diff --git a/.gitignore b/.gitignore index 3c42450..a8120f4 100644 --- a/.gitignore +++ b/.gitignore @@ -9,10 +9,12 @@ *.cmake *.pyc *.asv +*.DS_Store bin/ cubin/ /misc/ .vscode/ +.idea/ temp* *.pdf src/*/trslt/*.json diff --git a/results/Affinity/AffinityRun.py b/results/Affinity/AffinityRun.py index 4b23308..604233b 100644 --- a/results/Affinity/AffinityRun.py +++ b/results/Affinity/AffinityRun.py @@ -1,14 +1,19 @@ +''' + Get Loads of Results from Affinity Run +''' + import os import os.path as op import sys import pandas as pd import numpy as np +import statsmodels.api as sm -thispath = op.abspath(op.dirname(__file__)) -resultpath = op.dirname(thispath) +affpath = op.abspath(op.dirname(__file__)) +resultpath = op.dirname(affpath) toppath = op.dirname(resultpath) pypath = op.join(toppath, "runtools") -datapath = op.join(thispath, "rslts") +datapath = op.join(affpath, "rslts") sys.path.append(pypath) @@ -16,33 +21,273 @@ import timing_analysis as ta import timing_help as th -timeFrame = readPath(datapath) -coll = dict() -annodict = {} -pltpth = op.join(op.dirname(datapath), "AffinityPlots") +import matplotlib.colors as mc + +#SET THIS TO SAVE OR SHOW FIGS +savFig=False + +hxMap=mc.ListedColormap(th.hxColors) + +kodiakX=[int(k) for k in [5e6, 2e7, 4e7, 6e7]] + +nTime = lambda df, x, y, z: df[x]*df[y]/df[z] -#idx = pd.MultiIndex(levels=[[],[]], labels=[[],[]], names=["Types", "Metric"]) -bestCollect = pd.DataFrame(columns=list(timeFrame.keys())) -for kType, iFrame in timeFrame.items(): - thisdf = ta.RawInterp(iFrame, kType) +nPerf = "normTime" + +ylbl = "time per timestep (us)" + +ffs=np.format_float_scientific + +def normalizeGroups(dfi): + dft=dfi.copy() + dft["grp"] = None + for kx in kodiakX: + dft.loc[(dfi["nX"] < kx+1e7) & (dfi["nX"] > kx-1e7), "grp"] = kx - keepdf = thisdf.interpit() - dfT, figt, axT = ta.contourRaw(keepdf, kType, getfig=True) - mnT = ta.plotmins(dfT, axT) - figt = th.formatSubplot(figt) + dft[nPerf] = nTime(dft, "time", "grp", "nX") + return dft + +def summaryIndiv(dfi): + if nPerf not in dfi.columns: + dfi = normalizeGroups(dfi) + + dfout=pd.DataFrame(columns=["NoGpu","Gpu"], index=dfi["grp"].unique()) - keepEfficiency = thisdf.efficient(keepdf) - _, fige, _ = ta.contourRaw(keepEfficiency, kType, vals="efficiency", getfig=True) - fige = th.formatSubplot(fige) + for k, i in dfi.groupby("grp"): + dfout.loc[k, "NoGpu"] = i.loc[i["gpuA"] < 2, nPerf].min() + dfout.loc[k, "Gpu"] = i.loc[i["gpuA"] > 2, nPerf].min() - bestCollect[kType] = mnT + dfout["Speedup"] = dfout["NoGpu"]/dfout["Gpu"] + return dfout + +def summarizeGPU(ddf, fcollect): + dflist=[] + for kdf, dfi in ddf.items(): + dfs = fcollect(dfi) + dfs.columns = pd.MultiIndex.from_product([[kdf], dfs.columns]) + dflist.append(dfs) + + dfout = pd.concat(dflist, axis=1) + return dfout + +def headToCol(dfa): + nms=["idx", "case"] + d=dfa.stack(0) + d.index.names=nms + di=d.reset_index(level=nms[1]) + return di + +def getTpbCount(dfa, typ): + cases= ["gpuA", "grp", "case"] + dff = headToCol(dfa) + dff.drop(["nX", "time"], axis=1, inplace=True) + dff.reset_index(drop=True,inplace=True) + kidx = dff.groupby(cases)['normTime'].idxmin() + dffin=dff.loc[kidx] + return dffin.groupby(typ)["tpb"].value_counts().to_frame().unstack(0)["tpb"].fillna(0).astype(int) + + +def squaredf(df, cols, deg=2): + dfc=df.copy() + for c in cols: + for k in range(2,deg+1): + nc=c+str(k) + dfc[nc]=df[c]**k + + return dfc + +def summarizeTPBAFF(ddf, deg=1, inter=False, xcoli=["tpb", "gpuA"]): + idx = pd.MultiIndex.from_product([list(ddf.keys()), kodiakX]) - plotname = op.join(pltpth, "RawContour" + kType + "Time" + ".pdf") - figt.savefig(plotname, bbox_inches='tight') - plotname = op.join(pltpth, "RawContour" + kType + "Efficiency" + ".pdf") - fige.savefig(plotname, bbox_inches='tight') + if inter: xcoli=xcoli + ["tpb-gpuA"] + + xcol=xcoli+[x+str(k) for x in xcoli for k in range(2,deg+1)] - # plt.show() + dfmod = pd.DataFrame(index=idx, columns=xcol + ["const", "rsq", "rsqa"], dtype=float) + modcoll={} + for kdf, dfi in ddf.items(): + if inter: + dfi["tpb-gpuA"] = dfi["tpb"]*dfi["gpuA"] + for kx, dx in dfi.groupby("grp"): + + X = squaredf(dx[xcoli], xcoli, deg) + + X = sm.add_constant(X) + mod=sm.OLS(dx[nPerf], X) + res=mod.fit() + modcoll[(kdf, kx)] = res + rser=pd.Series({"rsq": res.rsquared, "rsqa": res.rsquared_adj}) + dfmod.loc[kdf,kx] = res.params.append(rser) + return dfmod, modcoll + +def pmods(mods, f=print): + pr=True + kold=list(mods.keys())[0][0] + for k, m in mods.items(): + if pr: f("## " + k[0] + "\n\n") + pr=False + f("#### " + str(k[1]) + "\n\n") + f(str(m.summary()) + "\n\n") + if not k[0] == kold: + pr=True + kold=k[0] + +def plotmdl(df, ti, axi, yf, nf): + xv = np.arange(0,nf) + yfx=lambda df: yf(df, xv) + yv = df.apply(yfx, axis=1).apply(pd.Series).T + + yv["GPU Affinity"] = xv + yv.set_index("GPU Affinity", inplace=True) + yv.plot(ax=axi, title=ti, markersize=0, cmap=hxMap) + if axi.colNum == 0: + axi.set_ylabel(ylbl) + if axi.rowNum == 0: + axi.set_xlabel("") + + axi.set_xlim([-10,210]) + handles, labels = axi.get_legend_handles_labels() + labels=[ffs(int(k), trim="-", exp_digits=1) for k in labels] + axi.legend(handles, labels, title="Grid Size") + return yv + + +if __name__ == "__main__": + + pltpth = op.join(affpath, "AffinityPlots") + dpath = datapath + if len(sys.argv) == 2: + dpath = op.join(datapath, sys.argv[1]) + pltpth = op.join(op.join(affpath, "AffinityPlots"), sys.argv[1]) + + os.makedirs(pltpth, exist_ok=True) + timeFrame = readPath(dpath) + coll = dict() + annodict = {} + + bestCollect = pd.DataFrame(columns=list(timeFrame.keys())) + for kType, iFrame in timeFrame.items(): + thisdf = ta.RawInterp(iFrame, kType) + + keepdf = thisdf.interpit() + figt, mnT = ta.contourRaw(keepdf, kType, getfig=True) + + keepEfficiency = thisdf.efficient(keepdf) + fige, _ = ta.contourRaw(keepEfficiency, kType, vals="efficiency", getfig=True, minmax="max") + + bestCollect[kType] = mnT + fige.suptitle(kType+" Efficiency") + figt.suptitle(kType+" Timing") + plotname = op.join(pltpth, "RawContour" + kType + "Time" + ".pdf") + plotnameeff = op.join(pltpth, "RawContour" + kType + "Efficiency" + ".pdf") + if savFig: + figt.savefig(plotname, bbox_inches='tight') + fige.savefig(plotnameeff, bbox_inches='tight') + + coll[kType] = normalizeGroups(iFrame) + + + dfo = summarizeGPU(coll, summaryIndiv) + dfall = summarizeGPU(coll, lambda x: x.copy()) + dfm, mods = summarizeTPBAFF(coll, 2, xcoli=["gpuA"]) + ctpbCase = getTpbCount(dfall, "case") + ctpbSize = getTpbCount(dfall, "grp") + ctpbGpua = getTpbCount(dfall, "gpuA") + ctpbGpua.columns = [int(k) for k in ctpbGpua.columns] + + #Paths to writeout + sgpuPath = op.join(dpath, "summaryGPU.csv") + fullModels = op.join(dpath, "GpuAvsGridDimModels.md") + koplot = op.join(dpath, "GPUA_model.pdf") + kompplot = op.join(dpath, "MethodCompare.pdf") + speedout = op.join(dpath, "SweepSpeedup.csv") + scaleout = op.join(dpath, "SweepScale.csv") + Barout2 = op.join(dpath, "BestTpbs-nx_problem.pdf") + Barout1 = op.join(dpath, "BestTpbs-gpuA.pdf") + + doff = lambda dfun, x: x**2*dfun["gpuA2"] + x*dfun["gpuA"] + dfun["const"] + + f, ax = plt.subplots(2,2, figsize=(12,10)) + f.suptitle("Kodiak hSweep Affinity Test") + axx = ax.ravel() + for a, k in zip(axx, coll.keys()): + df=coll[k] + ncolor=len(df["grp"].unique()) + df.plot.scatter(x="gpuA", y=nPerf, c="grp", cmap=hxMap, + colorbar=False, legend=False, ax=a) + a.set_xlabel("") + a.set_ylabel("") + + for a, k in zip(axx, dfm.index.get_level_values(level=0).unique()): + plotmdl(dfm.loc[k], k, a, doff, 200) + + + sweeps=[f for f in dfo.columns.get_level_values(0).unique() if "Swept" in f] + dfc = pd.DataFrame() + dx="Gpu" + fgn, ax = plt.subplots(1,2, figsize=(12,5)) + axx=ax.ravel() + dfmove=[] + dft=[] + for s, a in zip(sweeps, axx): + c=s.replace("Swept","Classic") + dfc[s]=dfo[c][dx]/dfo[s][dx] + dfxx=dfo.loc[:,([s,c], dx)] + dfxx.columns=dfxx.columns.droplevel(1) + dfxx.index.names=["Grid Size"] + ty=s.replace("Swept","") + dfxx.columns = [d.replace(ty, "") for d in dfxx.columns] + dfxx.plot(ax=a, title=ty) + if a.colNum == 0: + a.set_ylabel(ylbl) + else: + a.get_legend().remove() + + acc=a.get_xlim() + fac=acc[0]*.5 + a.set_xlim([acc[0]-fac, acc[1]+fac]) + dfxx.reset_index(inplace=True) + changemat=dfxx.iloc[1:,].values/dfxx.iloc[:-1,].values + dfxlo=pd.DataFrame(data=changemat, columns=dfxx.columns) + dfxlo.columns=["Delta-GridSize"] + list(dfxlo.columns[1:].values) + dfxlo.set_index("Delta-GridSize", inplace=True) + dfmove.append(dfxlo) + dft.append(ty) + + dfscale=pd.concat(dfmove, axis=1, keys=dft) + fog, ax = plt.subplots(1, 2, sharey=True, figsize=(12,5)) + fga, ag = plt.subplots(1, 1, figsize=(6,5)) + fog.suptitle("Frequency of best tpb") + fga.suptitle("Frequency of best tpb by gpuA") + axx=ax.ravel() + topct = lambda df: df/df.sum()*100.0 + cs = topct(ctpbSize).T + cg = topct(ctpbGpua).T + cc = topct(ctpbCase).T + #And there is still some axis, saving, formatting to go. + ctpbSize.columns = [ffs(int(k), trim="-", exp_digits=1) for k in ctpbSize.columns] + for a, c in zip(axx, (ctpbCase, ctpbSize)): + c.plot.bar(ax=a) + a.legend().set_title("") + if not a.colNum: + a.set_ylabel("Frequency of Best Outcome (%)") + + ctpbGpua.plot.bar(ax=ag) + ag.set_ylabel("Frequency of Best Outcome (%)") + fog.savefig(Barout2, bbox_inches='tight') + fga.savefig(Barout1, bbox_inches='tight') + + if savFig: + dfscale.to_csv(scaleout) + dfc.to_csv(speedout) + dfout.to_csv(sgpuPath) + f.savefig(koplot, bbox_inches='tight') + fgn.savefig(kompplot, bbox_inches='tight') + with open(fullModels, "w") as fm: + pmods(mods, fm.write) + else: + plt.show() + diff --git a/results/Affinity/rslts/kodiak/GpuAvsGridDimModels.md b/results/Affinity/rslts/kodiak/GpuAvsGridDimModels.md new file mode 100644 index 0000000..0383602 --- /dev/null +++ b/results/Affinity/rslts/kodiak/GpuAvsGridDimModels.md @@ -0,0 +1,504 @@ +## EulerClassic + +#### 5000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.707 +Model: OLS Adj. R-squared: 0.698 +Method: Least Squares F-statistic: 76.12 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 1.56e-17 +Time: 16:15:29 Log-Likelihood: -582.18 +No. Observations: 66 AIC: 1170. +Df Residuals: 63 BIC: 1177. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 7952.9422 521.847 15.240 0.000 6910.114 8995.771 +gpuA -127.0059 12.140 -10.462 0.000 -151.265 -102.747 +gpuA2 0.4862 0.058 8.317 0.000 0.369 0.603 +============================================================================== +Omnibus: 1.245 Durbin-Watson: 2.148 +Prob(Omnibus): 0.537 Jarque-Bera (JB): 0.922 +Skew: 0.289 Prob(JB): 0.631 +Kurtosis: 3.025 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 20000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.751 +Model: OLS Adj. R-squared: 0.743 +Method: Least Squares F-statistic: 95.11 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 9.32e-20 +Time: 16:15:29 Log-Likelihood: -673.32 +No. Observations: 66 AIC: 1353. +Df Residuals: 63 BIC: 1359. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 3.488e+04 2076.056 16.802 0.000 3.07e+04 3.9e+04 +gpuA -561.9062 48.295 -11.635 0.000 -658.416 -465.396 +gpuA2 2.1429 0.233 9.214 0.000 1.678 2.608 +============================================================================== +Omnibus: 1.361 Durbin-Watson: 2.012 +Prob(Omnibus): 0.506 Jarque-Bera (JB): 1.395 +Skew: 0.314 Prob(JB): 0.498 +Kurtosis: 2.664 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 40000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.779 +Model: OLS Adj. R-squared: 0.772 +Method: Least Squares F-statistic: 110.9 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 2.30e-21 +Time: 16:15:29 Log-Likelihood: -714.64 +No. Observations: 66 AIC: 1435. +Df Residuals: 63 BIC: 1442. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 7.082e+04 3883.070 18.238 0.000 6.31e+04 7.86e+04 +gpuA -1114.4382 90.332 -12.337 0.000 -1294.952 -933.925 +gpuA2 4.1929 0.435 9.639 0.000 3.324 5.062 +============================================================================== +Omnibus: 1.255 Durbin-Watson: 2.114 +Prob(Omnibus): 0.534 Jarque-Bera (JB): 1.174 +Skew: 0.315 Prob(JB): 0.556 +Kurtosis: 2.825 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 60000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.775 +Model: OLS Adj. R-squared: 0.768 +Method: Least Squares F-statistic: 108.3 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 4.09e-21 +Time: 16:15:29 Log-Likelihood: -741.02 +No. Observations: 66 AIC: 1488. +Df Residuals: 63 BIC: 1495. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 1.051e+05 5790.674 18.158 0.000 9.36e+04 1.17e+05 +gpuA -1623.3813 134.708 -12.051 0.000 -1892.574 -1354.189 +gpuA2 6.0550 0.649 9.334 0.000 4.759 7.351 +============================================================================== +Omnibus: 1.193 Durbin-Watson: 2.101 +Prob(Omnibus): 0.551 Jarque-Bera (JB): 1.039 +Skew: 0.303 Prob(JB): 0.595 +Kurtosis: 2.894 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 5000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.759 +Model: OLS Adj. R-squared: 0.751 +Method: Least Squares F-statistic: 99.18 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 3.44e-20 +Time: 16:15:29 Log-Likelihood: -555.02 +No. Observations: 66 AIC: 1116. +Df Residuals: 63 BIC: 1123. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 6077.8579 345.765 17.578 0.000 5386.901 6768.815 +gpuA -92.3894 8.044 -11.486 0.000 -108.463 -76.316 +gpuA2 0.3436 0.039 8.871 0.000 0.266 0.421 +============================================================================== +Omnibus: 1.154 Durbin-Watson: 2.083 +Prob(Omnibus): 0.562 Jarque-Bera (JB): 1.091 +Skew: 0.301 Prob(JB): 0.580 +Kurtosis: 2.818 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +## EulerSwept + +#### 20000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.766 +Model: OLS Adj. R-squared: 0.759 +Method: Least Squares F-statistic: 103.3 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 1.28e-20 +Time: 16:15:29 Log-Likelihood: -645.80 +No. Observations: 66 AIC: 1298. +Df Residuals: 63 BIC: 1304. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 2.433e+04 1368.335 17.777 0.000 2.16e+04 2.71e+04 +gpuA -373.0640 31.831 -11.720 0.000 -436.674 -309.454 +gpuA2 1.3870 0.153 9.048 0.000 1.081 1.693 +============================================================================== +Omnibus: 1.159 Durbin-Watson: 2.078 +Prob(Omnibus): 0.560 Jarque-Bera (JB): 1.094 +Skew: 0.302 Prob(JB): 0.579 +Kurtosis: 2.819 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 40000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.765 +Model: OLS Adj. R-squared: 0.758 +Method: Least Squares F-statistic: 102.5 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 1.54e-20 +Time: 16:15:29 Log-Likelihood: -691.96 +No. Observations: 66 AIC: 1390. +Df Residuals: 63 BIC: 1396. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 4.871e+04 2753.554 17.692 0.000 4.32e+04 5.42e+04 +gpuA -747.6937 64.056 -11.673 0.000 -875.699 -619.688 +gpuA2 2.7795 0.308 9.010 0.000 2.163 3.396 +============================================================================== +Omnibus: 1.154 Durbin-Watson: 2.080 +Prob(Omnibus): 0.562 Jarque-Bera (JB): 1.088 +Skew: 0.301 Prob(JB): 0.581 +Kurtosis: 2.821 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 60000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.765 +Model: OLS Adj. R-squared: 0.758 +Method: Least Squares F-statistic: 102.7 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 1.50e-20 +Time: 16:15:29 Log-Likelihood: -718.47 +No. Observations: 66 AIC: 1443. +Df Residuals: 63 BIC: 1450. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 7.287e+04 4114.999 17.709 0.000 6.46e+04 8.11e+04 +gpuA -1117.1600 95.727 -11.670 0.000 -1308.455 -925.865 +gpuA2 4.1507 0.461 9.004 0.000 3.229 5.072 +============================================================================== +Omnibus: 1.124 Durbin-Watson: 2.093 +Prob(Omnibus): 0.570 Jarque-Bera (JB): 1.058 +Skew: 0.297 Prob(JB): 0.589 +Kurtosis: 2.824 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 5000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.538 +Model: OLS Adj. R-squared: 0.523 +Method: Least Squares F-statistic: 36.62 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 2.81e-11 +Time: 16:15:29 Log-Likelihood: -294.31 +No. Observations: 66 AIC: 594.6 +Df Residuals: 63 BIC: 601.2 +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 161.0722 6.657 24.196 0.000 147.769 174.375 +gpuA -1.2097 0.155 -7.811 0.000 -1.519 -0.900 +gpuA2 0.0049 0.001 6.583 0.000 0.003 0.006 +============================================================================== +Omnibus: 0.776 Durbin-Watson: 2.090 +Prob(Omnibus): 0.679 Jarque-Bera (JB): 0.652 +Skew: 0.239 Prob(JB): 0.722 +Kurtosis: 2.908 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +## HeatClassic + +#### 20000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.532 +Model: OLS Adj. R-squared: 0.517 +Method: Least Squares F-statistic: 35.76 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 4.20e-11 +Time: 16:15:29 Log-Likelihood: -549.97 +No. Observations: 66 AIC: 1106. +Df Residuals: 63 BIC: 1112. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 3260.6917 320.296 10.180 0.000 2620.632 3900.752 +gpuA -56.2114 7.451 -7.544 0.000 -71.101 -41.322 +gpuA2 0.2238 0.036 6.238 0.000 0.152 0.296 +============================================================================== +Omnibus: 1.209 Durbin-Watson: 2.288 +Prob(Omnibus): 0.546 Jarque-Bera (JB): 0.593 +Skew: 0.147 Prob(JB): 0.744 +Kurtosis: 3.359 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 40000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.571 +Model: OLS Adj. R-squared: 0.558 +Method: Least Squares F-statistic: 41.98 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 2.58e-12 +Time: 16:15:29 Log-Likelihood: -594.58 +No. Observations: 66 AIC: 1195. +Df Residuals: 63 BIC: 1202. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 6900.2780 629.652 10.959 0.000 5642.020 8158.536 +gpuA -119.0618 14.648 -8.128 0.000 -148.333 -89.791 +gpuA2 0.4720 0.071 6.691 0.000 0.331 0.613 +============================================================================== +Omnibus: 1.020 Durbin-Watson: 2.214 +Prob(Omnibus): 0.600 Jarque-Bera (JB): 0.578 +Skew: 0.216 Prob(JB): 0.749 +Kurtosis: 3.155 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 60000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.701 +Model: OLS Adj. R-squared: 0.692 +Method: Least Squares F-statistic: 73.92 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 2.98e-17 +Time: 16:15:29 Log-Likelihood: -609.74 +No. Observations: 66 AIC: 1225. +Df Residuals: 63 BIC: 1232. +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 1.152e+04 792.302 14.540 0.000 9937.038 1.31e+04 +gpuA -194.9280 18.431 -10.576 0.000 -231.760 -158.096 +gpuA2 0.7609 0.089 8.572 0.000 0.584 0.938 +============================================================================== +Omnibus: 0.844 Durbin-Watson: 1.834 +Prob(Omnibus): 0.656 Jarque-Bera (JB): 0.944 +Skew: 0.204 Prob(JB): 0.624 +Kurtosis: 2.579 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 5000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.732 +Model: OLS Adj. R-squared: 0.724 +Method: Least Squares F-statistic: 86.23 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 9.20e-19 +Time: 16:15:29 Log-Likelihood: -293.50 +No. Observations: 66 AIC: 593.0 +Df Residuals: 63 BIC: 599.6 +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 111.8979 6.576 17.017 0.000 98.758 125.038 +gpuA -1.6946 0.153 -11.078 0.000 -2.000 -1.389 +gpuA2 0.0065 0.001 8.773 0.000 0.005 0.008 +============================================================================== +Omnibus: 11.804 Durbin-Watson: 1.819 +Prob(Omnibus): 0.003 Jarque-Bera (JB): 15.007 +Skew: 0.728 Prob(JB): 0.000551 +Kurtosis: 4.827 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +## HeatSwept + +#### 20000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.733 +Model: OLS Adj. R-squared: 0.725 +Method: Least Squares F-statistic: 86.55 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 8.46e-19 +Time: 16:15:29 Log-Likelihood: -385.08 +No. Observations: 66 AIC: 776.2 +Df Residuals: 63 BIC: 782.7 +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 443.8657 26.336 16.854 0.000 391.237 496.494 +gpuA -6.7916 0.613 -11.086 0.000 -8.016 -5.567 +gpuA2 0.0259 0.003 8.771 0.000 0.020 0.032 +============================================================================== +Omnibus: 10.421 Durbin-Watson: 1.856 +Prob(Omnibus): 0.005 Jarque-Bera (JB): 12.171 +Skew: 0.686 Prob(JB): 0.00228 +Kurtosis: 4.595 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 40000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.735 +Model: OLS Adj. R-squared: 0.727 +Method: Least Squares F-statistic: 87.34 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 6.85e-19 +Time: 16:15:29 Log-Likelihood: -430.54 +No. Observations: 66 AIC: 867.1 +Df Residuals: 63 BIC: 873.7 +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 886.2461 52.446 16.898 0.000 781.441 991.052 +gpuA -13.5915 1.220 -11.140 0.000 -16.030 -11.153 +gpuA2 0.0518 0.006 8.816 0.000 0.040 0.064 +============================================================================== +Omnibus: 9.959 Durbin-Watson: 1.863 +Prob(Omnibus): 0.007 Jarque-Bera (JB): 11.251 +Skew: 0.675 Prob(JB): 0.00360 +Kurtosis: 4.507 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + +#### 60000000 + + OLS Regression Results +============================================================================== +Dep. Variable: normTime R-squared: 0.736 +Model: OLS Adj. R-squared: 0.728 +Method: Least Squares F-statistic: 88.03 +Date: Fri, 01 Mar 2019 Prob (F-statistic): 5.71e-19 +Time: 16:15:29 Log-Likelihood: -457.11 +No. Observations: 66 AIC: 920.2 +Df Residuals: 63 BIC: 926.8 +Df Model: 2 +Covariance Type: nonrobust +============================================================================== + coef std err t P>|t| [0.025 0.975] +------------------------------------------------------------------------------ +const 1329.8297 78.440 16.953 0.000 1173.080 1486.579 +gpuA -20.3997 1.825 -11.180 0.000 -24.046 -16.753 +gpuA2 0.0777 0.009 8.845 0.000 0.060 0.095 +============================================================================== +Omnibus: 10.045 Durbin-Watson: 1.859 +Prob(Omnibus): 0.007 Jarque-Bera (JB): 11.431 +Skew: 0.676 Prob(JB): 0.00329 +Kurtosis: 4.526 Cond. No. 4.85e+04 +============================================================================== + +Warnings: +[1] Standard Errors assume that the covariance matrix of the errors is correctly specified. +[2] The condition number is large, 4.85e+04. This might indicate that there are +strong multicollinearity or other numerical problems. + diff --git a/results/Affinity/rslts/kodiak/ModelOut.html b/results/Affinity/rslts/kodiak/ModelOut.html new file mode 100644 index 0000000..7d12365 --- /dev/null +++ b/results/Affinity/rslts/kodiak/ModelOut.html @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
gpuAgpuA2constrsqrsqaBestAffinity
ProblemGridSize
EulerClassic5000000-127.0060.4862177952.940.7073050.698013130.606
20000000-561.9062.14295348810.7511960.743297131.106
40000000-1114.444.1929170818.10.7787850.771762132.896
60000000-1623.386.0551051480.774710.767558134.053
EulerSwept5000000-92.38940.3436056077.860.7589460.751294134.441
20000000-373.0641.3870324325.20.7663920.758976134.483
40000000-747.6942.7795148714.80.7650030.757543134.501
60000000-1117.164.1506972872.10.7652020.757748134.575
HeatClassic5000000-1.209660.00490915161.0720.5375930.522913123.204
20000000-56.21140.2238453260.690.5316350.516766125.559
40000000-119.0620.4719766900.280.5713220.557713126.131
60000000-194.9280.76087911520.30.70120.691714128.094
HeatSwept5000000-1.694560.00646227111.8980.732440.723946131.112
20000000-6.791610.0258779443.8660.7331530.724682131.224
40000000-13.59150.0518008886.2460.7349330.726518131.19
60000000-20.39970.07772511329.830.7364670.728101131.23
\ No newline at end of file diff --git a/results/Affinity/rslts/kodiak/SweepScale.csv b/results/Affinity/rslts/kodiak/SweepScale.csv new file mode 100644 index 0000000..181e825 --- /dev/null +++ b/results/Affinity/rslts/kodiak/SweepScale.csv @@ -0,0 +1,6 @@ +,Euler,Euler,Heat,Heat +,Classic,Swept,Classic,Swept +Delta-GridSize,,,, +4.0,3.6456361962520947,3.414045913985325,3.0438106836389816,3.7082140418681453 +2.0,1.9606875729473539,1.9662097233822717,1.8928768155534603,1.9585449815289695 +1.5,1.502908629886935,1.506095304627357,1.4858439736998001,1.5006360493619362 diff --git a/results/Affinity/rslts/kodiak/SweepSpeedup.csv b/results/Affinity/rslts/kodiak/SweepSpeedup.csv new file mode 100644 index 0000000..6434c63 --- /dev/null +++ b/results/Affinity/rslts/kodiak/SweepSpeedup.csv @@ -0,0 +1,5 @@ +,EulerSwept,HeatSwept +5000000,1.6580121471810811,6.658915857756082 +20000000,1.770482661884607,5.465833147829844 +40000000,1.7655102159216594,5.2825689176328305 +60000000,1.761774657626146,5.230497558189415 diff --git a/results/Affinity/rslts/kodiak/summaryGPU.csv b/results/Affinity/rslts/kodiak/summaryGPU.csv new file mode 100644 index 0000000..b0e4462 --- /dev/null +++ b/results/Affinity/rslts/kodiak/summaryGPU.csv @@ -0,0 +1,6 @@ +,EulerClassic,EulerClassic,EulerClassic,EulerSwept,EulerSwept,EulerSwept,HeatClassic,HeatClassic,HeatClassic,HeatSwept,HeatSwept,HeatSwept +,NoGpu,Gpu,Speedup,NoGpu,Gpu,Speedup,NoGpu,Gpu,Speedup,NoGpu,Gpu,Speedup +5000000,10896.383875215004,711.8338963708212,15.307481044059,8288.354640430089,429.329723296097,19.305336180308757,204.7003460931905,90.62497381439556,2.258763092306398,138.70761564027137,13.609568847282945,10.191918435973331 +20000000,47877.494999179944,2595.0874183286282,18.449280228877818,33056.29451612086,1465.75138757149,22.5524565737507,5368.912455987745,275.84526350076015,19.46349336526835,545.3794527938942,50.467194303265885,10.806613292520623 +40000000,94578.5306828337,5088.155651828973,18.58797905461811,66202.32261838247,2881.9746303041206,22.97116772724556,11002.691064416882,522.141103960824,21.072256102715116,1088.4477151409474,98.8422701345088,11.011965970224491 +60000000,139262.03315278725,7647.033039341745,18.21125035504945,99529.18339346872,4340.528458756199,22.93019947667601,16548.31418405575,775.8202127411512,21.330088997793382,1633.7479598961534,148.32627376461457,11.01455540161967 diff --git a/results/Affinity/rslts/kodiak/tEulerC.csv b/results/Affinity/rslts/kodiak/tEulerC.csv new file mode 100644 index 0000000..edcb59f --- /dev/null +++ b/results/Affinity/rslts/kodiak/tEulerC.csv @@ -0,0 +1,265 @@ +tpb,gpuA,nX,time +64,0.0000,5004288,11783.87815075 +64,20.0000,5018624,2812.13139812 +64,40.0000,5017600,1679.29029275 +64,60.0000,5016576,1225.09731800 +64,80.0000,5012480,960.13265738 +64,100.0000,5022720,813.99975062 +64,120.0000,5019648,792.31906238 +64,140.0000,5035008,801.94281775 +64,160.0000,5018624,805.18877563 +64,180.0000,5031936,811.22733137 +64,200.0000,5136384,830.96740388 +64,0.0000,19998720,48623.35153288 +64,20.0000,20015104,14200.17176550 +64,40.0000,20020224,6944.46290487 +64,60.0000,19995648,4628.62926112 +64,80.0000,20049920,3637.31779462 +64,100.0000,19979264,2991.15298900 +64,120.0000,20078592,3045.81016138 +64,140.0000,19987456,3062.34361250 +64,160.0000,20074496,3098.82832213 +64,180.0000,20127744,3124.47561675 +64,200.0000,20117504,3136.43867500 +64,0.0000,40006656,97887.80852587 +64,20.0000,40000512,30230.11087313 +64,40.0000,39990272,17999.74328963 +64,60.0000,39991296,11950.35099237 +64,80.0000,40008704,8003.30436638 +64,100.0000,40070144,5952.42356062 +64,120.0000,40025088,6021.71066375 +64,140.0000,39974912,6074.14717112 +64,160.0000,39975936,6120.90046937 +64,180.0000,40061952,6169.40677712 +64,200.0000,40020992,6192.32921700 +64,0.0000,60005376,146062.35850775 +64,20.0000,60015616,45580.10057712 +64,40.0000,60010496,25714.65400900 +64,60.0000,59986944,19169.69952175 +64,80.0000,60058624,14307.63681287 +64,100.0000,60049408,11641.39742238 +64,120.0000,59971584,9023.45686113 +64,140.0000,59962368,9087.32309750 +64,160.0000,60050432,9167.94896500 +64,180.0000,59996160,9213.63170375 +64,200.0000,60138496,9279.87821501 +128,0.0000,5013504,11757.46340212 +128,20.0000,4988928,2766.47418625 +128,40.0000,5017600,1671.34885662 +128,60.0000,5087232,1224.00494725 +128,80.0000,5103616,977.99042162 +128,100.0000,5134336,829.41286687 +128,120.0000,5019648,783.61794475 +128,140.0000,5187584,815.17688875 +128,160.0000,5191680,821.51525750 +128,180.0000,5031936,802.23850475 +128,200.0000,5136384,821.41753050 +128,0.0000,19998720,47874.43083950 +128,20.0000,20015104,15075.12919188 +128,40.0000,20070400,6712.52218875 +128,60.0000,20066304,4675.84769813 +128,80.0000,20049920,3592.19171800 +128,100.0000,20090880,2979.54962349 +128,120.0000,20078592,2990.41510213 +128,140.0000,20140032,3029.20488925 +128,160.0000,20074496,3041.62322575 +128,180.0000,20127744,3067.88597163 +128,200.0000,20117504,3079.56767587 +128,0.0000,39997440,94572.47765687 +128,20.0000,40030208,30424.32167438 +128,40.0000,40040448,17873.19761575 +128,60.0000,39991296,11613.22394975 +128,80.0000,40099840,8473.85956313 +128,100.0000,39958528,5999.73280512 +128,120.0000,40157184,5934.77746688 +128,140.0000,39974912,5965.04125500 +128,160.0000,40148992,6035.97486338 +128,180.0000,40255488,6087.85873562 +128,200.0000,40235008,6113.13958250 +128,0.0000,59996160,142772.46349949 +128,20.0000,59985920,45456.53581388 +128,40.0000,60010496,27007.73269538 +128,60.0000,60057600,18476.24612613 +128,80.0000,59967488,14727.70278325 +128,100.0000,60049408,10747.32587525 +128,120.0000,59971584,9196.43597838 +128,140.0000,60114944,8954.23480925 +128,160.0000,60223488,9033.10393688 +128,180.0000,59996160,9053.38325850 +128,200.0000,59924480,9084.66930625 +256,0.0000,5013504,11372.29297150 +256,20.0000,4988928,2775.72455713 +256,40.0000,5017600,1692.89858737 +256,60.0000,5087232,1222.97662762 +256,80.0000,5103616,993.21932763 +256,100.0000,4911104,789.28606275 +256,120.0000,5283840,768.81978338 +256,140.0000,4882432,721.24009050 +256,160.0000,4845568,721.49283888 +256,180.0000,5419008,803.85873387 +256,200.0000,5136384,767.87321788 +256,0.0000,20017152,48435.26719313 +256,20.0000,20074496,14854.54966738 +256,40.0000,20070400,7239.42334425 +256,60.0000,20066304,4647.95095062 +256,80.0000,20049920,3616.48418600 +256,100.0000,20090880,2972.54657962 +256,120.0000,20078592,2737.58108637 +256,140.0000,20140032,2770.59887412 +256,160.0000,20074496,2781.72689051 +256,180.0000,20127744,2805.26021662 +256,200.0000,20545536,2875.54629738 +256,0.0000,39997440,98394.44690462 +256,20.0000,40030208,30472.42979600 +256,40.0000,40140800,18102.67986950 +256,60.0000,40132608,12208.79334425 +256,80.0000,40099840,8654.66111275 +256,100.0000,40181760,5934.13886738 +256,120.0000,40157184,5411.07995600 +256,140.0000,40280064,5480.66289175 +256,160.0000,40148992,5503.76790537 +256,180.0000,40255488,5550.41552200 +256,200.0000,40235008,5575.29760387 +256,0.0000,60014592,147062.42835262 +256,20.0000,59985920,45192.13517400 +256,40.0000,60010496,27050.43564863 +256,60.0000,60198912,19388.07943537 +256,80.0000,60149760,14837.61907525 +256,100.0000,60272640,11601.01377488 +256,120.0000,60235776,9102.71150774 +256,140.0000,60420096,8192.80759775 +256,160.0000,60223488,8228.02971000 +256,180.0000,60383232,8301.69005325 +256,200.0000,59924480,8274.25051100 +512,0.0000,5013504,11734.08713275 +512,20.0000,4988928,2776.03545225 +512,40.0000,5218304,1757.60390088 +512,60.0000,5087232,1226.01334375 +512,80.0000,5103616,982.39118925 +512,100.0000,5357568,860.41989487 +512,120.0000,5283840,752.24328300 +512,140.0000,4882432,704.83720562 +512,160.0000,5537792,795.71747888 +512,180.0000,4644864,683.35053888 +512,200.0000,5136384,750.13970025 +512,0.0000,20054016,48630.30086950 +512,20.0000,19955712,14963.54845137 +512,40.0000,20070400,6874.29857688 +512,60.0000,20348928,4727.43878438 +512,80.0000,20414464,3753.96199987 +512,100.0000,20537344,3002.42100750 +512,120.0000,20078592,2661.10078650 +512,140.0000,20750336,2774.09229375 +512,160.0000,20766720,2796.77918713 +512,180.0000,20127744,2728.29530312 +512,200.0000,20545536,2796.81594300 +512,0.0000,40034304,96892.25797912 +512,20.0000,40148992,30448.46302288 +512,40.0000,40140800,17654.23429062 +512,60.0000,40132608,12196.48608287 +512,80.0000,40099840,7698.94203937 +512,100.0000,40181760,5986.18090975 +512,120.0000,40157184,5258.97153137 +512,140.0000,40280064,5326.87250074 +512,160.0000,40148992,5350.06961750 +512,180.0000,40255488,5394.62859838 +512,200.0000,41091072,5531.10533112 +512,0.0000,60014592,139295.90167925 +512,20.0000,60104704,45522.65821025 +512,40.0000,60211200,26413.62101562 +512,60.0000,59916288,19195.42062262 +512,80.0000,60514304,14856.85446826 +512,100.0000,59826176,11596.34789525 +512,120.0000,60235776,9295.56653462 +512,140.0000,59809792,7879.34753700 +512,160.0000,60915712,8084.51174700 +512,180.0000,60383232,8061.78847450 +512,200.0000,59924480,8039.16515600 +768,0.0000,4976640,10845.47596975 +768,20.0000,4988928,2792.95322113 +768,40.0000,5419008,1815.12057187 +768,60.0000,5087232,1236.05428675 +768,80.0000,5468160,1048.65413175 +768,100.0000,5357568,861.03767624 +768,120.0000,4755456,692.02235288 +768,140.0000,5492736,791.94083375 +768,160.0000,6230016,890.56868663 +768,180.0000,4644864,692.39359725 +768,200.0000,5136384,763.17893888 +768,0.0000,20017152,49198.33373462 +768,20.0000,19955712,14777.58384725 +768,40.0000,19869696,6867.77474938 +768,60.0000,20348928,4708.52046838 +768,80.0000,20779008,3728.01794175 +768,100.0000,20090880,2950.66332800 +768,120.0000,20606976,2673.84520737 +768,140.0000,20140032,2637.00820725 +768,160.0000,20766720,2735.43453638 +768,180.0000,20901888,2772.44657512 +768,200.0000,20545536,2734.28289151 +768,0.0000,40034304,97760.30247062 +768,20.0000,39911424,30057.62142337 +768,40.0000,40341504,18051.58786838 +768,60.0000,39849984,12062.78438925 +768,80.0000,40464384,8433.04798563 +768,100.0000,40181760,6060.88282325 +768,120.0000,39628800,5040.93756738 +768,140.0000,40280064,5168.37778675 +768,160.0000,41533440,5366.09072737 +768,180.0000,39481344,5136.71369338 +768,200.0000,41091072,5366.20771538 +768,0.0000,60051456,147135.99642937 +768,20.0000,60223488,45687.20991049 +768,40.0000,60211200,27198.45217412 +768,60.0000,60198912,19344.43592938 +768,80.0000,60149760,14600.60034875 +768,100.0000,60272640,11685.50407750 +768,120.0000,60235776,8672.93402488 +768,140.0000,60420096,7700.57450587 +768,160.0000,60223488,7733.58930663 +768,180.0000,60383232,7798.93083138 +768,200.0000,61636608,7995.51330800 +1024,0.0000,5013504,11281.82796837 +1024,20.0000,5226496,2941.37355088 +1024,40.0000,4816896,1601.53070475 +1024,60.0000,5652480,1360.15460113 +1024,80.0000,5832704,1119.29043988 +1024,100.0000,5357568,860.05091688 +1024,120.0000,6340608,903.34375838 +1024,140.0000,4882432,725.45867475 +1024,160.0000,5537792,820.24783438 +1024,180.0000,6193152,903.53652112 +1024,200.0000,6848512,998.67660187 +1024,0.0000,20054016,49121.57814274 +1024,20.0000,19955712,14947.33541937 +1024,40.0000,20070400,6697.18386175 +1024,60.0000,20348928,4716.77040937 +1024,80.0000,20414464,3706.92997388 +1024,100.0000,19644416,2926.04467963 +1024,120.0000,21135360,3125.80374337 +1024,140.0000,19529728,2601.19634900 +1024,160.0000,19382272,2600.57194188 +1024,180.0000,21676032,2912.26790538 +1024,200.0000,20545536,2778.75635363 +1024,0.0000,40108032,95041.36025074 +1024,20.0000,39911424,30408.53713763 +1024,40.0000,40140800,18010.89885788 +1024,60.0000,40697856,11917.53740050 +1024,80.0000,40828928,8372.03282737 +1024,100.0000,41074688,6154.80216125 +1024,120.0000,40157184,5188.25280937 +1024,140.0000,41500672,5408.23080150 +1024,160.0000,41533440,5454.66838375 +1024,180.0000,40255488,5321.71928750 +1024,200.0000,41091072,5453.26037125 +1024,0.0000,60014592,140573.98987537 +1024,20.0000,60342272,45183.92840912 +1024,40.0000,60211200,27166.83289512 +1024,60.0000,59916288,18764.45838175 +1024,80.0000,59785216,14688.55746837 +1024,100.0000,60719104,11679.45586675 +1024,120.0000,61292544,9497.34152763 +1024,140.0000,61030400,7906.04479563 +1024,160.0000,60915712,7949.04941650 +1024,180.0000,61931520,8127.78019587 +1024,200.0000,61636608,8126.44736350 diff --git a/results/Affinity/rslts/kodiak/tEulerS.csv b/results/Affinity/rslts/kodiak/tEulerS.csv new file mode 100644 index 0000000..29cb9ff --- /dev/null +++ b/results/Affinity/rslts/kodiak/tEulerS.csv @@ -0,0 +1,265 @@ +tpb,gpuA,nX,time +64,0.0000,5004288,8517.35432971 +64,20.0000,5018624,2633.92132161 +64,40.0000,5017600,1561.44198316 +64,60.0000,5016576,1135.76307498 +64,80.0000,5012480,902.16634556 +64,100.0000,5022720,759.58651834 +64,120.0000,5019648,672.75757261 +64,140.0000,5035008,675.36134606 +64,160.0000,5018624,673.43523802 +64,180.0000,5031936,679.05126934 +64,200.0000,5136384,699.06377532 +64,0.0000,19998720,34022.79539832 +64,20.0000,20015104,10494.18025548 +64,40.0000,20020224,6224.95793139 +64,60.0000,19995648,4391.31895060 +64,80.0000,20049920,3439.75209781 +64,100.0000,19979264,2771.49000025 +64,120.0000,20078592,2605.91770883 +64,140.0000,19987456,2614.19440195 +64,160.0000,20074496,2645.68461315 +64,180.0000,20127744,2668.83248915 +64,200.0000,20117504,2678.71626210 +64,0.0000,40006656,68035.36968638 +64,20.0000,40000512,21122.04029130 +64,40.0000,39990272,12394.83227208 +64,60.0000,39991296,8855.81157934 +64,80.0000,40008704,6883.20266455 +64,100.0000,40070144,5576.62030040 +64,120.0000,40025088,5176.20747692 +64,140.0000,39974912,5210.53452633 +64,160.0000,39975936,5250.10029092 +64,180.0000,40061952,5292.51966131 +64,200.0000,40020992,5312.83800973 +64,0.0000,60005376,100920.69750636 +64,20.0000,60015616,31432.02185990 +64,40.0000,60010496,18726.59938735 +64,60.0000,59986944,13338.17415993 +64,80.0000,60058624,10278.71686939 +64,100.0000,60049408,8400.93399576 +64,120.0000,59971584,7734.64833396 +64,140.0000,59962368,7808.59524813 +64,160.0000,60050432,7876.82407323 +64,180.0000,59996160,7916.78765794 +64,200.0000,60138496,7973.37581700 +128,0.0000,5013504,8434.59294634 +128,20.0000,4988928,2613.91694273 +128,40.0000,5017600,1561.68832608 +128,60.0000,5087232,1150.27480167 +128,80.0000,5103616,918.43340675 +128,100.0000,5134336,773.92177677 +128,120.0000,5019648,662.77176071 +128,140.0000,5187584,604.81089467 +128,160.0000,5191680,550.31680727 +128,180.0000,5031936,508.56831897 +128,200.0000,5136384,504.05840613 +128,0.0000,19998720,33398.42121539 +128,20.0000,20015104,10500.63245369 +128,40.0000,20070400,6286.57395668 +128,60.0000,20066304,4414.60078685 +128,80.0000,20049920,3423.16287189 +128,100.0000,20090880,2773.82002677 +128,120.0000,20078592,2376.13764728 +128,140.0000,20140032,2060.35034923 +128,160.0000,20074496,1942.53610769 +128,180.0000,20127744,1949.53712575 +128,200.0000,20117504,1955.32351730 +128,0.0000,39997440,67525.25341135 +128,20.0000,40030208,20899.28753349 +128,40.0000,40040448,12317.88939318 +128,60.0000,39991296,8798.98630976 +128,80.0000,40099840,6799.80733192 +128,100.0000,39958528,5536.84409288 +128,120.0000,40157184,4737.23566023 +128,140.0000,39974912,4053.12564828 +128,160.0000,40148992,3852.38471925 +128,180.0000,40255488,3883.59639243 +128,200.0000,40235008,3897.94087861 +128,0.0000,59996160,100038.98503162 +128,20.0000,59985920,31077.89565749 +128,40.0000,60010496,18427.89044223 +128,60.0000,60057600,13182.08378250 +128,80.0000,59967488,10250.90229594 +128,100.0000,60049408,8413.60830801 +128,120.0000,59971584,7021.25990998 +128,140.0000,60114944,6106.33904482 +128,160.0000,60223488,5765.92586031 +128,180.0000,59996160,5776.11368302 +128,200.0000,59924480,5796.43890513 +256,0.0000,5013504,8420.36535379 +256,20.0000,4988928,2605.71704638 +256,40.0000,5017600,1559.84119531 +256,60.0000,5087232,1145.62124144 +256,80.0000,5103616,917.61514124 +256,100.0000,4911104,745.33760144 +256,120.0000,5283840,691.60527095 +256,140.0000,4882432,575.02280865 +256,160.0000,4845568,518.22198598 +256,180.0000,5419008,522.25264174 +256,200.0000,5136384,465.83263244 +256,0.0000,20017152,33689.50398289 +256,20.0000,20074496,10684.71958408 +256,40.0000,20070400,6177.77340712 +256,60.0000,20066304,4405.10029179 +256,80.0000,20049920,3410.52715687 +256,100.0000,20090880,2780.88103250 +256,120.0000,20078592,2349.07772347 +256,140.0000,20140032,2039.82682279 +256,160.0000,20074496,2001.17772111 +256,180.0000,20127744,1657.22745338 +256,200.0000,20545536,1694.42137339 +256,0.0000,39997440,67279.37844457 +256,20.0000,40030208,20638.12363790 +256,40.0000,40140800,12265.06899628 +256,60.0000,40132608,8707.90710541 +256,80.0000,40099840,6827.30811769 +256,100.0000,40181760,5570.52586037 +256,120.0000,40157184,4695.63915873 +256,140.0000,40280064,4116.08426376 +256,160.0000,40148992,3603.07194383 +256,180.0000,40255488,3291.05576959 +256,200.0000,40235008,3301.09291369 +256,0.0000,60014592,99553.38889087 +256,20.0000,59985920,30934.70925546 +256,40.0000,60010496,18451.59856759 +256,60.0000,60198912,13226.18456857 +256,80.0000,60149760,10384.96513541 +256,100.0000,60272640,8306.59030816 +256,120.0000,60235776,7049.65887835 +256,140.0000,60420096,6100.15128324 +256,160.0000,60223488,5399.98548834 +256,180.0000,60383232,4923.71649926 +256,200.0000,59924480,4906.54517262 +512,0.0000,5013504,8421.85283916 +512,20.0000,4988928,2603.71929688 +512,40.0000,5218304,1606.19586979 +512,60.0000,5087232,1141.84812785 +512,80.0000,5103616,915.14829080 +512,100.0000,5357568,804.53770399 +512,120.0000,5283840,691.03920660 +512,140.0000,4882432,575.61892882 +512,160.0000,5537792,579.39734202 +512,180.0000,4644864,461.51459735 +512,200.0000,5136384,464.19325905 +512,0.0000,20054016,33145.57295635 +512,20.0000,19955712,10269.24243886 +512,40.0000,20070400,6198.26937996 +512,60.0000,20348928,4508.23746255 +512,80.0000,20414464,3479.22860739 +512,100.0000,20537344,2820.76042596 +512,120.0000,20078592,2335.79846069 +512,140.0000,20750336,2106.44279377 +512,160.0000,20766720,1861.01173698 +512,180.0000,20127744,1623.86472049 +512,200.0000,20545536,1702.24275868 +512,0.0000,40034304,66259.96740229 +512,20.0000,40148992,20865.36253175 +512,40.0000,40140800,12358.58142932 +512,60.0000,40132608,8687.75378236 +512,80.0000,40099840,6734.40995622 +512,100.0000,40181760,5511.77559685 +512,120.0000,40157184,4662.33445957 +512,140.0000,40280064,4048.96564310 +512,160.0000,40148992,3596.91740141 +512,180.0000,40255488,3227.17706399 +512,200.0000,41091072,3124.49100979 +512,0.0000,60014592,100893.55124714 +512,20.0000,60104704,30903.59685826 +512,40.0000,60211200,18580.81434003 +512,60.0000,59916288,13169.79943961 +512,80.0000,60514304,10243.37570597 +512,100.0000,59826176,8303.96757254 +512,120.0000,60235776,6992.83160404 +512,140.0000,59809792,6084.34876774 +512,160.0000,60915712,5420.44571007 +512,180.0000,60383232,4835.55014075 +512,200.0000,59924480,4553.75530717 +768,0.0000,4976640,8249.63144755 +768,20.0000,4988928,2584.97909375 +768,40.0000,5419008,1670.95241994 +768,60.0000,5087232,1147.52076138 +768,80.0000,5468160,978.13087282 +768,100.0000,5357568,811.43924770 +768,120.0000,4755456,632.08725994 +768,140.0000,5492736,636.15204409 +768,160.0000,6230016,642.18961846 +768,180.0000,4644864,464.86515383 +768,200.0000,5136384,471.60042878 +768,0.0000,20017152,33125.29614935 +768,20.0000,19955712,10364.19708587 +768,40.0000,19869696,6063.36498280 +768,60.0000,20348928,4408.42657946 +768,80.0000,20779008,3563.55025266 +768,100.0000,20090880,2795.97543798 +768,120.0000,20606976,2398.28146827 +768,140.0000,20140032,2038.04285841 +768,160.0000,20766720,1863.94231408 +768,180.0000,20901888,1723.23996027 +768,200.0000,20545536,1721.25868653 +768,0.0000,40034304,66259.09773026 +768,20.0000,39911424,20517.11990879 +768,40.0000,40341504,12418.02121644 +768,60.0000,39849984,8690.64698619 +768,80.0000,40464384,6884.27456601 +768,100.0000,40181760,5573.07924455 +768,120.0000,39628800,4599.28641582 +768,140.0000,40280064,4102.57519864 +768,160.0000,41533440,3736.86148813 +768,180.0000,39481344,3261.44246305 +768,200.0000,41091072,3408.74741897 +768,0.0000,60051456,100402.20237827 +768,20.0000,60223488,31248.07614486 +768,40.0000,60211200,18575.86604155 +768,60.0000,60198912,13193.49655790 +768,80.0000,60149760,10216.22562936 +768,100.0000,60272640,8319.74790540 +768,120.0000,60235776,7089.09108152 +768,140.0000,60420096,6141.46195458 +768,160.0000,60223488,5385.89089608 +768,180.0000,60383232,4985.39065007 +768,200.0000,61636608,5097.79041170 +1024,0.0000,5013504,8318.65543554 +1024,20.0000,5226496,2688.51088110 +1024,40.0000,4816896,1501.09369727 +1024,60.0000,5652480,1266.48847986 +1024,80.0000,5832704,1041.88226624 +1024,100.0000,5357568,808.39018823 +1024,120.0000,6340608,813.57048132 +1024,140.0000,4882432,579.78039783 +1024,160.0000,5537792,583.26358715 +1024,180.0000,6193152,589.60186536 +1024,200.0000,6848512,588.05395239 +1024,0.0000,20054016,33536.90815539 +1024,20.0000,19955712,10256.84667042 +1024,40.0000,20070400,6193.29853185 +1024,60.0000,20348928,4408.05102747 +1024,80.0000,20414464,3428.69245423 +1024,100.0000,19644416,2726.29648632 +1024,120.0000,21135360,2463.28362768 +1024,140.0000,19529728,1981.04486108 +1024,160.0000,19382272,1742.04483911 +1024,180.0000,21676032,1735.93653369 +1024,200.0000,20545536,1505.73239502 +1024,0.0000,40108032,67378.32563122 +1024,20.0000,39911424,20830.45251990 +1024,40.0000,40140800,12214.98398206 +1024,60.0000,40697856,8817.03462610 +1024,80.0000,40828928,6936.94526416 +1024,100.0000,41074688,5693.10851465 +1024,120.0000,40157184,4663.50199622 +1024,140.0000,41500672,4194.11465320 +1024,160.0000,41533440,3691.57730457 +1024,180.0000,40255488,3198.06748120 +1024,200.0000,41091072,2960.58567590 +1024,0.0000,60014592,100325.03777917 +1024,20.0000,60342272,31046.49547827 +1024,40.0000,60211200,18575.78582849 +1024,60.0000,59916288,13138.35770178 +1024,80.0000,59785216,10036.60961755 +1024,100.0000,60719104,8326.84979822 +1024,120.0000,61292544,7182.06777942 +1024,140.0000,61030400,6150.68463391 +1024,160.0000,60915712,5405.91338342 +1024,180.0000,61931520,4918.43451233 +1024,200.0000,61636608,4458.92418542 diff --git a/results/Affinity/rslts/kodiak/tHeatC.csv b/results/Affinity/rslts/kodiak/tHeatC.csv new file mode 100644 index 0000000..95bfa3d --- /dev/null +++ b/results/Affinity/rslts/kodiak/tHeatC.csv @@ -0,0 +1,265 @@ +tpb,gpuA,nX,time +64,0.0000,5004288,204.87589711 +64,20.0000,5018624,104.33697360 +64,40.0000,5017600,92.54232373 +64,60.0000,5016576,97.67801115 +64,80.0000,5012480,99.73342373 +64,100.0000,5022720,100.90793915 +64,120.0000,5019648,100.76084886 +64,140.0000,5035008,100.98372081 +64,160.0000,5018624,101.04701535 +64,180.0000,5031936,101.76483261 +64,200.0000,5136384,103.82936608 +64,0.0000,19998720,5467.81605945 +64,20.0000,20015104,286.52001790 +64,40.0000,20020224,283.42102265 +64,60.0000,19995648,299.35141223 +64,80.0000,20049920,309.26371576 +64,100.0000,19979264,313.68735773 +64,120.0000,20078592,319.58999000 +64,140.0000,19987456,321.20908300 +64,160.0000,20074496,324.33057267 +64,180.0000,20127744,326.92544878 +64,200.0000,20117504,328.20844058 +64,0.0000,40006656,11004.52191221 +64,20.0000,40000512,1050.83629299 +64,40.0000,39990272,539.13865227 +64,60.0000,39991296,572.26335683 +64,80.0000,40008704,590.66536753 +64,100.0000,40070144,603.67562117 +64,120.0000,40025088,610.66978976 +64,140.0000,39974912,616.06167172 +64,160.0000,39975936,620.75781236 +64,180.0000,40061952,625.07452757 +64,200.0000,40020992,627.60251248 +64,0.0000,60005376,16557.22592386 +64,20.0000,60015616,4877.38249257 +64,40.0000,60010496,796.49476106 +64,60.0000,59986944,845.64693730 +64,80.0000,60058624,874.23044513 +64,100.0000,60049408,891.35539303 +64,120.0000,59971584,902.57033288 +64,140.0000,59962368,911.32390291 +64,160.0000,60050432,919.18125659 +64,180.0000,59996160,923.63536733 +64,200.0000,60138496,930.08926094 +128,0.0000,5013504,206.28898685 +128,20.0000,4988928,102.93517354 +128,40.0000,5017600,92.60115059 +128,60.0000,5087232,99.00308825 +128,80.0000,5103616,101.59187206 +128,100.0000,5134336,101.84105585 +128,120.0000,5019648,101.05205545 +128,140.0000,5187584,103.79536748 +128,160.0000,5191680,104.43791651 +128,180.0000,5031936,102.30342518 +128,200.0000,5136384,104.09434613 +128,0.0000,19998720,5422.53955552 +128,20.0000,20015104,286.70563382 +128,40.0000,20070400,285.76515399 +128,60.0000,20066304,302.71010880 +128,80.0000,20049920,311.69858442 +128,100.0000,20090880,318.32521324 +128,120.0000,20078592,321.94487606 +128,140.0000,20140032,326.86490710 +128,160.0000,20074496,328.25512635 +128,180.0000,20127744,329.89370862 +128,200.0000,20117504,331.13616709 +128,0.0000,39997440,11055.97938403 +128,20.0000,40030208,1217.34285406 +128,40.0000,40040448,545.05957492 +128,60.0000,39991296,577.85223524 +128,80.0000,40099840,597.64778491 +128,100.0000,39958528,607.80578701 +128,120.0000,40157184,618.51126709 +128,140.0000,39974912,622.15889371 +128,160.0000,40148992,629.27719309 +128,180.0000,40255488,634.45785145 +128,200.0000,40235008,637.72552182 +128,0.0000,59996160,16561.26688356 +128,20.0000,59985920,4904.46153903 +128,40.0000,60010496,805.10562777 +128,60.0000,60057600,855.59714814 +128,80.0000,59967488,881.76954902 +128,100.0000,60049408,900.63658922 +128,120.0000,59971584,911.95839458 +128,140.0000,60114944,922.92918469 +128,160.0000,60223488,931.42499670 +128,180.0000,59996160,933.59978291 +128,200.0000,59924480,937.05092340 +256,0.0000,5013504,206.01332698 +256,20.0000,4988928,105.80605380 +256,40.0000,5017600,92.67532853 +256,60.0000,5087232,99.18221199 +256,80.0000,5103616,100.70786870 +256,100.0000,4911104,99.89502560 +256,120.0000,5283840,104.76738113 +256,140.0000,4882432,99.92234653 +256,160.0000,4845568,99.69777741 +256,180.0000,5419008,108.46722539 +256,200.0000,5136384,104.95041058 +256,0.0000,20017152,5446.50232748 +256,20.0000,20074496,287.68374681 +256,40.0000,20070400,285.08089795 +256,60.0000,20066304,301.89326084 +256,80.0000,20049920,310.95504250 +256,100.0000,20090880,317.01908735 +256,120.0000,20078592,321.00977061 +256,140.0000,20140032,324.84943168 +256,160.0000,20074496,325.98742568 +256,180.0000,20127744,328.73475336 +256,200.0000,20545536,336.93646013 +256,0.0000,39997440,11052.16764357 +256,20.0000,40030208,1095.08541338 +256,40.0000,40140800,544.43631203 +256,60.0000,40132608,578.48162437 +256,80.0000,40099840,595.96042213 +256,100.0000,40181760,609.30666692 +256,120.0000,40157184,617.03021809 +256,140.0000,40280064,625.32690235 +256,160.0000,40148992,627.29448718 +256,180.0000,40255488,632.69662087 +256,200.0000,40235008,635.50858102 +256,0.0000,60014592,16582.95166692 +256,20.0000,59985920,4915.73091075 +256,40.0000,60010496,803.27656047 +256,60.0000,60198912,855.35781146 +256,80.0000,60149760,882.14431778 +256,100.0000,60272640,902.58982411 +256,120.0000,60235776,914.10180681 +256,140.0000,60420096,925.59145623 +256,160.0000,60223488,929.19528044 +256,180.0000,60383232,937.37960557 +256,200.0000,59924480,934.71424809 +512,0.0000,5013504,205.77775411 +512,20.0000,4988928,105.11343743 +512,40.0000,5218304,94.90464172 +512,60.0000,5087232,98.92665122 +512,80.0000,5103616,101.08816664 +512,100.0000,5357568,104.54126119 +512,120.0000,5283840,105.03861602 +512,140.0000,4882432,99.23943693 +512,160.0000,5537792,109.41462287 +512,180.0000,4644864,98.61391455 +512,200.0000,5136384,105.32351877 +512,0.0000,20054016,5461.81631448 +512,20.0000,19955712,284.48418214 +512,40.0000,20070400,281.43757567 +512,60.0000,20348928,301.94530428 +512,80.0000,20414464,311.47714164 +512,100.0000,20537344,319.04023529 +512,120.0000,20078592,316.72891290 +512,140.0000,20750336,329.67239218 +512,160.0000,20766720,332.00442543 +512,180.0000,20127744,324.01747868 +512,200.0000,20545536,332.00699920 +512,0.0000,40034304,11234.75491280 +512,20.0000,40148992,1073.91897895 +512,40.0000,40140800,535.18283686 +512,60.0000,40132608,568.41264657 +512,80.0000,40099840,585.87075886 +512,100.0000,40181760,598.40245318 +512,120.0000,40157184,606.06787791 +512,140.0000,40280064,613.83661722 +512,160.0000,40148992,616.11365152 +512,180.0000,40255488,621.55570136 +512,200.0000,41091072,636.39236313 +512,0.0000,60014592,16707.21097335 +512,20.0000,60104704,5088.80225444 +512,40.0000,60211200,790.24770161 +512,60.0000,59916288,835.23907655 +512,80.0000,60514304,870.60373136 +512,100.0000,59826176,877.67439768 +512,120.0000,60235776,895.67068602 +512,140.0000,59809792,898.21871251 +512,160.0000,60915712,921.29537793 +512,180.0000,60383232,918.57521419 +512,200.0000,59924480,915.99980116 +768,0.0000,4976640,205.32040788 +768,20.0000,4988928,103.59126984 +768,40.0000,5419008,98.21949162 +768,60.0000,5087232,98.33717299 +768,80.0000,5468160,103.33691455 +768,100.0000,5357568,103.30766972 +768,120.0000,4755456,98.45645018 +768,140.0000,5492736,107.75510404 +768,160.0000,6230016,119.29320964 +768,180.0000,4644864,97.61159642 +768,200.0000,5136384,103.09787491 +768,0.0000,20017152,5373.51683531 +768,20.0000,19955712,286.05648493 +768,40.0000,19869696,274.04807644 +768,60.0000,20348928,296.45332828 +768,80.0000,20779008,311.09685866 +768,100.0000,20090880,307.16558677 +768,120.0000,20606976,318.47081246 +768,140.0000,20140032,314.83066932 +768,160.0000,20766720,325.72074357 +768,180.0000,20901888,329.25579381 +768,200.0000,20545536,325.65490690 +768,0.0000,40034304,11060.97118669 +768,20.0000,39911424,1081.65270516 +768,40.0000,40341504,526.59893585 +768,60.0000,39849984,551.65436328 +768,80.0000,40464384,577.62997940 +768,100.0000,40181760,584.97897995 +768,120.0000,39628800,585.00570377 +768,140.0000,40280064,599.96894790 +768,160.0000,41533440,621.84782021 +768,180.0000,39481344,595.90820259 +768,200.0000,41091072,621.71621329 +768,0.0000,60051456,16562.50601830 +768,20.0000,60223488,4914.79756697 +768,40.0000,60211200,847.88033218 +768,60.0000,60198912,819.13206410 +768,80.0000,60149760,845.12939708 +768,100.0000,60272640,863.43695245 +768,120.0000,60235776,874.55749407 +768,140.0000,60420096,885.54243723 +768,160.0000,60223488,889.07045828 +768,180.0000,60383232,896.27783341 +768,200.0000,61636608,918.58899960 +1024,0.0000,5013504,205.65351712 +1024,20.0000,5226496,107.98881896 +1024,40.0000,4816896,91.07491180 +1024,60.0000,5652480,105.28083106 +1024,80.0000,5832704,109.11973826 +1024,100.0000,5357568,104.83556522 +1024,120.0000,6340608,120.39230079 +1024,140.0000,4882432,100.11871476 +1024,160.0000,5537792,110.47204205 +1024,180.0000,6193152,120.86564867 +1024,200.0000,6848512,129.46729019 +1024,0.0000,20054016,5397.99298560 +1024,20.0000,19955712,285.92928054 +1024,40.0000,20070400,279.37402930 +1024,60.0000,20348928,299.01973227 +1024,80.0000,20414464,308.66879416 +1024,100.0000,19644416,303.66544873 +1024,120.0000,21135360,328.94914749 +1024,140.0000,19529728,308.53753967 +1024,160.0000,19382272,308.52503510 +1024,180.0000,21676032,343.64264772 +1024,200.0000,20545536,328.96766517 +1024,0.0000,40108032,11488.21896585 +1024,20.0000,39911424,1218.02913474 +1024,40.0000,40140800,528.31255162 +1024,60.0000,40697856,567.66602300 +1024,80.0000,40828928,587.58824104 +1024,100.0000,41074688,602.06995250 +1024,120.0000,40157184,597.17952547 +1024,140.0000,41500672,622.57184406 +1024,160.0000,41533440,627.30430338 +1024,180.0000,40255488,612.01743073 +1024,200.0000,41091072,627.45695985 +1024,0.0000,60014592,16648.72112260 +1024,20.0000,60342272,5051.04849242 +1024,40.0000,60211200,778.55109989 +1024,60.0000,59916288,822.55233588 +1024,80.0000,59785216,846.37559762 +1024,100.0000,60719104,876.61998150 +1024,120.0000,61292544,896.98757047 +1024,140.0000,61030400,902.22551037 +1024,160.0000,60915712,906.58935508 +1024,180.0000,61931520,926.53130628 +1024,200.0000,61636608,926.25114544 diff --git a/results/Affinity/rslts/kodiak/tHeatS.csv b/results/Affinity/rslts/kodiak/tHeatS.csv new file mode 100644 index 0000000..7987314 --- /dev/null +++ b/results/Affinity/rslts/kodiak/tHeatS.csv @@ -0,0 +1,265 @@ +tpb,gpuA,nX,time +64,0.0000,5004288,189.70309255 +64,20.0000,5018624,62.22814532 +64,40.0000,5017600,37.88999980 +64,60.0000,5016576,26.16634734 +64,80.0000,5012480,22.18076732 +64,100.0000,5022720,17.89041309 +64,120.0000,5019648,17.49654792 +64,140.0000,5035008,18.83949950 +64,160.0000,5018624,17.88661631 +64,180.0000,5031936,17.97988414 +64,200.0000,5136384,18.31690505 +64,0.0000,19998720,742.77556620 +64,20.0000,20015104,238.76906739 +64,40.0000,20020224,141.03115560 +64,60.0000,19995648,97.06591983 +64,80.0000,20049920,78.22304538 +64,100.0000,19979264,66.84346715 +64,120.0000,20078592,64.42041614 +64,140.0000,19987456,63.82025709 +64,160.0000,20074496,65.00887091 +64,180.0000,20127744,64.20949910 +64,200.0000,20117504,64.48140570 +64,0.0000,40006656,1473.90421021 +64,20.0000,40000512,462.95611232 +64,40.0000,39990272,270.22139157 +64,60.0000,39991296,201.51174755 +64,80.0000,40008704,161.08636492 +64,100.0000,40070144,123.61354498 +64,120.0000,40025088,124.19467802 +64,140.0000,39974912,124.00451618 +64,160.0000,39975936,125.58558996 +64,180.0000,40061952,125.19882673 +64,200.0000,40020992,126.71510014 +64,0.0000,60005376,2213.49198168 +64,20.0000,60015616,697.56108986 +64,40.0000,60010496,414.94488563 +64,60.0000,59986944,296.84552646 +64,80.0000,60058624,231.34753235 +64,100.0000,60049408,185.50569199 +64,120.0000,59971584,183.24308012 +64,140.0000,59962368,184.88250519 +64,160.0000,60050432,186.30229952 +64,180.0000,59996160,186.13300085 +64,200.0000,60138496,188.43994714 +128,0.0000,5013504,163.65414946 +128,20.0000,4988928,50.78511267 +128,40.0000,5017600,31.03491409 +128,60.0000,5087232,22.92593491 +128,80.0000,5103616,17.88060723 +128,100.0000,5134336,14.95350175 +128,120.0000,5019648,14.69761901 +128,140.0000,5187584,16.62662754 +128,160.0000,5191680,15.44138464 +128,180.0000,5031936,15.07603909 +128,200.0000,5136384,15.40948298 +128,0.0000,19998720,662.61756160 +128,20.0000,20015104,202.60166808 +128,40.0000,20070400,123.66268291 +128,60.0000,20066304,86.11132798 +128,80.0000,20049920,67.32250624 +128,100.0000,20090880,56.23663399 +128,120.0000,20078592,54.64916853 +128,140.0000,20140032,54.63176732 +128,160.0000,20074496,56.12175280 +128,180.0000,20127744,55.32249221 +128,200.0000,20117504,55.56241713 +128,0.0000,39997440,1328.68856844 +128,20.0000,40030208,417.09920218 +128,40.0000,40040448,241.90357298 +128,60.0000,39991296,175.32030032 +128,80.0000,40099840,133.46990425 +128,100.0000,39958528,110.58977896 +128,120.0000,40157184,107.94067123 +128,140.0000,39974912,106.78478834 +128,160.0000,40148992,109.01568780 +128,180.0000,40255488,108.95122904 +128,200.0000,40235008,110.49910159 +128,0.0000,59996160,1983.31048452 +128,20.0000,59985920,626.34857548 +128,40.0000,60010496,368.59430691 +128,60.0000,60057600,261.79046116 +128,80.0000,59967488,203.58807089 +128,100.0000,60049408,169.08233531 +128,120.0000,59971584,157.73736227 +128,140.0000,60114944,160.65879173 +128,160.0000,60223488,162.18731759 +128,180.0000,59996160,161.53829468 +128,200.0000,59924480,163.08748512 +256,0.0000,5013504,150.61770745 +256,20.0000,4988928,47.98317123 +256,40.0000,5017600,28.28753389 +256,60.0000,5087232,22.64072721 +256,80.0000,5103616,16.68950179 +256,100.0000,4911104,14.98000289 +256,120.0000,5283840,14.57797348 +256,140.0000,4882432,13.77541610 +256,160.0000,4845568,14.82014057 +256,180.0000,5419008,15.12803483 +256,200.0000,5136384,14.70541008 +256,0.0000,20017152,604.26459415 +256,20.0000,20074496,185.24826468 +256,40.0000,20070400,111.28004115 +256,60.0000,20066304,79.38668143 +256,80.0000,20049920,63.10202060 +256,100.0000,20090880,51.86663441 +256,120.0000,20078592,50.72270412 +256,140.0000,20140032,51.45202403 +256,160.0000,20074496,52.34735768 +256,180.0000,20127744,51.68937072 +256,200.0000,20545536,53.00344362 +256,0.0000,39997440,1204.52354483 +256,20.0000,40030208,375.14825144 +256,40.0000,40140800,223.32498034 +256,60.0000,40132608,159.56046865 +256,80.0000,40099840,125.71707623 +256,100.0000,40181760,100.51217526 +256,120.0000,40157184,100.43270641 +256,140.0000,40280064,100.64522288 +256,160.0000,40148992,102.15382867 +256,180.0000,40255488,101.94711788 +256,200.0000,40235008,102.36566242 +256,0.0000,60014592,1806.82329404 +256,20.0000,59985920,565.52081444 +256,40.0000,60010496,332.29364735 +256,60.0000,60198912,236.76445795 +256,80.0000,60149760,183.21216869 +256,100.0000,60272640,154.06193670 +256,120.0000,60235776,148.90913669 +256,140.0000,60420096,151.22478667 +256,160.0000,60223488,151.85927289 +256,180.0000,60383232,152.24562470 +256,200.0000,59924480,152.63993869 +512,0.0000,5013504,142.09595461 +512,20.0000,4988928,45.24064794 +512,40.0000,5218304,29.34636966 +512,60.0000,5087232,20.44430592 +512,80.0000,5103616,15.39072112 +512,100.0000,5357568,14.58283811 +512,120.0000,5283840,14.51728184 +512,140.0000,4882432,13.60321648 +512,160.0000,5537792,16.47036773 +512,180.0000,4644864,13.15286274 +512,200.0000,5136384,14.70705770 +512,0.0000,20054016,566.64278397 +512,20.0000,19955712,174.11968271 +512,40.0000,20070400,104.98749936 +512,60.0000,20348928,80.52317964 +512,80.0000,20414464,59.20659123 +512,100.0000,20537344,52.24740857 +512,120.0000,20078592,50.66551019 +512,140.0000,20750336,52.65695668 +512,160.0000,20766720,54.27734687 +512,180.0000,20127744,51.96689063 +512,200.0000,20545536,53.21346524 +512,0.0000,40034304,1134.29439142 +512,20.0000,40148992,351.65354999 +512,40.0000,40140800,209.07256858 +512,60.0000,40132608,149.82002952 +512,80.0000,40099840,117.47349995 +512,100.0000,40181760,99.29140941 +512,120.0000,40157184,101.27779663 +512,140.0000,40280064,101.03142272 +512,160.0000,40148992,103.03220728 +512,180.0000,40255488,102.29715694 +512,200.0000,41091072,105.48587357 +512,0.0000,60014592,1696.32639982 +512,20.0000,60104704,529.27331581 +512,40.0000,60211200,314.64102828 +512,60.0000,59916288,223.66156868 +512,80.0000,60514304,176.47865061 +512,100.0000,59826176,147.96574328 +512,120.0000,60235776,148.99800895 +512,140.0000,59809792,150.35958604 +512,160.0000,60915712,154.38932471 +512,180.0000,60383232,152.93542751 +512,200.0000,59924480,153.33085468 +768,0.0000,4976640,138.05957366 +768,20.0000,4988928,43.80197995 +768,40.0000,5419008,29.07043259 +768,60.0000,5087232,19.27982188 +768,80.0000,5468160,16.08743332 +768,100.0000,5357568,16.01418018 +768,120.0000,4755456,14.06591053 +768,140.0000,5492736,16.69580199 +768,160.0000,6230016,19.93580198 +768,180.0000,4644864,13.97463414 +768,200.0000,5136384,15.71393382 +768,0.0000,20017152,553.83572853 +768,20.0000,19955712,172.62163178 +768,40.0000,19869696,101.91389205 +768,60.0000,20348928,76.63824887 +768,80.0000,20779008,61.13391313 +768,100.0000,20090880,56.72575162 +768,120.0000,20606976,57.56462426 +768,140.0000,20140032,57.15497858 +768,160.0000,20766720,60.39994772 +768,180.0000,20901888,59.63909139 +768,200.0000,20545536,59.31450737 +768,0.0000,40034304,1103.31084419 +768,20.0000,39911424,344.38523604 +768,40.0000,40341504,207.67400840 +768,60.0000,39849984,144.23887829 +768,80.0000,40464384,115.13071408 +768,100.0000,40181760,109.97555341 +768,120.0000,39628800,111.02510171 +768,140.0000,40280064,112.91707439 +768,160.0000,41533440,118.18861095 +768,180.0000,39481344,112.19747745 +768,200.0000,41091072,118.19195696 +768,0.0000,60051456,1658.44406107 +768,20.0000,60223488,518.00940045 +768,40.0000,60211200,306.90569389 +768,60.0000,60198912,219.74889785 +768,80.0000,60149760,171.73731088 +768,100.0000,60272640,164.85085667 +768,120.0000,60235776,167.30384060 +768,140.0000,60420096,169.56387362 +768,160.0000,60223488,169.83644005 +768,180.0000,60383232,171.76904069 +768,200.0000,61636608,175.84177408 +1024,0.0000,5013504,139.17866372 +1024,20.0000,5226496,46.12340810 +1024,40.0000,4816896,26.34263359 +1024,60.0000,5652480,21.12095630 +1024,80.0000,5832704,17.06023481 +1024,100.0000,5357568,15.00363730 +1024,120.0000,6340608,17.61010747 +1024,140.0000,4882432,14.72159233 +1024,160.0000,5537792,17.46984375 +1024,180.0000,6193152,17.43620161 +1024,200.0000,6848512,20.07246714 +1024,0.0000,20054016,546.85241362 +1024,20.0000,19955712,171.12057754 +1024,40.0000,20070400,103.01260733 +1024,60.0000,20348928,74.28560303 +1024,80.0000,20414464,58.28307529 +1024,100.0000,19644416,54.09770224 +1024,120.0000,21135360,56.99836811 +1024,140.0000,19529728,53.22264155 +1024,160.0000,19382272,54.60276421 +1024,180.0000,21676032,60.12091201 +1024,200.0000,20545536,57.00698594 +1024,0.0000,40108032,1091.38739473 +1024,20.0000,39911424,338.51258374 +1024,40.0000,40140800,202.00916172 +1024,60.0000,40697856,147.18881304 +1024,80.0000,40828928,114.61059605 +1024,100.0000,41074688,109.31525044 +1024,120.0000,40157184,109.29914385 +1024,140.0000,41500672,112.27782617 +1024,160.0000,41533440,114.43494438 +1024,180.0000,40255488,110.94630659 +1024,200.0000,41091072,114.40834800 +1024,0.0000,60014592,1634.14528740 +1024,20.0000,60342272,512.67767598 +1024,40.0000,60211200,304.16745205 +1024,60.0000,59916288,215.87478906 +1024,80.0000,59785216,169.18394829 +1024,100.0000,60719104,161.63374668 +1024,120.0000,61292544,164.43701924 +1024,140.0000,61030400,165.98778423 +1024,160.0000,60915712,166.81332822 +1024,180.0000,61931520,170.33031230 +1024,200.0000,61636608,170.74171172 diff --git a/results/Affinity/rslts/tEulerC.csv b/results/Affinity/rslts/storage/tEulerC.csv similarity index 100% rename from results/Affinity/rslts/tEulerC.csv rename to results/Affinity/rslts/storage/tEulerC.csv diff --git a/results/Affinity/rslts/tEulerS.csv b/results/Affinity/rslts/storage/tEulerS.csv similarity index 100% rename from results/Affinity/rslts/tEulerS.csv rename to results/Affinity/rslts/storage/tEulerS.csv diff --git a/results/Affinity/rslts/tHeatC.csv b/results/Affinity/rslts/storage/tHeatC.csv similarity index 100% rename from results/Affinity/rslts/tHeatC.csv rename to results/Affinity/rslts/storage/tHeatC.csv diff --git a/results/Affinity/rslts/tHeatS.csv b/results/Affinity/rslts/storage/tHeatS.csv similarity index 100% rename from results/Affinity/rslts/tHeatS.csv rename to results/Affinity/rslts/storage/tHeatS.csv diff --git a/results/Illustration/twod.py b/results/Illustration/twod.py deleted file mode 100644 index 2510e5e..0000000 --- a/results/Illustration/twod.py +++ /dev/null @@ -1,17 +0,0 @@ -from iglob import * - -plt.style.use('classic') -aniname = "papier" -ext = ".pdf" -plt.rcParams['hatch.color'] = 'k' - -sz = 80 -szbor = 2/3*sz -fc = 0 -markerz = '.' -lww = 2 - -def savePlot(fh, n, ip=impath): - plotfile = op.join(ip, aniname + "-" + str(n) + ext) - fh.tight_layout() - fh.savefig(plotfile, dpi=200, bbox_inches="tight") \ No newline at end of file diff --git a/results/Residual/EulerClassic/gpuAEulerClassic.pdf b/results/Residual/EulerClassic/gpuAEulerClassic.pdf deleted file mode 100644 index e09aa8a..0000000 Binary files a/results/Residual/EulerClassic/gpuAEulerClassic.pdf and /dev/null differ diff --git a/results/Residual/EulerClassic/nXEulerClassic.pdf b/results/Residual/EulerClassic/nXEulerClassic.pdf deleted file mode 100644 index cc39a25..0000000 Binary files a/results/Residual/EulerClassic/nXEulerClassic.pdf and /dev/null differ diff --git a/results/Residual/EulerClassic/tpbEulerClassic.pdf b/results/Residual/EulerClassic/tpbEulerClassic.pdf deleted file mode 100644 index 6edfed2..0000000 Binary files a/results/Residual/EulerClassic/tpbEulerClassic.pdf and /dev/null differ diff --git a/results/Residual/EulerSwept/gpuAEulerSwept.pdf b/results/Residual/EulerSwept/gpuAEulerSwept.pdf deleted file mode 100644 index da0a1de..0000000 Binary files a/results/Residual/EulerSwept/gpuAEulerSwept.pdf and /dev/null differ diff --git a/results/Residual/EulerSwept/nXEulerSwept.pdf b/results/Residual/EulerSwept/nXEulerSwept.pdf deleted file mode 100644 index 36c0276..0000000 Binary files a/results/Residual/EulerSwept/nXEulerSwept.pdf and /dev/null differ diff --git a/results/Residual/EulerSwept/tpbEulerSwept.pdf b/results/Residual/EulerSwept/tpbEulerSwept.pdf deleted file mode 100644 index 40a2006..0000000 Binary files a/results/Residual/EulerSwept/tpbEulerSwept.pdf and /dev/null differ diff --git a/results/Residual/HeatClassic/gpuAHeatClassic.pdf b/results/Residual/HeatClassic/gpuAHeatClassic.pdf deleted file mode 100644 index 91b0ccc..0000000 Binary files a/results/Residual/HeatClassic/gpuAHeatClassic.pdf and /dev/null differ diff --git a/results/Residual/HeatClassic/nXHeatClassic.pdf b/results/Residual/HeatClassic/nXHeatClassic.pdf deleted file mode 100644 index 156c0cb..0000000 Binary files a/results/Residual/HeatClassic/nXHeatClassic.pdf and /dev/null differ diff --git a/results/Residual/HeatClassic/tpbHeatClassic.pdf b/results/Residual/HeatClassic/tpbHeatClassic.pdf deleted file mode 100644 index 60aa5b2..0000000 Binary files a/results/Residual/HeatClassic/tpbHeatClassic.pdf and /dev/null differ diff --git a/results/Residual/HeatSwept/gpuAHeatSwept.pdf b/results/Residual/HeatSwept/gpuAHeatSwept.pdf deleted file mode 100644 index 76a68fe..0000000 Binary files a/results/Residual/HeatSwept/gpuAHeatSwept.pdf and /dev/null differ diff --git a/results/Residual/HeatSwept/nXHeatSwept.pdf b/results/Residual/HeatSwept/nXHeatSwept.pdf deleted file mode 100644 index 2b17531..0000000 Binary files a/results/Residual/HeatSwept/nXHeatSwept.pdf and /dev/null differ diff --git a/results/Residual/HeatSwept/tpbHeatSwept.pdf b/results/Residual/HeatSwept/tpbHeatSwept.pdf deleted file mode 100644 index d4661e5..0000000 Binary files a/results/Residual/HeatSwept/tpbHeatSwept.pdf and /dev/null differ diff --git a/results/tEulerS.csv b/results/tEulerS.csv deleted file mode 100644 index 7ed72b9..0000000 --- a/results/tEulerS.csv +++ /dev/null @@ -1,617 +0,0 @@ -tpb,gpuA,nX,time -64,20.0000,499200,2702.36179648 -64,20.0000,752640,3486.02045342 -64,20.0000,998400,5129.43396055 -64,20.0000,2503680,9290.56078314 -64,20.0000,4999680,21443.34438550 -64,20.0000,7503360,29186.07892981 -64,20.0000,9999360,37616.82068684 -64,24.0000,499712,2247.72534997 -64,24.0000,753664,3100.62946551 -64,24.0000,999424,4421.95342356 -64,24.0000,2498560,9698.40194362 -64,24.0000,5005312,19278.44521059 -64,24.0000,7503872,28040.80453289 -64,24.0000,10002432,33745.09863644 -64,28.0000,504832,2245.38420539 -64,28.0000,748544,3015.49052337 -64,28.0000,1000960,4284.74923054 -64,28.0000,2498048,9523.48956074 -64,28.0000,5004800,19119.79581255 -64,28.0000,7502848,26868.49675805 -64,28.0000,10000896,36275.19523243 -64,32.0000,506880,2274.31923270 -64,32.0000,755712,3340.28484099 -64,32.0000,1004544,3681.31471583 -64,32.0000,2506752,9230.85657961 -64,32.0000,5004288,18618.96440090 -64,32.0000,7501824,24758.80525739 -64,32.0000,9999360,34029.32771886 -64,36.0000,505856,1825.33341337 -64,36.0000,749056,3073.66263819 -64,36.0000,1001984,3722.18100198 -64,36.0000,2500096,9024.71813073 -64,36.0000,5000192,14735.39539305 -64,36.0000,7500288,23753.14393604 -64,36.0000,10000384,32818.54407721 -64,40.0000,501760,1768.31925533 -64,40.0000,747520,2875.13523938 -64,40.0000,1003520,3613.70215140 -64,40.0000,2498560,8359.67455727 -64,40.0000,5007360,15491.48037139 -64,40.0000,7505920,23044.04528730 -64,40.0000,10004480,30341.56845860 -64,44.0000,505344,1834.27215097 -64,44.0000,752640,2689.91113421 -64,44.0000,999936,3385.99453884 -64,44.0000,2505216,8110.30433710 -64,44.0000,4999680,16345.21764588 -64,44.0000,7504896,22402.29211006 -64,44.0000,9999360,29692.55431952 -64,48.0000,506880,1810.49530012 -64,48.0000,754688,2560.52963525 -64,48.0000,1002496,3527.02916143 -64,48.0000,2500608,7549.45745981 -64,48.0000,5001216,15121.65587262 -64,48.0000,7501824,20826.56852278 -64,48.0000,10002432,27386.18773531 -64,52.0000,506368,1824.90561350 -64,52.0000,753664,2495.79756621 -64,52.0000,1000960,3076.91506893 -64,52.0000,2508288,7286.93746951 -64,52.0000,5004800,14129.10905730 -64,52.0000,7501312,20488.80277402 -64,52.0000,9997824,29310.80728888 -64,56.0000,503808,1736.82348424 -64,56.0000,749568,2505.47186312 -64,56.0000,1007616,3242.19572117 -64,56.0000,2506752,7174.06847562 -64,56.0000,5001216,14809.19021772 -64,56.0000,7507968,20986.17830362 -64,56.0000,10002432,28352.09263986 -64,60.0000,499200,1629.94671628 -64,60.0000,755200,2487.17525566 -64,60.0000,998400,3320.13568080 -64,60.0000,2508800,7026.60331926 -64,60.0000,5004800,13648.24704203 -64,60.0000,7500800,21716.10182975 -64,60.0000,10009600,28025.78339064 -96,20.0000,506880,2544.01712427 -96,20.0000,748800,3410.02276492 -96,20.0000,1002240,4557.59501173 -96,20.0000,2499840,10883.25844871 -96,20.0000,4999680,18828.13817688 -96,20.0000,7499520,29193.75399748 -96,20.0000,9999360,38682.71824386 -96,24.0000,503808,2260.77532011 -96,24.0000,749568,3234.34919119 -96,24.0000,1007616,4467.97990137 -96,24.0000,2506752,9929.44694701 -96,24.0000,5001216,19228.58902623 -96,24.0000,7507968,28743.02556590 -96,24.0000,10002432,34247.42930229 -96,28.0000,509184,2198.43554355 -96,28.0000,757248,3105.31696157 -96,28.0000,1005312,4139.76562402 -96,28.0000,2506752,9408.31449060 -96,28.0000,5000448,17168.53276132 -96,28.0000,7507200,25491.01737520 -96,28.0000,10000896,32066.13914125 -96,32.0000,497664,1910.92041750 -96,32.0000,760320,2928.72992300 -96,32.0000,1009152,4068.28747382 -96,32.0000,2502144,9468.20533228 -96,32.0000,5004288,17230.99724641 -96,32.0000,7506432,24826.84997339 -96,32.0000,10008576,35730.01116987 -96,36.0000,510720,1990.10069408 -96,36.0000,758784,2730.59497750 -96,36.0000,1006848,3366.30110230 -96,36.0000,2509824,8241.53423309 -96,36.0000,5005056,16206.85368303 -96,36.0000,7500288,24738.73065578 -96,36.0000,10010112,32164.41218106 -96,40.0000,506880,2006.26537913 -96,40.0000,752640,2429.17730458 -96,40.0000,998400,3532.22866617 -96,40.0000,2503680,7600.75396725 -96,40.0000,5007360,15551.72767904 -96,40.0000,7511040,22070.52453406 -96,40.0000,9999360,28064.10465449 -96,44.0000,499968,1673.43256966 -96,44.0000,758016,2901.39084534 -96,44.0000,999936,3329.07143803 -96,44.0000,2499840,7245.15378002 -96,44.0000,4999680,15297.37124367 -96,44.0000,7499520,18885.72052121 -96,44.0000,9999360,27639.27059751 -96,48.0000,506880,1617.31994105 -96,48.0000,760320,2297.19298936 -96,48.0000,996864,3064.03424059 -96,48.0000,2500608,8205.64082454 -96,48.0000,5001216,13426.25023117 -96,48.0000,7501824,20178.75222696 -96,48.0000,10002432,27499.46677969 -96,52.0000,512256,1587.60962742 -96,52.0000,759552,2267.82262325 -96,52.0000,1006848,2868.81720263 -96,52.0000,2508288,7466.44743615 -96,52.0000,4998912,13921.66742257 -96,52.0000,7507200,20722.73313053 -96,52.0000,9997824,26382.23459796 -96,56.0000,497664,1542.27160272 -96,56.0000,755712,2383.84844528 -96,56.0000,1013760,2865.11260839 -96,56.0000,2506752,6924.19743254 -96,56.0000,5013504,13925.36781847 -96,56.0000,7501824,20016.22892798 -96,56.0000,10008576,26531.44418247 -96,60.0000,499200,1569.87671341 -96,60.0000,748800,2391.50746474 -96,60.0000,998400,2774.18105139 -96,60.0000,2496000,7318.98241100 -96,60.0000,5011200,13876.51217362 -96,60.0000,7507200,20396.74078188 -96,60.0000,10003200,27069.83165135 -128,20.0000,506880,2339.84425191 -128,20.0000,752640,2994.78795320 -128,20.0000,998400,4375.77825690 -128,20.0000,2503680,10267.47121461 -128,20.0000,5007360,19392.54064882 -128,20.0000,7511040,28653.28148953 -128,20.0000,9999360,37611.09224861 -128,24.0000,507904,2391.00549666 -128,24.0000,753664,2873.45560297 -128,24.0000,999424,4243.75645225 -128,24.0000,2506752,9150.15299642 -128,24.0000,4997120,18958.83703043 -128,24.0000,7503872,26516.55626675 -128,24.0000,10010624,35392.24873696 -128,28.0000,504832,2126.37252278 -128,28.0000,748544,2746.95361417 -128,28.0000,1009664,3945.54613602 -128,28.0000,2506752,9492.09224847 -128,28.0000,4996096,16552.81547989 -128,28.0000,7502848,24398.13268563 -128,28.0000,10009600,34443.37874414 -128,32.0000,497664,1701.38590629 -128,32.0000,755712,2959.21947275 -128,32.0000,1013760,3958.95014443 -128,32.0000,2506752,8970.39538102 -128,32.0000,5013504,15539.72225104 -128,32.0000,7501824,25145.49108252 -128,32.0000,10008576,31751.38540211 -128,36.0000,505856,1700.56397716 -128,36.0000,758784,2841.61980427 -128,36.0000,1011712,3299.25297272 -128,36.0000,2509824,9186.77703492 -128,36.0000,5000192,16167.05451456 -128,36.0000,7510016,22851.31102517 -128,36.0000,10000384,29271.56993084 -128,40.0000,512000,1761.29017084 -128,40.0000,757760,2474.97419043 -128,40.0000,1003520,3388.07761196 -128,40.0000,2498560,7763.78567966 -128,40.0000,4997120,15300.72642934 -128,40.0000,7495680,22888.83427779 -128,40.0000,10014720,27486.73462442 -128,44.0000,516096,1826.17733639 -128,44.0000,752640,2733.75372802 -128,44.0000,1010688,3437.67009557 -128,44.0000,2515968,7486.01266079 -128,44.0000,5010432,13735.53695896 -128,44.0000,7504896,22006.43824680 -128,44.0000,9999360,28871.63464985 -128,48.0000,495616,1501.67114205 -128,48.0000,765952,2449.49604311 -128,48.0000,1013760,3006.50990435 -128,48.0000,2500608,7435.11957782 -128,48.0000,5001216,13803.60463545 -128,48.0000,7501824,20762.38340565 -128,48.0000,10002432,27482.86635393 -128,52.0000,494592,1660.36803571 -128,52.0000,753664,2179.87626554 -128,52.0000,1012736,2941.72822956 -128,52.0000,2496512,7118.79264268 -128,52.0000,5016576,13763.90977511 -128,52.0000,7513088,19998.10610026 -128,52.0000,10009600,27015.87277272 -128,56.0000,516096,1569.98315028 -128,56.0000,761856,2161.24798097 -128,56.0000,1007616,2747.01806761 -128,56.0000,2506752,6899.46304238 -128,56.0000,5013504,13447.07413089 -128,56.0000,7495680,19427.81424002 -128,56.0000,10002432,26622.46254465 -128,60.0000,512000,1471.86006818 -128,60.0000,768000,2228.17636908 -128,60.0000,998400,2789.19272953 -128,60.0000,2508800,7026.50448869 -128,60.0000,5017600,13648.58927471 -128,60.0000,7500800,20417.56675120 -128,60.0000,10009600,27449.63392615 -192,20.0000,506880,2305.50369810 -192,20.0000,760320,2977.94940453 -192,20.0000,1013760,4564.39183345 -192,20.0000,2511360,8873.70115471 -192,20.0000,4999680,19524.56671094 -192,20.0000,7511040,27672.47399167 -192,20.0000,9999360,37471.01068970 -192,24.0000,516096,2239.70087984 -192,24.0000,761856,3374.24998482 -192,24.0000,1007616,4232.57265772 -192,24.0000,2506752,9452.49531004 -192,24.0000,5013504,17293.40774436 -192,24.0000,7495680,26579.83280600 -192,24.0000,10002432,34044.11951464 -192,28.0000,496128,1812.65896748 -192,28.0000,757248,2663.86633591 -192,28.0000,1018368,3938.28199733 -192,28.0000,2506752,7885.16746390 -192,28.0000,5013504,17044.77826281 -192,28.0000,7494144,24525.96779617 -192,28.0000,10000896,31746.03842790 -192,32.0000,497664,1779.26239040 -192,32.0000,746496,2863.71751674 -192,32.0000,995328,3652.96952308 -192,32.0000,2515968,8552.18228840 -192,32.0000,5004288,15484.52332379 -192,32.0000,7520256,21249.19423035 -192,32.0000,10008576,31307.41665761 -192,36.0000,496128,1668.28492804 -192,36.0000,758784,2753.23859283 -192,36.0000,1021440,3309.07514408 -192,36.0000,2509824,8171.21825521 -192,36.0000,5019648,15757.28795595 -192,36.0000,7500288,21351.62351150 -192,36.0000,10010112,30927.86255810 -192,40.0000,522240,1609.91518743 -192,40.0000,768000,2277.33086499 -192,40.0000,1013760,3541.82164347 -192,40.0000,2519040,7485.79139038 -192,40.0000,5007360,13893.30235266 -192,40.0000,7495680,20728.85939999 -192,40.0000,10014720,27319.18975238 -192,44.0000,516096,1881.89059023 -192,44.0000,774144,2387.11363266 -192,44.0000,999936,2913.40650311 -192,44.0000,2515968,7402.83508859 -192,44.0000,4999680,14016.98293667 -192,44.0000,7515648,18823.12452746 -192,44.0000,9999360,25003.12503368 -192,48.0000,506880,1584.99258142 -192,48.0000,743424,2382.80057434 -192,48.0000,1013760,3189.98731081 -192,48.0000,2500608,6753.88815857 -192,48.0000,5001216,13568.08480526 -192,48.0000,7501824,19371.05406135 -192,48.0000,10002432,24784.48413904 -192,52.0000,494592,1418.40895254 -192,52.0000,741888,1938.46006952 -192,52.0000,1024512,2790.23510123 -192,52.0000,2508288,7024.06844449 -192,52.0000,5016576,13458.43727153 -192,52.0000,7524864,20052.78845392 -192,52.0000,9997824,25549.15821741 -192,56.0000,516096,1575.26957374 -192,56.0000,774144,2157.74307412 -192,56.0000,995328,2977.01583495 -192,56.0000,2506752,6940.35466701 -192,56.0000,5013504,13007.16743110 -192,56.0000,7520256,20474.53300347 -192,56.0000,10027008,26258.42356966 -192,60.0000,499200,1513.51833391 -192,60.0000,768000,2119.04984381 -192,60.0000,998400,2735.05580567 -192,60.0000,2496000,6738.64486199 -192,60.0000,4992000,13561.39631262 -192,60.0000,7526400,20232.44714217 -192,60.0000,10022400,26682.27509610 -256,20.0000,522240,2201.57342061 -256,20.0000,768000,3328.42708107 -256,20.0000,1013760,4150.35816176 -256,20.0000,2519040,8938.58282102 -256,20.0000,5007360,17371.07265563 -256,20.0000,7495680,27344.50221298 -256,20.0000,10014720,35606.02706340 -256,24.0000,524288,1928.27506671 -256,24.0000,753664,2713.26534095 -256,24.0000,1015808,3490.10219650 -256,24.0000,2523136,8811.56254382 -256,24.0000,5013504,18051.83255956 -256,24.0000,7503872,25456.74157048 -256,24.0000,9994240,33681.31296029 -256,28.0000,522240,2241.49055661 -256,28.0000,765952,2837.30059626 -256,28.0000,1009664,3636.60887593 -256,28.0000,2506752,8235.39383118 -256,28.0000,5013504,17415.11883244 -256,28.0000,7520256,24803.23884695 -256,28.0000,9992192,32135.73513286 -256,32.0000,516096,1846.70238504 -256,32.0000,774144,2434.02030023 -256,32.0000,995328,3502.94871226 -256,32.0000,2506752,7643.42285101 -256,32.0000,5013504,15630.41391117 -256,32.0000,7520256,22905.91520686 -256,32.0000,10027008,29800.43100459 -256,36.0000,505856,1811.71924822 -256,36.0000,778240,2502.28695453 -256,36.0000,1011712,3386.64408478 -256,36.0000,2490368,7790.62154747 -256,36.0000,5019648,15526.17656333 -256,36.0000,7510016,20652.14331424 -256,36.0000,10000384,29283.86108270 -256,40.0000,491520,1794.40498589 -256,40.0000,778240,2677.00945574 -256,40.0000,1024000,3158.38318969 -256,40.0000,2498560,7084.38071703 -256,40.0000,4997120,13465.52803639 -256,40.0000,7495680,20483.04541007 -256,40.0000,9994240,26909.70460101 -256,44.0000,516096,1763.27007394 -256,44.0000,774144,2306.23095755 -256,44.0000,1032192,3064.23038008 -256,44.0000,2494464,6554.34327939 -256,44.0000,5031936,14118.48438401 -256,44.0000,7526400,19925.01093755 -256,44.0000,10020864,25627.20387701 -256,48.0000,495616,1447.45184789 -256,48.0000,765952,2119.82937559 -256,48.0000,991232,3018.83210029 -256,48.0000,2523136,7338.33505757 -256,48.0000,5001216,13116.06346142 -256,48.0000,7524352,19959.09078017 -256,48.0000,10002432,24681.81253662 -256,52.0000,518144,1345.00595076 -256,52.0000,753664,2130.56524831 -256,52.0000,989184,2752.08777378 -256,52.0000,2496512,6409.87173196 -256,52.0000,4993024,13098.19466301 -256,52.0000,7489536,19660.92457610 -256,52.0000,10033152,25534.59824551 -256,56.0000,491520,1372.67113915 -256,56.0000,786432,2387.78075529 -256,56.0000,1032192,2763.67661972 -256,56.0000,2506752,6536.18101090 -256,56.0000,5013504,13824.53792862 -256,56.0000,7520256,20313.77626080 -256,56.0000,10027008,26310.13148597 -256,60.0000,512000,1439.31303469 -256,60.0000,768000,2220.93399082 -256,60.0000,1024000,2802.69395028 -256,60.0000,2508800,6748.91590126 -256,60.0000,5017600,13604.14656145 -256,60.0000,7526400,20309.30626724 -256,60.0000,10035200,27000.88090367 -384,20.0000,506880,2107.63271465 -384,20.0000,783360,2895.41448272 -384,20.0000,1013760,3741.97769304 -384,20.0000,2534400,9882.51040148 -384,20.0000,5022720,17179.70739732 -384,20.0000,7511040,25677.83015412 -384,20.0000,9999360,34334.75481678 -384,24.0000,491520,2025.26042397 -384,24.0000,786432,2978.66640396 -384,24.0000,1032192,3899.16137900 -384,24.0000,2506752,8918.13878403 -384,24.0000,5013504,17190.77636105 -384,24.0000,7520256,24634.13930910 -384,24.0000,10027008,32570.99510163 -384,28.0000,522240,1796.52500060 -384,28.0000,783360,2885.66178823 -384,28.0000,992256,3253.52323148 -384,28.0000,2506752,7856.28660012 -384,28.0000,5013504,16468.82873173 -384,28.0000,7520256,22428.08529111 -384,28.0000,10027008,30674.38905091 -384,32.0000,497664,1876.01022018 -384,32.0000,774144,2410.23209668 -384,32.0000,995328,3442.80690648 -384,32.0000,2488320,7161.18849525 -384,32.0000,5031936,15276.43359678 -384,32.0000,7520256,22162.79310311 -384,32.0000,10008576,27919.95225951 -384,36.0000,525312,2070.76262134 -384,36.0000,758784,2475.65939907 -384,36.0000,992256,2994.97260604 -384,36.0000,2509824,7131.35486887 -384,36.0000,5019648,14426.01814751 -384,36.0000,7529472,21115.10730298 -384,36.0000,10039296,27743.91080751 -384,40.0000,491520,1505.22404863 -384,40.0000,737280,2584.85343336 -384,40.0000,1044480,3151.02882857 -384,40.0000,2519040,6711.72090048 -384,40.0000,5038080,13957.63173815 -384,40.0000,7495680,20612.32606801 -384,40.0000,10014720,26997.58551380 -384,44.0000,516096,1548.10098484 -384,44.0000,774144,2464.55595475 -384,44.0000,1032192,3397.44690546 -384,44.0000,2515968,7188.84955543 -384,44.0000,5031936,12885.39685251 -384,44.0000,7547904,19670.28395612 -384,44.0000,9999360,25935.65431907 -384,48.0000,540672,1519.06370424 -384,48.0000,743424,2080.23207825 -384,48.0000,1013760,2751.29432133 -384,48.0000,2500608,6347.90939647 -384,48.0000,5001216,12510.25388176 -384,48.0000,7501824,19203.05619868 -384,48.0000,10002432,25339.37817396 -384,52.0000,494592,1343.76332510 -384,52.0000,777216,2108.84496454 -384,52.0000,989184,2572.53999165 -384,52.0000,2543616,6786.57607515 -384,52.0000,5016576,13098.22678797 -384,52.0000,7489536,18858.24275109 -384,52.0000,10033152,25253.63371585 -384,56.0000,516096,1484.23934399 -384,56.0000,737280,2187.13514565 -384,56.0000,1032192,2795.22456171 -384,56.0000,2506752,6666.02394840 -384,56.0000,5013504,13274.17438575 -384,56.0000,7520256,19866.91061147 -384,56.0000,10027008,26134.06639922 -384,60.0000,537600,1511.47629864 -384,60.0000,768000,2135.94838630 -384,60.0000,998400,2748.49683046 -384,60.0000,2534400,7226.59956808 -384,60.0000,4992000,13352.11213707 -384,60.0000,7526400,20192.72213296 -384,60.0000,9984000,26670.66229637 -512,20.0000,491520,1823.53780838 -512,20.0000,737280,2698.03463016 -512,20.0000,1044480,3782.71582304 -512,20.0000,2519040,9285.65522190 -512,20.0000,5038080,18439.21339605 -512,20.0000,7495680,26817.90309725 -512,20.0000,10014720,34285.16653366 -512,24.0000,524288,1904.46822671 -512,24.0000,786432,2953.17725977 -512,24.0000,1048576,3953.94506631 -512,24.0000,2490368,8711.92873456 -512,24.0000,5046272,17901.66721912 -512,24.0000,7536640,24927.12275125 -512,24.0000,10027008,32288.99999522 -512,28.0000,487424,1666.73265630 -512,28.0000,765952,2613.39399731 -512,28.0000,1044480,3281.86963452 -512,28.0000,2506752,8371.05733808 -512,28.0000,5013504,16122.04272533 -512,28.0000,7520256,22494.17232815 -512,28.0000,10027008,29862.44676867 -512,32.0000,516096,1723.15869713 -512,32.0000,737280,2388.60765239 -512,32.0000,1032192,3106.09594453 -512,32.0000,2506752,7399.43503868 -512,32.0000,5013504,15064.61156532 -512,32.0000,7520256,22510.60935669 -512,32.0000,10027008,29147.49999763 -512,36.0000,544768,1690.24564093 -512,36.0000,778240,2631.86014490 -512,36.0000,1011712,3088.61379744 -512,36.0000,2490368,7418.34595101 -512,36.0000,4980736,14776.91699984 -512,36.0000,7548928,22885.04276657 -512,36.0000,10039296,30138.90184229 -512,40.0000,491520,1612.02973686 -512,40.0000,737280,2367.53030913 -512,40.0000,983040,3171.42676795 -512,40.0000,2539520,8156.92526521 -512,40.0000,4997120,15639.93969467 -512,40.0000,7536640,23593.45287550 -512,40.0000,9994240,31282.43063111 -512,44.0000,516096,1708.97337375 -512,44.0000,774144,2654.47364654 -512,44.0000,1032192,3498.02710116 -512,44.0000,2494464,8196.81637222 -512,44.0000,4988928,16370.97407365 -512,44.0000,7483392,24575.14306298 -512,44.0000,10063872,32970.89133412 -512,48.0000,540672,1885.11767192 -512,48.0000,811008,2795.33298453 -512,48.0000,991232,3494.60029975 -512,48.0000,2523136,8615.38940808 -512,48.0000,5046272,17270.48540488 -512,48.0000,7479296,25534.06514926 -512,48.0000,10002432,34123.40965588 -512,52.0000,565248,2031.18281206 -512,52.0000,753664,2685.56078663 -512,52.0000,1036288,3690.20947255 -512,52.0000,2543616,9023.59961765 -512,52.0000,4993024,17661.06300056 -512,52.0000,7536640,26659.13692908 -512,52.0000,9986048,35301.53416796 -512,56.0000,491520,1819.36885929 -512,56.0000,786432,2895.30103328 -512,56.0000,983040,3618.22068226 -512,56.0000,2555904,9342.61572547 -512,56.0000,5013504,18302.54076049 -512,56.0000,7569408,27615.05934177 -512,56.0000,10027008,36571.77026616 -512,60.0000,512000,1955.19626141 -512,60.0000,819200,3094.56762625 -512,60.0000,1024000,3864.25759643 -512,60.0000,2560000,9630.66605618 -512,60.0000,5017600,18832.71773113 -512,60.0000,7475200,28057.51736742 -512,60.0000,10035200,37645.29078035 -768,20.0000,552960,2401.10397113 -768,20.0000,737280,2931.31556475 -768,20.0000,1013760,3506.37852468 -768,20.0000,2488320,8912.93895741 -768,20.0000,5068800,17965.78694925 -768,20.0000,7557120,25937.46877304 -768,20.0000,10045440,34228.45595262 -768,24.0000,491520,1844.27371079 -768,24.0000,786432,2717.41995080 -768,24.0000,983040,3790.03431987 -768,24.0000,2555904,8743.24904924 -768,24.0000,5013504,16544.87097579 -768,24.0000,7569408,24474.77180624 -768,24.0000,10027008,32245.24855614 -768,28.0000,522240,1886.29453381 -768,28.0000,731136,2434.68159302 -768,28.0000,1044480,3406.91220128 -768,28.0000,2506752,8367.47845240 -768,28.0000,5013504,16524.67967660 -768,28.0000,7520256,22463.55920127 -768,28.0000,10027008,31126.25471796 -768,32.0000,552960,1992.89179661 -768,32.0000,774144,2591.28974920 -768,32.0000,995328,2871.56343234 -768,32.0000,2543616,7358.49000965 -768,32.0000,4976640,14799.82720180 -768,32.0000,7520256,21684.70925905 -768,32.0000,10063872,29126.77344725 -768,36.0000,583680,1752.96492649 -768,36.0000,817152,2455.76605878 -768,36.0000,1050624,2984.82952922 -768,36.0000,2568192,6877.36859827 -768,36.0000,5019648,13734.88472944 -768,36.0000,7471104,20466.90717565 -768,36.0000,10039296,26852.06863239 -768,40.0000,491520,1331.49382291 -768,40.0000,737280,2206.34562500 -768,40.0000,983040,2748.50354727 -768,40.0000,2580480,7297.15485464 -768,40.0000,5038080,13657.70427792 -768,40.0000,7495680,19072.01043584 -768,40.0000,10076160,25941.73389177 -768,44.0000,516096,1453.23151215 -768,44.0000,774144,2062.97940829 -768,44.0000,1032192,2884.28716136 -768,44.0000,2580480,6753.54756866 -768,44.0000,5031936,12885.93278238 -768,44.0000,7483392,18609.07148908 -768,44.0000,10063872,25202.96660562 -768,48.0000,540672,1563.63325589 -768,48.0000,811008,2089.02460608 -768,48.0000,1081344,3011.51824268 -768,48.0000,2568192,6308.48860425 -768,48.0000,5001216,12259.09901162 -768,48.0000,7569408,18510.55257474 -768,48.0000,10002432,24275.62805965 -768,52.0000,565248,1456.89347251 -768,52.0000,847872,2192.68729967 -768,52.0000,989184,2658.01037577 -768,52.0000,2543616,6530.24808024 -768,52.0000,5087232,12916.68821465 -768,52.0000,7489536,18852.30754587 -768,52.0000,10033152,25323.86649964 -768,56.0000,589824,1617.65860111 -768,56.0000,737280,2041.13379798 -768,56.0000,1032192,2734.16450981 -768,56.0000,2506752,6703.00260412 -768,56.0000,5013504,13003.08644546 -768,56.0000,7520256,19504.15720542 -768,56.0000,10027008,26001.44888415 -768,60.0000,614400,1654.70599225 -768,60.0000,768000,2142.62571976 -768,60.0000,1075200,2938.99711334 -768,60.0000,2611200,6994.76796118 -768,60.0000,5068800,13503.47556625 -768,60.0000,7526400,20063.69366339 -768,60.0000,9984000,26616.20904550 diff --git a/results/timings.m b/results/timings.m deleted file mode 100644 index 69e13cf..0000000 --- a/results/timings.m +++ /dev/null @@ -1,12 +0,0 @@ -clear -clc -close all - -notefile = fileread('notes.json'); -jj = jsondecode(notefile); -fname = fieldnames(jj); -for k = 1:length(fname) - f = fname{k} -end - -h5disp('rawResults.h5', strcat('/',fname{end})) diff --git a/runtools/main_help.py b/runtools/main_help.py index 8c6d320..cb47291 100644 --- a/runtools/main_help.py +++ b/runtools/main_help.py @@ -92,7 +92,6 @@ def saveplot(f, cat, rundetail, titler): plotname = op.join(plotpath, titler + ".pdf") f.savefig(plotname, bbox_inches='tight') - #Divisions and threads per block need to be lists (even singletons) at least. def runMPICUDA(exece, nproc, scheme, eqfile, mpiopt="", outdir=" rslts ", eqopt=""): diff --git a/runtools/timing_analysis.py b/runtools/timing_analysis.py index b43bd31..0ea205b 100644 --- a/runtools/timing_analysis.py +++ b/runtools/timing_analysis.py @@ -106,16 +106,23 @@ def plotRaws(iobj, subax, respvar, nstep): return figC -def plotmins(df, axi, sidx, stacker=['nX', 'gpuA']): +# minmax is either min or max. (Best run is min time and max efficiency) +# or none if skip it. +def plotmins(df, axi, sidx, stacker=['nX', 'gpuA'], minmax="min"): + if not minmax: + return None + dff = df.stack(stacker[0]) dfff = dff.unstack(stacker[1]) - mnplace = dfff.idxmin(axis=1) + mnplace = dfff.idxmax(axis=1) if minmax=="max" else dfff.idxmin(axis=1) + for a, si in zip(axi, sidx): a.plot(mnplace[si][0], mnplace[si][1], 'r.', markersize=20) return mnplace -def contourRaw(df, typs, tytle=None, vals='time', getfig=False): +#Returns extemis values and locations in mns. Returns figure handle if getFig is true. +def contourRaw(df, typs, tytle=None, vals='time', getfig=False, minmax="min"): anno = {'ti':'10000' , 'yl': 'GPU Affinity', 'xl': 'threads per block'} dfCont = pd.pivot_table(df, values=vals, index='gpuA', columns=['nX', 'tpb']) fCont, axCont = plt.subplots(2, 2, figsize=boxfigsize) @@ -131,12 +138,12 @@ def contourRaw(df, typs, tytle=None, vals='time', getfig=False): if tytle: fCont.suptitle(tytle + " -- " + meas[vals]) - if getfig: - return dfCont, fCont, axc - - mns = plotmins(dfCont, axc, subidx) + mns = plotmins(dfCont, axc, subidx, minmax=minmax) formatSubplot(fCont) + if getfig: + return fCont, mns + saveplot(fCont, "Performance", plotDir, "RawContour"+typs+vals) plt.close(fCont) @@ -208,8 +215,6 @@ def saveplot(f, *args): if titles: fio.suptitle("Best interpolated run vs observation") perfPath = op.join(resultpath,"Performance") - mnCoords = pd.DataFrame() - axdct = dict(zip(eqs, axio.ravel())) for ke, ie in collInst.items(): @@ -225,7 +230,7 @@ def saveplot(f, *args): ists = iss.iFrame.set_index('nX') iss.efficient() - mnCoords[typ] = contourRaw(iss.iFrame, typ, tytles) + contourRaw(iss.iFrame, typ, tytles) fRawS = plotRaws(iss, 'tpb', ['time', 'efficiency'], 2) for rsub, it in fRawS.items(): diff --git a/src/hFinish.sh b/src/shellLaunch/OSU_cluster/hFinish.sh similarity index 100% rename from src/hFinish.sh rename to src/shellLaunch/OSU_cluster/hFinish.sh