE: logfile


 Here is the input file:

 Typical Production MD NVT
 &cntrl
  ntx=5, irest=1,
  ntc=2, ntf=2,
  nstlim=10000,
  ntpr=1000, ntwx=1000,
  ntwr=10000,
  dt=0.002, cut=8.,
  ntt=1, tautp=10.0,
  temp0=300.0,
  ntb=2, ntp=1, taup=10.0,
  ioutfm=1,
 /




|--------------------- INFORMATION ----------------------
| GPU (CUDA) Version of PMEMD in use: NVIDIA GPU IN USE.
|                     Version 12.3
|
|                      04/24/2013
|
| Implementation by:
|                    Ross C. Walker     (SDSC)
|                    Scott Le Grand     (nVIDIA)
|                    Duncan Poole       (nVIDIA)
|
| CAUTION: The CUDA code is currently experimental.
|          You use it at your own risk. Be sure to
|          check ALL results carefully.
|
| Precision model in use:
|      [SPFP] - Mixed Single/Double/Fixed Point Precision.
|               (Default)
|
|--------------------------------------------------------

|----------------- CITATION INFORMATION -----------------
|
|    When publishing work that utilized the CUDA version
|    of AMBER, please cite the following in addition to
|    the regular AMBER citations:
|
|  - Romelia Salomon-Ferrer; Andreas W. Goetz; Duncan
|    Poole; Scott Le Grand; Ross C. Walker "Routine
|    microsecond molecular dynamics simulations with
|    AMBER - Part II: Particle Mesh Ewald", J. Chem.
|    Theory Comput., 2012, (In review).
|
|  - Andreas W. Goetz; Mark J. Williamson; Dong Xu;
|    Duncan Poole; Scott Le Grand; Ross C. Walker
|    "Routine microsecond molecular dynamics simulations
|    with AMBER - Part I: Generalized Born", J. Chem.
|    Theory Comput., 2012, 8 (5), pp1542-1555.
|
|  - Scott Le Grand; Andreas W. Goetz; Ross C. Walker
|    "SPFP: Speed without compromise - a mixed precision
|    model for GPU accelerated molecular dynamics
|    simulations.", Comp. Phys. Comm., 2013, 184
|    pp374-380, DOI: 10.1016/j.cpc.2012.09.022
|
|--------------------------------------------------------

|------------------- GPU DEVICE INFO --------------------
|
|                         Task ID:      0
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      0
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      1
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      1
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      2
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      0
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|
|                         Task ID:      3
|   CUDA Capable Devices Detected:      2
|           CUDA Device ID in use:      1
|                CUDA Device Name: Tesla K20Xm
|     CUDA Device Global Mem Size:   6143 MB
| CUDA Device Num Multiprocessors:     14
|           CUDA Device Core Freq:   0.73 GHz
|
|--------------------------------------------------------

| INFO:    Axis order optimization will be used.


| Conditional Compilation Defines Used:
| DIRFRC_COMTRANS
| DIRFRC_EFS
| DIRFRC_NOVEC
| MPI
| PUBFFT
| FFTLOADBAL_2PROC
| BINTRAJ
| MKL
| CUDA

| Largest sphere to fit in unit cell has radius =    39.339

|  INFO: Old style PARM file read


| Note: 1-4 EEL scale factors were NOT found in the topology file.
|       Using default value of 1.2.

| Note: 1-4 VDW scale factors were NOT found in the topology file.
|       Using default value of 2.0.
| Duplicated  437 dihedrals

| Duplicated 1846 dihedrals

--------------------------------------------------------------------------------
   1.  RESOURCE   USE:
--------------------------------------------------------------------------------

 getting new box info from bottom of inpcrd

 NATOM  =   90906 NTYPES =      19 NBONH =   87891 MBONA  =    3077
 NTHETH =    6433 MTHETA =    4178 NPHIH =   11305 MPHIA  =    5519
 NHPARM =       0 NPARM  =       0 NNB   =  145596 NRES   =   28750
 NBONA  =    3077 NTHETA =    4178 NPHIA =    5519 NUMBND =      54
 NUMANG =     126 NPTRA  =      75 NATYP =      31 NPHB   =       1
 IFBOX  =       1 NMXRS  =      24 IFCAP =       0 NEXTRA =       0
 NCOPY  =       0

| Coordinate Index Table dimensions:    28   16   15
| Direct force subcell size =     5.0745    5.2086    5.2452

     BOX TYPE: RECTILINEAR

--------------------------------------------------------------------------------
   2.  CONTROL  DATA  FOR  THE  RUN
--------------------------------------------------------------------------------

factor IX (ACTIVATED PROTEIN)

General flags:
     imin    =       0, nmropt  =       0

Nature and format of input:
     ntx     =       5, irest   =       1, ntrx    =       1

Nature and format of output:
     ntxo    =       1, ntpr    =    1000, ntrx    =       1, ntwr    =   10000
     iwrap   =       0, ntwx    =    1000, ntwv    =       0, ntwe    =       0
     ioutfm  =       1, ntwprt  =       0, idecomp =       0, rbornstat=      0

Potential function:
     ntf     =       2, ntb     =       2, igb     =       0, nsnb    =      25
     ipol    =       0, gbsa    =       0, iesp    =       0
     dielc   =   1.00000, cut     =   8.00000, intdiel =   1.00000

Frozen or restrained atoms:
     ibelly  =       0, ntr     =       0

Molecular dynamics:
     nstlim  =     10000, nscm    =      1000, nrespa  =         1
     t       =   0.00000, dt      =   0.00200, vlimit  =  -1.00000

Berendsen (weak-coupling) temperature regulation:
     temp0   = 300.00000, tempi   =   0.00000, tautp   =  10.00000

Pressure regulation:
     ntp     =       1
     pres0   =   1.00000, comp    =  44.60000, taup    =  10.00000

SHAKE:
     ntc     =       2, jfastw  =       0
     tol     =   0.00001

| Intermolecular bonds treatment:
|     no_intermolecular_bonds =       1

| Energy averages sample interval:
|     ene_avg_sampling =    1000

Ewald parameters:
     verbose =       0, ew_type =       0, nbflag  =       1, use_pme =       1
     vdwmeth =       1, eedmeth =       1, netfrc  =       1
     Box X =  142.086   Box Y =   83.337   Box Z =   78.678
     Alpha =   90.000   Beta  =   90.000   Gamma =   90.000
     NFFT1 =  144       NFFT2 =   84       NFFT3 =   80
     Cutoff=    8.000   Tol   =0.100E-04
     Ewald Coefficient =  0.34864
     Interpolation order =    4

| PMEMD ewald parallel performance parameters:
|     block_fft =    0
|     fft_blk_y_divisor =    2
|     excl_recip =    0
|     excl_master =    0
|     atm_redist_freq =  320

--------------------------------------------------------------------------------
   3.  ATOMIC COORDINATES AND VELOCITIES
--------------------------------------------------------------------------------

factor IX (ACTIVATED PROTEIN)
 begin time read from input coords =  2542.675 ps


 Number of triangulated 3-point waters found:    28358

     Sum of charges from parm topology file =   0.00031225
     Forcing neutrality...

| Dynamic Memory, Types Used:
| Reals             3876951
| Integers          3639776

| Nonbonded Pairs Initial Allocation:     5181642

| GPU memory information (estimate):
| KB of GPU memory in use:     96029
| KB of CPU memory in use:     96029

| Running AMBER/MPI version on    4 nodes


--------------------------------------------------------------------------------
   4.  RESULTS
--------------------------------------------------------------------------------

 ---------------------------------------------------
 APPROXIMATING switch and d/dx switch using CUBIC SPLINE INTERPOLATION
 using   5000.0 points per unit in tabled values
 TESTING RELATIVE ERROR over r ranging from 0.0 to cutoff
| CHECK switch(x): max rel err =   0.2738E-14   at   2.422500
| CHECK d/dx switch(x): max rel err =   0.8332E-11   at   2.782960
 ---------------------------------------------------
|---------------------------------------------------
| APPROXIMATING direct energy using CUBIC SPLINE INTERPOLATION
|  with   50.0 points per unit in tabled values
| Relative Error Limit not exceeded for r .gt.   2.47
| APPROXIMATING direct force using CUBIC SPLINE INTERPOLATION
|  with   50.0 points per unit in tabled values
| Relative Error Limit not exceeded for r .gt.   2.89
|---------------------------------------------------
check COM velocity, temp:        0.000018     0.00(Removed)

 NSTEP =     1000   TIME(PS) =    2544.675  TEMP(K) =   296.90  PRESS =  -694.5
 Etot   =   -233748.6862  EKtot   =     54523.3398  EPtot      =   -288272.0261
 BOND   =      1137.6172  ANGLE   =      2934.5131  DIHED      =      2246.0865
 1-4 NB =      1288.3081  1-4 EEL =     15112.1345  VDWAALS    =     36457.3797
 EELEC  =   -347448.0652  EHBOND  =         0.0000  RESTRAINT  =         0.0000
 EKCMT  =     25361.2361  VIRIAL  =     39519.1411  VOLUME     =    944163.2170
                                                    Density    =         0.9747
 ------------------------------------------------------------------------------

check COM velocity, temp:        0.000027     0.00(Removed)

 NSTEP =     2000   TIME(PS) =    2546.675  TEMP(K) =   295.89  PRESS =  -968.7
 Etot   =   -233339.5533  EKtot   =     54337.9648  EPtot      =   -287677.5181
 BOND   =      1127.3253  ANGLE   =      2924.9643  DIHED      =      2215.0624
 1-4 NB =      1298.3079  1-4 EEL =     15114.4109  VDWAALS    =     35626.9347
 EELEC  =   -345984.5237  EHBOND  =         0.0000  RESTRAINT  =         0.0000
 EKCMT  =     25131.5725  VIRIAL  =     45093.5005  VOLUME     =    954386.4124
                                                    Density    =         0.9643
 ------------------------------------------------------------------------------
