gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Porting GA for all the operations

Browse Source
This commit is contained in:
Philippe Tillet
2014-10-03 09:29:45 +02:00
parent 2f6d41f661
commit 044419f9f0
6 changed files with 76 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
autotune/python/model.py
View File

@@ -13,12 +13,13 @@ def train_model(X, Y, profiles):
Xmean = np.mean(X, axis=0)
Xstd = np.std(X, axis=0)
X = (X - Xmean)/Xstd
Ymax = np.max(Y)
Y = Y/Ymax
ref = np.argmax(np.bincount(np.argmax(Y, axis=1))) #most common profile
#Cross-validation data-sets
cut = int(0.1*X.shape[0]+1)
cut = int(0.800*X.shape[0]+1)
XTr = X[0:cut, :]
YTr = Y[0:cut, :]
XTe = X[cut:,:]
@@ -26,23 +27,15 @@ def train_model(X, Y, profiles):
#Train the model
print("Training the model...")
ds = SupervisedDataSet(X.shape[1], Y.shape[1])
for idx, x in enumerate(X):
ds.addSample(x, Y[idx,:])
clf = buildNetwork(*[X.shape[1], 100, Y.shape[1]], hiddenclass = TanhLayer, outclass = LinearLayer)
#print fnn;
#trainer = RPropMinusTrainer( fnn, dataset=ds, verbose=True);
trainer = BackpropTrainer( clf, dataset=ds, verbose=True, momentum=0.01, weightdecay=0.01, learningrate=0.002, batchlearning=False)
trainer.trainUntilConvergence(maxEpochs=100)
clf = ensemble.RandomForestRegressor(40).fit(XTr,YTr)
#Evaluate the model
GFlops = np.empty(XTe.shape[0])
speedups = np.empty(XTe.shape[0])
optspeedups = np.empty(XTe.shape[0])
for i,x in enumerate(XTe):
predictions = clf.activate(x)
predictions = clf.predict(x)
label = np.argmax(predictions)
# print YTe[i,label], YTe[i,ref], np.max(YTe[i,:])
speedups[i] = YTe[i,label]/YTe[i,ref]
optspeedups[i] = np.max(YTe[i,:])/YTe[i,ref]
GFlops[i] = YTe[i,ref]*Ymax
@@ -52,7 +45,5 @@ def train_model(X, Y, profiles):
print("Average testing speedup : %f (Optimal : %f)"%(sp.stats.gmean(speedups), sp.stats.gmean(optspeedups)))
print("Average GFLOP/s : %f (Default %f, Optimal %f)"%(np.mean(np.multiply(GFlops,speedups)), np.mean(GFlops), np.mean(np.multiply(GFlops,optspeedups))))
print("Minimum speedup is %f wrt %i GFlops"%(np.min(speedups), GFlops[np.argmin(speedups)]))
print("Maximum speedup is %f wrt %i GFlops"%(np.max(speedups), GFlops[np.argmax(speedups)]))
print("--------")
print clf
print("Maximum speedup is %f wrt %i GFlops for %s"%(np.max(speedups), GFlops[np.argmax(speedups)], X[np.argmax(speedups)]*Xstd+Xmean))
print("--------")