commit f5cc0a9c6f1af5c0c778660e7c341462041fc9ed parent 4520d4ce46c26bdb71dab7baa3a346391995cda3 Author: Ivan Gankevich <igankevich@ya.ru> Date: Wed, 10 May 2017 20:02:30 +0300 Add scripts to plot the data. Diffstat:
167 files changed, 2255 insertions(+), 516 deletions(-)
diff --git a/.gitignore b/.gitignore @@ -0,0 +1 @@ +/bin/ diff --git a/Makefile b/Makefile @@ -0,0 +1,2 @@ +all: + ./R/plot-cpu-gpu.R diff --git a/R/common.R b/R/common.R @@ -0,0 +1,45 @@ +load_log_file_as_data_frame <- function (prefix, pattern) { + runtime <- data.frame() + dirs <- sort(list.files(prefix)) + rownum <- 1 + for (d in dirs) { + files <- sort(list.files(file.path(prefix, d), pattern=pattern)) + for (f in files) { + lines <- readLines(file.path(prefix, d, f)) + t <- lines[grepl("^prfl.*=.*$", lines, perl=TRUE)] + t <- gsub("^prfl\\s+.*=\\s*([0-9]+)us$", "\\1", t, perl=TRUE) + t <- sum(as.numeric(t)) + s <- lines[grepl("^Output grid size", lines, perl=TRUE)] + s <- gsub( + "Output grid size\\s*=\\s*\\([0-9]+,([0-9]+),[0-9]+\\)", + "\\1", + s, + perl=TRUE + ) + s <- as.numeric(s) + # add new column if needed + if (!("t" %in% colnames(runtime))) { + runtime[, "t"] <- rep(NA, nrow(runtime)) + } + if (!("size" %in% colnames(runtime))) { + runtime[, "size"] <- rep(NA, nrow(runtime)) + } + # add new row if needed +# r <- paste(d, s, sep="-") + r <- rownum + if (!(r %in% rownames(runtime))) { + runtime[r, ] <- rep(NA, ncol(runtime)) + } + runtime[r, ] <- c(t, s) + rownum <- rownum + 1 + } + } + runtime +} + +arma.plot_cpu_gpu <- function () { + data1 <- load_log_file_as_data_frame("data", "^linear.*\\.log$") + data2 <- load_log_file_as_data_frame("data", "^high_amplitude_realtime.*\\.log$") + print(data1) + print(data2) +} diff --git a/R/plot-cpu-gpu.R b/R/plot-cpu-gpu.R @@ -0,0 +1,5 @@ +#!/usr/bin/Rscript + +source(file.path("R", "common.R")) + +data <- arma.plot_cpu_gpu() diff --git a/benchmark-cpu-gpu b/benchmark-cpu-gpu @@ -1,36 +0,0 @@ -#!/bin/sh - -inputfile=$(mktemp) -for solver in linear high_amplitude_realtime -do -for size in 128 256 512 1024 -do - echo - echo "********************************************************************************" - echo " solver = $solver" - echo " size = $size" - echo "********************************************************************************" - echo - cat >$inputfile << EOF -out_grid = (200,$size,40) : (199,8,8) - -model = plain_wave -plain_wave = { - func = cos - amplitudes = [4] - wavenumbers = [0.125] - phases = [0] - velocities = [0.5] -} -verification = none - -velocity_potential_solver = $solver { - wnmax = from (0,0) to (0,0.25) npoints (2,2) - depth = 12 - domain = from (10,-12) to (10,4) npoints (1,128) -} -EOF - ./arma-$solver -c $inputfile 2>&1 | tee $solver-$size.log -done -done -rm -f $inputfile diff --git a/data/run-01/high_amplitude_realtime-0128.log b/data/run-01/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.BsswSbB5uX +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 958916us +prfl create_vector_field 22us +prfl dev_to_host_copy = 26311us +prfl fft = 8867us +prfl second_function = 45010us +prfl window_function = 183954us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-01/high_amplitude_realtime-0256.log b/data/run-01/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.BsswSbB5uX +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 1000724us +prfl create_vector_field 23us +prfl dev_to_host_copy = 54577us +prfl fft = 19152us +prfl second_function = 104108us +prfl window_function = 184745us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-01/high_amplitude_realtime-0512.log b/data/run-01/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.BsswSbB5uX +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 906712us +prfl create_vector_field 20us +prfl dev_to_host_copy = 108087us +prfl fft = 39537us +prfl second_function = 166292us +prfl window_function = 183322us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-01/high_amplitude_realtime-1024.log b/data/run-01/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.BsswSbB5uX +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1125883us +prfl create_vector_field 23us +prfl dev_to_host_copy = 210073us +prfl fft = 81523us +prfl second_function = 411099us +prfl window_function = 182989us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-01/linear-0128.log b/data/run-01/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.BsswSbB5uX +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 124127us +prfl second_function = 1332us +prfl window_function = 1639221us diff --git a/data/run-01/linear-0256.log b/data/run-01/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.BsswSbB5uX +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239684us +prfl second_function = 2593us +prfl window_function = 3264777us diff --git a/data/run-01/linear-0512.log b/data/run-01/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.BsswSbB5uX +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 474463us +prfl second_function = 6965us +prfl window_function = 6521411us diff --git a/data/run-01/linear-1024.log b/data/run-01/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.BsswSbB5uX +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1047772us +prfl second_function = 14138us +prfl window_function = 14202924us diff --git a/data/run-02/high_amplitude_realtime-0128.log b/data/run-02/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.d7L6r3OYaQ +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 1166479us +prfl create_vector_field 22us +prfl dev_to_host_copy = 27689us +prfl fft = 8700us +prfl second_function = 49869us +prfl window_function = 187262us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-02/high_amplitude_realtime-0256.log b/data/run-02/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.d7L6r3OYaQ +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 1008534us +prfl create_vector_field 24us +prfl dev_to_host_copy = 54270us +prfl fft = 18974us +prfl second_function = 95068us +prfl window_function = 185864us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-02/high_amplitude_realtime-0512.log b/data/run-02/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.d7L6r3OYaQ +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 949139us +prfl create_vector_field 23us +prfl dev_to_host_copy = 123806us +prfl fft = 39868us +prfl second_function = 164250us +prfl window_function = 255012us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-02/high_amplitude_realtime-1024.log b/data/run-02/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.d7L6r3OYaQ +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1182097us +prfl create_vector_field 21us +prfl dev_to_host_copy = 221485us +prfl fft = 81544us +prfl second_function = 426406us +prfl window_function = 255702us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-02/linear-0128.log b/data/run-02/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.d7L6r3OYaQ +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123748us +prfl second_function = 1338us +prfl window_function = 1638204us diff --git a/data/run-02/linear-0256.log b/data/run-02/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.d7L6r3OYaQ +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239090us +prfl second_function = 2668us +prfl window_function = 3289663us diff --git a/data/run-02/linear-0512.log b/data/run-02/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.d7L6r3OYaQ +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 474192us +prfl second_function = 6203us +prfl window_function = 6527459us diff --git a/data/run-02/linear-1024.log b/data/run-02/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.d7L6r3OYaQ +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1074246us +prfl second_function = 14313us +prfl window_function = 14506855us diff --git a/data/run-03/high_amplitude_realtime-0128.log b/data/run-03/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.OcI8D4rqWa +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 995528us +prfl create_vector_field 21us +prfl dev_to_host_copy = 29668us +prfl fft = 9124us +prfl second_function = 41220us +prfl window_function = 183052us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-03/high_amplitude_realtime-0256.log b/data/run-03/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.OcI8D4rqWa +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 803250us +prfl create_vector_field 20us +prfl dev_to_host_copy = 54253us +prfl fft = 18958us +prfl second_function = 84440us +prfl window_function = 185085us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-03/high_amplitude_realtime-0512.log b/data/run-03/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.OcI8D4rqWa +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 906222us +prfl create_vector_field 23us +prfl dev_to_host_copy = 111942us +prfl fft = 39720us +prfl second_function = 166568us +prfl window_function = 182075us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-03/high_amplitude_realtime-1024.log b/data/run-03/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.OcI8D4rqWa +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1129602us +prfl create_vector_field 21us +prfl dev_to_host_copy = 215750us +prfl fft = 81053us +prfl second_function = 415255us +prfl window_function = 182702us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-03/linear-0128.log b/data/run-03/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.OcI8D4rqWa +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123834us +prfl second_function = 1328us +prfl window_function = 1640243us diff --git a/data/run-03/linear-0256.log b/data/run-03/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.OcI8D4rqWa +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 240696us +prfl second_function = 3614us +prfl window_function = 3265501us diff --git a/data/run-03/linear-0512.log b/data/run-03/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.OcI8D4rqWa +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 474830us +prfl second_function = 7182us +prfl window_function = 6549456us diff --git a/data/run-03/linear-1024.log b/data/run-03/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.OcI8D4rqWa +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1154397us +prfl second_function = 14264us +prfl window_function = 15493166us diff --git a/data/run-04/high_amplitude_realtime-0128.log b/data/run-04/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lN5mL86KNo +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 885419us +prfl create_vector_field 21us +prfl dev_to_host_copy = 25270us +prfl fft = 8870us +prfl second_function = 43652us +prfl window_function = 182983us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-04/high_amplitude_realtime-0256.log b/data/run-04/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lN5mL86KNo +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 994780us +prfl create_vector_field 21us +prfl dev_to_host_copy = 55378us +prfl fft = 18711us +prfl second_function = 96702us +prfl window_function = 184552us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-04/high_amplitude_realtime-0512.log b/data/run-04/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lN5mL86KNo +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 916383us +prfl create_vector_field 23us +prfl dev_to_host_copy = 112495us +prfl fft = 39529us +prfl second_function = 162804us +prfl window_function = 183164us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-04/high_amplitude_realtime-1024.log b/data/run-04/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lN5mL86KNo +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1003107us +prfl create_vector_field 23us +prfl dev_to_host_copy = 216182us +prfl fft = 81911us +prfl second_function = 411292us +prfl window_function = 183780us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-04/linear-0128.log b/data/run-04/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lN5mL86KNo +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 124474us +prfl second_function = 1334us +prfl window_function = 1695188us diff --git a/data/run-04/linear-0256.log b/data/run-04/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lN5mL86KNo +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 240857us +prfl second_function = 2611us +prfl window_function = 3265219us diff --git a/data/run-04/linear-0512.log b/data/run-04/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lN5mL86KNo +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 473971us +prfl second_function = 7175us +prfl window_function = 6549544us diff --git a/data/run-04/linear-1024.log b/data/run-04/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lN5mL86KNo +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1065533us +prfl second_function = 10024us +prfl window_function = 14511873us diff --git a/data/run-05/high_amplitude_realtime-0128.log b/data/run-05/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.Rh39h2qKYh +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 892032us +prfl create_vector_field 25us +prfl dev_to_host_copy = 28300us +prfl fft = 8879us +prfl second_function = 45246us +prfl window_function = 184239us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-05/high_amplitude_realtime-0256.log b/data/run-05/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.Rh39h2qKYh +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 813123us +prfl create_vector_field 23us +prfl dev_to_host_copy = 54952us +prfl fft = 19016us +prfl second_function = 92105us +prfl window_function = 192743us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-05/high_amplitude_realtime-0512.log b/data/run-05/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.Rh39h2qKYh +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 955837us +prfl create_vector_field 24us +prfl dev_to_host_copy = 113468us +prfl fft = 39942us +prfl second_function = 200771us +prfl window_function = 185157us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-05/high_amplitude_realtime-1024.log b/data/run-05/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.Rh39h2qKYh +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 923333us +prfl create_vector_field 22us +prfl dev_to_host_copy = 212986us +prfl fft = 80943us +prfl second_function = 326251us +prfl window_function = 182597us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-05/linear-0128.log b/data/run-05/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.Rh39h2qKYh +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123704us +prfl second_function = 1342us +prfl window_function = 1641176us diff --git a/data/run-05/linear-0256.log b/data/run-05/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.Rh39h2qKYh +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239487us +prfl second_function = 2627us +prfl window_function = 3258401us diff --git a/data/run-05/linear-0512.log b/data/run-05/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.Rh39h2qKYh +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 474957us +prfl second_function = 5107us +prfl window_function = 6531316us diff --git a/data/run-05/linear-1024.log b/data/run-05/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.Rh39h2qKYh +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1130321us +prfl second_function = 14254us +prfl window_function = 15241897us diff --git a/data/run-06/high_amplitude_realtime-0128.log b/data/run-06/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.nWORujupjw +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 964331us +prfl create_vector_field 23us +prfl dev_to_host_copy = 25656us +prfl fft = 8871us +prfl second_function = 45006us +prfl window_function = 184003us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-06/high_amplitude_realtime-0256.log b/data/run-06/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.nWORujupjw +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 800685us +prfl create_vector_field 22us +prfl dev_to_host_copy = 55019us +prfl fft = 19218us +prfl second_function = 85155us +prfl window_function = 188543us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-06/high_amplitude_realtime-0512.log b/data/run-06/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.nWORujupjw +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 860778us +prfl create_vector_field 21us +prfl dev_to_host_copy = 112375us +prfl fft = 39650us +prfl second_function = 164658us +prfl window_function = 184988us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-06/high_amplitude_realtime-1024.log b/data/run-06/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.nWORujupjw +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1013354us +prfl create_vector_field 23us +prfl dev_to_host_copy = 216432us +prfl fft = 81067us +prfl second_function = 331265us +prfl window_function = 183023us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-06/linear-0128.log b/data/run-06/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.nWORujupjw +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123870us +prfl second_function = 1315us +prfl window_function = 1642858us diff --git a/data/run-06/linear-0256.log b/data/run-06/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.nWORujupjw +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 237958us +prfl second_function = 2603us +prfl window_function = 3253563us diff --git a/data/run-06/linear-0512.log b/data/run-06/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.nWORujupjw +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 488005us +prfl second_function = 7109us +prfl window_function = 6624526us diff --git a/data/run-06/linear-1024.log b/data/run-06/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.nWORujupjw +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1190873us +prfl second_function = 10066us +prfl window_function = 16070800us diff --git a/data/run-07/high_amplitude_realtime-0128.log b/data/run-07/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.rZq8vEagBx +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 963889us +prfl create_vector_field 25us +prfl dev_to_host_copy = 26484us +prfl fft = 8927us +prfl second_function = 48032us +prfl window_function = 183146us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-07/high_amplitude_realtime-0256.log b/data/run-07/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.rZq8vEagBx +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 823496us +prfl create_vector_field 22us +prfl dev_to_host_copy = 53734us +prfl fft = 19149us +prfl second_function = 102341us +prfl window_function = 187600us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-07/high_amplitude_realtime-0512.log b/data/run-07/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.rZq8vEagBx +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 949762us +prfl create_vector_field 21us +prfl dev_to_host_copy = 110424us +prfl fft = 39406us +prfl second_function = 163175us +prfl window_function = 182856us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-07/high_amplitude_realtime-1024.log b/data/run-07/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.rZq8vEagBx +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 924590us +prfl create_vector_field 24us +prfl dev_to_host_copy = 217081us +prfl fft = 82096us +prfl second_function = 331118us +prfl window_function = 182528us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-07/linear-0128.log b/data/run-07/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.rZq8vEagBx +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123219us +prfl second_function = 1344us +prfl window_function = 1633367us diff --git a/data/run-07/linear-0256.log b/data/run-07/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.rZq8vEagBx +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239360us +prfl second_function = 2579us +prfl window_function = 3256616us diff --git a/data/run-07/linear-0512.log b/data/run-07/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.rZq8vEagBx +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 477199us +prfl second_function = 5136us +prfl window_function = 6560502us diff --git a/data/run-07/linear-1024.log b/data/run-07/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.rZq8vEagBx +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1191580us +prfl second_function = 10102us +prfl window_function = 16195098us diff --git a/data/run-08/high_amplitude_realtime-0128.log b/data/run-08/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.C3oxrneNJ0 +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 1069136us +prfl create_vector_field 25us +prfl dev_to_host_copy = 30439us +prfl fft = 8921us +prfl second_function = 53994us +prfl window_function = 256113us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-08/high_amplitude_realtime-0256.log b/data/run-08/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.C3oxrneNJ0 +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 748775us +prfl create_vector_field 23us +prfl dev_to_host_copy = 52337us +prfl fft = 19073us +prfl second_function = 86147us +prfl window_function = 184668us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-08/high_amplitude_realtime-0512.log b/data/run-08/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.C3oxrneNJ0 +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 1056548us +prfl create_vector_field 21us +prfl dev_to_host_copy = 112135us +prfl fft = 39768us +prfl second_function = 203910us +prfl window_function = 182459us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-08/high_amplitude_realtime-1024.log b/data/run-08/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.C3oxrneNJ0 +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 1247955us +prfl create_vector_field 21us +prfl dev_to_host_copy = 236403us +prfl fft = 81174us +prfl second_function = 391052us +prfl window_function = 182365us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-08/linear-0128.log b/data/run-08/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.C3oxrneNJ0 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123715us +prfl second_function = 1858us +prfl window_function = 1647289us diff --git a/data/run-08/linear-0256.log b/data/run-08/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.C3oxrneNJ0 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239895us +prfl second_function = 2607us +prfl window_function = 3288491us diff --git a/data/run-08/linear-0512.log b/data/run-08/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.C3oxrneNJ0 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 473284us +prfl second_function = 5091us +prfl window_function = 6513362us diff --git a/data/run-08/linear-1024.log b/data/run-08/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.C3oxrneNJ0 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1022008us +prfl second_function = 11230us +prfl window_function = 14059711us diff --git a/data/run-09/high_amplitude_realtime-0128.log b/data/run-09/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.F1C8voxdbu +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 39221us +prfl create_vector_field 24us +prfl dev_to_host_copy = 26569us +prfl fft = 8771us +prfl second_function = 46009us +prfl window_function = 226425us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-09/high_amplitude_realtime-0256.log b/data/run-09/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.F1C8voxdbu +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 36488us +prfl create_vector_field 24us +prfl dev_to_host_copy = 53391us +prfl fft = 18906us +prfl second_function = 84780us +prfl window_function = 189881us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-09/high_amplitude_realtime-0512.log b/data/run-09/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.F1C8voxdbu +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 39913us +prfl create_vector_field 23us +prfl dev_to_host_copy = 113338us +prfl fft = 39475us +prfl second_function = 178428us +prfl window_function = 188770us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-09/high_amplitude_realtime-1024.log b/data/run-09/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.F1C8voxdbu +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 44724us +prfl create_vector_field 20us +prfl dev_to_host_copy = 219039us +prfl fft = 81029us +prfl second_function = 329347us +prfl window_function = 188090us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-09/linear-0128.log b/data/run-09/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.F1C8voxdbu +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123537us +prfl second_function = 1901us +prfl window_function = 1648622us diff --git a/data/run-09/linear-0256.log b/data/run-09/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.F1C8voxdbu +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239440us +prfl second_function = 2579us +prfl window_function = 3256203us diff --git a/data/run-09/linear-0512.log b/data/run-09/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.F1C8voxdbu +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 473981us +prfl second_function = 5127us +prfl window_function = 6549389us diff --git a/data/run-09/linear-1024.log b/data/run-09/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.F1C8voxdbu +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1098564us +prfl second_function = 11721us +prfl window_function = 14948201us diff --git a/data/run-10/high_amplitude_realtime-0128.log b/data/run-10/high_amplitude_realtime-0128.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lV4vWyjNcb +_vbo_phi=1 +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 5120 +oDist = 5120 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 128 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 0.000195313 +tr = 1 +loc = 1 +tmpbufsize = 10485760 +prfl setup 37784us +prfl create_vector_field 24us +prfl dev_to_host_copy = 25327us +prfl fft = 8892us +prfl second_function = 54522us +prfl window_function = 263047us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-10/high_amplitude_realtime-0256.log b/data/run-10/high_amplitude_realtime-0256.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lV4vWyjNcb +_vbo_phi=1 +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 10240 +oDist = 10240 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 256 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 9.76563e-05 +tr = 1 +loc = 1 +tmpbufsize = 20971520 +prfl setup 35175us +prfl create_vector_field 22us +prfl dev_to_host_copy = 54533us +prfl fft = 19029us +prfl second_function = 82210us +prfl window_function = 189100us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-10/high_amplitude_realtime-0512.log b/data/run-10/high_amplitude_realtime-0512.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lV4vWyjNcb +_vbo_phi=1 +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 20480 +oDist = 20480 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 512 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 4.88281e-05 +tr = 1 +loc = 1 +tmpbufsize = 41943040 +prfl setup 38170us +prfl create_vector_field 20us +prfl dev_to_host_copy = 111112us +prfl fft = 38959us +prfl second_function = 170188us +prfl window_function = 189890us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-10/high_amplitude_realtime-1024.log b/data/run-10/high_amplitude_realtime-1024.log @@ -0,0 +1,42 @@ +OpenCL platform = AMD Accelerated Parallel Processing +OpenCL platform vendor = Advanced Micro Devices, Inc. +OpenCL device type = GPU +Input file = /run/user/1000/tmp.lV4vWyjNcb +_vbo_phi=1 +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity30High_amplitude_realtime_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +iLayout = 1 +oLayout = 1 +batchSize = 128 +dim = 2 +dimSize = 2 +iDist = 40960 +oDist = 40960 +inStrides = (0,1) +[ 40 1 ] + +outStrides = (0,1) +[ 40 1 ] + +lengths = (0,1) +[ 1024 40 ] + +precision = 2 +scale_forward = 1 +scale_backward = 2.44141e-05 +tr = 1 +loc = 1 +tmpbufsize = 83886080 +prfl setup 44289us +prfl create_vector_field 23us +prfl dev_to_host_copy = 213355us +prfl fft = 80205us +prfl second_function = 409910us +prfl window_function = 187705us +Warning: Program terminating, but clFFT resources not freed. +Please consider explicitly calling clfftTeardown( ). diff --git a/data/run-10/linear-0128.log b/data/run-10/linear-0128.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lV4vWyjNcb +Output grid size = (200,128,40) +Output grid patch size = (1,0.0629921,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 123990us +prfl second_function = 1323us +prfl window_function = 1628622us diff --git a/data/run-10/linear-0256.log b/data/run-10/linear-0256.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lV4vWyjNcb +Output grid size = (200,256,40) +Output grid patch size = (1,0.0313725,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 239618us +prfl second_function = 2619us +prfl window_function = 3258278us diff --git a/data/run-10/linear-0512.log b/data/run-10/linear-0512.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lV4vWyjNcb +Output grid size = (200,512,40) +Output grid patch size = (1,0.0156556,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 473299us +prfl second_function = 7163us +prfl window_function = 6549919us diff --git a/data/run-10/linear-1024.log b/data/run-10/linear-1024.log @@ -0,0 +1,12 @@ +Input file = /run/user/1000/tmp.lV4vWyjNcb +Output grid size = (200,1024,40) +Output grid patch size = (1,0.00782014,0.205128) +Model = plain_wave +Verification scheme = none +Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] +Velocity potential solver name = N4arma8velocity13Linear_solverIdEE +Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) +prfl dev_to_host_copy = 0us +prfl fft = 1053032us +prfl second_function = 14256us +prfl window_function = 14177107us diff --git a/run-01/high_amplitude_realtime-1024.log b/run-01/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-01/high_amplitude_realtime-128.log b/run-01/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-01/high_amplitude_realtime-256.log b/run-01/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-01/high_amplitude_realtime-512.log b/run-01/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-01/linear-1024.log b/run-01/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.BsswSbB5uX -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1047772us -prfl second_function = 14138us -prfl window_function = 14202924us diff --git a/run-01/linear-128.log b/run-01/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.BsswSbB5uX -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 124127us -prfl second_function = 1332us -prfl window_function = 1639221us diff --git a/run-01/linear-256.log b/run-01/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.BsswSbB5uX -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239684us -prfl second_function = 2593us -prfl window_function = 3264777us diff --git a/run-01/linear-512.log b/run-01/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.BsswSbB5uX -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 474463us -prfl second_function = 6965us -prfl window_function = 6521411us diff --git a/run-02/high_amplitude_realtime-1024.log b/run-02/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-02/high_amplitude_realtime-128.log b/run-02/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-02/high_amplitude_realtime-256.log b/run-02/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-02/high_amplitude_realtime-512.log b/run-02/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-02/linear-1024.log b/run-02/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.d7L6r3OYaQ -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1074246us -prfl second_function = 14313us -prfl window_function = 14506855us diff --git a/run-02/linear-128.log b/run-02/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.d7L6r3OYaQ -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123748us -prfl second_function = 1338us -prfl window_function = 1638204us diff --git a/run-02/linear-256.log b/run-02/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.d7L6r3OYaQ -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239090us -prfl second_function = 2668us -prfl window_function = 3289663us diff --git a/run-02/linear-512.log b/run-02/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.d7L6r3OYaQ -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 474192us -prfl second_function = 6203us -prfl window_function = 6527459us diff --git a/run-03/high_amplitude_realtime-1024.log b/run-03/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-03/high_amplitude_realtime-128.log b/run-03/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-03/high_amplitude_realtime-256.log b/run-03/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-03/high_amplitude_realtime-512.log b/run-03/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-03/linear-1024.log b/run-03/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.OcI8D4rqWa -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1154397us -prfl second_function = 14264us -prfl window_function = 15493166us diff --git a/run-03/linear-128.log b/run-03/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.OcI8D4rqWa -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123834us -prfl second_function = 1328us -prfl window_function = 1640243us diff --git a/run-03/linear-256.log b/run-03/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.OcI8D4rqWa -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 240696us -prfl second_function = 3614us -prfl window_function = 3265501us diff --git a/run-03/linear-512.log b/run-03/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.OcI8D4rqWa -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 474830us -prfl second_function = 7182us -prfl window_function = 6549456us diff --git a/run-04/high_amplitude_realtime-1024.log b/run-04/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-04/high_amplitude_realtime-128.log b/run-04/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-04/high_amplitude_realtime-256.log b/run-04/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-04/high_amplitude_realtime-512.log b/run-04/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-04/linear-1024.log b/run-04/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lN5mL86KNo -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1065533us -prfl second_function = 10024us -prfl window_function = 14511873us diff --git a/run-04/linear-128.log b/run-04/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lN5mL86KNo -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 124474us -prfl second_function = 1334us -prfl window_function = 1695188us diff --git a/run-04/linear-256.log b/run-04/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lN5mL86KNo -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 240857us -prfl second_function = 2611us -prfl window_function = 3265219us diff --git a/run-04/linear-512.log b/run-04/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lN5mL86KNo -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 473971us -prfl second_function = 7175us -prfl window_function = 6549544us diff --git a/run-05/high_amplitude_realtime-1024.log b/run-05/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-05/high_amplitude_realtime-128.log b/run-05/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-05/high_amplitude_realtime-256.log b/run-05/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-05/high_amplitude_realtime-512.log b/run-05/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-05/linear-1024.log b/run-05/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.Rh39h2qKYh -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1130321us -prfl second_function = 14254us -prfl window_function = 15241897us diff --git a/run-05/linear-128.log b/run-05/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.Rh39h2qKYh -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123704us -prfl second_function = 1342us -prfl window_function = 1641176us diff --git a/run-05/linear-256.log b/run-05/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.Rh39h2qKYh -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239487us -prfl second_function = 2627us -prfl window_function = 3258401us diff --git a/run-05/linear-512.log b/run-05/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.Rh39h2qKYh -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 474957us -prfl second_function = 5107us -prfl window_function = 6531316us diff --git a/run-06/high_amplitude_realtime-1024.log b/run-06/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-06/high_amplitude_realtime-128.log b/run-06/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-06/high_amplitude_realtime-256.log b/run-06/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-06/high_amplitude_realtime-512.log b/run-06/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-06/linear-1024.log b/run-06/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.nWORujupjw -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1190873us -prfl second_function = 10066us -prfl window_function = 16070800us diff --git a/run-06/linear-128.log b/run-06/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.nWORujupjw -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123870us -prfl second_function = 1315us -prfl window_function = 1642858us diff --git a/run-06/linear-256.log b/run-06/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.nWORujupjw -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 237958us -prfl second_function = 2603us -prfl window_function = 3253563us diff --git a/run-06/linear-512.log b/run-06/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.nWORujupjw -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 488005us -prfl second_function = 7109us -prfl window_function = 6624526us diff --git a/run-07/high_amplitude_realtime-1024.log b/run-07/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-07/high_amplitude_realtime-128.log b/run-07/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-07/high_amplitude_realtime-256.log b/run-07/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-07/high_amplitude_realtime-512.log b/run-07/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-07/linear-1024.log b/run-07/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.rZq8vEagBx -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1191580us -prfl second_function = 10102us -prfl window_function = 16195098us diff --git a/run-07/linear-128.log b/run-07/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.rZq8vEagBx -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123219us -prfl second_function = 1344us -prfl window_function = 1633367us diff --git a/run-07/linear-256.log b/run-07/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.rZq8vEagBx -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239360us -prfl second_function = 2579us -prfl window_function = 3256616us diff --git a/run-07/linear-512.log b/run-07/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.rZq8vEagBx -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 477199us -prfl second_function = 5136us -prfl window_function = 6560502us diff --git a/run-08/high_amplitude_realtime-1024.log b/run-08/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-08/high_amplitude_realtime-128.log b/run-08/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-08/high_amplitude_realtime-256.log b/run-08/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-08/high_amplitude_realtime-512.log b/run-08/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-08/linear-1024.log b/run-08/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.C3oxrneNJ0 -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1022008us -prfl second_function = 11230us -prfl window_function = 14059711us diff --git a/run-08/linear-128.log b/run-08/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.C3oxrneNJ0 -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123715us -prfl second_function = 1858us -prfl window_function = 1647289us diff --git a/run-08/linear-256.log b/run-08/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.C3oxrneNJ0 -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239895us -prfl second_function = 2607us -prfl window_function = 3288491us diff --git a/run-08/linear-512.log b/run-08/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.C3oxrneNJ0 -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 473284us -prfl second_function = 5091us -prfl window_function = 6513362us diff --git a/run-09/high_amplitude_realtime-1024.log b/run-09/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-09/high_amplitude_realtime-128.log b/run-09/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-09/high_amplitude_realtime-256.log b/run-09/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-09/high_amplitude_realtime-512.log b/run-09/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-09/linear-1024.log b/run-09/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.F1C8voxdbu -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1098564us -prfl second_function = 11721us -prfl window_function = 14948201us diff --git a/run-09/linear-128.log b/run-09/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.F1C8voxdbu -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123537us -prfl second_function = 1901us -prfl window_function = 1648622us diff --git a/run-09/linear-256.log b/run-09/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.F1C8voxdbu -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239440us -prfl second_function = 2579us -prfl window_function = 3256203us diff --git a/run-09/linear-512.log b/run-09/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.F1C8voxdbu -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 473981us -prfl second_function = 5127us -prfl window_function = 6549389us diff --git a/run-10/high_amplitude_realtime-1024.log b/run-10/high_amplitude_realtime-1024.log Binary files differ. diff --git a/run-10/high_amplitude_realtime-128.log b/run-10/high_amplitude_realtime-128.log Binary files differ. diff --git a/run-10/high_amplitude_realtime-256.log b/run-10/high_amplitude_realtime-256.log Binary files differ. diff --git a/run-10/high_amplitude_realtime-512.log b/run-10/high_amplitude_realtime-512.log Binary files differ. diff --git a/run-10/linear-1024.log b/run-10/linear-1024.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lV4vWyjNcb -Output grid size = (200,1024,40) -Output grid patch size = (1,0.00782014,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 1053032us -prfl second_function = 14256us -prfl window_function = 14177107us diff --git a/run-10/linear-128.log b/run-10/linear-128.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lV4vWyjNcb -Output grid size = (200,128,40) -Output grid patch size = (1,0.0629921,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 123990us -prfl second_function = 1323us -prfl window_function = 1628622us diff --git a/run-10/linear-256.log b/run-10/linear-256.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lV4vWyjNcb -Output grid size = (200,256,40) -Output grid patch size = (1,0.0313725,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 239618us -prfl second_function = 2619us -prfl window_function = 3258278us diff --git a/run-10/linear-512.log b/run-10/linear-512.log @@ -1,12 +0,0 @@ -Input file = /run/user/1000/tmp.lV4vWyjNcb -Output grid size = (200,512,40) -Output grid patch size = (1,0.0156556,0.205128) -Model = plain_wave -Verification scheme = none -Plain wave model = func=cos,amplitudes=[4],wavenumbers=[0.125],phases=[0],velocities=[0.5] -Velocity potential solver name = N4arma8velocity13Linear_solverIdEE -Velocity potential solver = wnmax=from (0,0) to (0,0.25) npoints (2,2),depth=12,domain=from (10,-12) to (10,4) npoints (1,128) -prfl dev_to_host_copy = 0us -prfl fft = 473299us -prfl second_function = 7163us -prfl window_function = 6549919us diff --git a/sh/benchmark-cpu-gpu b/sh/benchmark-cpu-gpu @@ -0,0 +1,36 @@ +#!/bin/sh + +inputfile=$(mktemp) +for solver in linear high_amplitude_realtime +do +for size in 128 256 512 1024 +do + echo + echo "********************************************************************************" + echo " solver = $solver" + echo " size = $size" + echo "********************************************************************************" + echo + cat >$inputfile << EOF +out_grid = (200,$size,40) : (199,8,8) + +model = plain_wave +plain_wave = { + func = cos + amplitudes = [4] + wavenumbers = [0.125] + phases = [0] + velocities = [0.5] +} +verification = none + +velocity_potential_solver = $solver { + wnmax = from (0,0) to (0,0.25) npoints (2,2) + depth = 12 + domain = from (10,-12) to (10,4) npoints (1,128) +} +EOF + ./arma-$solver -c $inputfile 2>&1 | tee $solver-$size.log +done +done +rm -f $inputfile diff --git a/sh/remove-nonprintable b/sh/remove-nonprintable @@ -0,0 +1,6 @@ +#!/bin/sh + +set -e +tmp=$(mktemp) +tr -cd '\11\12\15\40-\176' < $1 >$tmp +mv $tmp $1