def valueMonteCarloGPU(ctx,queue,S_init,nPaths,Exp_Time, dtMonte,Strike,Int_Rate,Vol,PTYPE, nMonteLoops=1):
nextStepPathKernel = ElementwiseKernel(ctx,"float *latestStep, float *ran, float Strike, float Int_Rate, float Exp_Time, float dt, float Vol","float rval = exp((Int_Rate - 0.5f * Vol*Vol)*dt + Vol * sqrt(dt) * ran[i]); latestStep[i] *= rval;","nextStepPathKernel")
excersisePriceKernel = ElementwiseKernel(ctx,"float *latestStep, float Strike, float Int_Rate, float Exp_Time","float rval = (latestStep[i]-Strike); latestStep[i] = exp(-Int_Rate*Exp_Time) * max(rval,0.0f);","excersisePriceKernel")
sumKernel = ReductionKernel(ctx, numpy.float32, neutral="0", reduce_expr="a+b", map_expr="x[i]", arguments="__global float *x")
maxWorkItems = 1*2**9
multiplier = 1
if(nPaths > maxWorkItems):
multiplier = math.ceil(nPaths/maxWorkItems)
nPaths = multiplier * maxWorkItems
else:
maxWorkItems = nPaths
#print(maxWorkItems, multiplier, nPaths)
nTimeStepsMonte = math.ceil(Exp_Time/dtMonte)
#print(nTimeStepsMonte,nMonteLoops)
#set up random number generator
gen = RanluxGenerator(queue, maxWorkItems, luxury=4, seed=time.time())
#the arrays
ran = cl.array.zeros(queue, maxWorkItems, numpy.float32)
latestStep = cl.array.zeros_like(ran)
means = numpy.zeros(nMonteLoops)
theMean = 0
#the loop
for loop in range(nMonteLoops):
theSum = 0
for mult in range(multiplier):
latestStep.fill(S_init)
for t in range(nTimeStepsMonte):
gen.fill_normal(ran)
gen.synchronize(queue)
nextStepPathKernel(latestStep, ran, Strike, Int_Rate, Exp_Time, dtMonte, Vol)
excersisePriceKernel(latestStep, Strike, Int_Rate, Exp_Time)
#print(latestStep)
#add to array
theSum += sumKernel(latestStep, queue).get()
means[loop] = theSum / nPaths
monteAverage = numpy.mean(means)
monteStdDeviation = numpy.std(means)
return monteAverage,dtMonte, monteStdDeviation
ran = cl.array.zeros(queue, nPaths, numpy.float32)
latestStep = cl.array.empty_like(ran)
averages = numpy.zeros(nLoops)
#averages = cl.array.zeros(queue, nLoops, numpy.float32)
tStartMonte = time.time()
theSum = 0
for loop in range(0,nLoops):
latestStep.fill(S_init)
for t in range(0,nTimeStepsMonte):
gen.fill_normal(ran)
gen.synchronize(queue)
nextStepPathKernel(latestStep, ran, Strike, Int_Rate, Exp_Time, dtMonte, Vol)
excersisePriceKernel(latestStep, Strike, Int_Rate, Exp_Time)
#theSum = cl.array.sum(latestStep).get()
latestStep_numpy = latestStep.get()
theSum = numpy.sum(latestStep_numpy)
#theSum = sumKernel(latestStep).get()
if(theSum == 0):
print("theSum was zero")
def valueMonteCarloGPU(ctx,
queue,
S_init,
nPaths,
Exp_Time,
dtMonte,
Strike,
Int_Rate,
Vol,
PTYPE,
nMonteLoops=1):
nextStepPathKernel = ElementwiseKernel(
ctx,
"float *latestStep, float *ran, float Strike, float Int_Rate, float Exp_Time, float dt, float Vol",
"float rval = exp((Int_Rate - 0.5f * Vol*Vol)*dt + Vol * sqrt(dt) * ran[i]); latestStep[i] *= rval;",
"nextStepPathKernel")
excersisePriceKernel = ElementwiseKernel(
ctx, "float *latestStep, float Strike, float Int_Rate, float Exp_Time",
"float rval = (latestStep[i]-Strike); latestStep[i] = exp(-Int_Rate*Exp_Time) * max(rval,0.0f);",
"excersisePriceKernel")
sumKernel = ReductionKernel(ctx,
numpy.float32,
neutral="0",
reduce_expr="a+b",
map_expr="x[i]",
arguments="__global float *x")
maxWorkItems = 1 * 2**9
multiplier = 1
if (nPaths > maxWorkItems):
multiplier = math.ceil(nPaths / maxWorkItems)
nPaths = multiplier * maxWorkItems
else:
maxWorkItems = nPaths
#print(maxWorkItems, multiplier, nPaths)
nTimeStepsMonte = math.ceil(Exp_Time / dtMonte)
#print(nTimeStepsMonte,nMonteLoops)
#set up random number generator
gen = RanluxGenerator(queue, maxWorkItems, luxury=4, seed=time.time())
#the arrays
ran = cl.array.zeros(queue, maxWorkItems, numpy.float32)
latestStep = cl.array.zeros_like(ran)
means = numpy.zeros(nMonteLoops)
theMean = 0
#the loop
for loop in range(nMonteLoops):
theSum = 0
for mult in range(multiplier):
latestStep.fill(S_init)
for t in range(nTimeStepsMonte):
gen.fill_normal(ran)
gen.synchronize(queue)
nextStepPathKernel(latestStep, ran, Strike, Int_Rate, Exp_Time,
dtMonte, Vol)
excersisePriceKernel(latestStep, Strike, Int_Rate, Exp_Time)
#print(latestStep)
#add to array
theSum += sumKernel(latestStep, queue).get()
means[loop] = theSum / nPaths
monteAverage = numpy.mean(means)
monteStdDeviation = numpy.std(means)
return monteAverage, dtMonte, monteStdDeviation
ran = cl.array.zeros(queue, nPaths, numpy.float32)
latestStep = cl.array.empty_like(ran)
averages = numpy.zeros(nLoops)
#averages = cl.array.zeros(queue, nLoops, numpy.float32)
tStartMonte = time.time()
theSum = 0
for loop in range(0, nLoops):
latestStep.fill(S_init)
for t in range(0, nTimeStepsMonte):
gen.fill_normal(ran)
gen.synchronize(queue)
nextStepPathKernel(latestStep, ran, Strike, Int_Rate, Exp_Time,
dtMonte, Vol)
excersisePriceKernel(latestStep, Strike, Int_Rate, Exp_Time)
#theSum = cl.array.sum(latestStep).get()
latestStep_numpy = latestStep.get()
theSum = numpy.sum(latestStep_numpy)
#theSum = sumKernel(latestStep).get()
if (theSum == 0):
print("theSum was zero")
